+2015-02-04 Christophe Lyon <christophe.lyon@linaro.org>
+
+ Backport from trunk r216640-r216661.
+ 2014-10-24 Christophe Lyon <christophe.lyon@linaro.org>
+
+ * gcc.target/aarch64/advsimd-intrinsics/vuzp.c: New file.
+ * gcc.target/aarch64/advsimd-intrinsics/vzip.c: Likewise.
+
+ 2014-10-24 Christophe Lyon <christophe.lyon@linaro.org>
+
+ * gcc.target/aarch64/advsimd-intrinsics/vmul.c: New file.
+
+ 2014-10-24 Christophe Lyon <christophe.lyon@linaro.org>
+
+ * gcc.target/aarch64/advsimd-intrinsics/vldX_lane.c: New file.
+
+ 2014-10-24 Christophe Lyon <christophe.lyon@linaro.org>
+
+ * gcc.target/aarch64/advsimd-intrinsics/vldX.c: New file.
+
+ 2014-10-24 Christophe Lyon <christophe.lyon@linaro.org>
+
+ * gcc.target/aarch64/advsimd-intrinsics/vld1_dup.c: New file.
+
+ 2014-10-24 Christophe Lyon <christophe.lyon@linaro.org>
+
+ * gcc.target/aarch64/advsimd-intrinsics/vdup-vmov.c: New file.
+
+ 2014-10-24 Christophe Lyon <christophe.lyon@linaro.org>
+
+ * gcc.target/aarch64/advsimd-intrinsics/vclz.c: New file.
+
+ 2014-10-24 Christophe Lyon <christophe.lyon@linaro.org>
+
+ * gcc.target/aarch64/advsimd-intrinsics/vbsl.c: New file.
+
+ 2014-10-24 Christophe Lyon <christophe.lyon@linaro.org>
+
+ * gcc.target/aarch64/advsimd-intrinsics/vaddw.c: New file.
+
+ 2014-10-24 Christophe Lyon <christophe.lyon@linaro.org>
+
+ * gcc.target/aarch64/advsimd-intrinsics/vaddl.c: New file.
+
+ 2014-10-24 Christophe Lyon <christophe.lyon@linaro.org>
+
+ * gcc.target/aarch64/advsimd-intrinsics/vaddhn.c: New file.
+
+ 2014-10-24 Christophe Lyon <christophe.lyon@linaro.org>
+
+ * gcc.target/aarch64/advsimd-intrinsics/vabdl.c: New file.
+
+ 2014-10-24 Christophe Lyon <christophe.lyon@linaro.org>
+
+ * gcc.target/aarch64/advsimd-intrinsics/vabd.c: New file.
+
+ 2014-10-24 Christophe Lyon <christophe.lyon@linaro.org>
+
+ * gcc.target/aarch64/advsimd-intrinsics/vabal.c: New file.
+
+ 2014-10-24 Christophe Lyon <christophe.lyon@linaro.org>
+
+ * gcc.target/aarch64/advsimd-intrinsics/binary_sat_op.inc: New
+ file.
+ * gcc.target/aarch64/advsimd-intrinsics/vqadd.c: Likewise.
+ * gcc.target/aarch64/advsimd-intrinsics/vqsub.c: Likewise.
+
+ 2014-10-24 Christophe Lyon <christophe.lyon@linaro.org>
+
+ * gcc.target/aarch64/advsimd-intrinsics/unary_sat_op.inc: New
+ file.
+ * gcc.target/aarch64/advsimd-intrinsics/vqabs.c: Likewise.
+ * gcc.target/aarch64/advsimd-intrinsics/vqneg.c: Likewise.
+
+ 2014-10-24 Christophe Lyon <christophe.lyon@linaro.org>
+
+ * gcc.target/aarch64/advsimd-intrinsics/cmp_fp_op.inc: New file.
+ * gcc.target/aarch64/advsimd-intrinsics/vcage.c: Likewise.
+ * gcc.target/aarch64/advsimd-intrinsics/vcagt.c: Likewise.
+ * gcc.target/aarch64/advsimd-intrinsics/vcale.c: Likewise.
+ * gcc.target/aarch64/advsimd-intrinsics/vcalt.c: Likewise.
+
+ 2014-10-24 Christophe Lyon <christophe.lyon@linaro.org>
+
+ * gcc.target/aarch64/advsimd-intrinsics/cmp_op.inc: New file.
+ * gcc.target/aarch64/advsimd-intrinsics/vceq.c: Likewise.
+ * gcc.target/aarch64/advsimd-intrinsics/vcge.c: Likewise.
+ * gcc.target/aarch64/advsimd-intrinsics/vcgt.c: Likewise.
+ * gcc.target/aarch64/advsimd-intrinsics/vcle.c: Likewise.
+ * gcc.target/aarch64/advsimd-intrinsics/vclt.c: Likewise.
+
+ 2014-10-24 Christophe Lyon <christophe.lyon@linaro.org>
+
+ * gcc.target/aarch64/advsimd-intrinsics/binary_op.inc: New file.
+ * gcc.target/aarch64/advsimd-intrinsics/vadd.c: Likewise.
+ * gcc.target/aarch64/advsimd-intrinsics/vand.c: Likewise.
+ * gcc.target/aarch64/advsimd-intrinsics/vbic.c: Likewise.
+ * gcc.target/aarch64/advsimd-intrinsics/veor.c: Likewise.
+ * gcc.target/aarch64/advsimd-intrinsics/vorn.c: Likewise.
+ * gcc.target/aarch64/advsimd-intrinsics/vorr.c: Likewise.
+ * gcc.target/aarch64/advsimd-intrinsics/vsub.c: Likewise.
+
+ 2014-10-24 Christophe Lyon <christophe.lyon@linaro.org>
+
+ * gcc.target/aarch64/advsimd-intrinsics/unary_op.inc: New file.
+ * gcc.target/aarch64/advsimd-intrinsics/vabs.c: Likewise.
+ * gcc.target/aarch64/advsimd-intrinsics/vneg.c: Likewise.
+
+ 2014-10-24 Christophe Lyon <christophe.lyon@linaro.org>
+
+ * gcc.target/arm/README.advsimd-intrinsics: New file.
+ * gcc.target/aarch64/advsimd-intrinsics/README: Likewise.
+ * gcc.target/aarch64/advsimd-intrinsics/arm-neon-ref.h: Likewise.
+ * gcc.target/aarch64/advsimd-intrinsics/compute-ref-data.h:
+ Likewise.
+ * gcc.target/aarch64/advsimd-intrinsics/advsimd-intrinsics.exp:
+ Likewise.
+ * gcc.target/aarch64/advsimd-intrinsics/vaba.c: Likewise.
+ * gcc.target/aarch64/advsimd-intrinsics/vld1.c: Likewise.
+ * gcc.target/aarch64/advsimd-intrinsics/vshl.c: Likewise.
+
2015-02-05 Prathamesh Kulkarni <prathamesh.kulkarni@linaro.org>
Backport from trunk r217230.
--- /dev/null
+This directory contains executable tests for ARM/AArch64 Advanced SIMD
+(Neon) intrinsics.
+
+It is meant to cover execution cases of all the Advanced SIMD
+intrinsics, but does not scan the generated assembler code.
+
+The general framework is composed as follows:
+- advsimd-intrinsics.exp: main dejagnu driver
+- *.c: actual tests, generally one per intrinsinc family
+- arm-neon-ref.h: contains macro definitions to save typing in actual
+ test files
+- compute-ref-data.h: contains input vectors definitions
+- *.inc: generic tests, shared by several families of intrinsics. For
+ instance, unary or binary operators
+
+A typical .c test file starts with the following contents (look at
+vld1.c and vaba.c for sample cases):
+#include <arm_neon.h>
+#include "arm-neon-ref.h"
+#include "compute-ref-data.h"
+
+Then, definitions of expected results, based on common input values,
+as defined in compute-ref-data.h.
+For example:
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x16, 0x17, 0x18, 0x19 };
+defines the expected results of an operator generating int16x4 values.
+
+The common input values defined in compute-ref-data.h have been chosen
+to avoid corner-case values for most operators, yet exposing negative
+values for signed operators. For this reason, their range is also
+limited. For instance, the initialization of buffer_int16x4 will be
+{ -16, -15, -14, -13 }.
+
+The initialization of floating-point values is done via hex notation,
+to avoid potential rounding problems.
+
+To test special values and corner cases, specific initialization
+values should be used in dedicated tests, to ensure proper coverage.
+An example of this is vshl.
+
+When a variant of an intrinsic is not available, its expected result
+should be defined to the value of CLEAN_PATTERN_8 as defined in
+arm-neon-ref.h. For example:
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+if the given intrinsic has no variant producing an int64x1 result,
+like the vcmp family (eg. vclt).
+
+This is because the helper function (check_results(), defined in
+arm-neon-ref.h), iterates over all the possible variants, to save
+typing in each individual test file. Alternatively, one can directly
+call the CHECK/CHECK_FP macros to check only a few expected results
+(see vabs.c for an example).
+
+Then, define the TEST_MSG string, which will be used when reporting errors.
+
+Next, define the function performing the actual tests, in general
+relying on the helpers provided by arm-neon-ref.h, which means:
+
+* declare necessary vectors of suitable types: using
+ DECL_VARIABLE_ALL_VARIANTS when all variants are supported, or the
+ relevant of subset calls to DECL_VARIABLE.
+
+* call clean_results() to initialize the 'results' buffers.
+
+* initialize the input vectors, using VLOAD, VDUP or VSET_LANE (vld*
+ tests do not need this step, since their actual purpose is to
+ initialize vectors).
+
+* execute the intrinsic on relevant variants, for instance using
+ TEST_MACRO_ALL_VARIANTS_2_5.
+
+* call check_results() to check that the results match the expected
+ values.
+
+A template test file could be:
+=================================================================
+#include <arm_neon.h>
+#include "arm-neon-ref.h"
+#include "compute-ref-data.h"
+
+/* Expected results. */
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf6, 0xf7, 0xf8, 0xf9,
+ 0xfa, 0xfb, 0xfc, 0xfd };
+/* and as many others as necessary. */
+
+#define TEST_MSG "VMYINTRINSIC"
+void exec_myintrinsic (void)
+{
+ /* my test: v4=vmyintrinsic(v1,v2,v3), then store the result. */
+#define TEST_VMYINTR(Q, T1, T2, W, N) \
+ VECT_VAR(vector_res, T1, W, N) = \
+ vmyintr##Q##_##T2##W(VECT_VAR(vector1, T1, W, N), \
+ VECT_VAR(vector2, T1, W, N), \
+ VECT_VAR(vector3, T1, W, N)); \
+ vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N), VECT_VAR(vector_res, T1, W, N))
+
+#define DECL_VMYINTR_VAR(VAR) \
+ DECL_VARIABLE(VAR, int, 8, 8);
+/* And as many others as necessary. */
+
+ DECL_VMYINTR_VAR(vector1);
+ DECL_VMYINTR_VAR(vector2);
+ DECL_VMYINTR_VAR(vector3);
+ DECL_VMYINTR_VAR(vector_res);
+
+ clean_results ();
+
+ /* Initialize input "vector1" from "buffer". */
+ VLOAD(vector1, buffer, , int, s, 8, 8);
+/* And as many others as necessary. */
+
+ /* Choose init value arbitrarily. */
+ VDUP(vector2, , int, s, 8, 8, 1);
+/* And as many others as necessary. */
+
+ /* Choose init value arbitrarily. */
+ VDUP(vector3, , int, s, 8, 8, -5);
+/* And as many others as necessary. */
+
+ /* Execute the tests. */
+ TEST_VMYINTR(, int, s, 8, 8);
+/* And as many others as necessary. */
+
+ check_results (TEST_MSG, "");
+}
+
+int main (void)
+{
+ exec_vmyintrinsic ();
+ return 0;
+}
+=================================================================
--- /dev/null
+# Copyright (C) 2014 Free Software Foundation, Inc.
+
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with GCC; see the file COPYING3. If not see
+# <http://www.gnu.org/licenses/>.
+
+# GCC testsuite that uses the `dg.exp' driver.
+
+# Exit immediately if this isn't an ARM or AArch64 target.
+if {![istarget arm*-*-*]
+ && ![istarget aarch64*-*-*]} then {
+ return
+}
+
+# Load support procs.
+load_lib gcc-dg.exp
+
+# Initialize `dg'.
+load_lib c-torture.exp
+load_lib target-supports.exp
+load_lib torture-options.exp
+
+dg-init
+
+torture-init
+set-torture-options $C_TORTURE_OPTIONS {{}} $LTO_TORTURE_OPTIONS
+
+# Make sure Neon flags are provided, if necessary.
+set additional_flags [add_options_for_arm_neon ""]
+
+# Main loop.
+foreach src [lsort [glob -nocomplain $srcdir/$subdir/*.c]] {
+ # If we're only testing specific files and this isn't one of them, skip it.
+ if ![runtest_file_p $runtests $src] then {
+ continue
+ }
+
+ c-torture-execute $src $additional_flags
+ gcc-dg-runtest $src $additional_flags
+}
+
+# All done.
+torture-finish
+dg-finish
--- /dev/null
+/* This file defines helper operations shared by all the tests. */
+
+#ifndef _ARM_NEON_REF_H_
+#define _ARM_NEON_REF_H_
+
+#include <stdio.h>
+#include <inttypes.h>
+
+/* helper type, to help write floating point results in integer form. */
+typedef uint32_t hfloat32_t;
+
+extern void abort(void);
+extern void *memset(void *, int, size_t);
+extern void *memcpy(void *, const void *, size_t);
+extern size_t strlen(const char *);
+
+/* Various string construction helpers. */
+
+/*
+ The most useful at user-level are VECT_VAR and VECT_VAR_DECL, which
+ construct variable names or declarations, such as:
+ VECT_VAR(expected, int, 16, 4) -> expected_int16x4
+ VECT_VAR_DECL(expected, int, 16, 4) -> int16x4_t expected_int16x4
+*/
+
+#define xSTR(X) #X
+#define STR(X) xSTR(X)
+
+#define xNAME1(V,T) V ## _ ## T
+#define xNAME(V,T) xNAME1(V,T)
+
+/* VAR(foo,int,16) -> foo_int16 */
+#define VAR(V,T,W) xNAME(V,T##W)
+/* VAR_DECL(foo,int,16) -> int16_t foo_int16 */
+#define VAR_DECL(V, T, W) T##W##_t VAR(V,T,W)
+
+/* VECT_NAME(int,16,4) -> int16x4 */
+#define VECT_NAME(T, W, N) T##W##x##N
+/* VECT_ARRAY_NAME(int,16,4,2) -> int16x4x2 */
+#define VECT_ARRAY_NAME(T, W, N, L) T##W##x##N##x##L
+/* VECT_TYPE(int,16,4) -> int16x4_t */
+#define VECT_TYPE(T, W, N) xNAME(VECT_NAME(T,W,N),t)
+/* VECT_ARRAY_TYPE(int,16,4,2) -> int16x4x2_t */
+#define VECT_ARRAY_TYPE(T, W, N, L) xNAME(VECT_ARRAY_NAME(T,W,N,L),t)
+
+/* VECT_VAR(foo,int,16,4) -> foo_int16x4 */
+#define VECT_VAR(V,T,W,N) xNAME(V,VECT_NAME(T,W,N))
+/* VECT_VAR_DECL(foo,int,16,4) -> int16_t foo_int16x4 */
+#define VECT_VAR_DECL(V, T, W, N) T##W##_t VECT_VAR(V,T,W,N)
+
+/* Array declarations. */
+/* ARRAY(foo,int,16,4) -> int16_t foo_int16x4[4] */
+#define ARRAY(V, T, W, N) VECT_VAR_DECL(V,T,W,N)[N]
+
+/* Arrays of vectors. */
+/* VECT_ARRAY_VAR(foo,int,16,4,2) -> foo_int16x4x2 */
+#define VECT_ARRAY_VAR(V,T,W,N,L) xNAME(V,VECT_ARRAY_NAME(T,W,N,L))
+/* VECT_ARRAY(foo,int,16,4,2) -> int16_t foo_int16x4x2[4*2] */
+#define VECT_ARRAY(V, T, W, N, L) T##W##_t VECT_ARRAY_VAR(V,T,W,N,L)[N*L]
+
+/* Check results vs expected values. Operates on one vector. */
+#define CHECK(MSG,T,W,N,FMT,EXPECTED,COMMENT) \
+ { \
+ int i; \
+ for(i=0; i<N ; i++) \
+ { \
+ if (VECT_VAR(result, T, W, N)[i] != \
+ VECT_VAR(EXPECTED, T, W, N)[i]) { \
+ fprintf(stderr, \
+ "ERROR in %s (%s line %d in buffer '%s') at type %s " \
+ "index %d: got 0x%" FMT " != 0x%" FMT " %s\n", \
+ MSG, __FILE__, __LINE__, \
+ STR(EXPECTED), \
+ STR(VECT_NAME(T, W, N)), \
+ i, \
+ VECT_VAR(result, T, W, N)[i], \
+ VECT_VAR(EXPECTED, T, W, N)[i], \
+ strlen(COMMENT) > 0 ? COMMENT : ""); \
+ abort(); \
+ } \
+ } \
+ }
+
+/* Floating-point variant. */
+#define CHECK_FP(MSG,T,W,N,FMT,EXPECTED,COMMENT) \
+ { \
+ int i; \
+ for(i=0; i<N ; i++) \
+ { \
+ union fp_operand { \
+ uint##W##_t i; \
+ float##W##_t f; \
+ } tmp_res, tmp_exp; \
+ tmp_res.f = VECT_VAR(result, T, W, N)[i]; \
+ tmp_exp.i = VECT_VAR(EXPECTED, h##T, W, N)[i]; \
+ if (tmp_res.i != tmp_exp.i) { \
+ fprintf(stderr, \
+ "ERROR in %s (%s line %d in buffer '%s') at type %s " \
+ "index %d: got 0x%" FMT " != 0x%" FMT " %s\n", \
+ MSG, __FILE__, __LINE__, \
+ STR(EXPECTED), \
+ STR(VECT_NAME(T, W, N)), \
+ i, \
+ tmp_res.i, \
+ tmp_exp.i, \
+ strlen(COMMENT) > 0 ? COMMENT : ""); \
+ abort(); \
+ } \
+ } \
+ }
+
+/* Clean buffer with a non-zero pattern to help diagnose buffer
+ overflows. */
+#define CLEAN_PATTERN_8 0x33
+
+#define CLEAN(VAR,T,W,N) \
+ memset(VECT_VAR(VAR, T, W, N), \
+ CLEAN_PATTERN_8, \
+ sizeof(VECT_VAR(VAR, T, W, N)));
+
+/* Define output buffers, one of each size. */
+static ARRAY(result, int, 8, 8);
+static ARRAY(result, int, 16, 4);
+static ARRAY(result, int, 32, 2);
+static ARRAY(result, int, 64, 1);
+static ARRAY(result, uint, 8, 8);
+static ARRAY(result, uint, 16, 4);
+static ARRAY(result, uint, 32, 2);
+static ARRAY(result, uint, 64, 1);
+static ARRAY(result, poly, 8, 8);
+static ARRAY(result, poly, 16, 4);
+static ARRAY(result, float, 32, 2);
+static ARRAY(result, int, 8, 16);
+static ARRAY(result, int, 16, 8);
+static ARRAY(result, int, 32, 4);
+static ARRAY(result, int, 64, 2);
+static ARRAY(result, uint, 8, 16);
+static ARRAY(result, uint, 16, 8);
+static ARRAY(result, uint, 32, 4);
+static ARRAY(result, uint, 64, 2);
+static ARRAY(result, poly, 8, 16);
+static ARRAY(result, poly, 16, 8);
+static ARRAY(result, float, 32, 4);
+
+/* Declare expected results, one of each size. They are defined and
+ initialized in each test file. */
+extern ARRAY(expected, int, 8, 8);
+extern ARRAY(expected, int, 16, 4);
+extern ARRAY(expected, int, 32, 2);
+extern ARRAY(expected, int, 64, 1);
+extern ARRAY(expected, uint, 8, 8);
+extern ARRAY(expected, uint, 16, 4);
+extern ARRAY(expected, uint, 32, 2);
+extern ARRAY(expected, uint, 64, 1);
+extern ARRAY(expected, poly, 8, 8);
+extern ARRAY(expected, poly, 16, 4);
+extern ARRAY(expected, hfloat, 32, 2);
+extern ARRAY(expected, int, 8, 16);
+extern ARRAY(expected, int, 16, 8);
+extern ARRAY(expected, int, 32, 4);
+extern ARRAY(expected, int, 64, 2);
+extern ARRAY(expected, uint, 8, 16);
+extern ARRAY(expected, uint, 16, 8);
+extern ARRAY(expected, uint, 32, 4);
+extern ARRAY(expected, uint, 64, 2);
+extern ARRAY(expected, poly, 8, 16);
+extern ARRAY(expected, poly, 16, 8);
+extern ARRAY(expected, hfloat, 32, 4);
+
+/* Check results. Operates on all possible vector types. */
+#define CHECK_RESULTS(test_name,comment) \
+ { \
+ CHECK(test_name, int, 8, 8, PRIx8, expected, comment); \
+ CHECK(test_name, int, 16, 4, PRIx16, expected, comment); \
+ CHECK(test_name, int, 32, 2, PRIx32, expected, comment); \
+ CHECK(test_name, int, 64, 1, PRIx64, expected, comment); \
+ CHECK(test_name, uint, 8, 8, PRIx8, expected, comment); \
+ CHECK(test_name, uint, 16, 4, PRIx16, expected, comment); \
+ CHECK(test_name, uint, 32, 2, PRIx32, expected, comment); \
+ CHECK(test_name, uint, 64, 1, PRIx64, expected, comment); \
+ CHECK(test_name, poly, 8, 8, PRIx8, expected, comment); \
+ CHECK(test_name, poly, 16, 4, PRIx16, expected, comment); \
+ CHECK_FP(test_name, float, 32, 2, PRIx32, expected, comment); \
+ \
+ CHECK(test_name, int, 8, 16, PRIx8, expected, comment); \
+ CHECK(test_name, int, 16, 8, PRIx16, expected, comment); \
+ CHECK(test_name, int, 32, 4, PRIx32, expected, comment); \
+ CHECK(test_name, int, 64, 2, PRIx64, expected, comment); \
+ CHECK(test_name, uint, 8, 16, PRIx8, expected, comment); \
+ CHECK(test_name, uint, 16, 8, PRIx16, expected, comment); \
+ CHECK(test_name, uint, 32, 4, PRIx32, expected, comment); \
+ CHECK(test_name, uint, 64, 2, PRIx64, expected, comment); \
+ CHECK(test_name, poly, 8, 16, PRIx8, expected, comment); \
+ CHECK(test_name, poly, 16, 8, PRIx16, expected, comment); \
+ CHECK_FP(test_name, float, 32, 4, PRIx32, expected, comment); \
+ } \
+
+#define CHECK_RESULTS_NAMED(test_name,EXPECTED,comment) \
+ { \
+ CHECK(test_name, int, 8, 8, PRIx8, EXPECTED, comment); \
+ CHECK(test_name, int, 16, 4, PRIx16, EXPECTED, comment); \
+ CHECK(test_name, int, 32, 2, PRIx32, EXPECTED, comment); \
+ CHECK(test_name, int, 64, 1, PRIx64, EXPECTED, comment); \
+ CHECK(test_name, uint, 8, 8, PRIx8, EXPECTED, comment); \
+ CHECK(test_name, uint, 16, 4, PRIx16, EXPECTED, comment); \
+ CHECK(test_name, uint, 32, 2, PRIx32, EXPECTED, comment); \
+ CHECK(test_name, uint, 64, 1, PRIx64, EXPECTED, comment); \
+ CHECK(test_name, poly, 8, 8, PRIx8, EXPECTED, comment); \
+ CHECK(test_name, poly, 16, 4, PRIx16, EXPECTED, comment); \
+ CHECK_FP(test_name, float, 32, 2, PRIx32, EXPECTED, comment); \
+ \
+ CHECK(test_name, int, 8, 16, PRIx8, EXPECTED, comment); \
+ CHECK(test_name, int, 16, 8, PRIx16, EXPECTED, comment); \
+ CHECK(test_name, int, 32, 4, PRIx32, EXPECTED, comment); \
+ CHECK(test_name, int, 64, 2, PRIx64, EXPECTED, comment); \
+ CHECK(test_name, uint, 8, 16, PRIx8, EXPECTED, comment); \
+ CHECK(test_name, uint, 16, 8, PRIx16, EXPECTED, comment); \
+ CHECK(test_name, uint, 32, 4, PRIx32, EXPECTED, comment); \
+ CHECK(test_name, uint, 64, 2, PRIx64, EXPECTED, comment); \
+ CHECK(test_name, poly, 8, 16, PRIx8, EXPECTED, comment); \
+ CHECK(test_name, poly, 16, 8, PRIx16, EXPECTED, comment); \
+ CHECK_FP(test_name, float, 32, 4, PRIx32, EXPECTED, comment); \
+ } \
+
+
+
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+
+typedef union {
+ struct {
+ int _xxx:27;
+ unsigned int QC:1;
+ int V:1;
+ int C:1;
+ int Z:1;
+ int N:1;
+ } b;
+ unsigned int word;
+} _ARM_FPSCR;
+
+#else /* __ORDER_BIG_ENDIAN__ */
+
+typedef union {
+ struct {
+ int N:1;
+ int Z:1;
+ int C:1;
+ int V:1;
+ unsigned int QC:1;
+ int _dnm:27;
+ } b;
+ unsigned int word;
+} _ARM_FPSCR;
+
+#endif /* __ORDER_BIG_ENDIAN__ */
+
+#define Neon_Cumulative_Sat __read_neon_cumulative_sat()
+#define Set_Neon_Cumulative_Sat(x) __set_neon_cumulative_sat((x))
+
+#if defined(__aarch64__)
+static volatile int __read_neon_cumulative_sat (void) {
+ _ARM_FPSCR _afpscr_for_qc;
+ asm volatile ("mrs %0,fpsr" : "=r" (_afpscr_for_qc));
+ return _afpscr_for_qc.b.QC;
+}
+static void __set_neon_cumulative_sat (int x) {
+ _ARM_FPSCR _afpscr_for_qc;
+ asm volatile ("mrs %0,fpsr" : "=r" (_afpscr_for_qc));
+ _afpscr_for_qc.b.QC = x;
+ asm volatile ("msr fpsr,%0" : : "r" (_afpscr_for_qc));
+ return;
+}
+#else
+static volatile int __read_neon_cumulative_sat (void) {
+ _ARM_FPSCR _afpscr_for_qc;
+ asm volatile ("vmrs %0,fpscr" : "=r" (_afpscr_for_qc));
+ return _afpscr_for_qc.b.QC;
+}
+
+static void __set_neon_cumulative_sat (int x) {
+ _ARM_FPSCR _afpscr_for_qc;
+ asm volatile ("vmrs %0,fpscr" : "=r" (_afpscr_for_qc));
+ _afpscr_for_qc.b.QC = x;
+ asm volatile ("vmsr fpscr,%0" : : "r" (_afpscr_for_qc));
+ return;
+}
+#endif
+
+/* Declare expected cumulative saturation results, one for each
+ size. They are defined and initialized in relevant test files. */
+extern int VECT_VAR(expected_cumulative_sat, int, 8, 8);
+extern int VECT_VAR(expected_cumulative_sat, int, 16, 4);
+extern int VECT_VAR(expected_cumulative_sat, int, 32, 2);
+extern int VECT_VAR(expected_cumulative_sat, int, 64, 1);
+extern int VECT_VAR(expected_cumulative_sat, uint, 8, 8);
+extern int VECT_VAR(expected_cumulative_sat, uint, 16, 4);
+extern int VECT_VAR(expected_cumulative_sat, uint, 32, 2);
+extern int VECT_VAR(expected_cumulative_sat, uint, 64, 1);
+extern int VECT_VAR(expected_cumulative_sat, int, 8, 16);
+extern int VECT_VAR(expected_cumulative_sat, int, 16, 8);
+extern int VECT_VAR(expected_cumulative_sat, int, 32, 4);
+extern int VECT_VAR(expected_cumulative_sat, int, 64, 2);
+extern int VECT_VAR(expected_cumulative_sat, uint, 8, 16);
+extern int VECT_VAR(expected_cumulative_sat, uint, 16, 8);
+extern int VECT_VAR(expected_cumulative_sat, uint, 32, 4);
+extern int VECT_VAR(expected_cumulative_sat, uint, 64, 2);
+
+/* Check cumulative saturation flag vs expected value. */
+#define CHECK_CUMULATIVE_SAT(MSG,T,W,N,EXPECTED,COMMENT) \
+ { \
+ if (Neon_Cumulative_Sat != \
+ VECT_VAR(EXPECTED, T, W, N)) { \
+ fprintf(stderr, \
+ "ERROR in %s (%s line %d in cumulative_sat '%s') at type %s: " \
+ "got %d expected %d%s\n", \
+ MSG, __FILE__, __LINE__, \
+ STR(EXPECTED), \
+ STR(VECT_NAME(T, W, N)), \
+ Neon_Cumulative_Sat, \
+ VECT_VAR(EXPECTED, T, W, N), \
+ strlen(COMMENT) > 0 ? " " COMMENT : ""); \
+ abort(); \
+ } \
+ }
+
+#define CHECK_CUMULATIVE_SAT_NAMED(test_name,EXPECTED,comment) \
+ { \
+ CHECK_CUMULATIVE_SAT(test_name, int, 8, 8, PRIx8, EXPECTED, comment); \
+ CHECK_CUMULATIVE_SAT(test_name, int, 16, 4, PRIx16, EXPECTED, comment); \
+ CHECK_CUMULATIVE_SAT(test_name, int, 32, 2, PRIx32, EXPECTED, comment); \
+ CHECK_CUMULATIVE_SAT(test_name, int, 64, 1, PRIx64, EXPECTED, comment); \
+ CHECK_CUMULATIVE_SAT(test_name, uint, 8, 8, PRIx8, EXPECTED, comment); \
+ CHECK_CUMULATIVE_SAT(test_name, uint, 16, 4, PRIx16, EXPECTED, comment); \
+ CHECK_CUMULATIVE_SAT(test_name, uint, 32, 2, PRIx32, EXPECTED, comment); \
+ CHECK_CUMULATIVE_SAT(test_name, uint, 64, 1, PRIx64, EXPECTED, comment); \
+ CHECK_CUMULATIVE_SAT(test_name, poly, 8, 8, PRIx8, EXPECTED, comment); \
+ CHECK_CUMULATIVE_SAT(test_name, poly, 16, 4, PRIx16, EXPECTED, comment); \
+ CHECK_CUMULATIVE_SAT_FP(test_name, float, 32, 2, PRIx32, EXPECTED, comment); \
+ \
+ CHECK_CUMULATIVE_SAT(test_name, int, 8, 16, PRIx8, EXPECTED, comment); \
+ CHECK_CUMULATIVE_SAT(test_name, int, 16, 8, PRIx16, EXPECTED, comment); \
+ CHECK_CUMULATIVE_SAT(test_name, int, 32, 4, PRIx32, EXPECTED, comment); \
+ CHECK_CUMULATIVE_SAT(test_name, int, 64, 2, PRIx64, EXPECTED, comment); \
+ CHECK_CUMULATIVE_SAT(test_name, uint, 8, 16, PRIx8, EXPECTED, comment); \
+ CHECK_CUMULATIVE_SAT(test_name, uint, 16, 8, PRIx16, EXPECTED, comment); \
+ CHECK_CUMULATIVE_SAT(test_name, uint, 32, 4, PRIx32, EXPECTED, comment); \
+ CHECK_CUMULATIVE_SAT(test_name, uint, 64, 2, PRIx64, EXPECTED, comment); \
+ CHECK_CUMULATIVE_SAT(test_name, poly, 8, 16, PRIx8, EXPECTED, comment); \
+ CHECK_CUMULATIVE_SAT(test_name, poly, 16, 8, PRIx16, EXPECTED, comment); \
+ CHECK_CUMULATIVE_SAT_FP(test_name, float, 32, 4, PRIx32, EXPECTED, comment); \
+ } \
+
+
+/* Clean output buffers before execution. */
+static void clean_results (void)
+{
+ CLEAN(result, int, 8, 8);
+ CLEAN(result, int, 16, 4);
+ CLEAN(result, int, 32, 2);
+ CLEAN(result, int, 64, 1);
+ CLEAN(result, uint, 8, 8);
+ CLEAN(result, uint, 16, 4);
+ CLEAN(result, uint, 32, 2);
+ CLEAN(result, uint, 64, 1);
+ CLEAN(result, poly, 8, 8);
+ CLEAN(result, poly, 16, 4);
+ CLEAN(result, float, 32, 2);
+
+ CLEAN(result, int, 8, 16);
+ CLEAN(result, int, 16, 8);
+ CLEAN(result, int, 32, 4);
+ CLEAN(result, int, 64, 2);
+ CLEAN(result, uint, 8, 16);
+ CLEAN(result, uint, 16, 8);
+ CLEAN(result, uint, 32, 4);
+ CLEAN(result, uint, 64, 2);
+ CLEAN(result, poly, 8, 16);
+ CLEAN(result, poly, 16, 8);
+ CLEAN(result, float, 32, 4);
+}
+
+
+/* Helpers to declare variables of various types. */
+#define DECL_VARIABLE(VAR, T1, W, N) \
+ VECT_TYPE(T1, W, N) VECT_VAR(VAR, T1, W, N)
+
+/* Declare only 64 bits signed variants. */
+#define DECL_VARIABLE_64BITS_SIGNED_VARIANTS(VAR) \
+ DECL_VARIABLE(VAR, int, 8, 8); \
+ DECL_VARIABLE(VAR, int, 16, 4); \
+ DECL_VARIABLE(VAR, int, 32, 2); \
+ DECL_VARIABLE(VAR, int, 64, 1)
+
+/* Declare only 64 bits unsigned variants. */
+#define DECL_VARIABLE_64BITS_UNSIGNED_VARIANTS(VAR) \
+ DECL_VARIABLE(VAR, uint, 8, 8); \
+ DECL_VARIABLE(VAR, uint, 16, 4); \
+ DECL_VARIABLE(VAR, uint, 32, 2); \
+ DECL_VARIABLE(VAR, uint, 64, 1)
+
+/* Declare only 128 bits signed variants. */
+#define DECL_VARIABLE_128BITS_SIGNED_VARIANTS(VAR) \
+ DECL_VARIABLE(VAR, int, 8, 16); \
+ DECL_VARIABLE(VAR, int, 16, 8); \
+ DECL_VARIABLE(VAR, int, 32, 4); \
+ DECL_VARIABLE(VAR, int, 64, 2)
+
+/* Declare only 128 bits unsigned variants. */
+#define DECL_VARIABLE_128BITS_UNSIGNED_VARIANTS(VAR) \
+ DECL_VARIABLE(VAR, uint, 8, 16); \
+ DECL_VARIABLE(VAR, uint, 16, 8); \
+ DECL_VARIABLE(VAR, uint, 32, 4); \
+ DECL_VARIABLE(VAR, uint, 64, 2)
+
+/* Declare all 64 bits variants. */
+#define DECL_VARIABLE_64BITS_VARIANTS(VAR) \
+ DECL_VARIABLE_64BITS_SIGNED_VARIANTS(VAR); \
+ DECL_VARIABLE_64BITS_UNSIGNED_VARIANTS(VAR); \
+ DECL_VARIABLE(VAR, poly, 8, 8); \
+ DECL_VARIABLE(VAR, poly, 16, 4); \
+ DECL_VARIABLE(VAR, float, 32, 2)
+
+/* Declare all 128 bits variants. */
+#define DECL_VARIABLE_128BITS_VARIANTS(VAR) \
+ DECL_VARIABLE_128BITS_SIGNED_VARIANTS(VAR); \
+ DECL_VARIABLE_128BITS_UNSIGNED_VARIANTS(VAR); \
+ DECL_VARIABLE(VAR, poly, 8, 16); \
+ DECL_VARIABLE(VAR, poly, 16, 8); \
+ DECL_VARIABLE(VAR, float, 32, 4)
+
+/* Declare all variants. */
+#define DECL_VARIABLE_ALL_VARIANTS(VAR) \
+ DECL_VARIABLE_64BITS_VARIANTS(VAR); \
+ DECL_VARIABLE_128BITS_VARIANTS(VAR)
+
+/* Declare all signed variants. */
+#define DECL_VARIABLE_SIGNED_VARIANTS(VAR) \
+ DECL_VARIABLE_64BITS_SIGNED_VARIANTS(VAR); \
+ DECL_VARIABLE_128BITS_SIGNED_VARIANTS(VAR)
+
+/* Declare all unsigned variants. */
+#define DECL_VARIABLE_UNSIGNED_VARIANTS(VAR) \
+ DECL_VARIABLE_64BITS_UNSIGNED_VARIANTS(VAR); \
+ DECL_VARIABLE_128BITS_UNSIGNED_VARIANTS(VAR)
+
+/* Helpers to initialize vectors. */
+#define VDUP(VAR, Q, T1, T2, W, N, V) \
+ VECT_VAR(VAR, T1, W, N) = vdup##Q##_n_##T2##W(V)
+
+#define VSET_LANE(VAR, Q, T1, T2, W, N, L, V) \
+ VECT_VAR(VAR, T1, W, N) = vset##Q##_lane_##T2##W(V, \
+ VECT_VAR(VAR, T1, W, N), \
+ L)
+
+/* We need to load initial values first, so rely on VLD1. */
+#define VLOAD(VAR, BUF, Q, T1, T2, W, N) \
+ VECT_VAR(VAR, T1, W, N) = vld1##Q##_##T2##W(VECT_VAR(BUF, T1, W, N))
+
+/* Helpers to call macros with 1 constant and 5 variable
+ arguments. */
+#define TEST_MACRO_64BITS_SIGNED_VARIANTS_1_5(MACRO, VAR) \
+ MACRO(VAR, , int, s, 8, 8); \
+ MACRO(VAR, , int, s, 16, 4); \
+ MACRO(VAR, , int, s, 32, 2); \
+ MACRO(VAR, , int, s, 64, 1)
+
+#define TEST_MACRO_64BITS_UNSIGNED_VARIANTS_1_5(MACRO, VAR) \
+ MACRO(VAR, , uint, u, 8, 8); \
+ MACRO(VAR, , uint, u, 16, 4); \
+ MACRO(VAR, , uint, u, 32, 2); \
+ MACRO(VAR, , uint, u, 64, 1)
+
+#define TEST_MACRO_128BITS_SIGNED_VARIANTS_1_5(MACRO, VAR) \
+ MACRO(VAR, q, int, s, 8, 16); \
+ MACRO(VAR, q, int, s, 16, 8); \
+ MACRO(VAR, q, int, s, 32, 4); \
+ MACRO(VAR, q, int, s, 64, 2)
+
+#define TEST_MACRO_128BITS_UNSIGNED_VARIANTS_1_5(MACRO,VAR) \
+ MACRO(VAR, q, uint, u, 8, 16); \
+ MACRO(VAR, q, uint, u, 16, 8); \
+ MACRO(VAR, q, uint, u, 32, 4); \
+ MACRO(VAR, q, uint, u, 64, 2)
+
+#define TEST_MACRO_64BITS_VARIANTS_1_5(MACRO, VAR) \
+ TEST_MACRO_64BITS_SIGNED_VARIANTS_1_5(MACRO, VAR); \
+ TEST_MACRO_64BITS_UNSIGNED_VARIANTS_1_5(MACRO, VAR)
+
+#define TEST_MACRO_128BITS_VARIANTS_1_5(MACRO, VAR) \
+ TEST_MACRO_128BITS_SIGNED_VARIANTS_1_5(MACRO, VAR); \
+ TEST_MACRO_128BITS_UNSIGNED_VARIANTS_1_5(MACRO, VAR)
+
+#define TEST_MACRO_ALL_VARIANTS_1_5(MACRO, VAR) \
+ TEST_MACRO_64BITS_VARIANTS_1_5(MACRO, VAR); \
+ TEST_MACRO_128BITS_VARIANTS_1_5(MACRO, VAR)
+
+#define TEST_MACRO_SIGNED_VARIANTS_1_5(MACRO, VAR) \
+ TEST_MACRO_64BITS_SIGNED_VARIANTS_1_5(MACRO, VAR); \
+ TEST_MACRO_128BITS_SIGNED_VARIANTS_1_5(MACRO, VAR)
+
+/* Helpers to call macros with 2 constant and 5 variable
+ arguments. */
+#define TEST_MACRO_64BITS_SIGNED_VARIANTS_2_5(MACRO, VAR1, VAR2) \
+ MACRO(VAR1, VAR2, , int, s, 8, 8); \
+ MACRO(VAR1, VAR2, , int, s, 16, 4); \
+ MACRO(VAR1, VAR2, , int, s, 32, 2); \
+ MACRO(VAR1, VAR2 , , int, s, 64, 1)
+
+#define TEST_MACRO_64BITS_UNSIGNED_VARIANTS_2_5(MACRO, VAR1, VAR2) \
+ MACRO(VAR1, VAR2, , uint, u, 8, 8); \
+ MACRO(VAR1, VAR2, , uint, u, 16, 4); \
+ MACRO(VAR1, VAR2, , uint, u, 32, 2); \
+ MACRO(VAR1, VAR2, , uint, u, 64, 1)
+
+#define TEST_MACRO_128BITS_SIGNED_VARIANTS_2_5(MACRO, VAR1, VAR2) \
+ MACRO(VAR1, VAR2, q, int, s, 8, 16); \
+ MACRO(VAR1, VAR2, q, int, s, 16, 8); \
+ MACRO(VAR1, VAR2, q, int, s, 32, 4); \
+ MACRO(VAR1, VAR2, q, int, s, 64, 2)
+
+#define TEST_MACRO_128BITS_UNSIGNED_VARIANTS_2_5(MACRO, VAR1, VAR2) \
+ MACRO(VAR1, VAR2, q, uint, u, 8, 16); \
+ MACRO(VAR1, VAR2, q, uint, u, 16, 8); \
+ MACRO(VAR1, VAR2, q, uint, u, 32, 4); \
+ MACRO(VAR1, VAR2, q, uint, u, 64, 2)
+
+#define TEST_MACRO_64BITS_VARIANTS_2_5(MACRO, VAR1, VAR2) \
+ TEST_MACRO_64BITS_SIGNED_VARIANTS_2_5(MACRO, VAR1, VAR2); \
+ TEST_MACRO_64BITS_UNSIGNED_VARIANTS_2_5(MACRO, VAR1, VAR2); \
+ MACRO(VAR1, VAR2, , poly, p, 8, 8); \
+ MACRO(VAR1, VAR2, , poly, p, 16, 4)
+
+#define TEST_MACRO_128BITS_VARIANTS_2_5(MACRO, VAR1, VAR2) \
+ TEST_MACRO_128BITS_SIGNED_VARIANTS_2_5(MACRO, VAR1, VAR2); \
+ TEST_MACRO_128BITS_UNSIGNED_VARIANTS_2_5(MACRO, VAR1, VAR2); \
+ MACRO(VAR1, VAR2, q, poly, p, 8, 16); \
+ MACRO(VAR1, VAR2, q, poly, p, 16, 8)
+
+#define TEST_MACRO_ALL_VARIANTS_2_5(MACRO, VAR1, VAR2) \
+ TEST_MACRO_64BITS_VARIANTS_2_5(MACRO, VAR1, VAR2); \
+ TEST_MACRO_128BITS_VARIANTS_2_5(MACRO, VAR1, VAR2)
+
+#define TEST_MACRO_SIGNED_VARIANTS_2_5(MACRO, VAR1, VAR2) \
+ TEST_MACRO_64BITS_SIGNED_VARIANTS_2_5(MACRO, VAR1, VAR2); \
+ TEST_MACRO_128BITS_SIGNED_VARIANTS_2_5(MACRO, VAR1, VAR2)
+
+#endif /* _ARM_NEON_REF_H_ */
--- /dev/null
+/* Template file for binary operator validation.
+
+ This file is meant to be included by the relevant test files, which
+ have to define the intrinsic family to test. If a given intrinsic
+ supports variants which are not supported by all the other binary
+ operators, these can be tested by providing a definition for
+ EXTRA_TESTS. */
+
+#include <arm_neon.h>
+#include "arm-neon-ref.h"
+#include "compute-ref-data.h"
+
+#define FNNAME1(NAME) exec_ ## NAME
+#define FNNAME(NAME) FNNAME1(NAME)
+
+void FNNAME (INSN_NAME) (void)
+{
+ /* Basic test: y=OP(x1,x2), then store the result. */
+#define TEST_BINARY_OP1(INSN, Q, T1, T2, W, N) \
+ VECT_VAR(vector_res, T1, W, N) = \
+ INSN##Q##_##T2##W(VECT_VAR(vector, T1, W, N), \
+ VECT_VAR(vector2, T1, W, N)); \
+ vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N), VECT_VAR(vector_res, T1, W, N))
+
+#define TEST_BINARY_OP(INSN, Q, T1, T2, W, N) \
+ TEST_BINARY_OP1(INSN, Q, T1, T2, W, N) \
+
+ DECL_VARIABLE_ALL_VARIANTS(vector);
+ DECL_VARIABLE_ALL_VARIANTS(vector2);
+ DECL_VARIABLE_ALL_VARIANTS(vector_res);
+
+ clean_results ();
+
+ /* Initialize input "vector" from "buffer". */
+ TEST_MACRO_ALL_VARIANTS_2_5(VLOAD, vector, buffer);
+
+ /* Fill input vector2 with arbitrary values. */
+ VDUP(vector2, , int, s, 8, 8, 2);
+ VDUP(vector2, , int, s, 16, 4, -4);
+ VDUP(vector2, , int, s, 32, 2, 3);
+ VDUP(vector2, , int, s, 64, 1, 100);
+ VDUP(vector2, , uint, u, 8, 8, 20);
+ VDUP(vector2, , uint, u, 16, 4, 30);
+ VDUP(vector2, , uint, u, 32, 2, 40);
+ VDUP(vector2, , uint, u, 64, 1, 2);
+ VDUP(vector2, q, int, s, 8, 16, -10);
+ VDUP(vector2, q, int, s, 16, 8, -20);
+ VDUP(vector2, q, int, s, 32, 4, -30);
+ VDUP(vector2, q, int, s, 64, 2, 24);
+ VDUP(vector2, q, uint, u, 8, 16, 12);
+ VDUP(vector2, q, uint, u, 16, 8, 3);
+ VDUP(vector2, q, uint, u, 32, 4, 55);
+ VDUP(vector2, q, uint, u, 64, 2, 3);
+
+ /* Apply a binary operator named INSN_NAME. */
+ TEST_MACRO_ALL_VARIANTS_1_5(TEST_BINARY_OP, INSN_NAME);
+
+ CHECK_RESULTS (TEST_MSG, "");
+
+#ifdef EXTRA_TESTS
+ EXTRA_TESTS();
+#endif
+}
+
+int main (void)
+{
+ FNNAME (INSN_NAME) ();
+
+ return 0;
+}
--- /dev/null
+/* Template file for saturating binary operator validation.
+
+ This file is meant to be included by the relevant test files, which
+ have to define the intrinsic family to test. If a given intrinsic
+ supports variants which are not supported by all the other
+ saturating binary operators, these can be tested by providing a
+ definition for EXTRA_TESTS. */
+
+#include <arm_neon.h>
+#include "arm-neon-ref.h"
+#include "compute-ref-data.h"
+
+#define FNNAME1(NAME) exec_ ## NAME
+#define FNNAME(NAME) FNNAME1(NAME)
+
+void FNNAME (INSN_NAME) (void)
+{
+ /* vector_res = OP(vector1,vector2), then store the result. */
+
+#define TEST_BINARY_SAT_OP1(INSN, Q, T1, T2, W, N, EXPECTED_CUMULATIVE_SAT, CMT) \
+ Set_Neon_Cumulative_Sat(0); \
+ VECT_VAR(vector_res, T1, W, N) = \
+ INSN##Q##_##T2##W(VECT_VAR(vector1, T1, W, N), \
+ VECT_VAR(vector2, T1, W, N)); \
+ vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N), \
+ VECT_VAR(vector_res, T1, W, N)); \
+ CHECK_CUMULATIVE_SAT(TEST_MSG, T1, W, N, EXPECTED_CUMULATIVE_SAT, CMT)
+
+#define TEST_BINARY_SAT_OP(INSN, Q, T1, T2, W, N, EXPECTED_CUMULATIVE_SAT, CMT) \
+ TEST_BINARY_SAT_OP1(INSN, Q, T1, T2, W, N, EXPECTED_CUMULATIVE_SAT, CMT)
+
+ DECL_VARIABLE_ALL_VARIANTS(vector1);
+ DECL_VARIABLE_ALL_VARIANTS(vector2);
+ DECL_VARIABLE_ALL_VARIANTS(vector_res);
+
+ clean_results ();
+
+ /* Initialize input "vector1" from "buffer". */
+ TEST_MACRO_ALL_VARIANTS_2_5(VLOAD, vector1, buffer);
+
+ /* Choose arbitrary initialization values. */
+ VDUP(vector2, , int, s, 8, 8, 0x11);
+ VDUP(vector2, , int, s, 16, 4, 0x22);
+ VDUP(vector2, , int, s, 32, 2, 0x33);
+ VDUP(vector2, , int, s, 64, 1, 0x44);
+ VDUP(vector2, , uint, u, 8, 8, 0x55);
+ VDUP(vector2, , uint, u, 16, 4, 0x66);
+ VDUP(vector2, , uint, u, 32, 2, 0x77);
+ VDUP(vector2, , uint, u, 64, 1, 0x88);
+
+ VDUP(vector2, q, int, s, 8, 16, 0x11);
+ VDUP(vector2, q, int, s, 16, 8, 0x22);
+ VDUP(vector2, q, int, s, 32, 4, 0x33);
+ VDUP(vector2, q, int, s, 64, 2, 0x44);
+ VDUP(vector2, q, uint, u, 8, 16, 0x55);
+ VDUP(vector2, q, uint, u, 16, 8, 0x66);
+ VDUP(vector2, q, uint, u, 32, 4, 0x77);
+ VDUP(vector2, q, uint, u, 64, 2, 0x88);
+
+ /* Apply a saturating binary operator named INSN_NAME. */
+ TEST_BINARY_SAT_OP(INSN_NAME, , int, s, 8, 8, expected_cumulative_sat, "");
+ TEST_BINARY_SAT_OP(INSN_NAME, , int, s, 16, 4, expected_cumulative_sat, "");
+ TEST_BINARY_SAT_OP(INSN_NAME, , int, s, 32, 2, expected_cumulative_sat, "");
+ TEST_BINARY_SAT_OP(INSN_NAME, , int, s, 64, 1, expected_cumulative_sat, "");
+ TEST_BINARY_SAT_OP(INSN_NAME, , uint, u, 8, 8, expected_cumulative_sat, "");
+ TEST_BINARY_SAT_OP(INSN_NAME, , uint, u, 16, 4, expected_cumulative_sat, "");
+ TEST_BINARY_SAT_OP(INSN_NAME, , uint, u, 32, 2, expected_cumulative_sat, "");
+ TEST_BINARY_SAT_OP(INSN_NAME, , uint, u, 64, 1, expected_cumulative_sat, "");
+
+ TEST_BINARY_SAT_OP(INSN_NAME, q, int, s, 8, 16, expected_cumulative_sat, "");
+ TEST_BINARY_SAT_OP(INSN_NAME, q, int, s, 16, 8, expected_cumulative_sat, "");
+ TEST_BINARY_SAT_OP(INSN_NAME, q, int, s, 32, 4, expected_cumulative_sat, "");
+ TEST_BINARY_SAT_OP(INSN_NAME, q, int, s, 64, 2, expected_cumulative_sat, "");
+ TEST_BINARY_SAT_OP(INSN_NAME, q, uint, u, 8, 16, expected_cumulative_sat, "");
+ TEST_BINARY_SAT_OP(INSN_NAME, q, uint, u, 16, 8, expected_cumulative_sat, "");
+ TEST_BINARY_SAT_OP(INSN_NAME, q, uint, u, 32, 4, expected_cumulative_sat, "");
+ TEST_BINARY_SAT_OP(INSN_NAME, q, uint, u, 64, 2, expected_cumulative_sat, "");
+
+ CHECK_RESULTS (TEST_MSG, "");
+
+#ifdef EXTRA_TESTS
+ EXTRA_TESTS();
+#endif
+}
+
+int main (void)
+{
+ FNNAME (INSN_NAME) ();
+
+ return 0;
+}
--- /dev/null
+/* Template file for the validation of comparison operator with
+ floating-point support.
+
+ This file is meant to be included by the relevant test files, which
+ have to define the intrinsic family to test. If a given intrinsic
+ supports variants which are not supported by all the other
+ operators, these can be tested by providing a definition for
+ EXTRA_TESTS. */
+
+#include <arm_neon.h>
+#include "arm-neon-ref.h"
+#include "compute-ref-data.h"
+
+/* Additional expected results declaration, they are initialized in
+ each test file. */
+extern ARRAY(expected2, uint, 32, 2);
+extern ARRAY(expected2, uint, 32, 4);
+
+#define FNNAME1(NAME) exec_ ## NAME
+#define FNNAME(NAME) FNNAME1(NAME)
+
+void FNNAME (INSN_NAME) (void)
+{
+ /* Basic test: y=vcomp(x1,x2), then store the result. */
+#define TEST_VCOMP1(INSN, Q, T1, T2, T3, W, N) \
+ VECT_VAR(vector_res, T3, W, N) = \
+ INSN##Q##_##T2##W(VECT_VAR(vector, T1, W, N), \
+ VECT_VAR(vector2, T1, W, N)); \
+ vst1##Q##_u##W(VECT_VAR(result, T3, W, N), VECT_VAR(vector_res, T3, W, N))
+
+#define TEST_VCOMP(INSN, Q, T1, T2, T3, W, N) \
+ TEST_VCOMP1(INSN, Q, T1, T2, T3, W, N)
+
+ DECL_VARIABLE(vector, float, 32, 2);
+ DECL_VARIABLE(vector, float, 32, 4);
+ DECL_VARIABLE(vector2, float, 32, 2);
+ DECL_VARIABLE(vector2, float, 32, 4);
+ DECL_VARIABLE(vector_res, uint, 32, 2);
+ DECL_VARIABLE(vector_res, uint, 32, 4);
+
+ clean_results ();
+
+ /* Initialize input "vector" from "buffer". */
+ VLOAD(vector, buffer, , float, f, 32, 2);
+ VLOAD(vector, buffer, q, float, f, 32, 4);
+
+ /* Choose init value arbitrarily, will be used for vector
+ comparison. */
+ VDUP(vector2, , float, f, 32, 2, -16.0f);
+ VDUP(vector2, q, float, f, 32, 4, -14.0f);
+
+ /* Apply operator named INSN_NAME. */
+ TEST_VCOMP(INSN_NAME, , float, f, uint, 32, 2);
+ CHECK(TEST_MSG, uint, 32, 2, PRIx32, expected, "");
+
+ TEST_VCOMP(INSN_NAME, q, float, f, uint, 32, 4);
+ CHECK(TEST_MSG, uint, 32, 4, PRIx32, expected, "");
+
+ /* Test again, with different input values. */
+ VDUP(vector2, , float, f, 32, 2, -10.0f);
+ VDUP(vector2, q, float, f, 32, 4, 10.0f);
+
+ TEST_VCOMP(INSN_NAME, , float, f, uint, 32, 2);
+ CHECK(TEST_MSG, uint, 32, 2, PRIx32, expected2, "");
+
+ TEST_VCOMP(INSN_NAME, q, float, f, uint, 32, 4);
+ CHECK(TEST_MSG, uint, 32, 4, PRIx32, expected2,"");
+}
+
+int main (void)
+{
+ FNNAME (INSN_NAME) ();
+
+ return 0;
+}
--- /dev/null
+#include <arm_neon.h>
+#include "arm-neon-ref.h"
+#include "compute-ref-data.h"
+#include <math.h>
+
+/* Additional expected results declaration, they are initialized in
+ each test file. */
+extern ARRAY(expected_uint, uint, 8, 8);
+extern ARRAY(expected_uint, uint, 16, 4);
+extern ARRAY(expected_uint, uint, 32, 2);
+extern ARRAY(expected_q_uint, uint, 8, 16);
+extern ARRAY(expected_q_uint, uint, 16, 8);
+extern ARRAY(expected_q_uint, uint, 32, 4);
+extern ARRAY(expected_float, uint, 32, 2);
+extern ARRAY(expected_q_float, uint, 32, 4);
+extern ARRAY(expected_uint2, uint, 32, 2);
+extern ARRAY(expected_uint3, uint, 32, 2);
+extern ARRAY(expected_uint4, uint, 32, 2);
+extern ARRAY(expected_nan, uint, 32, 2);
+extern ARRAY(expected_mnan, uint, 32, 2);
+extern ARRAY(expected_nan2, uint, 32, 2);
+extern ARRAY(expected_inf, uint, 32, 2);
+extern ARRAY(expected_minf, uint, 32, 2);
+extern ARRAY(expected_inf2, uint, 32, 2);
+extern ARRAY(expected_mzero, uint, 32, 2);
+extern ARRAY(expected_p8, uint, 8, 8);
+extern ARRAY(expected_q_p8, uint, 8, 16);
+
+#define FNNAME1(NAME) exec_ ## NAME
+#define FNNAME(NAME) FNNAME1(NAME)
+
+void FNNAME (INSN_NAME) (void)
+{
+ /* Basic test: y=vcomp(x1,x2), then store the result. */
+#define TEST_VCOMP1(INSN, Q, T1, T2, T3, W, N) \
+ VECT_VAR(vector_res, T3, W, N) = \
+ INSN##Q##_##T2##W(VECT_VAR(vector, T1, W, N), \
+ VECT_VAR(vector2, T1, W, N)); \
+ vst1##Q##_u##W(VECT_VAR(result, T3, W, N), VECT_VAR(vector_res, T3, W, N))
+
+#define TEST_VCOMP(INSN, Q, T1, T2, T3, W, N) \
+ TEST_VCOMP1(INSN, Q, T1, T2, T3, W, N)
+
+ /* No need for 64 bits elements. */
+ DECL_VARIABLE(vector, int, 8, 8);
+ DECL_VARIABLE(vector, int, 16, 4);
+ DECL_VARIABLE(vector, int, 32, 2);
+ DECL_VARIABLE(vector, uint, 8, 8);
+ DECL_VARIABLE(vector, uint, 16, 4);
+ DECL_VARIABLE(vector, uint, 32, 2);
+ DECL_VARIABLE(vector, float, 32, 2);
+ DECL_VARIABLE(vector, int, 8, 16);
+ DECL_VARIABLE(vector, int, 16, 8);
+ DECL_VARIABLE(vector, int, 32, 4);
+ DECL_VARIABLE(vector, uint, 8, 16);
+ DECL_VARIABLE(vector, uint, 16, 8);
+ DECL_VARIABLE(vector, uint, 32, 4);
+ DECL_VARIABLE(vector, float, 32, 4);
+
+ DECL_VARIABLE(vector2, int, 8, 8);
+ DECL_VARIABLE(vector2, int, 16, 4);
+ DECL_VARIABLE(vector2, int, 32, 2);
+ DECL_VARIABLE(vector2, uint, 8, 8);
+ DECL_VARIABLE(vector2, uint, 16, 4);
+ DECL_VARIABLE(vector2, uint, 32, 2);
+ DECL_VARIABLE(vector2, float, 32, 2);
+ DECL_VARIABLE(vector2, int, 8, 16);
+ DECL_VARIABLE(vector2, int, 16, 8);
+ DECL_VARIABLE(vector2, int, 32, 4);
+ DECL_VARIABLE(vector2, uint, 8, 16);
+ DECL_VARIABLE(vector2, uint, 16, 8);
+ DECL_VARIABLE(vector2, uint, 32, 4);
+ DECL_VARIABLE(vector2, float, 32, 4);
+
+ DECL_VARIABLE(vector_res, uint, 8, 8);
+ DECL_VARIABLE(vector_res, uint, 16, 4);
+ DECL_VARIABLE(vector_res, uint, 32, 2);
+ DECL_VARIABLE(vector_res, uint, 8, 16);
+ DECL_VARIABLE(vector_res, uint, 16, 8);
+ DECL_VARIABLE(vector_res, uint, 32, 4);
+
+ clean_results ();
+
+ /* There is no 64 bits variant, don't use the generic initializer. */
+ VLOAD(vector, buffer, , int, s, 8, 8);
+ VLOAD(vector, buffer, , int, s, 16, 4);
+ VLOAD(vector, buffer, , int, s, 32, 2);
+ VLOAD(vector, buffer, , uint, u, 8, 8);
+ VLOAD(vector, buffer, , uint, u, 16, 4);
+ VLOAD(vector, buffer, , uint, u, 32, 2);
+ VLOAD(vector, buffer, , float, f, 32, 2);
+
+ VLOAD(vector, buffer, q, int, s, 8, 16);
+ VLOAD(vector, buffer, q, int, s, 16, 8);
+ VLOAD(vector, buffer, q, int, s, 32, 4);
+ VLOAD(vector, buffer, q, uint, u, 8, 16);
+ VLOAD(vector, buffer, q, uint, u, 16, 8);
+ VLOAD(vector, buffer, q, uint, u, 32, 4);
+ VLOAD(vector, buffer, q, float, f, 32, 4);
+
+ /* Choose init value arbitrarily, will be used for vector
+ comparison. */
+ VDUP(vector2, , int, s, 8, 8, -10);
+ VDUP(vector2, , int, s, 16, 4, -14);
+ VDUP(vector2, , int, s, 32, 2, -16);
+ VDUP(vector2, , uint, u, 8, 8, 0xF3);
+ VDUP(vector2, , uint, u, 16, 4, 0xFFF2);
+ VDUP(vector2, , uint, u, 32, 2, 0xFFFFFFF1);
+ VDUP(vector2, , float, f, 32, 2, -15.0f);
+
+ VDUP(vector2, q, int, s, 8, 16, -4);
+ VDUP(vector2, q, int, s, 16, 8, -10);
+ VDUP(vector2, q, int, s, 32, 4, -14);
+ VDUP(vector2, q, uint, u, 8, 16, 0xF4);
+ VDUP(vector2, q, uint, u, 16, 8, 0xFFF6);
+ VDUP(vector2, q, uint, u, 32, 4, 0xFFFFFFF2);
+ VDUP(vector2, q, float, f, 32, 4, -14.0f);
+
+ /* The comparison operators produce only unsigned results, which
+ means that our tests with uint* inputs write their results in the
+ same vectors as the int* variants. As a consequence, we have to
+ execute and test the int* first, then the uint* ones.
+ Same thing for float and poly8.
+ */
+
+ /* Apply operator named INSN_NAME. */
+ TEST_VCOMP(INSN_NAME, , int, s, uint, 8, 8);
+ TEST_VCOMP(INSN_NAME, , int, s, uint, 16, 4);
+ TEST_VCOMP(INSN_NAME, , int, s, uint, 32, 2);
+ TEST_VCOMP(INSN_NAME, q, int, s, uint, 8, 16);
+ TEST_VCOMP(INSN_NAME, q, int, s, uint, 16, 8);
+ TEST_VCOMP(INSN_NAME, q, int, s, uint, 32, 4);
+
+ CHECK(TEST_MSG, uint, 8, 8, PRIx8, expected, "");
+ CHECK(TEST_MSG, uint, 16, 4, PRIx16, expected, "");
+ CHECK(TEST_MSG, uint, 32, 2, PRIx32, expected, "");
+ CHECK(TEST_MSG, uint, 8, 16, PRIx8, expected, "");
+ CHECK(TEST_MSG, uint, 16, 8, PRIx16, expected, "");
+ CHECK(TEST_MSG, uint, 32, 4, PRIx32, expected, "");
+
+ /* Now the uint* variants. */
+ TEST_VCOMP(INSN_NAME, , uint, u, uint, 8, 8);
+ TEST_VCOMP(INSN_NAME, , uint, u, uint, 16, 4);
+ TEST_VCOMP(INSN_NAME, , uint, u, uint, 32, 2);
+ TEST_VCOMP(INSN_NAME, q, uint, u, uint, 8, 16);
+ TEST_VCOMP(INSN_NAME, q, uint, u, uint, 16, 8);
+ TEST_VCOMP(INSN_NAME, q, uint, u, uint, 32, 4);
+
+ CHECK(TEST_MSG, uint, 8, 8, PRIx8, expected_uint, "");
+ CHECK(TEST_MSG, uint, 16, 4, PRIx16, expected_uint, "");
+ CHECK(TEST_MSG, uint, 32, 2, PRIx32, expected_uint, "");
+ CHECK(TEST_MSG, uint, 8, 16, PRIx8, expected_q_uint, "");
+ CHECK(TEST_MSG, uint, 16, 8, PRIx16, expected_q_uint, "");
+ CHECK(TEST_MSG, uint, 32, 4, PRIx32, expected_q_uint, "");
+
+ /* The float variants. */
+ TEST_VCOMP(INSN_NAME, , float, f, uint, 32, 2);
+ CHECK(TEST_MSG, uint, 32, 2, PRIx32, expected_float, "");
+
+ TEST_VCOMP(INSN_NAME, q, float, f, uint, 32, 4);
+ CHECK(TEST_MSG, uint, 32, 4, PRIx32, expected_q_float, "");
+
+ /* Some "special" input values to test some corner cases. */
+ /* Extra tests to have 100% coverage on all the variants. */
+ VDUP(vector2, , uint, u, 32, 2, 0xFFFFFFF0);
+ TEST_VCOMP(INSN_NAME, , uint, u, uint, 32, 2);
+ CHECK(TEST_MSG, uint, 32, 2, PRIx32, expected_uint2, "uint 0xfffffff0");
+
+ VDUP(vector2, , int, s, 32, 2, -15);
+ TEST_VCOMP(INSN_NAME, , int, s, uint, 32, 2);
+ CHECK(TEST_MSG, uint, 32, 2, PRIx32, expected_uint3, "int -15");
+
+ VDUP(vector2, , float, f, 32, 2, -16.0f);
+ TEST_VCOMP(INSN_NAME, , float, f, uint, 32, 2);
+ CHECK(TEST_MSG, uint, 32, 2, PRIx32, expected_uint4, "float -16.0f");
+
+
+ /* Extra FP tests with special values (NaN, ....). */
+ VDUP(vector, , float, f, 32, 2, 1.0);
+ VDUP(vector2, , float, f, 32, 2, NAN);
+ TEST_VCOMP(INSN_NAME, , float, f, uint, 32, 2);
+ CHECK(TEST_MSG, uint, 32, 2, PRIx32, expected_nan, "FP special (NaN)");
+
+ VDUP(vector, , float, f, 32, 2, 1.0);
+ VDUP(vector2, , float, f, 32, 2, -NAN);
+ TEST_VCOMP(INSN_NAME, , float, f, uint, 32, 2);
+ CHECK(TEST_MSG, uint, 32, 2, PRIx32, expected_mnan, " FP special (-NaN)");
+
+ VDUP(vector, , float, f, 32, 2, NAN);
+ VDUP(vector2, , float, f, 32, 2, 1.0);
+ TEST_VCOMP(INSN_NAME, , float, f, uint, 32, 2);
+ CHECK(TEST_MSG, uint, 32, 2, PRIx32, expected_nan2, " FP special (NaN)");
+
+ VDUP(vector, , float, f, 32, 2, 1.0);
+ VDUP(vector2, , float, f, 32, 2, HUGE_VALF);
+ TEST_VCOMP(INSN_NAME, , float, f, uint, 32, 2);
+ CHECK(TEST_MSG, uint, 32, 2, PRIx32, expected_inf, " FP special (inf)");
+
+ VDUP(vector, , float, f, 32, 2, 1.0);
+ VDUP(vector2, , float, f, 32, 2, -HUGE_VALF);
+ TEST_VCOMP(INSN_NAME, , float, f, uint, 32, 2);
+ CHECK(TEST_MSG, uint, 32, 2, PRIx32, expected_minf, " FP special (-inf)");
+
+ VDUP(vector, , float, f, 32, 2, HUGE_VALF);
+ VDUP(vector2, , float, f, 32, 2, 1.0);
+ TEST_VCOMP(INSN_NAME, , float, f, uint, 32, 2);
+ CHECK(TEST_MSG, uint, 32, 2, PRIx32, expected_inf2, " FP special (inf)");
+
+ VDUP(vector, , float, f, 32, 2, -0.0);
+ VDUP(vector2, , float, f, 32, 2, 0.0);
+ TEST_VCOMP(INSN_NAME, , float, f, uint, 32, 2);
+ CHECK(TEST_MSG, uint, 32, 2, PRIx32, expected_mzero, " FP special (-0.0)");
+
+#ifdef EXTRA_TESTS
+ EXTRA_TESTS();
+#endif
+}
+
+int main (void)
+{
+ FNNAME (INSN_NAME) ();
+
+ return 0;
+}
--- /dev/null
+/* This file contains input data static definitions, shared by most of
+ the tests. */
+
+#include <arm_neon.h>
+#include "arm-neon-ref.h"
+
+/* Initialization helpers; 4 slices are needed for vld2, vld3 and
+ vld4. */
+#define MY_INIT_TABLE(T,W,N) xNAME(INIT_TABLE,N)(T##W##_t)
+#define MY_INIT_TABLE2(T,W,N) xNAME(INIT_TABLE2,N)(T##W##_t)
+#define MY_INIT_TABLE3(T,W,N) xNAME(INIT_TABLE3,N)(T##W##_t)
+#define MY_INIT_TABLE4(T,W,N) xNAME(INIT_TABLE4,N)(T##W##_t)
+
+/* Initialized input buffers. */
+#define VECT_VAR_DECL_INIT(V, T, W, N) \
+ VECT_VAR_DECL(V,T,W,N) [] = { MY_INIT_TABLE(T,W,N) }
+
+/* Specialized initializer with 4 entries, as used by vldX_dup and
+ vdup tests, which iterate 4 times on input buffers. */
+#define VECT_VAR_DECL_INIT4(V, T, W, N) \
+ VECT_VAR_DECL(V,T,W,N) [] = { MY_INIT_TABLE(T,W,4) };
+
+/* Initializers for arrays of vectors. */
+#define VECT_ARRAY_INIT2(V, T, W, N) \
+ T##W##_t VECT_ARRAY_VAR(V,T,W,N,2)[] = \
+ { MY_INIT_TABLE(T,W,N) \
+ MY_INIT_TABLE2(T,W,N) }
+
+#define VECT_ARRAY_INIT3(V, T, W, N) \
+ T##W##_t VECT_ARRAY_VAR(V,T,W,N,3)[] = \
+ { MY_INIT_TABLE(T,W,N) \
+ MY_INIT_TABLE2(T,W,N) \
+ MY_INIT_TABLE3(T,W,N) }
+
+#define VECT_ARRAY_INIT4(V, T, W, N) \
+ T##W##_t VECT_ARRAY_VAR(V,T,W,N,4)[] = \
+ { MY_INIT_TABLE(T,W,N) \
+ MY_INIT_TABLE2(T,W,N) \
+ MY_INIT_TABLE3(T,W,N) \
+ MY_INIT_TABLE4(T,W,N) }
+
+/* Sample initialization vectors. */
+#define INIT_TABLE_1(T) \
+ (T)-16,
+#define INIT_TABLE2_1(T) \
+ (T)-15,
+#define INIT_TABLE3_1(T) \
+ (T)-14,
+#define INIT_TABLE4_1(T) \
+ (T)-13,
+
+#define INIT_TABLE_2(T) \
+ (T)-16, (T)-15,
+#define INIT_TABLE2_2(T) \
+ (T)-14, (T)-13,
+#define INIT_TABLE3_2(T) \
+ (T)-12, (T)-11,
+#define INIT_TABLE4_2(T) \
+ (T)-10, (T)-9,
+
+/* Initializer for vld3_lane tests. */
+#define INIT_TABLE_3(T) \
+ (T)-16, (T)-15, (T)-14,
+
+#define INIT_TABLE_4(T) \
+ (T)-16, (T)-15, (T)-14, (T)-13,
+#define INIT_TABLE2_4(T) \
+ (T)-12, (T)-11, (T)-10, (T)-9,
+#define INIT_TABLE3_4(T) \
+ (T)-8, (T)-7, (T)-6, (T)-5,
+#define INIT_TABLE4_4(T) \
+ (T)-4, (T)-3, (T)-2, (T)-1,
+
+#define INIT_TABLE_8(T) \
+ (T)-16, (T)-15, (T)-14, (T)-13, (T)-12, (T)-11, (T)-10, (T)-9,
+#define INIT_TABLE2_8(T) \
+ (T)-8, (T)-7, (T)-6, (T)-5, (T)-4, (T)-3, (T)-2, (T)-1,
+#define INIT_TABLE3_8(T) \
+ (T)0, (T)1, (T)2, (T)3, (T)4, (T)5, (T)6, (T)7,
+#define INIT_TABLE4_8(T) \
+ (T)8, (T)9, (T)10, (T)11, (T)12, (T)13, (T)14, (T)15,
+
+#define INIT_TABLE_16(T) \
+ (T)-16, (T)-15, (T)-14, (T)-13, (T)-12, (T)-11, (T)-10, (T)-9, \
+ (T)-8, (T)-7, (T)-6, (T)-5, (T)-4, (T)-3, (T)-2, (T)-1,
+#define INIT_TABLE2_16(T) \
+ (T)0, (T)1, (T)2, (T)3, (T)4, (T)5, (T)6, (T)7, \
+ (T)8, (T)9, (T)10, (T)11, (T)12, (T)13, (T)14, (T)15,
+#define INIT_TABLE3_16(T) \
+ (T)16, (T)17, (T)18, (T)19, (T)20, (T)21, (T)22, (T)23, \
+ (T)24, (T)25, (T)26, (T)27, (T)28, (T)29, (T)30, (T)31,
+#define INIT_TABLE4_16(T) \
+ (T)32, (T)33, (T)34, (T)35, (T)36, (T)37, (T)38, (T)39, \
+ (T)40, (T)41, (T)42, (T)43, (T)44, (T)45, (T)46, (T)47,
+
+/* This one is used for padding between input buffers. */
+#define PAD(V, T, W, N) char VECT_VAR(V,T,W,N)=42
+
+/* Input buffers, one of each size. */
+/* Insert some padding to try to exhibit out of bounds accesses. */
+VECT_VAR_DECL_INIT(buffer, int, 8, 8);
+PAD(buffer_pad, int, 8, 8);
+VECT_VAR_DECL_INIT(buffer, int, 16, 4);
+PAD(buffer_pad, int, 16, 4);
+VECT_VAR_DECL_INIT(buffer, int, 32, 2);
+PAD(buffer_pad, int, 32, 2);
+VECT_VAR_DECL_INIT(buffer, int, 64, 1);
+PAD(buffer_pad, int, 64, 1);
+VECT_VAR_DECL_INIT(buffer, uint, 8, 8);
+PAD(buffer_pad, uint, 8, 8);
+VECT_VAR_DECL_INIT(buffer, poly, 8, 8);
+PAD(buffer_pad, poly, 8, 8);
+VECT_VAR_DECL_INIT(buffer, poly, 16, 4);
+PAD(buffer_pad, poly, 16, 4);
+VECT_VAR_DECL_INIT(buffer, uint, 16, 4);
+PAD(buffer_pad, uint, 16, 4);
+VECT_VAR_DECL_INIT(buffer, uint, 32, 2);
+PAD(buffer_pad, uint, 32, 2);
+VECT_VAR_DECL_INIT(buffer, uint, 64, 1);
+PAD(buffer_pad, uint, 64, 1);
+VECT_VAR_DECL_INIT(buffer, float, 32, 2);
+PAD(buffer_pad, float, 32, 2);
+VECT_VAR_DECL_INIT(buffer, int, 8, 16);
+PAD(buffer_pad, int, 8, 16);
+VECT_VAR_DECL_INIT(buffer, int, 16, 8);
+PAD(buffer_pad, int, 16, 8);
+VECT_VAR_DECL_INIT(buffer, int, 32, 4);
+PAD(buffer_pad, int, 32, 4);
+VECT_VAR_DECL_INIT(buffer, int, 64, 2);
+PAD(buffer_pad, int, 64, 2);
+VECT_VAR_DECL_INIT(buffer, uint, 8, 16);
+PAD(buffer_pad, uint, 8, 16);
+VECT_VAR_DECL_INIT(buffer, uint, 16, 8);
+PAD(buffer_pad, uint, 16, 8);
+VECT_VAR_DECL_INIT(buffer, uint, 32, 4);
+PAD(buffer_pad, uint, 32, 4);
+VECT_VAR_DECL_INIT(buffer, uint, 64, 2);
+PAD(buffer_pad, uint, 64, 2);
+VECT_VAR_DECL_INIT(buffer, poly, 8, 16);
+PAD(buffer_pad, poly, 8, 16);
+VECT_VAR_DECL_INIT(buffer, poly, 16, 8);
+PAD(buffer_pad, poly, 16, 8);
+VECT_VAR_DECL_INIT(buffer, float, 32, 4);
+PAD(buffer_pad, float, 32, 4);
+
+/* The tests for vld1_dup and vdup expect at least 4 entries in the
+ input buffer, so force 1- and 2-elements initializers to have 4
+ entries (using VECT_VAR_DECL_INIT4). */
+VECT_VAR_DECL_INIT(buffer_dup, int, 8, 8);
+VECT_VAR_DECL(buffer_dup_pad, int, 8, 8);
+VECT_VAR_DECL_INIT(buffer_dup, int, 16, 4);
+VECT_VAR_DECL(buffer_dup_pad, int, 16, 4);
+VECT_VAR_DECL_INIT4(buffer_dup, int, 32, 2);
+VECT_VAR_DECL(buffer_dup_pad, int, 32, 2);
+VECT_VAR_DECL_INIT4(buffer_dup, int, 64, 1);
+VECT_VAR_DECL(buffer_dup_pad, int, 64, 1);
+VECT_VAR_DECL_INIT(buffer_dup, uint, 8, 8);
+VECT_VAR_DECL(buffer_dup_pad, uint, 8, 8);
+VECT_VAR_DECL_INIT(buffer_dup, uint, 16, 4);
+VECT_VAR_DECL(buffer_dup_pad, uint, 16, 4);
+VECT_VAR_DECL_INIT4(buffer_dup, uint, 32, 2);
+VECT_VAR_DECL(buffer_dup_pad, uint, 32, 2);
+VECT_VAR_DECL_INIT4(buffer_dup, uint, 64, 1);
+VECT_VAR_DECL(buffer_dup_pad, uint, 64, 1);
+VECT_VAR_DECL_INIT(buffer_dup, poly, 8, 8);
+VECT_VAR_DECL(buffer_dup_pad, poly, 8, 8);
+VECT_VAR_DECL_INIT(buffer_dup, poly, 16, 4);
+VECT_VAR_DECL(buffer_dup_pad, poly, 16, 4);
+VECT_VAR_DECL_INIT4(buffer_dup, float, 32, 2);
+VECT_VAR_DECL(buffer_dup_pad, float, 32, 2);
+
+VECT_VAR_DECL_INIT(buffer_dup, int, 8, 16);
+VECT_VAR_DECL(buffer_dup_pad, int, 8, 16);
+VECT_VAR_DECL_INIT(buffer_dup, int, 16, 8);
+VECT_VAR_DECL(buffer_dup_pad, int, 16, 8);
+VECT_VAR_DECL_INIT(buffer_dup, int, 32, 4);
+VECT_VAR_DECL(buffer_dup_pad, int, 32, 4);
+VECT_VAR_DECL_INIT4(buffer_dup, int, 64, 2);
+VECT_VAR_DECL(buffer_dup_pad, int, 64, 2);
+VECT_VAR_DECL_INIT(buffer_dup, uint, 8, 16);
+VECT_VAR_DECL(buffer_dup_pad, uint, 8, 16);
+VECT_VAR_DECL_INIT(buffer_dup, uint, 16, 8);
+VECT_VAR_DECL(buffer_dup_pad, uint, 16, 8);
+VECT_VAR_DECL_INIT(buffer_dup, uint, 32, 4);
+VECT_VAR_DECL(buffer_dup_pad, uint, 32, 4);
+VECT_VAR_DECL_INIT4(buffer_dup, uint, 64, 2);
+VECT_VAR_DECL(buffer_dup_pad, uint, 64, 2);
+VECT_VAR_DECL_INIT(buffer_dup, poly, 8, 16);
+VECT_VAR_DECL(buffer_dup_pad, poly, 8, 16);
+VECT_VAR_DECL_INIT(buffer_dup, poly, 16, 8);
+VECT_VAR_DECL(buffer_dup_pad, poly, 16, 8);
+VECT_VAR_DECL_INIT(buffer_dup, float, 32, 4);
+VECT_VAR_DECL(buffer_dup_pad, float, 32, 4);
--- /dev/null
+/* Template file for unary operator validation.
+
+ This file is meant to be included by the relevant test files, which
+ have to define the intrinsic family to test. If a given intrinsic
+ supports variants which are not supported by all the other unary
+ operators, these can be tested by providing a definition for
+ EXTRA_TESTS. */
+
+#include <arm_neon.h>
+#include "arm-neon-ref.h"
+#include "compute-ref-data.h"
+
+#define FNNAME1(NAME) exec_ ## NAME
+#define FNNAME(NAME) FNNAME1(NAME)
+
+void FNNAME (INSN_NAME) (void)
+{
+ /* Basic test: y=OP(x), then store the result. */
+#define TEST_UNARY_OP1(INSN, Q, T1, T2, W, N) \
+ VECT_VAR(vector_res, T1, W, N) = \
+ INSN##Q##_##T2##W(VECT_VAR(vector, T1, W, N)); \
+ vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N), VECT_VAR(vector_res, T1, W, N))
+
+#define TEST_UNARY_OP(INSN, Q, T1, T2, W, N) \
+ TEST_UNARY_OP1(INSN, Q, T1, T2, W, N) \
+
+ /* No need for 64 bits variants in the general case. */
+ DECL_VARIABLE(vector, int, 8, 8);
+ DECL_VARIABLE(vector, int, 16, 4);
+ DECL_VARIABLE(vector, int, 32, 2);
+ DECL_VARIABLE(vector, int, 8, 16);
+ DECL_VARIABLE(vector, int, 16, 8);
+ DECL_VARIABLE(vector, int, 32, 4);
+
+ DECL_VARIABLE(vector_res, int, 8, 8);
+ DECL_VARIABLE(vector_res, int, 16, 4);
+ DECL_VARIABLE(vector_res, int, 32, 2);
+ DECL_VARIABLE(vector_res, int, 8, 16);
+ DECL_VARIABLE(vector_res, int, 16, 8);
+ DECL_VARIABLE(vector_res, int, 32, 4);
+
+ clean_results ();
+
+ /* Initialize input "vector" from "buffer". */
+ VLOAD(vector, buffer, , int, s, 8, 8);
+ VLOAD(vector, buffer, , int, s, 16, 4);
+ VLOAD(vector, buffer, , int, s, 32, 2);
+ VLOAD(vector, buffer, q, int, s, 8, 16);
+ VLOAD(vector, buffer, q, int, s, 16, 8);
+ VLOAD(vector, buffer, q, int, s, 32, 4);
+
+ /* Apply a unary operator named INSN_NAME. */
+ TEST_UNARY_OP(INSN_NAME, , int, s, 8, 8);
+ TEST_UNARY_OP(INSN_NAME, , int, s, 16, 4);
+ TEST_UNARY_OP(INSN_NAME, , int, s, 32, 2);
+ TEST_UNARY_OP(INSN_NAME, q, int, s, 8, 16);
+ TEST_UNARY_OP(INSN_NAME, q, int, s, 16, 8);
+ TEST_UNARY_OP(INSN_NAME, q, int, s, 32, 4);
+
+ CHECK_RESULTS (TEST_MSG, "");
+
+#ifdef EXTRA_TESTS
+ EXTRA_TESTS();
+#endif
+}
+
+int main (void)
+{
+ FNNAME (INSN_NAME)();
+
+ return 0;
+}
--- /dev/null
+/* Template file for saturating unary operator validation.
+
+ This file is meant to be included by the relevant test files, which
+ have to define the intrinsic family to test. If a given intrinsic
+ supports variants which are not supported by all the other
+ saturating unary operators, these can be tested by providing a
+ definition for EXTRA_TESTS. */
+
+#include <arm_neon.h>
+#include "arm-neon-ref.h"
+#include "compute-ref-data.h"
+
+#define FNNAME1(NAME) exec_ ## NAME
+#define FNNAME(NAME) FNNAME1(NAME)
+
+void FNNAME (INSN_NAME) (void)
+{
+ /* y=OP(x), then store the result. */
+#define TEST_UNARY_SAT_OP1(INSN, Q, T1, T2, W, N, EXPECTED_CUMULATIVE_SAT, CMT) \
+ Set_Neon_Cumulative_Sat(0); \
+ VECT_VAR(vector_res, T1, W, N) = \
+ INSN##Q##_##T2##W(VECT_VAR(vector, T1, W, N)); \
+ vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N), \
+ VECT_VAR(vector_res, T1, W, N)); \
+ CHECK_CUMULATIVE_SAT(TEST_MSG, T1, W, N, EXPECTED_CUMULATIVE_SAT, CMT)
+
+#define TEST_UNARY_SAT_OP(INSN, Q, T1, T2, W, N, EXPECTED_CUMULATIVE_SAT, CMT) \
+ TEST_UNARY_SAT_OP1(INSN, Q, T1, T2, W, N, EXPECTED_CUMULATIVE_SAT, CMT)
+
+ /* No need for 64 bits variants. */
+ DECL_VARIABLE(vector, int, 8, 8);
+ DECL_VARIABLE(vector, int, 16, 4);
+ DECL_VARIABLE(vector, int, 32, 2);
+ DECL_VARIABLE(vector, int, 8, 16);
+ DECL_VARIABLE(vector, int, 16, 8);
+ DECL_VARIABLE(vector, int, 32, 4);
+
+ DECL_VARIABLE(vector_res, int, 8, 8);
+ DECL_VARIABLE(vector_res, int, 16, 4);
+ DECL_VARIABLE(vector_res, int, 32, 2);
+ DECL_VARIABLE(vector_res, int, 8, 16);
+ DECL_VARIABLE(vector_res, int, 16, 8);
+ DECL_VARIABLE(vector_res, int, 32, 4);
+
+ clean_results ();
+
+ /* Initialize input "vector" from "buffer". */
+ VLOAD(vector, buffer, , int, s, 8, 8);
+ VLOAD(vector, buffer, , int, s, 16, 4);
+ VLOAD(vector, buffer, , int, s, 32, 2);
+ VLOAD(vector, buffer, q, int, s, 8, 16);
+ VLOAD(vector, buffer, q, int, s, 16, 8);
+ VLOAD(vector, buffer, q, int, s, 32, 4);
+
+ /* Apply a saturating unary operator named INSN_NAME. */
+ TEST_UNARY_SAT_OP(INSN_NAME, , int, s, 8, 8, expected_cumulative_sat, "");
+ TEST_UNARY_SAT_OP(INSN_NAME, , int, s, 16, 4, expected_cumulative_sat, "");
+ TEST_UNARY_SAT_OP(INSN_NAME, , int, s, 32, 2, expected_cumulative_sat, "");
+ TEST_UNARY_SAT_OP(INSN_NAME, q, int, s, 8, 16, expected_cumulative_sat, "");
+ TEST_UNARY_SAT_OP(INSN_NAME, q, int, s, 16, 8, expected_cumulative_sat, "");
+ TEST_UNARY_SAT_OP(INSN_NAME, q, int, s, 32, 4, expected_cumulative_sat, "");
+
+ CHECK(TEST_MSG, int, 8, 8, PRIx8, expected, "");
+ CHECK(TEST_MSG, int, 16, 4, PRIx8, expected, "");
+ CHECK(TEST_MSG, int, 32, 2, PRIx8, expected, "");
+ CHECK(TEST_MSG, int, 8, 16, PRIx8, expected, "");
+ CHECK(TEST_MSG, int, 16, 8, PRIx8, expected, "");
+ CHECK(TEST_MSG, int, 32, 4, PRIx8, expected, "");
+
+#ifdef EXTRA_TESTS
+ EXTRA_TESTS();
+#endif
+}
+
+int main (void)
+{
+ FNNAME (INSN_NAME) ();
+
+ return 0;
+}
--- /dev/null
+#include <arm_neon.h>
+#include "arm-neon-ref.h"
+#include "compute-ref-data.h"
+
+/* Expected results. */
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf6, 0xf7, 0xf8, 0xf9,
+ 0xfa, 0xfb, 0xfc, 0xfd };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x16, 0x17, 0x18, 0x19 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x20, 0x21 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x53, 0x54, 0x55, 0x56,
+ 0x57, 0x58, 0x59, 0x5a };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x907, 0x908, 0x909, 0x90a };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffe7, 0xffffffe8 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x5e, 0x5f, 0x60, 0x61,
+ 0x62, 0x63, 0x64, 0x65,
+ 0x66, 0x67, 0x68, 0x69,
+ 0x6a, 0x6b, 0x6c, 0x6d };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xb9c, 0xb9d, 0xb9e, 0xb9f,
+ 0xba0, 0xba1, 0xba2, 0xba3 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x26e0, 0x26e1, 0x26e2, 0x26e3 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf8, 0xf9, 0xfa, 0xfb,
+ 0xfc, 0xfd, 0xfe, 0xff,
+ 0x0, 0x1, 0x2, 0x3,
+ 0x4, 0x5, 0x6, 0x7 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff9, 0xfffa, 0xfffb, 0xfffc,
+ 0xfffd, 0xfffe, 0xffff, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xc, 0xd, 0xe, 0xf };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333,
+ 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333,
+ 0x33333333, 0x33333333 };
+
+#define TEST_MSG "VABA/VABAQ"
+void exec_vaba (void)
+{
+ /* Basic test: v4=vaba(v1,v2,v3), then store the result. */
+#define TEST_VABA(Q, T1, T2, W, N) \
+ VECT_VAR(vector_res, T1, W, N) = \
+ vaba##Q##_##T2##W(VECT_VAR(vector1, T1, W, N), \
+ VECT_VAR(vector2, T1, W, N), \
+ VECT_VAR(vector3, T1, W, N)); \
+ vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N), VECT_VAR(vector_res, T1, W, N))
+
+#define DECL_VABA_VAR(VAR) \
+ DECL_VARIABLE(VAR, int, 8, 8); \
+ DECL_VARIABLE(VAR, int, 16, 4); \
+ DECL_VARIABLE(VAR, int, 32, 2); \
+ DECL_VARIABLE(VAR, uint, 8, 8); \
+ DECL_VARIABLE(VAR, uint, 16, 4); \
+ DECL_VARIABLE(VAR, uint, 32, 2); \
+ DECL_VARIABLE(VAR, int, 8, 16); \
+ DECL_VARIABLE(VAR, int, 16, 8); \
+ DECL_VARIABLE(VAR, int, 32, 4); \
+ DECL_VARIABLE(VAR, uint, 8, 16); \
+ DECL_VARIABLE(VAR, uint, 16, 8); \
+ DECL_VARIABLE(VAR, uint, 32, 4)
+
+ DECL_VABA_VAR(vector1);
+ DECL_VABA_VAR(vector2);
+ DECL_VABA_VAR(vector3);
+ DECL_VABA_VAR(vector_res);
+
+ clean_results ();
+
+ /* Initialize input "vector1" from "buffer". */
+ VLOAD(vector1, buffer, , int, s, 8, 8);
+ VLOAD(vector1, buffer, , int, s, 16, 4);
+ VLOAD(vector1, buffer, , int, s, 32, 2);
+ VLOAD(vector1, buffer, , uint, u, 8, 8);
+ VLOAD(vector1, buffer, , uint, u, 16, 4);
+ VLOAD(vector1, buffer, , uint, u, 32, 2);
+ VLOAD(vector1, buffer, q, int, s, 8, 16);
+ VLOAD(vector1, buffer, q, int, s, 16, 8);
+ VLOAD(vector1, buffer, q, int, s, 32, 4);
+ VLOAD(vector1, buffer, q, uint, u, 8, 16);
+ VLOAD(vector1, buffer, q, uint, u, 16, 8);
+ VLOAD(vector1, buffer, q, uint, u, 32, 4);
+
+ /* Choose init value arbitrarily. */
+ VDUP(vector2, , int, s, 8, 8, 1);
+ VDUP(vector2, , int, s, 16, 4, -13);
+ VDUP(vector2, , int, s, 32, 2, 8);
+ VDUP(vector2, , uint, u, 8, 8, 1);
+ VDUP(vector2, , uint, u, 16, 4, 13);
+ VDUP(vector2, , uint, u, 32, 2, 8);
+ VDUP(vector2, q, int, s, 8, 16, 10);
+ VDUP(vector2, q, int, s, 16, 8, -12);
+ VDUP(vector2, q, int, s, 32, 4, 32);
+ VDUP(vector2, q, uint, u, 8, 16, 10);
+ VDUP(vector2, q, uint, u, 16, 8, 12);
+ VDUP(vector2, q, uint, u, 32, 4, 32);
+
+ /* Choose init value arbitrarily. */
+ VDUP(vector3, , int, s, 8, 8, -5);
+ VDUP(vector3, , int, s, 16, 4, 25);
+ VDUP(vector3, , int, s, 32, 2, -40);
+ VDUP(vector3, , uint, u, 8, 8, 100);
+ VDUP(vector3, , uint, u, 16, 4, 2340);
+ VDUP(vector3, , uint, u, 32, 2, 0xffffffff);
+ VDUP(vector3, q, int, s, 8, 16, -100);
+ VDUP(vector3, q, int, s, 16, 8, -3000);
+ VDUP(vector3, q, int, s, 32, 4, 10000);
+ VDUP(vector3, q, uint, u, 8, 16, 2);
+ VDUP(vector3, q, uint, u, 16, 8, 3);
+ VDUP(vector3, q, uint, u, 32, 4, 4);
+
+ /* Execute the tests. */
+ TEST_VABA(, int, s, 8, 8);
+ TEST_VABA(, int, s, 16, 4);
+ TEST_VABA(, int, s, 32, 2);
+ TEST_VABA(, uint, u, 8, 8);
+ TEST_VABA(, uint, u, 16, 4);
+ TEST_VABA(, uint, u, 32, 2);
+ TEST_VABA(q, int, s, 8, 16);
+ TEST_VABA(q, int, s, 16, 8);
+ TEST_VABA(q, int, s, 32, 4);
+ TEST_VABA(q, uint, u, 8, 16);
+ TEST_VABA(q, uint, u, 16, 8);
+ TEST_VABA(q, uint, u, 32, 4);
+
+ CHECK_RESULTS (TEST_MSG, "");
+}
+
+int main (void)
+{
+ exec_vaba ();
+ return 0;
+}
--- /dev/null
+#include <arm_neon.h>
+#include "arm-neon-ref.h"
+#include "compute-ref-data.h"
+
+/* Expected results. */
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff6, 0xfff7, 0xfff8, 0xfff9,
+ 0xfffa, 0xfffb, 0xfffc, 0xfffd };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x16, 0x17, 0x18, 0x19 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x20, 0x21 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x53, 0x54, 0x55, 0x56,
+ 0x57, 0x58, 0x59, 0x5a };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x907, 0x908, 0x909, 0x90a };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffe7,
+ 0xffffffe8 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333,
+ 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333,
+ 0x33333333, 0x33333333 };
+
+/* Expected results for cases with input values chosen to test
+ possible intermediate overflow. */
+VECT_VAR_DECL(expected2,int,16,8) [] = { 0xef, 0xf0, 0xf1, 0xf2,
+ 0xf3, 0xf4, 0xf5, 0xf6 };
+VECT_VAR_DECL(expected2,int,32,4) [] = { 0xffef, 0xfff0, 0xfff1, 0xfff2 };
+VECT_VAR_DECL(expected2,int,64,2) [] = { 0xffffffef, 0xfffffff0 };
+VECT_VAR_DECL(expected2,uint,16,8) [] = { 0xee, 0xef, 0xf0, 0xf1,
+ 0xf2, 0xf3, 0xf4, 0xf5 };
+VECT_VAR_DECL(expected2,uint,32,4) [] = { 0xffe2, 0xffe3, 0xffe4, 0xffe5 };
+VECT_VAR_DECL(expected2,uint,64,2) [] = { 0xffffffe7, 0xffffffe8 };
+
+#define TEST_MSG "VABAL"
+void exec_vabal (void)
+{
+ /* Basic test: v4=vabal(v1,v2,v3), then store the result. */
+#define TEST_VABAL(T1, T2, W, W2, N) \
+ VECT_VAR(vector_res, T1, W2, N) = \
+ vabal_##T2##W(VECT_VAR(vector1, T1, W2, N), \
+ VECT_VAR(vector2, T1, W, N), \
+ VECT_VAR(vector3, T1, W, N)); \
+ vst1q_##T2##W2(VECT_VAR(result, T1, W2, N), VECT_VAR(vector_res, T1, W2, N))
+
+#define DECL_VABAL_VAR_LONG(VAR) \
+ DECL_VARIABLE(VAR, int, 16, 8); \
+ DECL_VARIABLE(VAR, int, 32, 4); \
+ DECL_VARIABLE(VAR, int, 64, 2); \
+ DECL_VARIABLE(VAR, uint, 16, 8); \
+ DECL_VARIABLE(VAR, uint, 32, 4); \
+ DECL_VARIABLE(VAR, uint, 64, 2)
+
+#define DECL_VABAL_VAR_SHORT(VAR) \
+ DECL_VARIABLE(VAR, int, 8, 8); \
+ DECL_VARIABLE(VAR, int, 16, 4); \
+ DECL_VARIABLE(VAR, int, 32, 2); \
+ DECL_VARIABLE(VAR, uint, 8, 8); \
+ DECL_VARIABLE(VAR, uint, 16, 4); \
+ DECL_VARIABLE(VAR, uint, 32, 2)
+
+ DECL_VABAL_VAR_LONG(vector1);
+ DECL_VABAL_VAR_SHORT(vector2);
+ DECL_VABAL_VAR_SHORT(vector3);
+ DECL_VABAL_VAR_LONG(vector_res);
+
+ clean_results ();
+
+ /* Initialize input "vector1" from "buffer". */
+ VLOAD(vector1, buffer, q, int, s, 16, 8);
+ VLOAD(vector1, buffer, q, int, s, 32, 4);
+ VLOAD(vector1, buffer, q, int, s, 64, 2);
+ VLOAD(vector1, buffer, q, uint, u, 16, 8);
+ VLOAD(vector1, buffer, q, uint, u, 32, 4);
+ VLOAD(vector1, buffer, q, uint, u, 64, 2);
+
+
+ /* Choose init value arbitrarily. */
+ VDUP(vector2, , int, s, 8, 8, 1);
+ VDUP(vector2, , int, s, 16, 4, -13);
+ VDUP(vector2, , int, s, 32, 2, 8);
+ VDUP(vector2, , uint, u, 8, 8, 1);
+ VDUP(vector2, , uint, u, 16, 4, 13);
+ VDUP(vector2, , uint, u, 32, 2, 8);
+
+ /* Choose init value arbitrarily. */
+ VDUP(vector3, , int, s, 8, 8, -5);
+ VDUP(vector3, , int, s, 16, 4, 25);
+ VDUP(vector3, , int, s, 32, 2, -40);
+ VDUP(vector3, , uint, u, 8, 8, 100);
+ VDUP(vector3, , uint, u, 16, 4, 2340);
+ VDUP(vector3, , uint, u, 32, 2, 0xffffffff);
+
+ /* Execute the tests. */
+ TEST_VABAL(int, s, 8, 16, 8);
+ TEST_VABAL(int, s, 16, 32, 4);
+ TEST_VABAL(int, s, 32, 64, 2);
+ TEST_VABAL(uint, u, 8, 16, 8);
+ TEST_VABAL(uint, u, 16, 32, 4);
+ TEST_VABAL(uint, u, 32, 64, 2);
+
+ CHECK_RESULTS (TEST_MSG, "");
+
+ /* Use values that could lead to overflow intermediate
+ * calculations. */
+ VDUP(vector2, , int, s, 8, 8, 0x80);
+ VDUP(vector2, , int, s, 16, 4, 0x8000);
+ VDUP(vector2, , int, s, 32, 2, 0x80000000);
+ VDUP(vector2, , uint, u, 8, 8, 1);
+ VDUP(vector2, , uint, u, 16, 4, 13);
+ VDUP(vector2, , uint, u, 32, 2, 8);
+
+ VDUP(vector3, , int, s, 8, 8, 0x7f);
+ VDUP(vector3, , int, s, 16, 4, 0x7fff);
+ VDUP(vector3, , int, s, 32, 2, 0x7fffffff);
+ VDUP(vector3, , uint, u, 8, 8, 0xff);
+ VDUP(vector3, , uint, u, 16, 4, 0xffff);
+ VDUP(vector3, , uint, u, 32, 2, 0xffffffff);
+
+ TEST_VABAL(int, s, 8, 16, 8);
+ TEST_VABAL(int, s, 16, 32, 4);
+ TEST_VABAL(int, s, 32, 64, 2);
+ TEST_VABAL(uint, u, 8, 16, 8);
+ TEST_VABAL(uint, u, 16, 32, 4);
+ TEST_VABAL(uint, u, 32, 64, 2);
+
+ CHECK(TEST_MSG, int, 16, 8, PRIx16, expected2, " test intermediate overflow");
+ CHECK(TEST_MSG, int, 32, 4, PRIx32, expected2, " test intermediate overflow");
+ CHECK(TEST_MSG, int, 64, 2, PRIx64, expected2, " test intermediate overflow");
+ CHECK(TEST_MSG, uint, 16, 8, PRIx16, expected2, " test intermediate overflow");
+ CHECK(TEST_MSG, uint, 32, 4, PRIx32, expected2, " test intermediate overflow");
+ CHECK(TEST_MSG, uint, 64, 2, PRIx64, expected2, " test intermediate overflow");
+}
+
+int main (void)
+{
+ exec_vabal ();
+ return 0;
+}
--- /dev/null
+#include <arm_neon.h>
+#include "arm-neon-ref.h"
+#include "compute-ref-data.h"
+#include <math.h>
+
+/* Expected results. */
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x11, 0x10, 0xf, 0xe,
+ 0xd, 0xc, 0xb, 0xa };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3, 0x2, 0x1, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x18, 0x17 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xef, 0xf0, 0xf1, 0xf2,
+ 0xf3, 0xf4, 0xf5, 0xf6 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffe3, 0xffe4, 0xffe5, 0xffe6 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffe8, 0xffffffe9 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x41c26666, 0x41ba6666 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x1a, 0x19, 0x18, 0x17,
+ 0x16, 0x15, 0x14, 0x13,
+ 0x12, 0x11, 0x10, 0xf,
+ 0xe, 0xd, 0xc, 0xb };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x4, 0x3, 0x2, 0x1,
+ 0x0, 0x1, 0x2, 0x3 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x30, 0x2f, 0x2e, 0x2d };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xe6, 0xe7, 0xe8, 0xe9,
+ 0xea, 0xeb, 0xec, 0xed,
+ 0xee, 0xef, 0xf0, 0xf1,
+ 0xf2, 0xf3, 0xf4, 0xf5 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xffe4, 0xffe5, 0xffe6, 0xffe7,
+ 0xffe8, 0xffe9, 0xffea, 0xffeb };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffd0, 0xffffffd1,
+ 0xffffffd2, 0xffffffd3 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333,
+ 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x42407ae1, 0x423c7ae1,
+ 0x42387ae1, 0x42347ae1 };
+
+/* Additional expected results for float32 variants with specially
+ chosen input values. */
+VECT_VAR_DECL(expected_float32,hfloat,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+
+#define TEST_MSG "VABD/VABDQ"
+void exec_vabd (void)
+{
+ /* Basic test: v4=vabd(v1,v2), then store the result. */
+#define TEST_VABD(Q, T1, T2, W, N) \
+ VECT_VAR(vector_res, T1, W, N) = \
+ vabd##Q##_##T2##W(VECT_VAR(vector1, T1, W, N), \
+ VECT_VAR(vector2, T1, W, N)); \
+ vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N), VECT_VAR(vector_res, T1, W, N))
+
+#define DECL_VABD_VAR(VAR) \
+ DECL_VARIABLE(VAR, int, 8, 8); \
+ DECL_VARIABLE(VAR, int, 16, 4); \
+ DECL_VARIABLE(VAR, int, 32, 2); \
+ DECL_VARIABLE(VAR, uint, 8, 8); \
+ DECL_VARIABLE(VAR, uint, 16, 4); \
+ DECL_VARIABLE(VAR, uint, 32, 2); \
+ DECL_VARIABLE(VAR, float, 32, 2); \
+ DECL_VARIABLE(VAR, int, 8, 16); \
+ DECL_VARIABLE(VAR, int, 16, 8); \
+ DECL_VARIABLE(VAR, int, 32, 4); \
+ DECL_VARIABLE(VAR, uint, 8, 16); \
+ DECL_VARIABLE(VAR, uint, 16, 8); \
+ DECL_VARIABLE(VAR, uint, 32, 4); \
+ DECL_VARIABLE(VAR, float, 32, 4)
+
+ DECL_VABD_VAR(vector1);
+ DECL_VABD_VAR(vector2);
+ DECL_VABD_VAR(vector_res);
+
+ clean_results ();
+
+ /* Initialize input "vector1" from "buffer". */
+ VLOAD(vector1, buffer, , int, s, 8, 8);
+ VLOAD(vector1, buffer, , int, s, 16, 4);
+ VLOAD(vector1, buffer, , int, s, 32, 2);
+ VLOAD(vector1, buffer, , uint, u, 8, 8);
+ VLOAD(vector1, buffer, , uint, u, 16, 4);
+ VLOAD(vector1, buffer, , uint, u, 32, 2);
+ VLOAD(vector1, buffer, , float, f, 32, 2);
+ VLOAD(vector1, buffer, q, int, s, 8, 16);
+ VLOAD(vector1, buffer, q, int, s, 16, 8);
+ VLOAD(vector1, buffer, q, int, s, 32, 4);
+ VLOAD(vector1, buffer, q, uint, u, 8, 16);
+ VLOAD(vector1, buffer, q, uint, u, 16, 8);
+ VLOAD(vector1, buffer, q, uint, u, 32, 4);
+ VLOAD(vector1, buffer, q, float, f, 32, 4);
+
+ /* Choose init value arbitrarily. */
+ VDUP(vector2, , int, s, 8, 8, 1);
+ VDUP(vector2, , int, s, 16, 4, -13);
+ VDUP(vector2, , int, s, 32, 2, 8);
+ VDUP(vector2, , uint, u, 8, 8, 1);
+ VDUP(vector2, , uint, u, 16, 4, 13);
+ VDUP(vector2, , uint, u, 32, 2, 8);
+ VDUP(vector2, , float, f, 32, 2, 8.3f);
+ VDUP(vector2, q, int, s, 8, 16, 10);
+ VDUP(vector2, q, int, s, 16, 8, -12);
+ VDUP(vector2, q, int, s, 32, 4, 32);
+ VDUP(vector2, q, uint, u, 8, 16, 10);
+ VDUP(vector2, q, uint, u, 16, 8, 12);
+ VDUP(vector2, q, uint, u, 32, 4, 32);
+ VDUP(vector2, q, float, f, 32, 4, 32.12f);
+
+ /* Execute the tests. */
+ TEST_VABD(, int, s, 8, 8);
+ TEST_VABD(, int, s, 16, 4);
+ TEST_VABD(, int, s, 32, 2);
+ TEST_VABD(, uint, u, 8, 8);
+ TEST_VABD(, uint, u, 16, 4);
+ TEST_VABD(, uint, u, 32, 2);
+ TEST_VABD(, float, f, 32, 2);
+ TEST_VABD(q, int, s, 8, 16);
+ TEST_VABD(q, int, s, 16, 8);
+ TEST_VABD(q, int, s, 32, 4);
+ TEST_VABD(q, uint, u, 8, 16);
+ TEST_VABD(q, uint, u, 16, 8);
+ TEST_VABD(q, uint, u, 32, 4);
+ TEST_VABD(q, float, f, 32, 4);
+
+ CHECK_RESULTS (TEST_MSG, "");
+
+
+ /* Extra FP tests with special values (-0.0, ....) */
+ VDUP(vector1, q, float, f, 32, 4, -0.0f);
+ VDUP(vector2, q, float, f, 32, 4, 0.0);
+ TEST_VABD(q, float, f, 32, 4);
+ CHECK_FP(TEST_MSG, float, 32, 4, PRIx32, expected_float32, " FP special (-0.0)");
+
+ /* Extra FP tests with special values (-0.0, ....) */
+ VDUP(vector1, q, float, f, 32, 4, 0.0f);
+ VDUP(vector2, q, float, f, 32, 4, -0.0);
+ TEST_VABD(q, float, f, 32, 4);
+ CHECK_FP(TEST_MSG, float, 32, 4, PRIx32, expected_float32, " FP special (-0.0)");
+}
+
+int main (void)
+{
+ exec_vabd ();
+ return 0;
+}
--- /dev/null
+#include <arm_neon.h>
+#include "arm-neon-ref.h"
+#include "compute-ref-data.h"
+
+/* Expected results. */
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x11, 0x10, 0xf, 0xe,
+ 0xd, 0xc, 0xb, 0xa };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x3, 0x2, 0x1, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x18, 0x17 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xef, 0xf0, 0xf1, 0xf2,
+ 0xf3, 0xf4, 0xf5, 0xf6 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffe3, 0xffe4, 0xffe5, 0xffe6 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffe8,
+ 0xffffffe9 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333,
+ 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333,
+ 0x33333333, 0x33333333 };
+
+#define TEST_MSG "VABDL"
+void exec_vabdl (void)
+{
+ /* Basic test: v4=vabdl(v1,v2), then store the result. */
+#define TEST_VABDL(T1, T2, W, W2, N) \
+ VECT_VAR(vector_res, T1, W2, N) = \
+ vabdl_##T2##W(VECT_VAR(vector1, T1, W, N), \
+ VECT_VAR(vector2, T1, W, N)); \
+ vst1q_##T2##W2(VECT_VAR(result, T1, W2, N), VECT_VAR(vector_res, T1, W2, N))
+
+#define DECL_VABDL_VAR_LONG(VAR) \
+ DECL_VARIABLE(VAR, int, 16, 8); \
+ DECL_VARIABLE(VAR, int, 32, 4); \
+ DECL_VARIABLE(VAR, int, 64, 2); \
+ DECL_VARIABLE(VAR, uint, 16, 8); \
+ DECL_VARIABLE(VAR, uint, 32, 4); \
+ DECL_VARIABLE(VAR, uint, 64, 2)
+
+#define DECL_VABDL_VAR_SHORT(VAR) \
+ DECL_VARIABLE(VAR, int, 8, 8); \
+ DECL_VARIABLE(VAR, int, 16, 4); \
+ DECL_VARIABLE(VAR, int, 32, 2); \
+ DECL_VARIABLE(VAR, uint, 8, 8); \
+ DECL_VARIABLE(VAR, uint, 16, 4); \
+ DECL_VARIABLE(VAR, uint, 32, 2)
+
+ DECL_VABDL_VAR_SHORT(vector1);
+ DECL_VABDL_VAR_SHORT(vector2);
+ DECL_VABDL_VAR_LONG(vector_res);
+
+ clean_results ();
+
+ /* Initialize input "vector1" from "buffer". */
+ VLOAD(vector1, buffer, , int, s, 8, 8);
+ VLOAD(vector1, buffer, , int, s, 16, 4);
+ VLOAD(vector1, buffer, , int, s, 32, 2);
+ VLOAD(vector1, buffer, , uint, u, 8, 8);
+ VLOAD(vector1, buffer, , uint, u, 16, 4);
+ VLOAD(vector1, buffer, , uint, u, 32, 2);
+
+ /* Choose init value arbitrarily. */
+ VDUP(vector2, , int, s, 8, 8, 1);
+ VDUP(vector2, , int, s, 16, 4, -13);
+ VDUP(vector2, , int, s, 32, 2, 8);
+ VDUP(vector2, , uint, u, 8, 8, 1);
+ VDUP(vector2, , uint, u, 16, 4, 13);
+ VDUP(vector2, , uint, u, 32, 2, 8);
+
+ /* Execute the tests. */
+ TEST_VABDL(int, s, 8, 16, 8);
+ TEST_VABDL(int, s, 16, 32, 4);
+ TEST_VABDL(int, s, 32, 64, 2);
+ TEST_VABDL(uint, u, 8, 16, 8);
+ TEST_VABDL(uint, u, 16, 32, 4);
+ TEST_VABDL(uint, u, 32, 64, 2);
+
+ CHECK_RESULTS (TEST_MSG, "");
+}
+
+int main (void)
+{
+ exec_vabdl ();
+ return 0;
+}
--- /dev/null
+#define INSN_NAME vabs
+#define TEST_MSG "VABS/VABSQ"
+
+/* Extra tests for functions requiring floating-point types. */
+void exec_vabs_f32(void);
+#define EXTRA_TESTS exec_vabs_f32
+
+#include "unary_op.inc"
+
+/* Expected results. */
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x10, 0xf, 0xe, 0xd,
+ 0xc, 0xb, 0xa, 0x9 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x10, 0xf, 0xe, 0xd };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x10, 0xf };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x10, 0xf, 0xe, 0xd, 0xc, 0xb, 0xa, 0x9,
+ 0x8, 0x7, 0x6, 0x5, 0x4, 0x3, 0x2, 0x1 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x10, 0xf, 0xe, 0xd,
+ 0xc, 0xb, 0xa, 0x9 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x10, 0xf, 0xe, 0xd };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333,
+ 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333,
+ 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333,
+ 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333,
+ 0x33333333, 0x33333333 };
+
+/* Expected results for float32 variants. Needs to be separated since
+ the generic test function does not test floating-point
+ versions. */
+VECT_VAR_DECL(expected_float32,hfloat,32,2) [] = { 0x40133333, 0x40133333 };
+VECT_VAR_DECL(expected_float32,hfloat,32,4) [] = { 0x4059999a, 0x4059999a,
+ 0x4059999a, 0x4059999a };
+
+void exec_vabs_f32(void)
+{
+ DECL_VARIABLE(vector, float, 32, 2);
+ DECL_VARIABLE(vector, float, 32, 4);
+
+ DECL_VARIABLE(vector_res, float, 32, 2);
+ DECL_VARIABLE(vector_res, float, 32, 4);
+
+ VDUP(vector, , float, f, 32, 2, -2.3f);
+ VDUP(vector, q, float, f, 32, 4, 3.4f);
+
+ TEST_UNARY_OP(INSN_NAME, , float, f, 32, 2);
+ TEST_UNARY_OP(INSN_NAME, q, float, f, 32, 4);
+
+ CHECK_FP(TEST_MSG, float, 32, 2, PRIx32, expected_float32, "");
+ CHECK_FP(TEST_MSG, float, 32, 4, PRIx32, expected_float32, "");
+}
--- /dev/null
+#define INSN_NAME vadd
+#define TEST_MSG "VADD/VADDQ"
+
+/* Extra tests for functions requiring floating-point types. */
+void exec_vadd_f32(void);
+#define EXTRA_TESTS exec_vadd_f32
+
+#include "binary_op.inc"
+
+/* Expected results. */
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf2, 0xf3, 0xf4, 0xf5,
+ 0xf6, 0xf7, 0xf8, 0xf9 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xffec, 0xffed, 0xffee, 0xffef };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff3, 0xfffffff4 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x54 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x4, 0x5, 0x6, 0x7,
+ 0x8, 0x9, 0xa, 0xb };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xe, 0xf, 0x10, 0x11 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x18, 0x19 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xe6, 0xe7, 0xe8, 0xe9,
+ 0xea, 0xeb, 0xec, 0xed,
+ 0xee, 0xef, 0xf0, 0xf1,
+ 0xf2, 0xf3, 0xf4, 0xf5 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xffdc, 0xffdd, 0xffde, 0xffdf,
+ 0xffe0, 0xffe1, 0xffe2, 0xffe3 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffffffd2, 0xffffffd3,
+ 0xffffffd4, 0xffffffd5 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x8, 0x9 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xfc, 0xfd, 0xfe, 0xff,
+ 0x0, 0x1, 0x2, 0x3,
+ 0x4, 0x5, 0x6, 0x7,
+ 0x8, 0x9, 0xa, 0xb };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff3, 0xfff4, 0xfff5, 0xfff6,
+ 0xfff7, 0xfff8, 0xfff9, 0xfffa };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x27, 0x28, 0x29, 0x2a };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff3,
+ 0xfffffffffffffff4 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333,
+ 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333,
+ 0x33333333, 0x33333333 };
+
+/* Expected results for float32 variants. Needs to be separated since
+ the generic test function does not test floating-point
+ versions. */
+VECT_VAR_DECL(expected_float32,hfloat,32,2) [] = { 0x40d9999a, 0x40d9999a };
+VECT_VAR_DECL(expected_float32,hfloat,32,4) [] = { 0x41100000, 0x41100000,
+ 0x41100000, 0x41100000 };
+
+void exec_vadd_f32(void)
+{
+ DECL_VARIABLE(vector, float, 32, 2);
+ DECL_VARIABLE(vector, float, 32, 4);
+
+ DECL_VARIABLE(vector2, float, 32, 2);
+ DECL_VARIABLE(vector2, float, 32, 4);
+
+ DECL_VARIABLE(vector_res, float, 32, 2);
+ DECL_VARIABLE(vector_res, float, 32, 4);
+
+ VDUP(vector, , float, f, 32, 2, 2.3f);
+ VDUP(vector, q, float, f, 32, 4, 3.4f);
+
+ VDUP(vector2, , float, f, 32, 2, 4.5f);
+ VDUP(vector2, q, float, f, 32, 4, 5.6f);
+
+ TEST_BINARY_OP(INSN_NAME, , float, f, 32, 2);
+ TEST_BINARY_OP(INSN_NAME, q, float, f, 32, 4);
+
+ CHECK_FP(TEST_MSG, float, 32, 2, PRIx32, expected_float32, "");
+ CHECK_FP(TEST_MSG, float, 32, 4, PRIx32, expected_float32, "");
+}
--- /dev/null
+#include <arm_neon.h>
+#include "arm-neon-ref.h"
+#include "compute-ref-data.h"
+
+#if defined(__cplusplus)
+#include <cstdint>
+#else
+#include <stdint.h>
+#endif
+
+/* Expected results. */
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x32, 0x32, 0x32, 0x32,
+ 0x32, 0x32, 0x32, 0x32 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x32, 0x32, 0x32, 0x32 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x18, 0x18 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x3, 0x3, 0x3, 0x3,
+ 0x3, 0x3, 0x3, 0x3 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x37, 0x37, 0x37, 0x37 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x3, 0x3 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333,
+ 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333,
+ 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333,
+ 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333,
+ 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333,
+ 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333,
+ 0x33333333, 0x33333333 };
+
+#ifndef INSN_NAME
+#define INSN_NAME vaddhn
+#define TEST_MSG "VADDHN"
+#endif
+
+#define FNNAME1(NAME) void exec_ ## NAME (void)
+#define FNNAME(NAME) FNNAME1(NAME)
+
+FNNAME (INSN_NAME)
+{
+ /* Basic test: vec64=vaddhn(vec128_a, vec128_b), then store the result. */
+#define TEST_VADDHN1(INSN, T1, T2, W, W2, N) \
+ VECT_VAR(vector64, T1, W2, N) = INSN##_##T2##W(VECT_VAR(vector1, T1, W, N), \
+ VECT_VAR(vector2, T1, W, N)); \
+ vst1_##T2##W2(VECT_VAR(result, T1, W2, N), VECT_VAR(vector64, T1, W2, N))
+
+#define TEST_VADDHN(INSN, T1, T2, W, W2, N) \
+ TEST_VADDHN1(INSN, T1, T2, W, W2, N)
+
+ DECL_VARIABLE_64BITS_VARIANTS(vector64);
+ DECL_VARIABLE_128BITS_VARIANTS(vector1);
+ DECL_VARIABLE_128BITS_VARIANTS(vector2);
+
+ clean_results ();
+
+ /* Fill input vector1 and vector2 with arbitrary values */
+ VDUP(vector1, q, int, s, 16, 8, 50*(UINT8_MAX+1));
+ VDUP(vector1, q, int, s, 32, 4, 50*(UINT16_MAX+1));
+ VDUP(vector1, q, int, s, 64, 2, 24*((uint64_t)UINT32_MAX+1));
+ VDUP(vector1, q, uint, u, 16, 8, 3*(UINT8_MAX+1));
+ VDUP(vector1, q, uint, u, 32, 4, 55*(UINT16_MAX+1));
+ VDUP(vector1, q, uint, u, 64, 2, 3*((uint64_t)UINT32_MAX+1));
+
+ VDUP(vector2, q, int, s, 16, 8, (uint16_t)UINT8_MAX);
+ VDUP(vector2, q, int, s, 32, 4, (uint32_t)UINT16_MAX);
+ VDUP(vector2, q, int, s, 64, 2, (uint64_t)UINT32_MAX);
+ VDUP(vector2, q, uint, u, 16, 8, (uint16_t)UINT8_MAX);
+ VDUP(vector2, q, uint, u, 32, 4, (uint32_t)UINT16_MAX);
+ VDUP(vector2, q, uint, u, 64, 2, (uint64_t)UINT32_MAX);
+
+ TEST_VADDHN(INSN_NAME, int, s, 16, 8, 8);
+ TEST_VADDHN(INSN_NAME, int, s, 32, 16, 4);
+ TEST_VADDHN(INSN_NAME, int, s, 64, 32, 2);
+ TEST_VADDHN(INSN_NAME, uint, u, 16, 8, 8);
+ TEST_VADDHN(INSN_NAME, uint, u, 32, 16, 4);
+ TEST_VADDHN(INSN_NAME, uint, u, 64, 32, 2);
+
+ CHECK_RESULTS (TEST_MSG, "");
+}
+
+int main (void)
+{
+ FNNAME (INSN_NAME);
+ return 0;
+}
--- /dev/null
+#include <arm_neon.h>
+#include "arm-neon-ref.h"
+#include "compute-ref-data.h"
+
+/* Expected results. */
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x3, 0x3, 0x3, 0x3,
+ 0x3, 0x3, 0x3, 0x3 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x37, 0x37, 0x37, 0x37 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x3, 0x3 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xffe3, 0xffe4, 0xffe5, 0xffe6,
+ 0xffe7, 0xffe8, 0xffe9, 0xffea };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffffffe2, 0xffffffe3,
+ 0xffffffe4, 0xffffffe5 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xffffffffffffffe0,
+ 0xffffffffffffffe1 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x1e3, 0x1e4, 0x1e5, 0x1e6,
+ 0x1e7, 0x1e8, 0x1e9, 0x1ea };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x1ffe1, 0x1ffe2,
+ 0x1ffe3, 0x1ffe4 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x1ffffffe0, 0x1ffffffe1 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333,
+ 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333,
+ 0x33333333, 0x33333333 };
+
+#ifndef INSN_NAME
+#define INSN_NAME vaddl
+#define TEST_MSG "VADDL"
+#endif
+
+#define FNNAME1(NAME) void exec_ ## NAME (void)
+#define FNNAME(NAME) FNNAME1(NAME)
+
+FNNAME (INSN_NAME)
+{
+ /* Basic test: y=vaddl(x1,x2), then store the result. */
+#define TEST_VADDL1(INSN, T1, T2, W, W2, N) \
+ VECT_VAR(vector_res, T1, W2, N) = \
+ INSN##_##T2##W(VECT_VAR(vector, T1, W, N), \
+ VECT_VAR(vector2, T1, W, N)); \
+ vst1q_##T2##W2(VECT_VAR(result, T1, W2, N), VECT_VAR(vector_res, T1, W2, N))
+
+#define TEST_VADDL(INSN, T1, T2, W, W2, N) \
+ TEST_VADDL1(INSN, T1, T2, W, W2, N)
+
+ DECL_VARIABLE(vector, int, 8, 8);
+ DECL_VARIABLE(vector, int, 16, 4);
+ DECL_VARIABLE(vector, int, 32, 2);
+ DECL_VARIABLE(vector, uint, 8, 8);
+ DECL_VARIABLE(vector, uint, 16, 4);
+ DECL_VARIABLE(vector, uint, 32, 2);
+
+ DECL_VARIABLE(vector2, int, 8, 8);
+ DECL_VARIABLE(vector2, int, 16, 4);
+ DECL_VARIABLE(vector2, int, 32, 2);
+ DECL_VARIABLE(vector2, uint, 8, 8);
+ DECL_VARIABLE(vector2, uint, 16, 4);
+ DECL_VARIABLE(vector2, uint, 32, 2);
+
+ DECL_VARIABLE(vector_res, int, 16, 8);
+ DECL_VARIABLE(vector_res, int, 32, 4);
+ DECL_VARIABLE(vector_res, int, 64, 2);
+ DECL_VARIABLE(vector_res, uint, 16, 8);
+ DECL_VARIABLE(vector_res, uint, 32, 4);
+ DECL_VARIABLE(vector_res, uint, 64, 2);
+
+ clean_results ();
+
+ /* Initialize input "vector" from "buffer". */
+ VLOAD(vector, buffer, , int, s, 8, 8);
+ VLOAD(vector, buffer, , int, s, 16, 4);
+ VLOAD(vector, buffer, , int, s, 32, 2);
+ VLOAD(vector, buffer, , uint, u, 8, 8);
+ VLOAD(vector, buffer, , uint, u, 16, 4);
+ VLOAD(vector, buffer, , uint, u, 32, 2);
+
+ /* Choose init value arbitrarily. */
+ VDUP(vector2, , int, s, 8, 8, -13);
+ VDUP(vector2, , int, s, 16, 4, -14);
+ VDUP(vector2, , int, s, 32, 2, -16);
+ VDUP(vector2, , uint, u, 8, 8, 0xf3);
+ VDUP(vector2, , uint, u, 16, 4, 0xfff1);
+ VDUP(vector2, , uint, u, 32, 2, 0xfffffff0);
+
+ /* Execute the tests. */
+ TEST_VADDL(INSN_NAME, int, s, 8, 16, 8);
+ TEST_VADDL(INSN_NAME, int, s, 16, 32, 4);
+ TEST_VADDL(INSN_NAME, int, s, 32, 64, 2);
+ TEST_VADDL(INSN_NAME, uint, u, 8, 16, 8);
+ TEST_VADDL(INSN_NAME, uint, u, 16, 32, 4);
+ TEST_VADDL(INSN_NAME, uint, u, 32, 64, 2);
+
+ CHECK_RESULTS (TEST_MSG, "");
+}
+
+int main (void)
+{
+ FNNAME (INSN_NAME);
+ return 0;
+}
--- /dev/null
+#include <arm_neon.h>
+#include "arm-neon-ref.h"
+#include "compute-ref-data.h"
+
+/* Expected results. */
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x3, 0x3, 0x3, 0x3,
+ 0x3, 0x3, 0x3, 0x3 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x37, 0x37, 0x37, 0x37 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x3, 0x3 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xffe3, 0xffe4, 0xffe5, 0xffe6,
+ 0xffe7, 0xffe8, 0xffe9, 0xffea };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffffffe2, 0xffffffe3,
+ 0xffffffe4, 0xffffffe5 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xffffffffffffffe0,
+ 0xffffffffffffffe1 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xe3, 0xe4, 0xe5, 0xe6,
+ 0xe7, 0xe8, 0xe9, 0xea };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffe1, 0xffe2,
+ 0xffe3, 0xffe4 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffe0, 0xffffffe1 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333,
+ 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333,
+ 0x33333333, 0x33333333 };
+
+#ifndef INSN_NAME
+#define INSN_NAME vaddw
+#define TEST_MSG "VADDW"
+#endif
+
+#define FNNAME1(NAME) void exec_ ## NAME (void)
+#define FNNAME(NAME) FNNAME1(NAME)
+
+FNNAME (INSN_NAME)
+{
+ /* Basic test: y=vaddw(x1,x2), then store the result. */
+#define TEST_VADDW1(INSN, T1, T2, W, W2, N) \
+ VECT_VAR(vector_res, T1, W2, N) = \
+ INSN##_##T2##W(VECT_VAR(vector, T1, W2, N), \
+ VECT_VAR(vector2, T1, W, N)); \
+ vst1q_##T2##W2(VECT_VAR(result, T1, W2, N), VECT_VAR(vector_res, T1, W2, N))
+
+#define TEST_VADDW(INSN, T1, T2, W, W2, N) \
+ TEST_VADDW1(INSN, T1, T2, W, W2, N)
+
+ DECL_VARIABLE(vector, int, 16, 8);
+ DECL_VARIABLE(vector, int, 32, 4);
+ DECL_VARIABLE(vector, int, 64, 2);
+ DECL_VARIABLE(vector, uint, 16, 8);
+ DECL_VARIABLE(vector, uint, 32, 4);
+ DECL_VARIABLE(vector, uint, 64, 2);
+
+ DECL_VARIABLE(vector2, int, 8, 8);
+ DECL_VARIABLE(vector2, int, 16, 4);
+ DECL_VARIABLE(vector2, int, 32, 2);
+ DECL_VARIABLE(vector2, uint, 8, 8);
+ DECL_VARIABLE(vector2, uint, 16, 4);
+ DECL_VARIABLE(vector2, uint, 32, 2);
+
+ DECL_VARIABLE(vector_res, int, 16, 8);
+ DECL_VARIABLE(vector_res, int, 32, 4);
+ DECL_VARIABLE(vector_res, int, 64, 2);
+ DECL_VARIABLE(vector_res, uint, 16, 8);
+ DECL_VARIABLE(vector_res, uint, 32, 4);
+ DECL_VARIABLE(vector_res, uint, 64, 2);
+
+ clean_results ();
+
+ /* Initialize input "vector" from "buffer". */
+ VLOAD(vector, buffer, q, int, s, 16, 8);
+ VLOAD(vector, buffer, q, int, s, 32, 4);
+ VLOAD(vector, buffer, q, int, s, 64, 2);
+ VLOAD(vector, buffer, q, uint, u, 16, 8);
+ VLOAD(vector, buffer, q, uint, u, 32, 4);
+ VLOAD(vector, buffer, q, uint, u, 64, 2);
+
+ /* Choose init value arbitrarily. */
+ VDUP(vector2, , int, s, 8, 8, -13);
+ VDUP(vector2, , int, s, 16, 4, -14);
+ VDUP(vector2, , int, s, 32, 2, -16);
+ VDUP(vector2, , uint, u, 8, 8, 0xf3);
+ VDUP(vector2, , uint, u, 16, 4, 0xfff1);
+ VDUP(vector2, , uint, u, 32, 2, 0xfffffff0);
+
+ /* Execute the tests. */
+ TEST_VADDW(INSN_NAME, int, s, 8, 16, 8);
+ TEST_VADDW(INSN_NAME, int, s, 16, 32, 4);
+ TEST_VADDW(INSN_NAME, int, s, 32, 64, 2);
+ TEST_VADDW(INSN_NAME, uint, u, 8, 16, 8);
+ TEST_VADDW(INSN_NAME, uint, u, 16, 32, 4);
+ TEST_VADDW(INSN_NAME, uint, u, 32, 64, 2);
+
+ CHECK_RESULTS (TEST_MSG, "");
+}
+
+int main (void)
+{
+ FNNAME (INSN_NAME);
+ return 0;
+}
--- /dev/null
+#define INSN_NAME vand
+#define TEST_MSG "VAND/VANDQ"
+
+#include "binary_op.inc"
+
+/* Expected results. */
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x0, 0x2, 0x2,
+ 0x0, 0x0, 0x2, 0x2 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x0, 0x1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x60 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x10, 0x10, 0x10, 0x10,
+ 0x14, 0x14, 0x14, 0x14 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x10, 0x10, 0x12, 0x12 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x20, 0x20 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xf0, 0xf2, 0xf2,
+ 0xf4, 0xf4, 0xf6, 0xf6,
+ 0xf0, 0xf0, 0xf2, 0xf2,
+ 0xf4, 0xf4, 0xf6, 0xf6 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xffe0, 0xffe0, 0xffe0, 0xffe0,
+ 0xffe4, 0xffe4, 0xffe4, 0xffe4 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffffffe0, 0xffffffe0,
+ 0xffffffe2, 0xffffffe2 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x10, 0x10 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x0, 0x0, 0x0,
+ 0x4, 0x4, 0x4, 0x4,
+ 0x8, 0x8, 0x8, 0x8,
+ 0xc, 0xc, 0xc, 0xc };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x1, 0x2, 0x3,
+ 0x0, 0x1, 0x2, 0x3 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x30, 0x31, 0x32, 0x33 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x0, 0x1 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333,
+ 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333,
+ 0x33333333, 0x33333333 };
--- /dev/null
+#define INSN_NAME vbic
+#define TEST_MSG "VBIC/VBICQ"
+
+#include "binary_op.inc"
+
+/* Expected results. */
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf1, 0xf0, 0xf1,
+ 0xf4, 0xf5, 0xf4, 0xf5 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0x1, 0x2, 0x3 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xffffffffffffff90 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xe0, 0xe1, 0xe2, 0xe3,
+ 0xe0, 0xe1, 0xe2, 0xe3 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffe0, 0xffe1, 0xffe0, 0xffe1 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffd0, 0xffffffd1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x1, 0x0, 0x1,
+ 0x0, 0x1, 0x0, 0x1,
+ 0x8, 0x9, 0x8, 0x9,
+ 0x8, 0x9, 0x8, 0x9 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x10, 0x11, 0x12, 0x13,
+ 0x10, 0x11, 0x12, 0x13 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x10, 0x11, 0x10, 0x11 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xffffffffffffffe0, 0xffffffffffffffe1 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3,
+ 0xf0, 0xf1, 0xf2, 0xf3,
+ 0xf0, 0xf1, 0xf2, 0xf3,
+ 0xf0, 0xf1, 0xf2, 0xf3 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0,
+ 0xfff4, 0xfff4, 0xfff4, 0xfff4 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffc0, 0xffffffc0,
+ 0xffffffc0, 0xffffffc0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff0,
+ 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333,
+ 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333,
+ 0x33333333, 0x33333333 };
--- /dev/null
+#include <arm_neon.h>
+#include "arm-neon-ref.h"
+#include "compute-ref-data.h"
+
+/* Expected results. */
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf2, 0xf2, 0xf2, 0xf2,
+ 0xf6, 0xf6, 0xf6, 0xf6 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff0, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffffd };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf3, 0xf3, 0xf3, 0xf3,
+ 0xf7, 0xf7, 0xf7, 0xf7 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff0, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffff1 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf3, 0xf3, 0xf3, 0xf3,
+ 0xf7, 0xf7, 0xf7, 0xf7 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff0, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800004, 0xc1700004 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf2, 0xf2, 0xf2, 0xf2,
+ 0xf6, 0xf6, 0xf6, 0xf6,
+ 0xf2, 0xf2, 0xf2, 0xf2,
+ 0xf6, 0xf6, 0xf6, 0xf6 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xfff0, 0xfff2, 0xfff2,
+ 0xfff4, 0xfff4, 0xfff6, 0xfff6 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xfffffff0,
+ 0xfffffff2, 0xfffffff2 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffffd,
+ 0xfffffffffffffffd };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf3, 0xf3, 0xf3, 0xf3,
+ 0xf7, 0xf7, 0xf7, 0xf7,
+ 0xf3, 0xf3, 0xf3, 0xf3,
+ 0xf7, 0xf7, 0xf7, 0xf7 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xfff0, 0xfff2, 0xfff2,
+ 0xfff4, 0xfff4, 0xfff6, 0xfff6 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xfffffff0,
+ 0xfffffff2, 0xfffffff2 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffff1,
+ 0xfffffff1 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf3, 0xf3, 0xf3, 0xf3,
+ 0xf7, 0xf7, 0xf7, 0xf7,
+ 0xf3, 0xf3, 0xf3, 0xf3,
+ 0xf7, 0xf7, 0xf7, 0xf7 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff0, 0xfff0, 0xfff2, 0xfff2,
+ 0xfff4, 0xfff4, 0xfff6, 0xfff6 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1800001, 0xc1700001,
+ 0xc1600001, 0xc1500001 };
+
+#define TEST_MSG "VBSL/VBSLQ"
+void exec_vbsl (void)
+{
+ /* Basic test: y=vbsl(unsigned_vec,x1,x2), then store the result. */
+#define TEST_VBSL(T3, Q, T1, T2, W, N) \
+ VECT_VAR(vector_res, T1, W, N) = \
+ vbsl##Q##_##T2##W(VECT_VAR(vector_first, T3, W, N), \
+ VECT_VAR(vector, T1, W, N), \
+ VECT_VAR(vector2, T1, W, N)); \
+ vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N), VECT_VAR(vector_res, T1, W, N))
+
+ DECL_VARIABLE_ALL_VARIANTS(vector);
+ DECL_VARIABLE_ALL_VARIANTS(vector2);
+ DECL_VARIABLE_ALL_VARIANTS(vector_res);
+
+ DECL_VARIABLE_UNSIGNED_VARIANTS(vector_first);
+
+ clean_results ();
+
+ TEST_MACRO_ALL_VARIANTS_2_5(VLOAD, vector, buffer);
+ VLOAD(vector, buffer, , float, f, 32, 2);
+ VLOAD(vector, buffer, q, float, f, 32, 4);
+
+ /* Choose init value arbitrarily, will be used for vector
+ comparison. As we want different values for each type variant, we
+ can't use generic initialization macros. */
+ VDUP(vector2, , int, s, 8, 8, -10);
+ VDUP(vector2, , int, s, 16, 4, -14);
+ VDUP(vector2, , int, s, 32, 2, -30);
+ VDUP(vector2, , int, s, 64, 1, -33);
+ VDUP(vector2, , uint, u, 8, 8, 0xF3);
+ VDUP(vector2, , uint, u, 16, 4, 0xFFF2);
+ VDUP(vector2, , uint, u, 32, 2, 0xFFFFFFF0);
+ VDUP(vector2, , uint, u, 64, 1, 0xFFFFFFF3);
+ VDUP(vector2, , float, f, 32, 2, -30.3f);
+ VDUP(vector2, , poly, p, 8, 8, 0xF3);
+ VDUP(vector2, , poly, p, 16, 4, 0xFFF2);
+
+ VDUP(vector2, q, int, s, 8, 16, -10);
+ VDUP(vector2, q, int, s, 16, 8, -14);
+ VDUP(vector2, q, int, s, 32, 4, -30);
+ VDUP(vector2, q, int, s, 64, 2, -33);
+ VDUP(vector2, q, uint, u, 8, 16, 0xF3);
+ VDUP(vector2, q, uint, u, 16, 8, 0xFFF2);
+ VDUP(vector2, q, uint, u, 32, 4, 0xFFFFFFF0);
+ VDUP(vector2, q, uint, u, 64, 2, 0xFFFFFFF3);
+ VDUP(vector2, q, poly, p, 8, 16, 0xF3);
+ VDUP(vector2, q, poly, p, 16, 8, 0xFFF2);
+ VDUP(vector2, q, float, f, 32, 4, -30.4f);
+
+ VDUP(vector_first, , uint, u, 8, 8, 0xF4);
+ VDUP(vector_first, , uint, u, 16, 4, 0xFFF6);
+ VDUP(vector_first, , uint, u, 32, 2, 0xFFFFFFF2);
+ VDUP(vector_first, , uint, u, 64, 1, 0xFFFFFFF2);
+ VDUP(vector_first, q, uint, u, 8, 16, 0xF4);
+ VDUP(vector_first, q, uint, u, 16, 8, 0xFFF6);
+ VDUP(vector_first, q, uint, u, 32, 4, 0xFFFFFFF2);
+ VDUP(vector_first, q, uint, u, 64, 2, 0xFFFFFFF2);
+
+ /* Execute the tests. */
+ TEST_MACRO_ALL_VARIANTS_1_5(TEST_VBSL, uint);
+ TEST_VBSL(uint, , poly, p, 8, 8);
+ TEST_VBSL(uint, , poly, p, 16, 4);
+ TEST_VBSL(uint, q, poly, p, 8, 16);
+ TEST_VBSL(uint, q, poly, p, 16, 8);
+ TEST_VBSL(uint, , float, f, 32, 2);
+ TEST_VBSL(uint, q, float, f, 32, 4);
+
+ CHECK_RESULTS (TEST_MSG, "");
+}
+
+int main (void)
+{
+ exec_vbsl ();
+ return 0;
+}
--- /dev/null
+#define INSN_NAME vcage
+#define TEST_MSG "VCAGE/VCAGEQ"
+
+#include "cmp_fp_op.inc"
+
+/* Expected results. */
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0x0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x333, 0x3333, 0x3333, 0x3333,
+ 0x333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333,
+ 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x333, 0x3333, 0x3333, 0x3333,
+ 0x333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffff, 0xffffffff,
+ 0xffffffff, 0x0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333,
+ 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333,
+ 0x33333333, 0x33333333 };
+
+VECT_VAR_DECL(expected2,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected2,uint,32,4) [] = { 0xffffffff, 0xffffffff,
+ 0xffffffff, 0xffffffff };
--- /dev/null
+#define INSN_NAME vcagt
+#define TEST_MSG "VCAGT/VCAGTQ"
+
+#include "cmp_fp_op.inc"
+
+/* Expected results. */
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x333, 0x3333, 0x3333, 0x3333,
+ 0x333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffffffff, 0xffffffff, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x333, 0x3333, 0x3333, 0x3333,
+ 0x333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffff, 0xffffffff,
+ 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333,
+ 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333,
+ 0x33333333, 0x33333333 };
+
+VECT_VAR_DECL(expected2,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected2,uint,32,4) [] = { 0xffffffff, 0xffffffff,
+ 0xffffffff, 0xffffffff };
--- /dev/null
+#define INSN_NAME vcale
+#define TEST_MSG "VCALE/VCALEQ"
+
+#include "cmp_fp_op.inc"
+
+/* Expected results. */
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x333, 0x3333, 0x3333, 0x3333,
+ 0x333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffffffff, 0xffffffff, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x333, 0x3333, 0x3333, 0x3333,
+ 0x333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333,
+ 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333,
+ 0x33333333, 0x33333333 };
+
+VECT_VAR_DECL(expected2,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected2,uint,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
--- /dev/null
+#define INSN_NAME vcalt
+#define TEST_MSG "VCALT/VCALTQ"
+
+#include "cmp_fp_op.inc"
+
+/* Expected results. */
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x333, 0x3333, 0x3333, 0x3333,
+ 0x333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffffffff, 0xffffffff, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x333, 0x3333, 0x3333, 0x3333,
+ 0x333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0x0, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333,
+ 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333,
+ 0x33333333, 0x33333333 };
+
+VECT_VAR_DECL(expected2,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected2,uint,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
--- /dev/null
+#define INSN_NAME vceq
+#define TEST_MSG "VCEQ/VCEQQ"
+
+/* Extra tests for _p8 variants, which exist only for vceq. */
+void exec_vceq_p8(void);
+#define EXTRA_TESTS exec_vceq_p8
+
+#include "cmp_op.inc"
+
+/* Expected results. */
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0xff, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0xffff, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0x0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x333, 0x3333, 0x3333, 0x3333,
+ 0x333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333,
+ 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0x0,
+ 0xff, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0xffff, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0xffffffff, 0x0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333,
+ 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333,
+ 0x33333333, 0x33333333 };
+
+VECT_VAR_DECL(expected_uint,uint,8,8) [] = { 0x0, 0x0, 0x0, 0xff,
+ 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected_uint,uint,16,4) [] = { 0x0, 0x0, 0xffff, 0x0 };
+VECT_VAR_DECL(expected_uint,uint,32,2) [] = { 0x0, 0xffffffff };
+
+VECT_VAR_DECL(expected_q_uint,uint,8,16) [] = { 0x0, 0x0, 0x0, 0x0,
+ 0xff, 0x0, 0x0, 0x0,
+ 0, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected_q_uint,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0xffff, 0x0 };
+VECT_VAR_DECL(expected_q_uint,uint,32,4) [] = { 0x0, 0x0, 0xffffffff, 0x0 };
+
+VECT_VAR_DECL(expected_float,uint,32,2) [] = { 0x0, 0xffffffff };
+VECT_VAR_DECL(expected_q_float,uint,32,4) [] = { 0x0, 0x0, 0xffffffff, 0x0 };
+
+VECT_VAR_DECL(expected_uint2,uint,32,2) [] = { 0xffffffff, 0x0 };
+VECT_VAR_DECL(expected_uint3,uint,32,2) [] = { 0x0, 0xffffffff };
+VECT_VAR_DECL(expected_uint4,uint,32,2) [] = { 0xffffffff, 0x0 };
+
+VECT_VAR_DECL(expected_nan,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected_mnan,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected_nan2,uint,32,2) [] = { 0x0, 0x0 };
+
+VECT_VAR_DECL(expected_inf,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected_minf,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected_inf2,uint,32,2) [] = { 0x0, 0x0 };
+
+VECT_VAR_DECL(expected_mzero,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+
+VECT_VAR_DECL(expected_p8,uint,8,8) [] = { 0x0, 0x0, 0x0, 0xff,
+ 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected_q_p8,uint,8,16) [] = { 0x0, 0x0, 0x0, 0x0,
+ 0xff, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0x0 };
+
+void exec_vceq_p8(void)
+{
+ DECL_VARIABLE(vector, poly, 8, 8);
+ DECL_VARIABLE(vector, poly, 8, 16);
+
+ DECL_VARIABLE(vector2, poly, 8, 8);
+ DECL_VARIABLE(vector2, poly, 8, 16);
+
+ DECL_VARIABLE(vector_res, uint, 8, 8);
+ DECL_VARIABLE(vector_res, uint, 8, 16);
+
+ clean_results ();
+
+ VLOAD(vector, buffer, , poly, p, 8, 8);
+ VLOAD(vector, buffer, q, poly, p, 8, 16);
+
+ VDUP(vector2, , poly, p, 8, 8, 0xF3);
+ VDUP(vector2, q, poly, p, 8, 16, 0xF4);
+
+ TEST_VCOMP(INSN_NAME, , poly, p, uint, 8, 8);
+ TEST_VCOMP(INSN_NAME, q, poly, p, uint, 8, 16);
+
+ CHECK(TEST_MSG, uint, 8, 8, PRIx8, expected_p8, "p8");
+ CHECK(TEST_MSG, uint, 8, 16, PRIx8, expected_q_p8, "p8");
+}
--- /dev/null
+#define INSN_NAME vcge
+#define TEST_MSG "VCGE/VCGEQ"
+
+#include "cmp_op.inc"
+
+/* Expected results. */
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x333, 0x3333, 0x3333, 0x3333,
+ 0x333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333,
+ 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0x0,
+ 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333,
+ 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333,
+ 0x33333333, 0x33333333 };
+
+VECT_VAR_DECL(expected_uint,uint,8,8) [] = { 0x0, 0x0, 0x0, 0xff,
+ 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected_uint,uint,16,4) [] = { 0x0, 0x0, 0xffff, 0xffff };
+VECT_VAR_DECL(expected_uint,uint,32,2) [] = { 0x0, 0xffffffff };
+
+VECT_VAR_DECL(expected_q_uint,uint,8,16) [] = { 0x0, 0x0, 0x0, 0x0,
+ 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected_q_uint,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0,
+ 0, 0x0, 0xffff, 0xffff };
+VECT_VAR_DECL(expected_q_uint,uint,32,4) [] = { 0x0, 0x0, 0xffffffff, 0xffffffff };
+
+VECT_VAR_DECL(expected_float,uint,32,2) [] = { 0x0, 0xffffffff };
+VECT_VAR_DECL(expected_q_float,uint,32,4) [] = { 0x0, 0x0, 0xffffffff, 0xffffffff };
+
+VECT_VAR_DECL(expected_uint2,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected_uint3,uint,32,2) [] = { 0x0, 0xffffffff };
+VECT_VAR_DECL(expected_uint4,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+
+VECT_VAR_DECL(expected_nan,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected_mnan,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected_nan2,uint,32,2) [] = { 0x0, 0x0 };
+
+VECT_VAR_DECL(expected_inf,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected_minf,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected_inf2,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+
+VECT_VAR_DECL(expected_mzero,uint,32,2) [] = { 0xffffffff, 0xffffffff };
--- /dev/null
+#define INSN_NAME vcgt
+#define TEST_MSG "VCGT/VCGTQ"
+
+#include "cmp_op.inc"
+
+/* Expected results. */
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x333, 0x3333, 0x3333, 0x3333,
+ 0x333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333,
+ 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0xffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0x0, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333,
+ 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333,
+ 0x33333333, 0x33333333 };
+
+VECT_VAR_DECL(expected_uint,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0,
+ 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected_uint,uint,16,4) [] = { 0x0, 0x0, 0x0, 0xffff };
+VECT_VAR_DECL(expected_uint,uint,32,2) [] = { 0x0, 0x0 };
+
+VECT_VAR_DECL(expected_q_uint,uint,8,16) [] = { 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected_q_uint,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0xffff };
+VECT_VAR_DECL(expected_q_uint,uint,32,4) [] = { 0x0, 0x0, 0x0, 0xffffffff };
+
+VECT_VAR_DECL(expected_float,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected_q_float,uint,32,4) [] = { 0x0, 0x0, 0x0, 0xffffffff };
+
+VECT_VAR_DECL(expected_uint2,uint,32,2) [] = { 0x0, 0xffffffff };
+VECT_VAR_DECL(expected_uint3,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected_uint4,uint,32,2) [] = { 0x0, 0xffffffff };
+
+VECT_VAR_DECL(expected_nan,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected_mnan,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected_nan2,uint,32,2) [] = { 0x0, 0x0 };
+
+VECT_VAR_DECL(expected_inf,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected_minf,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected_inf2,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+
+VECT_VAR_DECL(expected_mzero,uint,32,2) [] = { 0x0, 0x0 };
--- /dev/null
+#define INSN_NAME vcle
+#define TEST_MSG "VCLE/VCLEQ"
+
+#include "cmp_op.inc"
+
+/* Expected results. */
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0xffff, 0xffff, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0x0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x333, 0x3333, 0x3333, 0x3333,
+ 0x333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333,
+ 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xffff, 0xffff, 0xffff, 0xffff,
+ 0xffff, 0xffff, 0xffff, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffff, 0xffffffff,
+ 0xffffffff, 0x0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333,
+ 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333,
+ 0x33333333, 0x33333333 };
+
+VECT_VAR_DECL(expected_uint,uint,8,8) [] = { 0xff, 0xff, 0xff, 0xff,
+ 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected_uint,uint,16,4) [] = { 0xffff, 0xffff, 0xffff, 0x0 };
+VECT_VAR_DECL(expected_uint,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+
+VECT_VAR_DECL(expected_q_uint,uint,8,16) [] = { 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected_q_uint,uint,16,8) [] = { 0xffff, 0xffff, 0xffff, 0xffff,
+ 0xffff, 0xffff, 0xffff, 0x0 };
+VECT_VAR_DECL(expected_q_uint,uint,32,4) [] = { 0xffffffff, 0xffffffff,
+ 0xffffffff, 0x0 };
+
+VECT_VAR_DECL(expected_float,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected_q_float,uint,32,4) [] = { 0xffffffff, 0xffffffff,
+ 0xffffffff, 0x0 };
+
+VECT_VAR_DECL(expected_uint2,uint,32,2) [] = { 0xffffffff, 0x0 };
+VECT_VAR_DECL(expected_uint3,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected_uint4,uint,32,2) [] = { 0xffffffff, 0x0 };
+
+VECT_VAR_DECL(expected_nan,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected_mnan,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected_nan2,uint,32,2) [] = { 0x0, 0x0 };
+
+VECT_VAR_DECL(expected_inf,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected_minf,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected_inf2,uint,32,2) [] = { 0x0, 0x0 };
+
+VECT_VAR_DECL(expected_mzero,uint,32,2) [] = { 0xffffffff, 0xffffffff };
--- /dev/null
+#define INSN_NAME vclt
+#define TEST_MSG "VCLT/VCLTQ"
+
+#include "cmp_op.inc"
+
+/* Expected results. */
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0xffff, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x333, 0x3333, 0x3333, 0x3333,
+ 0x333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333,
+ 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff,
+ 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xffff, 0xffff, 0xffff, 0xffff,
+ 0xffff, 0xffff, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffff, 0xffffffff, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333,
+ 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333,
+ 0x33333333, 0x33333333 };
+
+VECT_VAR_DECL(expected_uint,uint,8,8) [] = { 0xff, 0xff, 0xff, 0x0,
+ 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected_uint,uint,16,4) [] = { 0xffff, 0xffff, 0x0, 0x0 };
+VECT_VAR_DECL(expected_uint,uint,32,2) [] = { 0xffffffff, 0x0 };
+
+VECT_VAR_DECL(expected_q_uint,uint,8,16) [] = { 0xff, 0xff, 0xff, 0xff,
+ 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected_q_uint,uint,16,8) [] = { 0xffff, 0xffff, 0xffff, 0xffff,
+ 0xffff, 0xffff, 0x0, 0x0 };
+VECT_VAR_DECL(expected_q_uint,uint,32,4) [] = { 0xffffffff, 0xffffffff,
+ 0x0, 0x0 };
+
+VECT_VAR_DECL(expected_float,uint,32,2) [] = { 0xffffffff, 0x0 };
+VECT_VAR_DECL(expected_q_float,uint,32,4) [] = { 0xffffffff, 0xffffffff,
+ 0x0, 0x0 };
+
+VECT_VAR_DECL(expected_uint2,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected_uint3,uint,32,2) [] = { 0xffffffff, 0x0 };
+VECT_VAR_DECL(expected_uint4,uint,32,2) [] = { 0x0, 0x0 };
+
+VECT_VAR_DECL(expected_nan,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected_mnan,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected_nan2,uint,32,2) [] = { 0x0, 0x0 };
+
+VECT_VAR_DECL(expected_inf,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected_minf,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected_inf2,uint,32,2) [] = { 0x0, 0x0 };
+
+VECT_VAR_DECL(expected_mzero,uint,32,2) [] = { 0x0, 0x0 };
--- /dev/null
+#include <arm_neon.h>
+#include "arm-neon-ref.h"
+#include "compute-ref-data.h"
+
+/* Expected results. */
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3, 0x3, 0x3, 0x3 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x11, 0x11 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x5, 0x5 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2,
+ 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x3, 0x3, 0x3, 0x3 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3,
+ 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xd, 0xd, 0xd, 0xd,
+ 0xd, 0xd, 0xd, 0xd };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x1f, 0x1f, 0x1f, 0x1f };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333,
+ 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333,
+ 0x33333333, 0x33333333 };
+
+
+/* Expected results with input=0. */
+VECT_VAR_DECL(expected_with_0,int,8,8) [] = { 0x8, 0x8, 0x8, 0x8,
+ 0x8, 0x8, 0x8, 0x8 };
+VECT_VAR_DECL(expected_with_0,int,16,4) [] = { 0x10, 0x10, 0x10, 0x10 };
+VECT_VAR_DECL(expected_with_0,int,32,2) [] = { 0x20, 0x20 };
+VECT_VAR_DECL(expected_with_0,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected_with_0,uint,8,8) [] = { 0x8, 0x8, 0x8, 0x8,
+ 0x8, 0x8, 0x8, 0x8 };
+VECT_VAR_DECL(expected_with_0,uint,16,4) [] = { 0x10, 0x10, 0x10, 0x10 };
+VECT_VAR_DECL(expected_with_0,uint,32,2) [] = { 0x20, 0x20 };
+VECT_VAR_DECL(expected_with_0,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected_with_0,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected_with_0,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected_with_0,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected_with_0,int,8,16) [] = { 0x8, 0x8, 0x8, 0x8,
+ 0x8, 0x8, 0x8, 0x8,
+ 0x8, 0x8, 0x8, 0x8,
+ 0x8, 0x8, 0x8, 0x8 };
+VECT_VAR_DECL(expected_with_0,int,16,8) [] = { 0x10, 0x10, 0x10, 0x10,
+ 0x10, 0x10, 0x10, 0x10 };
+VECT_VAR_DECL(expected_with_0,int,32,4) [] = { 0x20, 0x20, 0x20, 0x20 };
+VECT_VAR_DECL(expected_with_0,int,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected_with_0,uint,8,16) [] = { 0x8, 0x8, 0x8, 0x8,
+ 0x8, 0x8, 0x8, 0x8,
+ 0x8, 0x8, 0x8, 0x8,
+ 0x8, 0x8, 0x8, 0x8 };
+VECT_VAR_DECL(expected_with_0,uint,16,8) [] = { 0x10, 0x10, 0x10, 0x10,
+ 0x10, 0x10, 0x10, 0x10 };
+VECT_VAR_DECL(expected_with_0,uint,32,4) [] = { 0x20, 0x20, 0x20, 0x20 };
+VECT_VAR_DECL(expected_with_0,uint,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected_with_0,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected_with_0,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333,
+ 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected_with_0,hfloat,32,4) [] = { 0x33333333, 0x33333333,
+ 0x33333333, 0x33333333 };
+
+#define INSN_NAME vclz
+#define TEST_MSG "VCLZ/VCLZQ"
+
+#define FNNAME1(NAME) void exec_ ## NAME (void)
+#define FNNAME(NAME) FNNAME1(NAME)
+
+FNNAME (INSN_NAME)
+{
+ /* Basic test: y=vclz(x), then store the result. */
+#define TEST_UNARY_OP1(INSN, Q, T1, T2, W, N) \
+ VECT_VAR(vector_res, T1, W, N) = \
+ INSN##Q##_##T2##W(VECT_VAR(vector, T1, W, N)); \
+ vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N), VECT_VAR(vector_res, T1, W, N))
+
+#define TEST_UNARY_OP(INSN, Q, T1, T2, W, N) \
+ TEST_UNARY_OP1(INSN, Q, T1, T2, W, N) \
+
+ /* No need for 64 bits variants */
+ DECL_VARIABLE(vector, int, 8, 8);
+ DECL_VARIABLE(vector, int, 16, 4);
+ DECL_VARIABLE(vector, int, 32, 2);
+ DECL_VARIABLE(vector, uint, 8, 8);
+ DECL_VARIABLE(vector, uint, 16, 4);
+ DECL_VARIABLE(vector, uint, 32, 2);
+ DECL_VARIABLE(vector, int, 8, 16);
+ DECL_VARIABLE(vector, int, 16, 8);
+ DECL_VARIABLE(vector, int, 32, 4);
+ DECL_VARIABLE(vector, uint, 8, 16);
+ DECL_VARIABLE(vector, uint, 16, 8);
+ DECL_VARIABLE(vector, uint, 32, 4);
+
+ DECL_VARIABLE(vector_res, int, 8, 8);
+ DECL_VARIABLE(vector_res, int, 16, 4);
+ DECL_VARIABLE(vector_res, int, 32, 2);
+ DECL_VARIABLE(vector_res, uint, 8, 8);
+ DECL_VARIABLE(vector_res, uint, 16, 4);
+ DECL_VARIABLE(vector_res, uint, 32, 2);
+ DECL_VARIABLE(vector_res, int, 8, 16);
+ DECL_VARIABLE(vector_res, int, 16, 8);
+ DECL_VARIABLE(vector_res, int, 32, 4);
+ DECL_VARIABLE(vector_res, uint, 8, 16);
+ DECL_VARIABLE(vector_res, uint, 16, 8);
+ DECL_VARIABLE(vector_res, uint, 32, 4);
+
+ clean_results ();
+
+ /* Fill input vector with arbitrary values. */
+ VDUP(vector, , int, s, 8, 8, 0x84);
+ VDUP(vector, , int, s, 16, 4, 0x1234);
+ VDUP(vector, , int, s, 32, 2, 0x5678);
+ VDUP(vector, , uint, u, 8, 8, 0x34);
+ VDUP(vector, , uint, u, 16, 4, 0x8234);
+ VDUP(vector, , uint, u, 32, 2, 0x7654321);
+ VDUP(vector, q, int, s, 8, 16, 0x34);
+ VDUP(vector, q, int, s, 16, 8, 0x1234);
+ VDUP(vector, q, int, s, 32, 4, 0x12345678);
+ VDUP(vector, q, uint, u, 8, 16, 0x13);
+ VDUP(vector, q, uint, u, 16, 8, 0x4);
+ VDUP(vector, q, uint, u, 32, 4, 0x1);
+
+ /* Apply a unary operator named INSN_NAME. */
+ TEST_UNARY_OP(INSN_NAME, , int, s, 8, 8);
+ TEST_UNARY_OP(INSN_NAME, , int, s, 16, 4);
+ TEST_UNARY_OP(INSN_NAME, , int, s, 32, 2);
+ TEST_UNARY_OP(INSN_NAME, , uint, u, 8, 8);
+ TEST_UNARY_OP(INSN_NAME, , uint, u, 16, 4);
+ TEST_UNARY_OP(INSN_NAME, , uint, u, 32, 2);
+ TEST_UNARY_OP(INSN_NAME, q, int, s, 8, 16);
+ TEST_UNARY_OP(INSN_NAME, q, int, s, 16, 8);
+ TEST_UNARY_OP(INSN_NAME, q, int, s, 32, 4);
+ TEST_UNARY_OP(INSN_NAME, q, uint, u, 8, 16);
+ TEST_UNARY_OP(INSN_NAME, q, uint, u, 16, 8);
+ TEST_UNARY_OP(INSN_NAME, q, uint, u, 32, 4);
+
+ CHECK_RESULTS (TEST_MSG, "");
+
+ /* Test with zero as input. */
+ VDUP(vector, , int, s, 8, 8, 0);
+ VDUP(vector, , int, s, 16, 4, 0);
+ VDUP(vector, , int, s, 32, 2, 0);
+ VDUP(vector, , uint, u, 8, 8, 0);
+ VDUP(vector, , uint, u, 16, 4, 0);
+ VDUP(vector, , uint, u, 32, 2, 0);
+ VDUP(vector, q, int, s, 8, 16, 0);
+ VDUP(vector, q, int, s, 16, 8, 0);
+ VDUP(vector, q, int, s, 32, 4, 0);
+ VDUP(vector, q, uint, u, 8, 16, 0);
+ VDUP(vector, q, uint, u, 16, 8, 0);
+ VDUP(vector, q, uint, u, 32, 4, 0);
+
+ /* Apply a unary operator named INSN_NAME. */
+ TEST_UNARY_OP(INSN_NAME, , int, s, 8, 8);
+ TEST_UNARY_OP(INSN_NAME, , int, s, 16, 4);
+ TEST_UNARY_OP(INSN_NAME, , int, s, 32, 2);
+ TEST_UNARY_OP(INSN_NAME, , uint, u, 8, 8);
+ TEST_UNARY_OP(INSN_NAME, , uint, u, 16, 4);
+ TEST_UNARY_OP(INSN_NAME, , uint, u, 32, 2);
+ TEST_UNARY_OP(INSN_NAME, q, int, s, 8, 16);
+ TEST_UNARY_OP(INSN_NAME, q, int, s, 16, 8);
+ TEST_UNARY_OP(INSN_NAME, q, int, s, 32, 4);
+ TEST_UNARY_OP(INSN_NAME, q, uint, u, 8, 16);
+ TEST_UNARY_OP(INSN_NAME, q, uint, u, 16, 8);
+ TEST_UNARY_OP(INSN_NAME, q, uint, u, 32, 4);
+
+ CHECK_RESULTS_NAMED (TEST_MSG, expected_with_0, " (input=0)");
+}
+
+int main (void)
+{
+ exec_vclz ();
+ return 0;
+}
--- /dev/null
+#include <arm_neon.h>
+#include "arm-neon-ref.h"
+#include "compute-ref-data.h"
+
+/* We test vdup and vmov in the same place since they are aliases. */
+
+/* Expected results. */
+/* Chunk 0. */
+VECT_VAR_DECL(expected0,int,8,8) [] = { 0xf0, 0xf0, 0xf0, 0xf0,
+ 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected0,int,16,4) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected0,int,32,2) [] = { 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected0,int,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected0,uint,8,8) [] = { 0xf0, 0xf0, 0xf0, 0xf0,
+ 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected0,uint,16,4) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected0,uint,32,2) [] = { 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected0,uint,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected0,poly,8,8) [] = { 0xf0, 0xf0, 0xf0, 0xf0,
+ 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected0,poly,16,4) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected0,hfloat,32,2) [] = { 0xc1800000, 0xc1800000 };
+VECT_VAR_DECL(expected0,int,8,16) [] = { 0xf0, 0xf0, 0xf0, 0xf0,
+ 0xf0, 0xf0, 0xf0, 0xf0,
+ 0xf0, 0xf0, 0xf0, 0xf0,
+ 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected0,int,16,8) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0,
+ 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected0,int,32,4) [] = { 0xfffffff0, 0xfffffff0,
+ 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected0,int,64,2) [] = { 0xfffffffffffffff0,
+ 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected0,uint,8,16) [] = { 0xf0, 0xf0, 0xf0, 0xf0,
+ 0xf0, 0xf0, 0xf0, 0xf0,
+ 0xf0, 0xf0, 0xf0, 0xf0,
+ 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected0,uint,16,8) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0,
+ 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected0,uint,32,4) [] = { 0xfffffff0, 0xfffffff0,
+ 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected0,uint,64,2) [] = { 0xfffffffffffffff0,
+ 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected0,poly,8,16) [] = { 0xf0, 0xf0, 0xf0, 0xf0,
+ 0xf0, 0xf0, 0xf0, 0xf0,
+ 0xf0, 0xf0, 0xf0, 0xf0,
+ 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected0,poly,16,8) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0,
+ 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected0,hfloat,32,4) [] = { 0xc1800000, 0xc1800000,
+ 0xc1800000, 0xc1800000 };
+
+/* Chunk 1. */
+VECT_VAR_DECL(expected1,int,8,8) [] = { 0xf1, 0xf1, 0xf1, 0xf1,
+ 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected1,int,16,4) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected1,int,32,2) [] = { 0xfffffff1, 0xfffffff1 };
+VECT_VAR_DECL(expected1,int,64,1) [] = { 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected1,uint,8,8) [] = { 0xf1, 0xf1, 0xf1, 0xf1,
+ 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected1,uint,16,4) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected1,uint,32,2) [] = { 0xfffffff1, 0xfffffff1 };
+VECT_VAR_DECL(expected1,uint,64,1) [] = { 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected1,poly,8,8) [] = { 0xf1, 0xf1, 0xf1, 0xf1,
+ 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected1,poly,16,4) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected1,hfloat,32,2) [] = { 0xc1700000, 0xc1700000 };
+VECT_VAR_DECL(expected1,int,8,16) [] = { 0xf1, 0xf1, 0xf1, 0xf1,
+ 0xf1, 0xf1, 0xf1, 0xf1,
+ 0xf1, 0xf1, 0xf1, 0xf1,
+ 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected1,int,16,8) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1,
+ 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected1,int,32,4) [] = { 0xfffffff1, 0xfffffff1,
+ 0xfffffff1, 0xfffffff1 };
+VECT_VAR_DECL(expected1,int,64,2) [] = { 0xfffffffffffffff1,
+ 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected1,uint,8,16) [] = { 0xf1, 0xf1, 0xf1, 0xf1,
+ 0xf1, 0xf1, 0xf1, 0xf1,
+ 0xf1, 0xf1, 0xf1, 0xf1,
+ 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected1,uint,16,8) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1,
+ 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected1,uint,32,4) [] = { 0xfffffff1, 0xfffffff1,
+ 0xfffffff1, 0xfffffff1 };
+VECT_VAR_DECL(expected1,uint,64,2) [] = { 0xfffffffffffffff1,
+ 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected1,poly,8,16) [] = { 0xf1, 0xf1, 0xf1, 0xf1,
+ 0xf1, 0xf1, 0xf1, 0xf1,
+ 0xf1, 0xf1, 0xf1, 0xf1,
+ 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected1,poly,16,8) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1,
+ 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected1,hfloat,32,4) [] = { 0xc1700000, 0xc1700000,
+ 0xc1700000, 0xc1700000 };
+
+/* Chunk 2. */
+VECT_VAR_DECL(expected2,int,8,8) [] = { 0xf2, 0xf2, 0xf2, 0xf2,
+ 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected2,int,16,4) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected2,int,32,2) [] = { 0xfffffff2, 0xfffffff2 };
+VECT_VAR_DECL(expected2,int,64,1) [] = { 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected2,uint,8,8) [] = { 0xf2, 0xf2, 0xf2, 0xf2,
+ 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected2,uint,16,4) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected2,uint,32,2) [] = { 0xfffffff2, 0xfffffff2 };
+VECT_VAR_DECL(expected2,uint,64,1) [] = { 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected2,poly,8,8) [] = { 0xf2, 0xf2, 0xf2, 0xf2,
+ 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected2,poly,16,4) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected2,hfloat,32,2) [] = { 0xc1600000, 0xc1600000 };
+VECT_VAR_DECL(expected2,int,8,16) [] = { 0xf2, 0xf2, 0xf2, 0xf2,
+ 0xf2, 0xf2, 0xf2, 0xf2,
+ 0xf2, 0xf2, 0xf2, 0xf2,
+ 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected2,int,16,8) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2,
+ 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected2,int,32,4) [] = { 0xfffffff2, 0xfffffff2,
+ 0xfffffff2, 0xfffffff2 };
+VECT_VAR_DECL(expected2,int,64,2) [] = { 0xfffffffffffffff2,
+ 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected2,uint,8,16) [] = { 0xf2, 0xf2, 0xf2, 0xf2,
+ 0xf2, 0xf2, 0xf2, 0xf2,
+ 0xf2, 0xf2, 0xf2, 0xf2,
+ 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected2,uint,16,8) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2,
+ 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected2,uint,32,4) [] = { 0xfffffff2, 0xfffffff2,
+ 0xfffffff2, 0xfffffff2 };
+VECT_VAR_DECL(expected2,uint,64,2) [] = { 0xfffffffffffffff2,
+ 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected2,poly,8,16) [] = { 0xf2, 0xf2, 0xf2, 0xf2,
+ 0xf2, 0xf2, 0xf2, 0xf2,
+ 0xf2, 0xf2, 0xf2, 0xf2,
+ 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected2,poly,16,8) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2,
+ 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected2,hfloat,32,4) [] = { 0xc1600000, 0xc1600000,
+ 0xc1600000, 0xc1600000 };
+
+#define TEST_MSG "VDUP/VDUPQ"
+void exec_vdup_vmov (void)
+{
+ int i;
+
+ /* Basic test: vec=vdup(x), then store the result. */
+#undef TEST_VDUP
+#define TEST_VDUP(Q, T1, T2, W, N) \
+ VECT_VAR(vector, T1, W, N) = \
+ vdup##Q##_n_##T2##W(VECT_VAR(buffer_dup, T1, W, N)[i]); \
+ vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N), VECT_VAR(vector, T1, W, N))
+
+ /* Basic test: vec=vmov(x), then store the result. */
+#define TEST_VMOV(Q, T1, T2, W, N) \
+ VECT_VAR(vector, T1, W, N) = \
+ vmov##Q##_n_##T2##W(VECT_VAR(buffer_dup, T1, W, N)[i]); \
+ vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N), VECT_VAR(vector, T1, W, N))
+
+ DECL_VARIABLE_ALL_VARIANTS(vector);
+
+ /* Try to read different places from the input buffer. */
+ for (i=0; i< 3; i++) {
+ clean_results ();
+
+ TEST_VDUP(, int, s, 8, 8);
+ TEST_VDUP(, int, s, 16, 4);
+ TEST_VDUP(, int, s, 32, 2);
+ TEST_VDUP(, int, s, 64, 1);
+ TEST_VDUP(, uint, u, 8, 8);
+ TEST_VDUP(, uint, u, 16, 4);
+ TEST_VDUP(, uint, u, 32, 2);
+ TEST_VDUP(, uint, u, 64, 1);
+ TEST_VDUP(, poly, p, 8, 8);
+ TEST_VDUP(, poly, p, 16, 4);
+ TEST_VDUP(, float, f, 32, 2);
+
+ TEST_VDUP(q, int, s, 8, 16);
+ TEST_VDUP(q, int, s, 16, 8);
+ TEST_VDUP(q, int, s, 32, 4);
+ TEST_VDUP(q, int, s, 64, 2);
+ TEST_VDUP(q, uint, u, 8, 16);
+ TEST_VDUP(q, uint, u, 16, 8);
+ TEST_VDUP(q, uint, u, 32, 4);
+ TEST_VDUP(q, uint, u, 64, 2);
+ TEST_VDUP(q, poly, p, 8, 16);
+ TEST_VDUP(q, poly, p, 16, 8);
+ TEST_VDUP(q, float, f, 32, 4);
+
+ switch (i) {
+ case 0:
+ CHECK_RESULTS_NAMED (TEST_MSG, expected0, "");
+ break;
+ case 1:
+ CHECK_RESULTS_NAMED (TEST_MSG, expected1, "");
+ break;
+ case 2:
+ CHECK_RESULTS_NAMED (TEST_MSG, expected2, "");
+ break;
+ default:
+ abort();
+ }
+ }
+
+ /* Do the same tests with vmov. Use the same expected results. */
+#undef TEST_MSG
+#define TEST_MSG "VMOV/VMOVQ"
+ for (i=0; i< 3; i++) {
+ clean_results ();
+
+ TEST_VMOV(, int, s, 8, 8);
+ TEST_VMOV(, int, s, 16, 4);
+ TEST_VMOV(, int, s, 32, 2);
+ TEST_VMOV(, int, s, 64, 1);
+ TEST_VMOV(, uint, u, 8, 8);
+ TEST_VMOV(, uint, u, 16, 4);
+ TEST_VMOV(, uint, u, 32, 2);
+ TEST_VMOV(, uint, u, 64, 1);
+ TEST_VMOV(, poly, p, 8, 8);
+ TEST_VMOV(, poly, p, 16, 4);
+ TEST_VMOV(, float, f, 32, 2);
+
+ TEST_VMOV(q, int, s, 8, 16);
+ TEST_VMOV(q, int, s, 16, 8);
+ TEST_VMOV(q, int, s, 32, 4);
+ TEST_VMOV(q, int, s, 64, 2);
+ TEST_VMOV(q, uint, u, 8, 16);
+ TEST_VMOV(q, uint, u, 16, 8);
+ TEST_VMOV(q, uint, u, 32, 4);
+ TEST_VMOV(q, uint, u, 64, 2);
+ TEST_VMOV(q, poly, p, 8, 16);
+ TEST_VMOV(q, poly, p, 16, 8);
+ TEST_VMOV(q, float, f, 32, 4);
+
+ switch (i) {
+ case 0:
+ CHECK_RESULTS_NAMED (TEST_MSG, expected0, "");
+ break;
+ case 1:
+ CHECK_RESULTS_NAMED (TEST_MSG, expected1, "");
+ break;
+ case 2:
+ CHECK_RESULTS_NAMED (TEST_MSG, expected2, "");
+ break;
+ default:
+ abort();
+ }
+ }
+}
+
+int main (void)
+{
+ exec_vdup_vmov ();
+ return 0;
+}
--- /dev/null
+#define INSN_NAME veor
+#define TEST_MSG "VEOR/VEORQ"
+
+#include "binary_op.inc"
+
+/* Expected results. */
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf2, 0xf3, 0xf0, 0xf1,
+ 0xf6, 0xf7, 0xf4, 0xf5 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xc, 0xd, 0xe, 0xf };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff3, 0xfffffff2 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xffffffffffffff94 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xe4, 0xe5, 0xe6, 0xe7,
+ 0xe0, 0xe1, 0xe2, 0xe3 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffee, 0xffef, 0xffec, 0xffed };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffd8, 0xffffffd9 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x6, 0x7, 0x4, 0x5,
+ 0x2, 0x3, 0x0, 0x1,
+ 0xe, 0xf, 0xc, 0xd,
+ 0xa, 0xb, 0x8, 0x9 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x1c, 0x1d, 0x1e, 0x1f,
+ 0x18, 0x19, 0x1a, 0x1b };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x12, 0x13, 0x10, 0x11 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xffffffffffffffe8,
+ 0xffffffffffffffe9 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xfc, 0xfd, 0xfe, 0xff,
+ 0xf8, 0xf9, 0xfa, 0xfb,
+ 0xf4, 0xf5, 0xf6, 0xf7,
+ 0xf0, 0xf1, 0xf2, 0xf3 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff3, 0xfff2, 0xfff1, 0xfff0,
+ 0xfff7, 0xfff6, 0xfff5, 0xfff4 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffc7, 0xffffffc6,
+ 0xffffffc5, 0xffffffc4 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff3,
+ 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333,
+ 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333,
+ 0x33333333, 0x33333333 };
--- /dev/null
+#include <arm_neon.h>
+#include "arm-neon-ref.h"
+#include "compute-ref-data.h"
+
+/* Expected results. */
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3,
+ 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3,
+ 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3,
+ 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3,
+ 0xf4, 0xf5, 0xf6, 0xf7,
+ 0xf8, 0xf9, 0xfa, 0xfb,
+ 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3,
+ 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xfffffff1,
+ 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff0,
+ 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3,
+ 0xf4, 0xf5, 0xf6, 0xf7,
+ 0xf8, 0xf9, 0xfa, 0xfb,
+ 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xfff1, 0xfff2,
+ 0xfff3, 0xfff4, 0xfff5,
+ 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xfffffff1,
+ 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff0,
+ 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3,
+ 0xf4, 0xf5, 0xf6, 0xf7,
+ 0xf8, 0xf9, 0xfa, 0xfb,
+ 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3,
+ 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1800000, 0xc1700000,
+ 0xc1600000, 0xc1500000 };
+
+#define TEST_MSG "VLD1/VLD1Q"
+void exec_vld1 (void)
+{
+ /* Basic test vec=vld1(buffer); then store vec: vst1(result, vector). */
+ /* This test actually tests vdl1 and vst1 at the same time. */
+#define TEST_VLD1(VAR, BUF, Q, T1, T2, W, N) \
+ VECT_VAR(VAR, T1, W, N) = vld1##Q##_##T2##W(VECT_VAR(BUF, T1, W, N)); \
+ vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N), VECT_VAR(VAR, T1, W, N))
+
+ DECL_VARIABLE_ALL_VARIANTS(vector);
+
+ clean_results ();
+
+ TEST_MACRO_ALL_VARIANTS_2_5(TEST_VLD1, vector, buffer);
+
+ TEST_VLD1(vector, buffer, , float, f, 32, 2);
+ TEST_VLD1(vector, buffer, q, float, f, 32, 4);
+
+ CHECK_RESULTS (TEST_MSG, "");
+}
+
+int main (void)
+{
+ exec_vld1 ();
+ return 0;
+}
--- /dev/null
+#include <arm_neon.h>
+#include "arm-neon-ref.h"
+#include "compute-ref-data.h"
+
+/* Expected results. */
+/* Chunk 0. */
+VECT_VAR_DECL(expected0,int,8,8) [] = { 0xf0, 0xf0, 0xf0, 0xf0,
+ 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected0,int,16,4) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected0,int,32,2) [] = { 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected0,int,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected0,uint,8,8) [] = { 0xf0, 0xf0, 0xf0, 0xf0,
+ 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected0,uint,16,4) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected0,uint,32,2) [] = { 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected0,uint,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected0,poly,8,8) [] = { 0xf0, 0xf0, 0xf0, 0xf0,
+ 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected0,poly,16,4) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected0,hfloat,32,2) [] = { 0xc1800000, 0xc1800000 };
+VECT_VAR_DECL(expected0,int,8,16) [] = { 0xf0, 0xf0, 0xf0, 0xf0,
+ 0xf0, 0xf0, 0xf0, 0xf0,
+ 0xf0, 0xf0, 0xf0, 0xf0,
+ 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected0,int,16,8) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0,
+ 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected0,int,32,4) [] = { 0xfffffff0, 0xfffffff0,
+ 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected0,int,64,2) [] = { 0xfffffffffffffff0,
+ 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected0,uint,8,16) [] = { 0xf0, 0xf0, 0xf0, 0xf0,
+ 0xf0, 0xf0, 0xf0, 0xf0,
+ 0xf0, 0xf0, 0xf0, 0xf0,
+ 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected0,uint,16,8) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0,
+ 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected0,uint,32,4) [] = { 0xfffffff0, 0xfffffff0,
+ 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected0,uint,64,2) [] = { 0xfffffffffffffff0,
+ 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected0,poly,8,16) [] = { 0xf0, 0xf0, 0xf0, 0xf0,
+ 0xf0, 0xf0, 0xf0, 0xf0,
+ 0xf0, 0xf0, 0xf0, 0xf0,
+ 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected0,poly,16,8) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0,
+ 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected0,hfloat,32,4) [] = { 0xc1800000, 0xc1800000,
+ 0xc1800000, 0xc1800000 };
+
+/* Chunk 1. */
+VECT_VAR_DECL(expected1,int,8,8) [] = { 0xf1, 0xf1, 0xf1, 0xf1,
+ 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected1,int,16,4) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected1,int,32,2) [] = { 0xfffffff1, 0xfffffff1 };
+VECT_VAR_DECL(expected1,int,64,1) [] = { 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected1,uint,8,8) [] = { 0xf1, 0xf1, 0xf1, 0xf1,
+ 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected1,uint,16,4) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected1,uint,32,2) [] = { 0xfffffff1, 0xfffffff1 };
+VECT_VAR_DECL(expected1,uint,64,1) [] = { 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected1,poly,8,8) [] = { 0xf1, 0xf1, 0xf1, 0xf1,
+ 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected1,poly,16,4) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected1,hfloat,32,2) [] = { 0xc1700000, 0xc1700000 };
+VECT_VAR_DECL(expected1,int,8,16) [] = { 0xf1, 0xf1, 0xf1, 0xf1,
+ 0xf1, 0xf1, 0xf1, 0xf1,
+ 0xf1, 0xf1, 0xf1, 0xf1,
+ 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected1,int,16,8) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1,
+ 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected1,int,32,4) [] = { 0xfffffff1, 0xfffffff1,
+ 0xfffffff1, 0xfffffff1 };
+VECT_VAR_DECL(expected1,int,64,2) [] = { 0xfffffffffffffff1,
+ 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected1,uint,8,16) [] = { 0xf1, 0xf1, 0xf1, 0xf1,
+ 0xf1, 0xf1, 0xf1, 0xf1,
+ 0xf1, 0xf1, 0xf1, 0xf1,
+ 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected1,uint,16,8) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1,
+ 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected1,uint,32,4) [] = { 0xfffffff1, 0xfffffff1,
+ 0xfffffff1, 0xfffffff1 };
+VECT_VAR_DECL(expected1,uint,64,2) [] = { 0xfffffffffffffff1,
+ 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected1,poly,8,16) [] = { 0xf1, 0xf1, 0xf1, 0xf1,
+ 0xf1, 0xf1, 0xf1, 0xf1,
+ 0xf1, 0xf1, 0xf1, 0xf1,
+ 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected1,poly,16,8) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1,
+ 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected1,hfloat,32,4) [] = { 0xc1700000, 0xc1700000,
+ 0xc1700000, 0xc1700000 };
+
+/* Chunk 2. */
+VECT_VAR_DECL(expected2,int,8,8) [] = { 0xf2, 0xf2, 0xf2, 0xf2,
+ 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected2,int,16,4) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected2,int,32,2) [] = { 0xfffffff2, 0xfffffff2 };
+VECT_VAR_DECL(expected2,int,64,1) [] = { 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected2,uint,8,8) [] = { 0xf2, 0xf2, 0xf2, 0xf2,
+ 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected2,uint,16,4) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected2,uint,32,2) [] = { 0xfffffff2, 0xfffffff2 };
+VECT_VAR_DECL(expected2,uint,64,1) [] = { 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected2,poly,8,8) [] = { 0xf2, 0xf2, 0xf2, 0xf2,
+ 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected2,poly,16,4) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected2,hfloat,32,2) [] = { 0xc1600000, 0xc1600000 };
+VECT_VAR_DECL(expected2,int,8,16) [] = { 0xf2, 0xf2, 0xf2, 0xf2,
+ 0xf2, 0xf2, 0xf2, 0xf2,
+ 0xf2, 0xf2, 0xf2, 0xf2,
+ 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected2,int,16,8) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2,
+ 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected2,int,32,4) [] = { 0xfffffff2, 0xfffffff2,
+ 0xfffffff2, 0xfffffff2 };
+VECT_VAR_DECL(expected2,int,64,2) [] = { 0xfffffffffffffff2,
+ 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected2,uint,8,16) [] = { 0xf2, 0xf2, 0xf2, 0xf2,
+ 0xf2, 0xf2, 0xf2, 0xf2,
+ 0xf2, 0xf2, 0xf2, 0xf2,
+ 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected2,uint,16,8) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2,
+ 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected2,uint,32,4) [] = { 0xfffffff2, 0xfffffff2,
+ 0xfffffff2, 0xfffffff2 };
+VECT_VAR_DECL(expected2,uint,64,2) [] = { 0xfffffffffffffff2,
+ 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected2,poly,8,16) [] = { 0xf2, 0xf2, 0xf2, 0xf2,
+ 0xf2, 0xf2, 0xf2, 0xf2,
+ 0xf2, 0xf2, 0xf2, 0xf2,
+ 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected2,poly,16,8) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2,
+ 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected2,hfloat,32,4) [] = { 0xc1600000, 0xc1600000,
+ 0xc1600000, 0xc1600000 };
+
+#define TEST_MSG "VLD1_DUP/VLD1_DUPQ"
+void exec_vld1_dup (void)
+{
+ int i;
+
+ /* Fill vector with buffer item #i. */
+#define TEST_VLD1_DUP(VAR, BUF, Q, T1, T2, W, N) \
+ VECT_VAR(VAR, T1, W, N) = \
+ vld1##Q##_dup_##T2##W(&VECT_VAR(BUF, T1, W, N)[i]); \
+ vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N), VECT_VAR(VAR, T1, W, N))
+
+ DECL_VARIABLE_ALL_VARIANTS(vector);
+
+ /* Try to read different places from the input buffer. */
+ for (i=0; i<3; i++) {
+ clean_results ();
+
+ TEST_MACRO_ALL_VARIANTS_2_5(TEST_VLD1_DUP, vector, buffer_dup);
+
+ TEST_VLD1_DUP(vector, buffer_dup, , float, f, 32, 2);
+ TEST_VLD1_DUP(vector, buffer_dup, q, float, f, 32, 4);
+
+ switch (i) {
+ case 0:
+ CHECK_RESULTS_NAMED (TEST_MSG, expected0, "");
+ break;
+ case 1:
+ CHECK_RESULTS_NAMED (TEST_MSG, expected1, "");
+ break;
+ case 2:
+ CHECK_RESULTS_NAMED (TEST_MSG, expected2, "");
+ break;
+ default:
+ abort();
+ }
+ }
+}
+
+int main (void)
+{
+ exec_vld1_dup ();
+ return 0;
+}
--- /dev/null
+#include <arm_neon.h>
+#include "arm-neon-ref.h"
+#include "compute-ref-data.h"
+
+/* Expected results. */
+
+/* vld2/chunk 0. */
+VECT_VAR_DECL(expected_vld2_0,int,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3,
+ 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected_vld2_0,int,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected_vld2_0,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected_vld2_0,int,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected_vld2_0,uint,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3,
+ 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected_vld2_0,uint,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected_vld2_0,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected_vld2_0,uint,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected_vld2_0,poly,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3,
+ 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected_vld2_0,poly,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected_vld2_0,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected_vld2_0,int,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3,
+ 0xf4, 0xf5, 0xf6, 0xf7,
+ 0xf8, 0xf9, 0xfa, 0xfb,
+ 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected_vld2_0,int,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3,
+ 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected_vld2_0,int,32,4) [] = { 0xfffffff0, 0xfffffff1,
+ 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected_vld2_0,int,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected_vld2_0,uint,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3,
+ 0xf4, 0xf5, 0xf6, 0xf7,
+ 0xf8, 0xf9, 0xfa, 0xfb,
+ 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected_vld2_0,uint,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3,
+ 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected_vld2_0,uint,32,4) [] = { 0xfffffff0, 0xfffffff1,
+ 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected_vld2_0,uint,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected_vld2_0,poly,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3,
+ 0xf4, 0xf5, 0xf6, 0xf7,
+ 0xf8, 0xf9, 0xfa, 0xfb,
+ 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected_vld2_0,poly,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3,
+ 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected_vld2_0,hfloat,32,4) [] = { 0xc1800000, 0xc1700000,
+ 0xc1600000, 0xc1500000 };
+
+/* vld2/chunk 1. */
+VECT_VAR_DECL(expected_vld2_1,int,8,8) [] = { 0xf8, 0xf9, 0xfa, 0xfb,
+ 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected_vld2_1,int,16,4) [] = { 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected_vld2_1,int,32,2) [] = { 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected_vld2_1,int,64,1) [] = { 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected_vld2_1,uint,8,8) [] = { 0xf8, 0xf9, 0xfa, 0xfb,
+ 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected_vld2_1,uint,16,4) [] = { 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected_vld2_1,uint,32,2) [] = { 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected_vld2_1,uint,64,1) [] = { 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected_vld2_1,poly,8,8) [] = { 0xf8, 0xf9, 0xfa, 0xfb,
+ 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected_vld2_1,poly,16,4) [] = { 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected_vld2_1,hfloat,32,2) [] = { 0xc1600000, 0xc1500000 };
+VECT_VAR_DECL(expected_vld2_1,int,8,16) [] = { 0x0, 0x1, 0x2, 0x3,
+ 0x4, 0x5, 0x6, 0x7,
+ 0x8, 0x9, 0xa, 0xb,
+ 0xc, 0xd, 0xe, 0xf };
+VECT_VAR_DECL(expected_vld2_1,int,16,8) [] = { 0xfff8, 0xfff9, 0xfffa, 0xfffb,
+ 0xfffc, 0xfffd, 0xfffe, 0xffff };
+VECT_VAR_DECL(expected_vld2_1,int,32,4) [] = { 0xfffffff4, 0xfffffff5,
+ 0xfffffff6, 0xfffffff7 };
+VECT_VAR_DECL(expected_vld2_1,int,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected_vld2_1,uint,8,16) [] = { 0x0, 0x1, 0x2, 0x3,
+ 0x4, 0x5, 0x6, 0x7,
+ 0x8, 0x9, 0xa, 0xb,
+ 0xc, 0xd, 0xe, 0xf };
+VECT_VAR_DECL(expected_vld2_1,uint,16,8) [] = { 0xfff8, 0xfff9, 0xfffa, 0xfffb,
+ 0xfffc, 0xfffd, 0xfffe, 0xffff };
+VECT_VAR_DECL(expected_vld2_1,uint,32,4) [] = { 0xfffffff4, 0xfffffff5,
+ 0xfffffff6, 0xfffffff7 };
+VECT_VAR_DECL(expected_vld2_1,uint,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected_vld2_1,poly,8,16) [] = { 0x0, 0x1, 0x2, 0x3,
+ 0x4, 0x5, 0x6, 0x7,
+ 0x8, 0x9, 0xa, 0xb,
+ 0xc, 0xd, 0xe, 0xf };
+VECT_VAR_DECL(expected_vld2_1,poly,16,8) [] = { 0xfff8, 0xfff9, 0xfffa, 0xfffb,
+ 0xfffc, 0xfffd, 0xfffe, 0xffff };
+VECT_VAR_DECL(expected_vld2_1,hfloat,32,4) [] = { 0xc1400000, 0xc1300000,
+ 0xc1200000, 0xc1100000 };
+
+/* vld3/chunk 0. */
+VECT_VAR_DECL(expected_vld3_0,int,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3,
+ 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected_vld3_0,int,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected_vld3_0,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected_vld3_0,int,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected_vld3_0,uint,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3,
+ 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected_vld3_0,uint,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected_vld3_0,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected_vld3_0,uint,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected_vld3_0,poly,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3,
+ 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected_vld3_0,poly,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected_vld3_0,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected_vld3_0,int,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3,
+ 0xf4, 0xf5, 0xf6, 0xf7,
+ 0xf8, 0xf9, 0xfa, 0xfb,
+ 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected_vld3_0,int,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3,
+ 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected_vld3_0,int,32,4) [] = { 0xfffffff0, 0xfffffff1,
+ 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected_vld3_0,int,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected_vld3_0,uint,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3,
+ 0xf4, 0xf5, 0xf6, 0xf7,
+ 0xf8, 0xf9, 0xfa, 0xfb,
+ 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected_vld3_0,uint,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3,
+ 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected_vld3_0,uint,32,4) [] = { 0xfffffff0, 0xfffffff1,
+ 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected_vld3_0,uint,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected_vld3_0,poly,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3,
+ 0xf4, 0xf5, 0xf6, 0xf7,
+ 0xf8, 0xf9, 0xfa, 0xfb,
+ 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected_vld3_0,poly,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3,
+ 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected_vld3_0,hfloat,32,4) [] = { 0xc1800000, 0xc1700000,
+ 0xc1600000, 0xc1500000 };
+
+/* vld3/chunk 1. */
+VECT_VAR_DECL(expected_vld3_1,int,8,8) [] = { 0xf8, 0xf9, 0xfa, 0xfb,
+ 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected_vld3_1,int,16,4) [] = { 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected_vld3_1,int,32,2) [] = { 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected_vld3_1,int,64,1) [] = { 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected_vld3_1,uint,8,8) [] = { 0xf8, 0xf9, 0xfa, 0xfb,
+ 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected_vld3_1,uint,16,4) [] = { 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected_vld3_1,uint,32,2) [] = { 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected_vld3_1,uint,64,1) [] = { 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected_vld3_1,poly,8,8) [] = { 0xf8, 0xf9, 0xfa, 0xfb,
+ 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected_vld3_1,poly,16,4) [] = { 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected_vld3_1,hfloat,32,2) [] = { 0xc1600000, 0xc1500000 };
+VECT_VAR_DECL(expected_vld3_1,int,8,16) [] = { 0x0, 0x1, 0x2, 0x3,
+ 0x4, 0x5, 0x6, 0x7,
+ 0x8, 0x9, 0xa, 0xb,
+ 0xc, 0xd, 0xe, 0xf };
+VECT_VAR_DECL(expected_vld3_1,int,16,8) [] = { 0xfff8, 0xfff9, 0xfffa, 0xfffb,
+ 0xfffc, 0xfffd, 0xfffe, 0xffff };
+VECT_VAR_DECL(expected_vld3_1,int,32,4) [] = { 0xfffffff4, 0xfffffff5,
+ 0xfffffff6, 0xfffffff7 };
+VECT_VAR_DECL(expected_vld3_1,int,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected_vld3_1,uint,8,16) [] = { 0x0, 0x1, 0x2, 0x3,
+ 0x4, 0x5, 0x6, 0x7,
+ 0x8, 0x9, 0xa, 0xb,
+ 0xc, 0xd, 0xe, 0xf };
+VECT_VAR_DECL(expected_vld3_1,uint,16,8) [] = { 0xfff8, 0xfff9, 0xfffa, 0xfffb,
+ 0xfffc, 0xfffd, 0xfffe, 0xffff };
+VECT_VAR_DECL(expected_vld3_1,uint,32,4) [] = { 0xfffffff4, 0xfffffff5,
+ 0xfffffff6, 0xfffffff7 };
+VECT_VAR_DECL(expected_vld3_1,uint,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected_vld3_1,poly,8,16) [] = { 0x0, 0x1, 0x2, 0x3,
+ 0x4, 0x5, 0x6, 0x7,
+ 0x8, 0x9, 0xa, 0xb,
+ 0xc, 0xd, 0xe, 0xf };
+VECT_VAR_DECL(expected_vld3_1,poly,16,8) [] = { 0xfff8, 0xfff9, 0xfffa, 0xfffb,
+ 0xfffc, 0xfffd, 0xfffe, 0xffff };
+VECT_VAR_DECL(expected_vld3_1,hfloat,32,4) [] = { 0xc1400000, 0xc1300000,
+ 0xc1200000, 0xc1100000 };
+
+/* vld3/chunk 2. */
+VECT_VAR_DECL(expected_vld3_2,int,8,8) [] = { 0x0, 0x1, 0x2, 0x3,
+ 0x4, 0x5, 0x6, 0x7 };
+VECT_VAR_DECL(expected_vld3_2,int,16,4) [] = { 0xfff8, 0xfff9,
+ 0xfffa, 0xfffb };
+VECT_VAR_DECL(expected_vld3_2,int,32,2) [] = { 0xfffffff4, 0xfffffff5 };
+VECT_VAR_DECL(expected_vld3_2,int,64,1) [] = { 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected_vld3_2,uint,8,8) [] = { 0x0, 0x1, 0x2, 0x3,
+ 0x4, 0x5, 0x6, 0x7 };
+VECT_VAR_DECL(expected_vld3_2,uint,16,4) [] = { 0xfff8, 0xfff9,
+ 0xfffa, 0xfffb };
+VECT_VAR_DECL(expected_vld3_2,uint,32,2) [] = { 0xfffffff4, 0xfffffff5 };
+VECT_VAR_DECL(expected_vld3_2,uint,64,1) [] = { 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected_vld3_2,poly,8,8) [] = { 0x0, 0x1, 0x2, 0x3,
+ 0x4, 0x5, 0x6, 0x7 };
+VECT_VAR_DECL(expected_vld3_2,poly,16,4) [] = { 0xfff8, 0xfff9,
+ 0xfffa, 0xfffb };
+VECT_VAR_DECL(expected_vld3_2,hfloat,32,2) [] = { 0xc1400000, 0xc1300000 };
+VECT_VAR_DECL(expected_vld3_2,int,8,16) [] = { 0x10, 0x11, 0x12, 0x13,
+ 0x14, 0x15, 0x16, 0x17,
+ 0x18, 0x19, 0x1a, 0x1b,
+ 0x1c, 0x1d, 0x1e, 0x1f };
+VECT_VAR_DECL(expected_vld3_2,int,16,8) [] = { 0x0, 0x1, 0x2, 0x3,
+ 0x4, 0x5, 0x6, 0x7 };
+VECT_VAR_DECL(expected_vld3_2,int,32,4) [] = { 0xfffffff8, 0xfffffff9,
+ 0xfffffffa, 0xfffffffb };
+VECT_VAR_DECL(expected_vld3_2,int,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected_vld3_2,uint,8,16) [] = { 0x10, 0x11, 0x12, 0x13,
+ 0x14, 0x15, 0x16, 0x17,
+ 0x18, 0x19, 0x1a, 0x1b,
+ 0x1c, 0x1d, 0x1e, 0x1f };
+VECT_VAR_DECL(expected_vld3_2,uint,16,8) [] = { 0x0, 0x1, 0x2, 0x3,
+ 0x4, 0x5, 0x6, 0x7 };
+VECT_VAR_DECL(expected_vld3_2,uint,32,4) [] = { 0xfffffff8, 0xfffffff9,
+ 0xfffffffa, 0xfffffffb };
+VECT_VAR_DECL(expected_vld3_2,uint,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected_vld3_2,poly,8,16) [] = { 0x10, 0x11, 0x12, 0x13,
+ 0x14, 0x15, 0x16, 0x17,
+ 0x18, 0x19, 0x1a, 0x1b,
+ 0x1c, 0x1d, 0x1e, 0x1f };
+VECT_VAR_DECL(expected_vld3_2,poly,16,8) [] = { 0x0, 0x1, 0x2, 0x3,
+ 0x4, 0x5, 0x6, 0x7 };
+VECT_VAR_DECL(expected_vld3_2,hfloat,32,4) [] = { 0xc1000000, 0xc0e00000,
+ 0xc0c00000, 0xc0a00000 };
+
+/* vld4/chunk 0. */
+VECT_VAR_DECL(expected_vld4_0,int,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3,
+ 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected_vld4_0,int,16,4) [] = { 0xfff0, 0xfff1,
+ 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected_vld4_0,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected_vld4_0,int,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected_vld4_0,uint,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3,
+ 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected_vld4_0,uint,16,4) [] = { 0xfff0, 0xfff1,
+ 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected_vld4_0,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected_vld4_0,uint,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected_vld4_0,poly,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3,
+ 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected_vld4_0,poly,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected_vld4_0,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected_vld4_0,int,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3,
+ 0xf4, 0xf5, 0xf6, 0xf7,
+ 0xf8, 0xf9, 0xfa, 0xfb,
+ 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected_vld4_0,int,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3,
+ 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected_vld4_0,int,32,4) [] = { 0xfffffff0, 0xfffffff1,
+ 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected_vld4_0,int,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected_vld4_0,uint,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3,
+ 0xf4, 0xf5, 0xf6, 0xf7,
+ 0xf8, 0xf9, 0xfa, 0xfb,
+ 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected_vld4_0,uint,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3,
+ 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected_vld4_0,uint,32,4) [] = { 0xfffffff0, 0xfffffff1,
+ 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected_vld4_0,uint,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected_vld4_0,poly,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3,
+ 0xf4, 0xf5, 0xf6, 0xf7,
+ 0xf8, 0xf9, 0xfa, 0xfb,
+ 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected_vld4_0,poly,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3,
+ 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected_vld4_0,hfloat,32,4) [] = { 0xc1800000, 0xc1700000,
+ 0xc1600000, 0xc1500000 };
+
+/* vld4/chunk 1. */
+VECT_VAR_DECL(expected_vld4_1,int,8,8) [] = { 0xf8, 0xf9, 0xfa, 0xfb,
+ 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected_vld4_1,int,16,4) [] = { 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected_vld4_1,int,32,2) [] = { 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected_vld4_1,int,64,1) [] = { 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected_vld4_1,uint,8,8) [] = { 0xf8, 0xf9, 0xfa, 0xfb,
+ 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected_vld4_1,uint,16,4) [] = { 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected_vld4_1,uint,32,2) [] = { 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected_vld4_1,uint,64,1) [] = { 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected_vld4_1,poly,8,8) [] = { 0xf8, 0xf9, 0xfa, 0xfb,
+ 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected_vld4_1,poly,16,4) [] = { 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected_vld4_1,hfloat,32,2) [] = { 0xc1600000, 0xc1500000 };
+VECT_VAR_DECL(expected_vld4_1,int,8,16) [] = { 0x0, 0x1, 0x2, 0x3,
+ 0x4, 0x5, 0x6, 0x7,
+ 0x8, 0x9, 0xa, 0xb,
+ 0xc, 0xd, 0xe, 0xf };
+VECT_VAR_DECL(expected_vld4_1,int,16,8) [] = { 0xfff8, 0xfff9, 0xfffa, 0xfffb,
+ 0xfffc, 0xfffd, 0xfffe, 0xffff };
+VECT_VAR_DECL(expected_vld4_1,int,32,4) [] = { 0xfffffff4, 0xfffffff5,
+ 0xfffffff6, 0xfffffff7 };
+VECT_VAR_DECL(expected_vld4_1,int,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected_vld4_1,uint,8,16) [] = { 0x0, 0x1, 0x2, 0x3,
+ 0x4, 0x5, 0x6, 0x7,
+ 0x8, 0x9, 0xa, 0xb,
+ 0xc, 0xd, 0xe, 0xf };
+VECT_VAR_DECL(expected_vld4_1,uint,16,8) [] = { 0xfff8, 0xfff9, 0xfffa, 0xfffb,
+ 0xfffc, 0xfffd, 0xfffe, 0xffff };
+VECT_VAR_DECL(expected_vld4_1,uint,32,4) [] = { 0xfffffff4, 0xfffffff5,
+ 0xfffffff6, 0xfffffff7 };
+VECT_VAR_DECL(expected_vld4_1,uint,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected_vld4_1,poly,8,16) [] = { 0x0, 0x1, 0x2, 0x3,
+ 0x4, 0x5, 0x6, 0x7,
+ 0x8, 0x9, 0xa, 0xb,
+ 0xc, 0xd, 0xe, 0xf };
+VECT_VAR_DECL(expected_vld4_1,poly,16,8) [] = { 0xfff8, 0xfff9, 0xfffa, 0xfffb,
+ 0xfffc, 0xfffd, 0xfffe, 0xffff };
+VECT_VAR_DECL(expected_vld4_1,hfloat,32,4) [] = { 0xc1400000, 0xc1300000,
+ 0xc1200000, 0xc1100000 };
+
+/* vld4/chunk 2. */
+VECT_VAR_DECL(expected_vld4_2,int,8,8) [] = { 0x0, 0x1, 0x2, 0x3,
+ 0x4, 0x5, 0x6, 0x7 };
+VECT_VAR_DECL(expected_vld4_2,int,16,4) [] = { 0xfff8, 0xfff9, 0xfffa, 0xfffb };
+VECT_VAR_DECL(expected_vld4_2,int,32,2) [] = { 0xfffffff4, 0xfffffff5 };
+VECT_VAR_DECL(expected_vld4_2,int,64,1) [] = { 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected_vld4_2,uint,8,8) [] = { 0x0, 0x1, 0x2, 0x3,
+ 0x4, 0x5, 0x6, 0x7 };
+VECT_VAR_DECL(expected_vld4_2,uint,16,4) [] = { 0xfff8, 0xfff9, 0xfffa, 0xfffb };
+VECT_VAR_DECL(expected_vld4_2,uint,32,2) [] = { 0xfffffff4, 0xfffffff5 };
+VECT_VAR_DECL(expected_vld4_2,uint,64,1) [] = { 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected_vld4_2,poly,8,8) [] = { 0x0, 0x1, 0x2, 0x3,
+ 0x4, 0x5, 0x6, 0x7 };
+VECT_VAR_DECL(expected_vld4_2,poly,16,4) [] = { 0xfff8, 0xfff9, 0xfffa, 0xfffb };
+VECT_VAR_DECL(expected_vld4_2,hfloat,32,2) [] = { 0xc1400000, 0xc1300000 };
+VECT_VAR_DECL(expected_vld4_2,int,8,16) [] = { 0x10, 0x11, 0x12, 0x13,
+ 0x14, 0x15, 0x16, 0x17,
+ 0x18, 0x19, 0x1a, 0x1b,
+ 0x1c, 0x1d, 0x1e, 0x1f };
+VECT_VAR_DECL(expected_vld4_2,int,16,8) [] = { 0x0, 0x1, 0x2, 0x3,
+ 0x4, 0x5, 0x6, 0x7 };
+VECT_VAR_DECL(expected_vld4_2,int,32,4) [] = { 0xfffffff8, 0xfffffff9,
+ 0xfffffffa, 0xfffffffb };
+VECT_VAR_DECL(expected_vld4_2,int,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected_vld4_2,uint,8,16) [] = { 0x10, 0x11, 0x12, 0x13,
+ 0x14, 0x15, 0x16, 0x17,
+ 0x18, 0x19, 0x1a, 0x1b,
+ 0x1c, 0x1d, 0x1e, 0x1f };
+VECT_VAR_DECL(expected_vld4_2,uint,16,8) [] = { 0x0, 0x1, 0x2, 0x3,
+ 0x4, 0x5, 0x6, 0x7 };
+VECT_VAR_DECL(expected_vld4_2,uint,32,4) [] = { 0xfffffff8, 0xfffffff9,
+ 0xfffffffa, 0xfffffffb };
+VECT_VAR_DECL(expected_vld4_2,uint,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected_vld4_2,poly,8,16) [] = { 0x10, 0x11, 0x12, 0x13,
+ 0x14, 0x15, 0x16, 0x17,
+ 0x18, 0x19, 0x1a, 0x1b,
+ 0x1c, 0x1d, 0x1e, 0x1f };
+VECT_VAR_DECL(expected_vld4_2,poly,16,8) [] = { 0x0, 0x1, 0x2, 0x3,
+ 0x4, 0x5, 0x6, 0x7 };
+VECT_VAR_DECL(expected_vld4_2,hfloat,32,4) [] = { 0xc1000000, 0xc0e00000,
+ 0xc0c00000, 0xc0a00000 };
+
+/* vld4/chunk 3. */
+VECT_VAR_DECL(expected_vld4_3,int,8,8) [] = { 0x8, 0x9, 0xa, 0xb,
+ 0xc, 0xd, 0xe, 0xf };
+VECT_VAR_DECL(expected_vld4_3,int,16,4) [] = { 0xfffc, 0xfffd, 0xfffe, 0xffff };
+VECT_VAR_DECL(expected_vld4_3,int,32,2) [] = { 0xfffffff6, 0xfffffff7 };
+VECT_VAR_DECL(expected_vld4_3,int,64,1) [] = { 0xfffffffffffffff3 };
+VECT_VAR_DECL(expected_vld4_3,uint,8,8) [] = { 0x8, 0x9, 0xa, 0xb,
+ 0xc, 0xd, 0xe, 0xf };
+VECT_VAR_DECL(expected_vld4_3,uint,16,4) [] = { 0xfffc, 0xfffd, 0xfffe, 0xffff };
+VECT_VAR_DECL(expected_vld4_3,uint,32,2) [] = { 0xfffffff6, 0xfffffff7 };
+VECT_VAR_DECL(expected_vld4_3,uint,64,1) [] = { 0xfffffffffffffff3 };
+VECT_VAR_DECL(expected_vld4_3,poly,8,8) [] = { 0x8, 0x9, 0xa, 0xb,
+ 0xc, 0xd, 0xe, 0xf };
+VECT_VAR_DECL(expected_vld4_3,poly,16,4) [] = { 0xfffc, 0xfffd, 0xfffe, 0xffff };
+VECT_VAR_DECL(expected_vld4_3,hfloat,32,2) [] = { 0xc1200000, 0xc1100000 };
+VECT_VAR_DECL(expected_vld4_3,int,8,16) [] = { 0x20, 0x21, 0x22, 0x23,
+ 0x24, 0x25, 0x26, 0x27,
+ 0x28, 0x29, 0x2a, 0x2b,
+ 0x2c, 0x2d, 0x2e, 0x2f };
+VECT_VAR_DECL(expected_vld4_3,int,16,8) [] = { 0x8, 0x9, 0xa, 0xb,
+ 0xc, 0xd, 0xe, 0xf };
+VECT_VAR_DECL(expected_vld4_3,int,32,4) [] = { 0xfffffffc, 0xfffffffd,
+ 0xfffffffe, 0xffffffff };
+VECT_VAR_DECL(expected_vld4_3,int,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected_vld4_3,uint,8,16) [] = { 0x20, 0x21, 0x22, 0x23,
+ 0x24, 0x25, 0x26, 0x27,
+ 0x28, 0x29, 0x2a, 0x2b,
+ 0x2c, 0x2d, 0x2e, 0x2f };
+VECT_VAR_DECL(expected_vld4_3,uint,16,8) [] = { 0x8, 0x9, 0xa, 0xb,
+ 0xc, 0xd, 0xe, 0xf };
+VECT_VAR_DECL(expected_vld4_3,uint,32,4) [] = { 0xfffffffc, 0xfffffffd,
+ 0xfffffffe, 0xffffffff };
+VECT_VAR_DECL(expected_vld4_3,uint,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected_vld4_3,poly,8,16) [] = { 0x20, 0x21, 0x22, 0x23,
+ 0x24, 0x25, 0x26, 0x27,
+ 0x28, 0x29, 0x2a, 0x2b,
+ 0x2c, 0x2d, 0x2e, 0x2f };
+VECT_VAR_DECL(expected_vld4_3,poly,16,8) [] = { 0x8, 0x9, 0xa, 0xb,
+ 0xc, 0xd, 0xe, 0xf };
+VECT_VAR_DECL(expected_vld4_3,hfloat,32,4) [] = { 0xc0800000, 0xc0400000,
+ 0xc0000000, 0xbf800000 };
+
+void exec_vldX (void)
+{
+ /* In this case, input variables are arrays of vectors. */
+#define DECL_VLDX(T1, W, N, X) \
+ VECT_ARRAY_TYPE(T1, W, N, X) VECT_ARRAY_VAR(vector, T1, W, N, X); \
+ VECT_VAR_DECL(result_bis_##X, T1, W, N)[X * N]
+
+ /* We need to use a temporary result buffer (result_bis), because
+ the one used for other tests is not large enough. A subset of the
+ result data is moved from result_bis to result, and it is this
+ subset which is used to check the actual behaviour. The next
+ macro enables to move another chunk of data from result_bis to
+ result. */
+#define TEST_VLDX(Q, T1, T2, W, N, X) \
+ VECT_ARRAY_VAR(vector, T1, W, N, X) = \
+ /* Use dedicated init buffer, of size X */ \
+ vld##X##Q##_##T2##W(VECT_ARRAY_VAR(buffer_vld##X, T1, W, N, X)); \
+ vst##X##Q##_##T2##W(VECT_VAR(result_bis_##X, T1, W, N), \
+ VECT_ARRAY_VAR(vector, T1, W, N, X)); \
+ memcpy(VECT_VAR(result, T1, W, N), VECT_VAR(result_bis_##X, T1, W, N), \
+ sizeof(VECT_VAR(result, T1, W, N)));
+
+ /* Overwrite "result" with the contents of "result_bis"[Y]. */
+#define TEST_EXTRA_CHUNK(T1, W, N, X,Y) \
+ memcpy(VECT_VAR(result, T1, W, N), \
+ &(VECT_VAR(result_bis_##X, T1, W, N)[Y*N]), \
+ sizeof(VECT_VAR(result, T1, W, N)));
+
+ /* We need all variants in 64 bits, but there is no 64x2 variant. */
+#define DECL_ALL_VLDX(X) \
+ DECL_VLDX(int, 8, 8, X); \
+ DECL_VLDX(int, 16, 4, X); \
+ DECL_VLDX(int, 32, 2, X); \
+ DECL_VLDX(int, 64, 1, X); \
+ DECL_VLDX(uint, 8, 8, X); \
+ DECL_VLDX(uint, 16, 4, X); \
+ DECL_VLDX(uint, 32, 2, X); \
+ DECL_VLDX(uint, 64, 1, X); \
+ DECL_VLDX(poly, 8, 8, X); \
+ DECL_VLDX(poly, 16, 4, X); \
+ DECL_VLDX(float, 32, 2, X); \
+ DECL_VLDX(int, 8, 16, X); \
+ DECL_VLDX(int, 16, 8, X); \
+ DECL_VLDX(int, 32, 4, X); \
+ DECL_VLDX(uint, 8, 16, X); \
+ DECL_VLDX(uint, 16, 8, X); \
+ DECL_VLDX(uint, 32, 4, X); \
+ DECL_VLDX(poly, 8, 16, X); \
+ DECL_VLDX(poly, 16, 8, X); \
+ DECL_VLDX(float, 32, 4, X)
+
+#define TEST_ALL_VLDX(X) \
+ TEST_VLDX(, int, s, 8, 8, X); \
+ TEST_VLDX(, int, s, 16, 4, X); \
+ TEST_VLDX(, int, s, 32, 2, X); \
+ TEST_VLDX(, int, s, 64, 1, X); \
+ TEST_VLDX(, uint, u, 8, 8, X); \
+ TEST_VLDX(, uint, u, 16, 4, X); \
+ TEST_VLDX(, uint, u, 32, 2, X); \
+ TEST_VLDX(, uint, u, 64, 1, X); \
+ TEST_VLDX(, poly, p, 8, 8, X); \
+ TEST_VLDX(, poly, p, 16, 4, X); \
+ TEST_VLDX(, float, f, 32, 2, X); \
+ TEST_VLDX(q, int, s, 8, 16, X); \
+ TEST_VLDX(q, int, s, 16, 8, X); \
+ TEST_VLDX(q, int, s, 32, 4, X); \
+ TEST_VLDX(q, uint, u, 8, 16, X); \
+ TEST_VLDX(q, uint, u, 16, 8, X); \
+ TEST_VLDX(q, uint, u, 32, 4, X); \
+ TEST_VLDX(q, poly, p, 8, 16, X); \
+ TEST_VLDX(q, poly, p, 16, 8, X); \
+ TEST_VLDX(q, float, f, 32, 4, X)
+
+#define TEST_ALL_EXTRA_CHUNKS(X, Y) \
+ TEST_EXTRA_CHUNK(int, 8, 8, X, Y); \
+ TEST_EXTRA_CHUNK(int, 16, 4, X, Y); \
+ TEST_EXTRA_CHUNK(int, 32, 2, X, Y); \
+ TEST_EXTRA_CHUNK(int, 64, 1, X, Y); \
+ TEST_EXTRA_CHUNK(uint, 8, 8, X, Y); \
+ TEST_EXTRA_CHUNK(uint, 16, 4, X, Y); \
+ TEST_EXTRA_CHUNK(uint, 32, 2, X, Y); \
+ TEST_EXTRA_CHUNK(uint, 64, 1, X, Y); \
+ TEST_EXTRA_CHUNK(poly, 8, 8, X, Y); \
+ TEST_EXTRA_CHUNK(poly, 16, 4, X, Y); \
+ TEST_EXTRA_CHUNK(float, 32, 2, X, Y); \
+ TEST_EXTRA_CHUNK(int, 8, 16, X, Y); \
+ TEST_EXTRA_CHUNK(int, 16, 8, X, Y); \
+ TEST_EXTRA_CHUNK(int, 32, 4, X, Y); \
+ TEST_EXTRA_CHUNK(uint, 8, 16, X, Y); \
+ TEST_EXTRA_CHUNK(uint, 16, 8, X, Y); \
+ TEST_EXTRA_CHUNK(uint, 32, 4, X, Y); \
+ TEST_EXTRA_CHUNK(poly, 8, 16, X, Y); \
+ TEST_EXTRA_CHUNK(poly, 16, 8, X, Y); \
+ TEST_EXTRA_CHUNK(float, 32, 4, X, Y)
+
+ DECL_ALL_VLDX(2);
+ DECL_ALL_VLDX(3);
+ DECL_ALL_VLDX(4);
+
+ /* Special input buffers of suitable size are needed for vld2/vld3/vld4. */
+ /* Input buffers for vld2, 1 of each size */
+ VECT_ARRAY_INIT2(buffer_vld2, int, 8, 8);
+ PAD(buffer_vld2_pad, int, 8, 8);
+ VECT_ARRAY_INIT2(buffer_vld2, int, 16, 4);
+ PAD(buffer_vld2_pad, int, 16, 4);
+ VECT_ARRAY_INIT2(buffer_vld2, int, 32, 2);
+ PAD(buffer_vld2_pad, int, 32, 2);
+ VECT_ARRAY_INIT2(buffer_vld2, int, 64, 1);
+ PAD(buffer_vld2_pad, int, 64, 1);
+ VECT_ARRAY_INIT2(buffer_vld2, uint, 8, 8);
+ PAD(buffer_vld2_pad, uint, 8, 8);
+ VECT_ARRAY_INIT2(buffer_vld2, uint, 16, 4);
+ PAD(buffer_vld2_pad, uint, 16, 4);
+ VECT_ARRAY_INIT2(buffer_vld2, uint, 32, 2);
+ PAD(buffer_vld2_pad, uint, 32, 2);
+ VECT_ARRAY_INIT2(buffer_vld2, uint, 64, 1);
+ PAD(buffer_vld2_pad, uint, 64, 1);
+ VECT_ARRAY_INIT2(buffer_vld2, poly, 8, 8);
+ PAD(buffer_vld2_pad, poly, 8, 8);
+ VECT_ARRAY_INIT2(buffer_vld2, poly, 16, 4);
+ PAD(buffer_vld2_pad, poly, 16, 4);
+ VECT_ARRAY_INIT2(buffer_vld2, float, 32, 2);
+ PAD(buffer_vld2_pad, float, 32, 2);
+
+ VECT_ARRAY_INIT2(buffer_vld2, int, 8, 16);
+ PAD(buffer_vld2_pad, int, 8, 16);
+ VECT_ARRAY_INIT2(buffer_vld2, int, 16, 8);
+ PAD(buffer_vld2_pad, int, 16, 8);
+ VECT_ARRAY_INIT2(buffer_vld2, int, 32, 4);
+ PAD(buffer_vld2_pad, int, 32, 4);
+ VECT_ARRAY_INIT2(buffer_vld2, int, 64, 2);
+ PAD(buffer_vld2_pad, int, 64, 2);
+ VECT_ARRAY_INIT2(buffer_vld2, uint, 8, 16);
+ PAD(buffer_vld2_pad, uint, 8, 16);
+ VECT_ARRAY_INIT2(buffer_vld2, uint, 16, 8);
+ PAD(buffer_vld2_pad, uint, 16, 8);
+ VECT_ARRAY_INIT2(buffer_vld2, uint, 32, 4);
+ PAD(buffer_vld2_pad, uint, 32, 4);
+ VECT_ARRAY_INIT2(buffer_vld2, uint, 64, 2);
+ PAD(buffer_vld2_pad, uint, 64, 2);
+ VECT_ARRAY_INIT2(buffer_vld2, poly, 8, 16);
+ PAD(buffer_vld2_pad, poly, 8, 16);
+ VECT_ARRAY_INIT2(buffer_vld2, poly, 16, 8);
+ PAD(buffer_vld2_pad, poly, 16, 8);
+ VECT_ARRAY_INIT2(buffer_vld2, float, 32, 4);
+ PAD(buffer_vld2_pad, float, 32, 4);
+
+ /* Input buffers for vld3, 1 of each size */
+ VECT_ARRAY_INIT3(buffer_vld3, int, 8, 8);
+ PAD(buffer_vld3_pad, int, 8, 8);
+ VECT_ARRAY_INIT3(buffer_vld3, int, 16, 4);
+ PAD(buffer_vld3_pad, int, 16, 4);
+ VECT_ARRAY_INIT3(buffer_vld3, int, 32, 2);
+ PAD(buffer_vld3_pad, int, 32, 2);
+ VECT_ARRAY_INIT3(buffer_vld3, int, 64, 1);
+ PAD(buffer_vld3_pad, int, 64, 1);
+ VECT_ARRAY_INIT3(buffer_vld3, uint, 8, 8);
+ PAD(buffer_vld3_pad, uint, 8, 8);
+ VECT_ARRAY_INIT3(buffer_vld3, uint, 16, 4);
+ PAD(buffer_vld3_pad, uint, 16, 4);
+ VECT_ARRAY_INIT3(buffer_vld3, uint, 32, 2);
+ PAD(buffer_vld3_pad, uint, 32, 2);
+ VECT_ARRAY_INIT3(buffer_vld3, uint, 64, 1);
+ PAD(buffer_vld3_pad, uint, 64, 1);
+ VECT_ARRAY_INIT3(buffer_vld3, poly, 8, 8);
+ PAD(buffer_vld3_pad, poly, 8, 8);
+ VECT_ARRAY_INIT3(buffer_vld3, poly, 16, 4);
+ PAD(buffer_vld3_pad, poly, 16, 4);
+ VECT_ARRAY_INIT3(buffer_vld3, float, 32, 2);
+ PAD(buffer_vld3_pad, float, 32, 2);
+
+ VECT_ARRAY_INIT3(buffer_vld3, int, 8, 16);
+ PAD(buffer_vld3_pad, int, 8, 16);
+ VECT_ARRAY_INIT3(buffer_vld3, int, 16, 8);
+ PAD(buffer_vld3_pad, int, 16, 8);
+ VECT_ARRAY_INIT3(buffer_vld3, int, 32, 4);
+ PAD(buffer_vld3_pad, int, 32, 4);
+ VECT_ARRAY_INIT3(buffer_vld3, int, 64, 2);
+ PAD(buffer_vld3_pad, int, 64, 2);
+ VECT_ARRAY_INIT3(buffer_vld3, uint, 8, 16);
+ PAD(buffer_vld3_pad, uint, 8, 16);
+ VECT_ARRAY_INIT3(buffer_vld3, uint, 16, 8);
+ PAD(buffer_vld3_pad, uint, 16, 8);
+ VECT_ARRAY_INIT3(buffer_vld3, uint, 32, 4);
+ PAD(buffer_vld3_pad, uint, 32, 4);
+ VECT_ARRAY_INIT3(buffer_vld3, uint, 64, 2);
+ PAD(buffer_vld3_pad, uint, 64, 2);
+ VECT_ARRAY_INIT3(buffer_vld3, poly, 8, 16);
+ PAD(buffer_vld3_pad, poly, 8, 16);
+ VECT_ARRAY_INIT3(buffer_vld3, poly, 16, 8);
+ PAD(buffer_vld3_pad, poly, 16, 8);
+ VECT_ARRAY_INIT3(buffer_vld3, float, 32, 4);
+ PAD(buffer_vld3_pad, float, 32, 4);
+
+ /* Input buffers for vld4, 1 of each size */
+ VECT_ARRAY_INIT4(buffer_vld4, int, 8, 8);
+ PAD(buffer_vld4_pad, int, 8, 8);
+ VECT_ARRAY_INIT4(buffer_vld4, int, 16, 4);
+ PAD(buffer_vld4_pad, int, 16, 4);
+ VECT_ARRAY_INIT4(buffer_vld4, int, 32, 2);
+ PAD(buffer_vld4_pad, int, 32, 2);
+ VECT_ARRAY_INIT4(buffer_vld4, int, 64, 1);
+ PAD(buffer_vld4_pad, int, 64, 1);
+ VECT_ARRAY_INIT4(buffer_vld4, uint, 8, 8);
+ PAD(buffer_vld4_pad, uint, 8, 8);
+ VECT_ARRAY_INIT4(buffer_vld4, uint, 16, 4);
+ PAD(buffer_vld4_pad, uint, 16, 4);
+ VECT_ARRAY_INIT4(buffer_vld4, uint, 32, 2);
+ PAD(buffer_vld4_pad, uint, 32, 2);
+ VECT_ARRAY_INIT4(buffer_vld4, uint, 64, 1);
+ PAD(buffer_vld4_pad, uint, 64, 1);
+ VECT_ARRAY_INIT4(buffer_vld4, poly, 8, 8);
+ PAD(buffer_vld4_pad, poly, 8, 8);
+ VECT_ARRAY_INIT4(buffer_vld4, poly, 16, 4);
+ PAD(buffer_vld4_pad, poly, 16, 4);
+ VECT_ARRAY_INIT4(buffer_vld4, float, 32, 2);
+ PAD(buffer_vld4_pad, float, 32, 2);
+
+ VECT_ARRAY_INIT4(buffer_vld4, int, 8, 16);
+ PAD(buffer_vld4_pad, int, 8, 16);
+ VECT_ARRAY_INIT4(buffer_vld4, int, 16, 8);
+ PAD(buffer_vld4_pad, int, 16, 8);
+ VECT_ARRAY_INIT4(buffer_vld4, int, 32, 4);
+ PAD(buffer_vld4_pad, int, 32, 4);
+ VECT_ARRAY_INIT4(buffer_vld4, int, 64, 2);
+ PAD(buffer_vld4_pad, int, 64, 2);
+ VECT_ARRAY_INIT4(buffer_vld4, uint, 8, 16);
+ PAD(buffer_vld4_pad, uint, 8, 16);
+ VECT_ARRAY_INIT4(buffer_vld4, uint, 16, 8);
+ PAD(buffer_vld4_pad, uint, 16, 8);
+ VECT_ARRAY_INIT4(buffer_vld4, uint, 32, 4);
+ PAD(buffer_vld4_pad, uint, 32, 4);
+ VECT_ARRAY_INIT4(buffer_vld4, uint, 64, 2);
+ PAD(buffer_vld4_pad, uint, 64, 2);
+ VECT_ARRAY_INIT4(buffer_vld4, poly, 8, 16);
+ PAD(buffer_vld4_pad, poly, 8, 16);
+ VECT_ARRAY_INIT4(buffer_vld4, poly, 16, 8);
+ PAD(buffer_vld4_pad, poly, 16, 8);
+ VECT_ARRAY_INIT4(buffer_vld4, float, 32, 4);
+ PAD(buffer_vld4_pad, float, 32, 4);
+
+ /* Check vld2/vld2q. */
+ clean_results ();
+#define TEST_MSG "VLD2/VLD2Q"
+ TEST_ALL_VLDX(2);
+ CHECK_RESULTS_NAMED (TEST_MSG, expected_vld2_0, "chunk 0");
+
+ TEST_ALL_EXTRA_CHUNKS(2, 1);
+ CHECK_RESULTS_NAMED (TEST_MSG, expected_vld2_1, "chunk 1");
+
+ /* Check vld3/vld3q. */
+ clean_results ();
+#undef TEST_MSG
+#define TEST_MSG "VLD3/VLD3Q"
+ TEST_ALL_VLDX(3);
+ CHECK_RESULTS_NAMED (TEST_MSG, expected_vld3_0, "chunk 0");
+
+ TEST_ALL_EXTRA_CHUNKS(3, 1);
+ CHECK_RESULTS_NAMED (TEST_MSG, expected_vld3_1, "chunk 1");
+
+ TEST_ALL_EXTRA_CHUNKS(3, 2);
+ CHECK_RESULTS_NAMED (TEST_MSG, expected_vld3_2, "chunk 2");
+
+ /* Check vld4/vld4q. */
+ clean_results ();
+#undef TEST_MSG
+#define TEST_MSG "VLD4/VLD4Q"
+ TEST_ALL_VLDX(4);
+ CHECK_RESULTS_NAMED (TEST_MSG, expected_vld4_0, "chunk 0");
+
+ TEST_ALL_EXTRA_CHUNKS(4, 1);
+ CHECK_RESULTS_NAMED (TEST_MSG, expected_vld4_1, "chunk 1");
+
+ TEST_ALL_EXTRA_CHUNKS(4, 2);
+ CHECK_RESULTS_NAMED (TEST_MSG, expected_vld4_2, "chunk 2");
+
+ TEST_ALL_EXTRA_CHUNKS(4, 3);
+ CHECK_RESULTS_NAMED (TEST_MSG, expected_vld4_3, "chunk 3");
+}
+
+int main (void)
+{
+ exec_vldX ();
+ return 0;
+}
--- /dev/null
+#include <arm_neon.h>
+#include "arm-neon-ref.h"
+#include "compute-ref-data.h"
+
+/* Expected results. */
+
+/* vld2/chunk 0. */
+VECT_VAR_DECL(expected_vld2_0,int,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa,
+ 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected_vld2_0,int,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected_vld2_0,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected_vld2_0,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected_vld2_0,uint,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa,
+ 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected_vld2_0,uint,16,4) [] = { 0xaaaa, 0xaaaa,
+ 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected_vld2_0,uint,32,2) [] = { 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected_vld2_0,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected_vld2_0,poly,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa,
+ 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected_vld2_0,poly,16,4) [] = { 0xaaaa, 0xaaaa,
+ 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected_vld2_0,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected_vld2_0,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected_vld2_0,int,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa,
+ 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected_vld2_0,int,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa,
+ 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected_vld2_0,int,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected_vld2_0,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected_vld2_0,uint,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa,
+ 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected_vld2_0,uint,32,4) [] = { 0xfffffff0, 0xfffffff1,
+ 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected_vld2_0,uint,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected_vld2_0,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected_vld2_0,poly,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa,
+ 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected_vld2_0,hfloat,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa,
+ 0xaaaaaaaa, 0xaaaaaaaa };
+
+/* vld2/chunk 1. */
+VECT_VAR_DECL(expected_vld2_1,int,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa,
+ 0xaa, 0xaa, 0xf0, 0xf1 };
+VECT_VAR_DECL(expected_vld2_1,int,16,4) [] = { 0xfff0, 0xfff1, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected_vld2_1,int,32,2) [] = { 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected_vld2_1,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected_vld2_1,uint,8,8) [] = { 0xf0, 0xf1, 0xaa, 0xaa,
+ 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected_vld2_1,uint,16,4) [] = { 0xaaaa, 0xaaaa, 0xfff0, 0xfff1 };
+VECT_VAR_DECL(expected_vld2_1,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected_vld2_1,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected_vld2_1,poly,8,8) [] = { 0xf0, 0xf1, 0xaa, 0xaa,
+ 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected_vld2_1,poly,16,4) [] = { 0xaaaa, 0xaaaa, 0xfff0, 0xfff1 };
+VECT_VAR_DECL(expected_vld2_1,hfloat,32,2) [] = { 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected_vld2_1,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected_vld2_1,int,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa,
+ 0xfff0, 0xfff1, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected_vld2_1,int,32,4) [] = { 0xfffffff0, 0xfffffff1,
+ 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected_vld2_1,int,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected_vld2_1,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected_vld2_1,uint,16,8) [] = { 0xaaaa, 0xaaaa, 0xfff0, 0xfff1,
+ 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected_vld2_1,uint,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa,
+ 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected_vld2_1,uint,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected_vld2_1,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected_vld2_1,poly,16,8) [] = { 0xaaaa, 0xaaaa, 0xfff0, 0xfff1,
+ 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected_vld2_1,hfloat,32,4) [] = { 0xc1800000, 0xc1700000,
+ 0xaaaaaaaa, 0xaaaaaaaa };
+
+/* vld3/chunk 0. */
+VECT_VAR_DECL(expected_vld3_0,int,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa,
+ 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected_vld3_0,int,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected_vld3_0,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected_vld3_0,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected_vld3_0,uint,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa,
+ 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected_vld3_0,uint,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected_vld3_0,uint,32,2) [] = { 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected_vld3_0,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected_vld3_0,poly,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa,
+ 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected_vld3_0,poly,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected_vld3_0,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected_vld3_0,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected_vld3_0,int,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa,
+ 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected_vld3_0,int,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa,
+ 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected_vld3_0,int,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected_vld3_0,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected_vld3_0,uint,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa,
+ 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected_vld3_0,uint,32,4) [] = { 0xfffffff0, 0xfffffff1,
+ 0xfffffff2, 0xaaaaaaaa };
+VECT_VAR_DECL(expected_vld3_0,uint,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected_vld3_0,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected_vld3_0,poly,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa,
+ 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected_vld3_0,hfloat,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa,
+ 0xaaaaaaaa, 0xaaaaaaaa };
+
+/* vld3/chunk 1. */
+VECT_VAR_DECL(expected_vld3_1,int,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa,
+ 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected_vld3_1,int,16,4) [] = { 0xaaaa, 0xaaaa, 0xfff0, 0xfff1 };
+VECT_VAR_DECL(expected_vld3_1,int,32,2) [] = { 0xfffffff2, 0xaaaaaaaa };
+VECT_VAR_DECL(expected_vld3_1,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected_vld3_1,uint,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa,
+ 0xf0, 0xf1, 0xf2, 0xaa };
+VECT_VAR_DECL(expected_vld3_1,uint,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected_vld3_1,uint,32,2) [] = { 0xaaaaaaaa, 0xfffffff0 };
+VECT_VAR_DECL(expected_vld3_1,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected_vld3_1,poly,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa,
+ 0xf0, 0xf1, 0xf2, 0xaa };
+VECT_VAR_DECL(expected_vld3_1,poly,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected_vld3_1,hfloat,32,2) [] = { 0xc1600000, 0xaaaaaaaa };
+VECT_VAR_DECL(expected_vld3_1,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected_vld3_1,int,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa,
+ 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected_vld3_1,int,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa,
+ 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected_vld3_1,int,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected_vld3_1,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected_vld3_1,uint,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa,
+ 0xaaaa, 0xaaaa, 0xaaaa, 0xfff0 };
+VECT_VAR_DECL(expected_vld3_1,uint,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa,
+ 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected_vld3_1,uint,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected_vld3_1,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected_vld3_1,poly,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa,
+ 0xaaaa, 0xaaaa, 0xaaaa, 0xfff0 };
+VECT_VAR_DECL(expected_vld3_1,hfloat,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa,
+ 0xc1800000, 0xc1700000 };
+
+/* vld3/chunk 2. */
+VECT_VAR_DECL(expected_vld3_2,int,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa,
+ 0xaa, 0xf0, 0xf1, 0xf2 };
+VECT_VAR_DECL(expected_vld3_2,int,16,4) [] = { 0xfff2, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected_vld3_2,int,32,2) [] = { 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected_vld3_2,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected_vld3_2,uint,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa,
+ 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected_vld3_2,uint,16,4) [] = { 0xaaaa, 0xfff0, 0xfff1, 0xfff2 };
+VECT_VAR_DECL(expected_vld3_2,uint,32,2) [] = { 0xfffffff1, 0xfffffff2 };
+VECT_VAR_DECL(expected_vld3_2,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected_vld3_2,poly,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa,
+ 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected_vld3_2,poly,16,4) [] = { 0xaaaa, 0xfff0, 0xfff1, 0xfff2 };
+VECT_VAR_DECL(expected_vld3_2,hfloat,32,2) [] = { 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected_vld3_2,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected_vld3_2,int,16,8) [] = { 0xaaaa, 0xaaaa, 0xfff0, 0xfff1,
+ 0xfff2, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected_vld3_2,int,32,4) [] = { 0xfffffff2, 0xaaaaaaaa,
+ 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected_vld3_2,int,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected_vld3_2,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected_vld3_2,uint,16,8) [] = { 0xfff1, 0xfff2, 0xaaaa, 0xaaaa,
+ 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected_vld3_2,uint,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa,
+ 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected_vld3_2,uint,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected_vld3_2,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected_vld3_2,poly,16,8) [] = { 0xfff1, 0xfff2, 0xaaaa, 0xaaaa,
+ 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected_vld3_2,hfloat,32,4) [] = { 0xc1600000, 0xaaaaaaaa,
+ 0xaaaaaaaa, 0xaaaaaaaa };
+
+/* vld4/chunk 0. */
+VECT_VAR_DECL(expected_vld4_0,int,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa,
+ 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected_vld4_0,int,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected_vld4_0,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected_vld4_0,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected_vld4_0,uint,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa,
+ 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected_vld4_0,uint,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected_vld4_0,uint,32,2) [] = { 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected_vld4_0,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected_vld4_0,poly,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa,
+ 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected_vld4_0,poly,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected_vld4_0,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected_vld4_0,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected_vld4_0,int,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa,
+ 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected_vld4_0,int,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa,
+ 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected_vld4_0,int,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected_vld4_0,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected_vld4_0,uint,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa,
+ 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected_vld4_0,uint,32,4) [] = { 0xfffffff0, 0xfffffff1,
+ 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected_vld4_0,uint,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected_vld4_0,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected_vld4_0,poly,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa,
+ 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected_vld4_0,hfloat,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa,
+ 0xaaaaaaaa, 0xaaaaaaaa };
+
+/* vld4/chunk 1. */
+VECT_VAR_DECL(expected_vld4_1,int,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa,
+ 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected_vld4_1,int,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected_vld4_1,int,32,2) [] = { 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected_vld4_1,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected_vld4_1,uint,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa,
+ 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected_vld4_1,uint,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected_vld4_1,uint,32,2) [] = { 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected_vld4_1,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected_vld4_1,poly,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa,
+ 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected_vld4_1,poly,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected_vld4_1,hfloat,32,2) [] = { 0xc1600000, 0xc1500000 };
+VECT_VAR_DECL(expected_vld4_1,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected_vld4_1,int,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa,
+ 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected_vld4_1,int,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa,
+ 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected_vld4_1,int,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected_vld4_1,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected_vld4_1,uint,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa,
+ 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected_vld4_1,uint,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa,
+ 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected_vld4_1,uint,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected_vld4_1,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected_vld4_1,poly,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa,
+ 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected_vld4_1,hfloat,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa,
+ 0xaaaaaaaa, 0xaaaaaaaa };
+
+/* vld4/chunk 2. */
+VECT_VAR_DECL(expected_vld4_2,int,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa,
+ 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected_vld4_2,int,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected_vld4_2,int,32,2) [] = { 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected_vld4_2,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected_vld4_2,uint,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3,
+ 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected_vld4_2,uint,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected_vld4_2,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected_vld4_2,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected_vld4_2,poly,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3,
+ 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected_vld4_2,poly,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected_vld4_2,hfloat,32,2) [] = { 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected_vld4_2,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected_vld4_2,int,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa,
+ 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected_vld4_2,int,32,4) [] = { 0xfffffff0, 0xfffffff1,
+ 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected_vld4_2,int,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected_vld4_2,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected_vld4_2,uint,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa,
+ 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected_vld4_2,uint,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa,
+ 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected_vld4_2,uint,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected_vld4_2,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected_vld4_2,poly,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa,
+ 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected_vld4_2,hfloat,32,4) [] = { 0xc1800000, 0xc1700000,
+ 0xc1600000, 0xc1500000 };
+
+/* vld4/chunk 3. */
+VECT_VAR_DECL(expected_vld4_3,int,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa,
+ 0xf0, 0xf1, 0xf2, 0xf3 };
+VECT_VAR_DECL(expected_vld4_3,int,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected_vld4_3,int,32,2) [] = { 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected_vld4_3,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected_vld4_3,uint,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa,
+ 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected_vld4_3,uint,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected_vld4_3,uint,32,2) [] = { 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected_vld4_3,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected_vld4_3,poly,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa,
+ 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected_vld4_3,poly,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected_vld4_3,hfloat,32,2) [] = { 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected_vld4_3,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected_vld4_3,int,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3,
+ 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected_vld4_3,int,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa,
+ 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected_vld4_3,int,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected_vld4_3,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected_vld4_3,uint,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa,
+ 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected_vld4_3,uint,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa,
+ 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected_vld4_3,uint,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected_vld4_3,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected_vld4_3,poly,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa,
+ 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected_vld4_3,hfloat,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa,
+ 0xaaaaaaaa, 0xaaaaaaaa };
+
+/* Declare additional input buffers as needed. */
+/* Input buffers for vld2_lane */
+VECT_VAR_DECL_INIT(buffer_vld2_lane, int, 8, 2);
+VECT_VAR_DECL_INIT(buffer_vld2_lane, int, 16, 2);
+VECT_VAR_DECL_INIT(buffer_vld2_lane, int, 32, 2);
+VECT_VAR_DECL_INIT(buffer_vld2_lane, int, 64, 2);
+VECT_VAR_DECL_INIT(buffer_vld2_lane, uint, 8, 2);
+VECT_VAR_DECL_INIT(buffer_vld2_lane, uint, 16, 2);
+VECT_VAR_DECL_INIT(buffer_vld2_lane, uint, 32, 2);
+VECT_VAR_DECL_INIT(buffer_vld2_lane, uint, 64, 2);
+VECT_VAR_DECL_INIT(buffer_vld2_lane, poly, 8, 2);
+VECT_VAR_DECL_INIT(buffer_vld2_lane, poly, 16, 2);
+VECT_VAR_DECL_INIT(buffer_vld2_lane, float, 32, 2);
+
+/* Input buffers for vld3_lane */
+VECT_VAR_DECL_INIT(buffer_vld3_lane, int, 8, 3);
+VECT_VAR_DECL_INIT(buffer_vld3_lane, int, 16, 3);
+VECT_VAR_DECL_INIT(buffer_vld3_lane, int, 32, 3);
+VECT_VAR_DECL_INIT(buffer_vld3_lane, int, 64, 3);
+VECT_VAR_DECL_INIT(buffer_vld3_lane, uint, 8, 3);
+VECT_VAR_DECL_INIT(buffer_vld3_lane, uint, 16, 3);
+VECT_VAR_DECL_INIT(buffer_vld3_lane, uint, 32, 3);
+VECT_VAR_DECL_INIT(buffer_vld3_lane, uint, 64, 3);
+VECT_VAR_DECL_INIT(buffer_vld3_lane, poly, 8, 3);
+VECT_VAR_DECL_INIT(buffer_vld3_lane, poly, 16, 3);
+VECT_VAR_DECL_INIT(buffer_vld3_lane, float, 32, 3);
+
+/* Input buffers for vld4_lane */
+VECT_VAR_DECL_INIT(buffer_vld4_lane, int, 8, 4);
+VECT_VAR_DECL_INIT(buffer_vld4_lane, int, 16, 4);
+VECT_VAR_DECL_INIT(buffer_vld4_lane, int, 32, 4);
+VECT_VAR_DECL_INIT(buffer_vld4_lane, int, 64, 4);
+VECT_VAR_DECL_INIT(buffer_vld4_lane, uint, 8, 4);
+VECT_VAR_DECL_INIT(buffer_vld4_lane, uint, 16, 4);
+VECT_VAR_DECL_INIT(buffer_vld4_lane, uint, 32, 4);
+VECT_VAR_DECL_INIT(buffer_vld4_lane, uint, 64, 4);
+VECT_VAR_DECL_INIT(buffer_vld4_lane, poly, 8, 4);
+VECT_VAR_DECL_INIT(buffer_vld4_lane, poly, 16, 4);
+VECT_VAR_DECL_INIT(buffer_vld4_lane, float, 32, 4);
+
+void exec_vldX_lane (void)
+{
+ /* In this case, input variables are arrays of vectors. */
+#define DECL_VLDX_LANE(T1, W, N, X) \
+ VECT_ARRAY_TYPE(T1, W, N, X) VECT_ARRAY_VAR(vector, T1, W, N, X); \
+ VECT_ARRAY_TYPE(T1, W, N, X) VECT_ARRAY_VAR(vector_src, T1, W, N, X); \
+ VECT_VAR_DECL(result_bis_##X, T1, W, N)[X * N]
+
+ /* We need to use a temporary result buffer (result_bis), because
+ the one used for other tests is not large enough. A subset of the
+ result data is moved from result_bis to result, and it is this
+ subset which is used to check the actual behaviour. The next
+ macro enables to move another chunk of data from result_bis to
+ result. */
+ /* We also use another extra input buffer (buffer_src), which we
+ fill with 0xAA, and which it used to load a vector from which we
+ read a given lane. */
+#define TEST_VLDX_LANE(Q, T1, T2, W, N, X, L) \
+ memset (VECT_VAR(buffer_src, T1, W, N), 0xAA, \
+ sizeof(VECT_VAR(buffer_src, T1, W, N))); \
+ \
+ VECT_ARRAY_VAR(vector_src, T1, W, N, X) = \
+ vld##X##Q##_##T2##W(VECT_VAR(buffer_src, T1, W, N)); \
+ \
+ VECT_ARRAY_VAR(vector, T1, W, N, X) = \
+ /* Use dedicated init buffer, of size. X */ \
+ vld##X##Q##_lane_##T2##W(VECT_VAR(buffer_vld##X##_lane, T1, W, X), \
+ VECT_ARRAY_VAR(vector_src, T1, W, N, X), \
+ L); \
+ vst##X##Q##_##T2##W(VECT_VAR(result_bis_##X, T1, W, N), \
+ VECT_ARRAY_VAR(vector, T1, W, N, X)); \
+ memcpy(VECT_VAR(result, T1, W, N), VECT_VAR(result_bis_##X, T1, W, N), \
+ sizeof(VECT_VAR(result, T1, W, N)))
+
+ /* Overwrite "result" with the contents of "result_bis"[Y]. */
+#define TEST_EXTRA_CHUNK(T1, W, N, X, Y) \
+ memcpy(VECT_VAR(result, T1, W, N), \
+ &(VECT_VAR(result_bis_##X, T1, W, N)[Y*N]), \
+ sizeof(VECT_VAR(result, T1, W, N)));
+
+ /* We need all variants in 64 bits, but there is no 64x2 variant. */
+#define DECL_ALL_VLDX_LANE(X) \
+ DECL_VLDX_LANE(int, 8, 8, X); \
+ DECL_VLDX_LANE(int, 16, 4, X); \
+ DECL_VLDX_LANE(int, 32, 2, X); \
+ DECL_VLDX_LANE(uint, 8, 8, X); \
+ DECL_VLDX_LANE(uint, 16, 4, X); \
+ DECL_VLDX_LANE(uint, 32, 2, X); \
+ DECL_VLDX_LANE(poly, 8, 8, X); \
+ DECL_VLDX_LANE(poly, 16, 4, X); \
+ DECL_VLDX_LANE(int, 16, 8, X); \
+ DECL_VLDX_LANE(int, 32, 4, X); \
+ DECL_VLDX_LANE(uint, 16, 8, X); \
+ DECL_VLDX_LANE(uint, 32, 4, X); \
+ DECL_VLDX_LANE(poly, 16, 8, X); \
+ DECL_VLDX_LANE(float, 32, 2, X); \
+ DECL_VLDX_LANE(float, 32, 4, X)
+
+ /* Add some padding to try to catch out of bound accesses. */
+#define ARRAY1(V, T, W, N) VECT_VAR_DECL(V,T,W,N)[1]={42}
+#define DUMMY_ARRAY(V, T, W, N, L) \
+ VECT_VAR_DECL(V,T,W,N)[N*L]={0}; \
+ ARRAY1(V##_pad,T,W,N)
+
+ /* Use the same lanes regardless of the size of the array (X), for
+ simplicity. */
+#define TEST_ALL_VLDX_LANE(X) \
+ TEST_VLDX_LANE(, int, s, 8, 8, X, 7); \
+ TEST_VLDX_LANE(, int, s, 16, 4, X, 2); \
+ TEST_VLDX_LANE(, int, s, 32, 2, X, 0); \
+ TEST_VLDX_LANE(, uint, u, 8, 8, X, 4); \
+ TEST_VLDX_LANE(, uint, u, 16, 4, X, 3); \
+ TEST_VLDX_LANE(, uint, u, 32, 2, X, 1); \
+ TEST_VLDX_LANE(, poly, p, 8, 8, X, 4); \
+ TEST_VLDX_LANE(, poly, p, 16, 4, X, 3); \
+ TEST_VLDX_LANE(q, int, s, 16, 8, X, 6); \
+ TEST_VLDX_LANE(q, int, s, 32, 4, X, 2); \
+ TEST_VLDX_LANE(q, uint, u, 16, 8, X, 5); \
+ TEST_VLDX_LANE(q, uint, u, 32, 4, X, 0); \
+ TEST_VLDX_LANE(q, poly, p, 16, 8, X, 5); \
+ TEST_VLDX_LANE(, float, f, 32, 2, X, 0); \
+ TEST_VLDX_LANE(q, float, f, 32, 4, X, 2)
+
+#define TEST_ALL_EXTRA_CHUNKS(X, Y) \
+ TEST_EXTRA_CHUNK(int, 8, 8, X, Y); \
+ TEST_EXTRA_CHUNK(int, 16, 4, X, Y); \
+ TEST_EXTRA_CHUNK(int, 32, 2, X, Y); \
+ TEST_EXTRA_CHUNK(uint, 8, 8, X, Y); \
+ TEST_EXTRA_CHUNK(uint, 16, 4, X, Y); \
+ TEST_EXTRA_CHUNK(uint, 32, 2, X, Y); \
+ TEST_EXTRA_CHUNK(poly, 8, 8, X, Y); \
+ TEST_EXTRA_CHUNK(poly, 16, 4, X, Y); \
+ TEST_EXTRA_CHUNK(int, 16, 8, X, Y); \
+ TEST_EXTRA_CHUNK(int, 32, 4, X, Y); \
+ TEST_EXTRA_CHUNK(uint, 16, 8, X, Y); \
+ TEST_EXTRA_CHUNK(uint, 32, 4, X, Y); \
+ TEST_EXTRA_CHUNK(poly, 16, 8, X, Y); \
+ TEST_EXTRA_CHUNK(float, 32, 2, X, Y); \
+ TEST_EXTRA_CHUNK(float, 32, 4, X, Y)
+
+ /* Declare the temporary buffers / variables. */
+ DECL_ALL_VLDX_LANE(2);
+ DECL_ALL_VLDX_LANE(3);
+ DECL_ALL_VLDX_LANE(4);
+
+ /* Define dummy input arrays, large enough for x4 vectors. */
+ DUMMY_ARRAY(buffer_src, int, 8, 8, 4);
+ DUMMY_ARRAY(buffer_src, int, 16, 4, 4);
+ DUMMY_ARRAY(buffer_src, int, 32, 2, 4);
+ DUMMY_ARRAY(buffer_src, uint, 8, 8, 4);
+ DUMMY_ARRAY(buffer_src, uint, 16, 4, 4);
+ DUMMY_ARRAY(buffer_src, uint, 32, 2, 4);
+ DUMMY_ARRAY(buffer_src, poly, 8, 8, 4);
+ DUMMY_ARRAY(buffer_src, poly, 16, 4, 4);
+ DUMMY_ARRAY(buffer_src, int, 16, 8, 4);
+ DUMMY_ARRAY(buffer_src, int, 32, 4, 4);
+ DUMMY_ARRAY(buffer_src, uint, 16, 8, 4);
+ DUMMY_ARRAY(buffer_src, uint, 32, 4, 4);
+ DUMMY_ARRAY(buffer_src, poly, 16, 8, 4);
+ DUMMY_ARRAY(buffer_src, float, 32, 2, 4);
+ DUMMY_ARRAY(buffer_src, float, 32, 4, 4);
+
+ /* Check vld2_lane/vld2q_lane. */
+ clean_results ();
+#define TEST_MSG "VLD2_LANE/VLD2Q_LANE"
+ TEST_ALL_VLDX_LANE(2);
+ CHECK_RESULTS_NAMED (TEST_MSG, expected_vld2_0, " chunk 0");
+
+ TEST_ALL_EXTRA_CHUNKS(2, 1);
+ CHECK_RESULTS_NAMED (TEST_MSG, expected_vld2_1, " chunk 1");
+
+ /* Check vld3_lane/vld3q_lane. */
+ clean_results ();
+#undef TEST_MSG
+#define TEST_MSG "VLD3_LANE/VLD3Q_LANE"
+ TEST_ALL_VLDX_LANE(3);
+ CHECK_RESULTS_NAMED (TEST_MSG, expected_vld3_0, " chunk 0");
+
+ TEST_ALL_EXTRA_CHUNKS(3, 1);
+ CHECK_RESULTS_NAMED (TEST_MSG, expected_vld3_1, " chunk 1");
+
+ TEST_ALL_EXTRA_CHUNKS(3, 2);
+ CHECK_RESULTS_NAMED (TEST_MSG, expected_vld3_2, " chunk 2");
+
+ /* Check vld4_lane/vld4q_lane. */
+ clean_results ();
+#undef TEST_MSG
+#define TEST_MSG "VLD4_LANE/VLD4Q_LANE"
+ TEST_ALL_VLDX_LANE(4);
+ CHECK_RESULTS_NAMED (TEST_MSG, expected_vld4_0, " chunk 0");
+
+ TEST_ALL_EXTRA_CHUNKS(4, 1);
+ CHECK_RESULTS_NAMED (TEST_MSG, expected_vld4_1, " chunk 1");
+ TEST_ALL_EXTRA_CHUNKS(4, 2);
+
+ CHECK_RESULTS_NAMED (TEST_MSG, expected_vld4_2, " chunk 2");
+
+ TEST_ALL_EXTRA_CHUNKS(4, 3);
+ CHECK_RESULTS_NAMED (TEST_MSG, expected_vld4_3, " chunk 3");
+}
+
+int main (void)
+{
+ exec_vldX_lane ();
+ return 0;
+}
--- /dev/null
+#include <arm_neon.h>
+#include "arm-neon-ref.h"
+#include "compute-ref-data.h"
+
+/* Expected results. */
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0x1, 0x12, 0x23,
+ 0x34, 0x45, 0x56, 0x67 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfde0, 0xfe02, 0xfe24, 0xfe46 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffcd0, 0xfffffd03 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xc0, 0x4, 0x48, 0x8c,
+ 0xd0, 0x14, 0x58, 0x9c };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfab0, 0xfb05, 0xfb5a, 0xfbaf };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffff9a0, 0xfffffa06 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xc0, 0x84, 0x48, 0xc,
+ 0xd0, 0x94, 0x58, 0x1c };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc4053333, 0xc3f9c000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x90, 0x7, 0x7e, 0xf5,
+ 0x6c, 0xe3, 0x5a, 0xd1,
+ 0x48, 0xbf, 0x36, 0xad,
+ 0x24, 0x9b, 0x12, 0x89 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xf780, 0xf808, 0xf890, 0xf918,
+ 0xf9a0, 0xfa28, 0xfab0, 0xfb38 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffff670, 0xfffff709,
+ 0xfffff7a2, 0xfffff83b };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x60, 0xa, 0xb4, 0x5e,
+ 0x8, 0xb2, 0x5c, 0x6,
+ 0xb0, 0x5a, 0x4, 0xae,
+ 0x58, 0x2, 0xac, 0x56 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xf450, 0xf50b, 0xf5c6, 0xf681,
+ 0xf73c, 0xf7f7, 0xf8b2, 0xf96d };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffff340, 0xfffff40c,
+ 0xfffff4d8, 0xfffff5a4 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x60, 0xca, 0x34, 0x9e,
+ 0xc8, 0x62, 0x9c, 0x36,
+ 0x30, 0x9a, 0x64, 0xce,
+ 0x98, 0x32, 0xcc, 0x66 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333,
+ 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc4c73333, 0xc4bac000,
+ 0xc4ae4ccd, 0xc4a1d999 };
+
+#ifndef INSN_NAME
+#define INSN_NAME vmul
+#define TEST_MSG "VMUL"
+#endif
+
+#define FNNAME1(NAME) exec_ ## NAME
+#define FNNAME(NAME) FNNAME1(NAME)
+
+void FNNAME (INSN_NAME) (void)
+{
+#define DECL_VMUL(T, W, N) \
+ DECL_VARIABLE(vector1, T, W, N); \
+ DECL_VARIABLE(vector2, T, W, N); \
+ DECL_VARIABLE(vector_res, T, W, N)
+
+ /* vector_res = OP(vector1, vector2), then store the result. */
+#define TEST_VMUL1(INSN, Q, T1, T2, W, N) \
+ VECT_VAR(vector_res, T1, W, N) = \
+ INSN##Q##_##T2##W(VECT_VAR(vector1, T1, W, N), \
+ VECT_VAR(vector2, T1, W, N)); \
+ vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N), \
+ VECT_VAR(vector_res, T1, W, N))
+
+#define TEST_VMUL(INSN, Q, T1, T2, W, N) \
+ TEST_VMUL1(INSN, Q, T1, T2, W, N)
+
+ DECL_VMUL(int, 8, 8);
+ DECL_VMUL(int, 16, 4);
+ DECL_VMUL(int, 32, 2);
+ DECL_VMUL(uint, 8, 8);
+ DECL_VMUL(uint, 16, 4);
+ DECL_VMUL(uint, 32, 2);
+ DECL_VMUL(poly, 8, 8);
+ DECL_VMUL(float, 32, 2);
+ DECL_VMUL(int, 8, 16);
+ DECL_VMUL(int, 16, 8);
+ DECL_VMUL(int, 32, 4);
+ DECL_VMUL(uint, 8, 16);
+ DECL_VMUL(uint, 16, 8);
+ DECL_VMUL(uint, 32, 4);
+ DECL_VMUL(poly, 8, 16);
+ DECL_VMUL(float, 32, 4);
+
+ clean_results ();
+
+ /* Initialize input "vector1" from "buffer". */
+ VLOAD(vector1, buffer, , int, s, 8, 8);
+ VLOAD(vector1, buffer, , int, s, 16, 4);
+ VLOAD(vector1, buffer, , int, s, 32, 2);
+ VLOAD(vector1, buffer, , uint, u, 8, 8);
+ VLOAD(vector1, buffer, , uint, u, 16, 4);
+ VLOAD(vector1, buffer, , uint, u, 32, 2);
+ VLOAD(vector1, buffer, , poly, p, 8, 8);
+ VLOAD(vector1, buffer, , float, f, 32, 2);
+ VLOAD(vector1, buffer, q, int, s, 8, 16);
+ VLOAD(vector1, buffer, q, int, s, 16, 8);
+ VLOAD(vector1, buffer, q, int, s, 32, 4);
+ VLOAD(vector1, buffer, q, uint, u, 8, 16);
+ VLOAD(vector1, buffer, q, uint, u, 16, 8);
+ VLOAD(vector1, buffer, q, uint, u, 32, 4);
+ VLOAD(vector1, buffer, q, poly, p, 8, 16);
+ VLOAD(vector1, buffer, q, float, f, 32, 4);
+
+ /* Choose init value arbitrarily. */
+ VDUP(vector2, , int, s, 8, 8, 0x11);
+ VDUP(vector2, , int, s, 16, 4, 0x22);
+ VDUP(vector2, , int, s, 32, 2, 0x33);
+ VDUP(vector2, , uint, u, 8, 8, 0x44);
+ VDUP(vector2, , uint, u, 16, 4, 0x55);
+ VDUP(vector2, , uint, u, 32, 2, 0x66);
+ VDUP(vector2, , poly, p, 8, 8, 0x44);
+ VDUP(vector2, , float, f, 32, 2, 33.3f);
+ VDUP(vector2, q, int, s, 8, 16, 0x77);
+ VDUP(vector2, q, int, s, 16, 8, 0x88);
+ VDUP(vector2, q, int, s, 32, 4, 0x99);
+ VDUP(vector2, q, uint, u, 8, 16, 0xAA);
+ VDUP(vector2, q, uint, u, 16, 8, 0xBB);
+ VDUP(vector2, q, uint, u, 32, 4, 0xCC);
+ VDUP(vector2, q, poly, p, 8, 16, 0xAA);
+ VDUP(vector2, q, float, f, 32, 4, 99.6f);
+
+ /* Execute the tests. */
+ TEST_VMUL(INSN_NAME, , int, s, 8, 8);
+ TEST_VMUL(INSN_NAME, , int, s, 16, 4);
+ TEST_VMUL(INSN_NAME, , int, s, 32, 2);
+ TEST_VMUL(INSN_NAME, , uint, u, 8, 8);
+ TEST_VMUL(INSN_NAME, , uint, u, 16, 4);
+ TEST_VMUL(INSN_NAME, , uint, u, 32, 2);
+ TEST_VMUL(INSN_NAME, , poly, p, 8, 8);
+ TEST_VMUL(INSN_NAME, , float, f, 32, 2);
+ TEST_VMUL(INSN_NAME, q, int, s, 8, 16);
+ TEST_VMUL(INSN_NAME, q, int, s, 16, 8);
+ TEST_VMUL(INSN_NAME, q, int, s, 32, 4);
+ TEST_VMUL(INSN_NAME, q, uint, u, 8, 16);
+ TEST_VMUL(INSN_NAME, q, uint, u, 16, 8);
+ TEST_VMUL(INSN_NAME, q, uint, u, 32, 4);
+ TEST_VMUL(INSN_NAME, q, poly, p, 8, 16);
+ TEST_VMUL(INSN_NAME, q, float, f, 32, 4);
+
+ CHECK_RESULTS (TEST_MSG, "");
+}
+
+int main (void)
+{
+ FNNAME (INSN_NAME) ();
+
+ return 0;
+}
--- /dev/null
+#define INSN_NAME vneg
+#define TEST_MSG "VNEG/VNEGQ"
+
+/* Extra tests for functions requiring floating-point types. */
+void exec_vneg_f32(void);
+#define EXTRA_TESTS exec_vneg_f32
+
+#include "unary_op.inc"
+
+/* Expected results. */
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x10, 0xf, 0xe, 0xd,
+ 0xc, 0xb, 0xa, 0x9 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x10, 0xf, 0xe, 0xd };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x10, 0xf };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x10, 0xf, 0xe, 0xd, 0xc, 0xb, 0xa, 0x9,
+ 0x8, 0x7, 0x6, 0x5, 0x4, 0x3, 0x2, 0x1 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x10, 0xf, 0xe, 0xd,
+ 0xc, 0xb, 0xa, 0x9 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x10, 0xf, 0xe, 0xd };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333,
+ 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333,
+ 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333,
+ 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333,
+ 0x33333333, 0x33333333 };
+
+/* Expected results for float32 variants. Needs to be separated since
+ the generic test function does not test floating-point
+ versions. */
+VECT_VAR_DECL(expected_float32,hfloat,32,2) [] = { 0xc0133333, 0xc0133333 };
+VECT_VAR_DECL(expected_float32,hfloat,32,4) [] = { 0xc059999a, 0xc059999a,
+ 0xc059999a, 0xc059999a };
+
+void exec_vneg_f32(void)
+{
+ DECL_VARIABLE(vector, float, 32, 2);
+ DECL_VARIABLE(vector, float, 32, 4);
+
+ DECL_VARIABLE(vector_res, float, 32, 2);
+ DECL_VARIABLE(vector_res, float, 32, 4);
+
+ VDUP(vector, , float, f, 32, 2, 2.3f);
+ VDUP(vector, q, float, f, 32, 4, 3.4f);
+
+ TEST_UNARY_OP(INSN_NAME, , float, f, 32, 2);
+ TEST_UNARY_OP(INSN_NAME, q, float, f, 32, 4);
+
+ CHECK_FP(TEST_MSG, float, 32, 2, PRIx32, expected_float32, "");
+ CHECK_FP(TEST_MSG, float, 32, 4, PRIx32, expected_float32, "");
+}
--- /dev/null
+#define INSN_NAME vorn
+#define TEST_MSG "VORN/VORNQ"
+
+#include "binary_op.inc"
+
+/* Expected results. */
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xfd, 0xfd, 0xff, 0xff,
+ 0xfd, 0xfd, 0xff, 0xff };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff3, 0xfff3, 0xfff3, 0xfff3 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffffc, 0xfffffffd };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffffb };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xfb, 0xfb, 0xfb, 0xfb,
+ 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff1, 0xfff1, 0xfff3, 0xfff3 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff7, 0xfffffff7 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffffd };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf9, 0xf9, 0xfb, 0xfb,
+ 0xfd, 0xfd, 0xff, 0xff,
+ 0xf9, 0xf9, 0xfb, 0xfb,
+ 0xfd, 0xfd, 0xff, 0xff };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff3, 0xfff3, 0xfff3, 0xfff3,
+ 0xfff7, 0xfff7, 0xfff7, 0xfff7 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffffd, 0xfffffffd,
+ 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff7,
+ 0xfffffffffffffff7 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf3, 0xf3, 0xf3, 0xf3,
+ 0xf7, 0xf7, 0xf7, 0xf7,
+ 0xfb, 0xfb, 0xfb, 0xfb,
+ 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfffc, 0xfffd, 0xfffe, 0xffff,
+ 0xfffc, 0xfffd, 0xfffe, 0xffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff8, 0xfffffff9,
+ 0xfffffffa, 0xfffffffb };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffffc,
+ 0xfffffffffffffffd };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333,
+ 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333,
+ 0x33333333, 0x33333333 };
--- /dev/null
+#define INSN_NAME vorr
+#define TEST_MSG "VORR/VORRQ"
+
+#include "binary_op.inc"
+
+/* Expected results. */
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf2, 0xf3, 0xf2, 0xf3,
+ 0xf6, 0xf7, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfffc, 0xfffd, 0xfffe, 0xffff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff3, 0xfffffff3 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff4 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf4, 0xf5, 0xf6, 0xf7,
+ 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfffe, 0xffff, 0xfffe, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff8, 0xfffffff9 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf6, 0xf7, 0xf6, 0xf7,
+ 0xf6, 0xf7, 0xf6, 0xf7,
+ 0xfe, 0xff, 0xfe, 0xff,
+ 0xfe, 0xff, 0xfe, 0xff };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfffc, 0xfffd, 0xfffe, 0xffff,
+ 0xfffc, 0xfffd, 0xfffe, 0xffff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff2, 0xfffffff3,
+ 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff8,
+ 0xfffffffffffffff9 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xfc, 0xfd, 0xfe, 0xff,
+ 0xfc, 0xfd, 0xfe, 0xff,
+ 0xfc, 0xfd, 0xfe, 0xff,
+ 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff3, 0xfff3, 0xfff3, 0xfff3,
+ 0xfff7, 0xfff7, 0xfff7, 0xfff7 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff7, 0xfffffff7,
+ 0xfffffff7, 0xfffffff7 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff3,
+ 0xfffffffffffffff3 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333,
+ 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333,
+ 0x33333333, 0x33333333 };
--- /dev/null
+#define INSN_NAME vqabs
+#define TEST_MSG "VQABS/VQABSQ"
+
+/* Extra tests for functions requiring corner cases tests. */
+void vqabs_extra(void);
+#define EXTRA_TESTS vqabs_extra
+
+#include "unary_sat_op.inc"
+
+/* Expected results. */
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x10, 0xf, 0xe, 0xd, 0xc, 0xb, 0xa, 0x9 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x10, 0xf, 0xe, 0xd };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x10, 0xf };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x10, 0xf, 0xe, 0xd,
+ 0xc, 0xb, 0xa, 0x9,
+ 0x8, 0x7, 0x6, 0x5,
+ 0x4, 0x3, 0x2, 0x1 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x10, 0xf, 0xe, 0xd,
+ 0xc, 0xb, 0xa, 0x9 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x10, 0xf, 0xe, 0xd };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333,
+ 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333,
+ 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333,
+ 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333,
+ 0x33333333, 0x33333333 };
+
+/* Expected values of cumulative_saturation flag. */
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+
+/* Expected results when input is the min negative value of the type. */
+VECT_VAR_DECL(expected_min_neg,int,8,8) [] = { 0x7f, 0x7f, 0x7f, 0x7f,
+ 0x7f, 0x7f, 0x7f, 0x7f };
+VECT_VAR_DECL(expected_min_neg,int,16,4) [] = { 0x7fff, 0x7fff,
+ 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected_min_neg,int,32,2) [] = { 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected_min_neg,int,8,16) [] = { 0x7f, 0x7f, 0x7f, 0x7f,
+ 0x7f, 0x7f, 0x7f, 0x7f,
+ 0x7f, 0x7f, 0x7f, 0x7f,
+ 0x7f, 0x7f, 0x7f, 0x7f };
+VECT_VAR_DECL(expected_min_neg,int,16,8) [] = { 0x7fff, 0x7fff,
+ 0x7fff, 0x7fff,
+ 0x7fff, 0x7fff,
+ 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected_min_neg,int,32,4) [] = { 0x7fffffff, 0x7fffffff,
+ 0x7fffffff, 0x7fffffff };
+
+/* Expected values of cumulative_saturation flag when input is the min
+ negative value of the type. */
+int VECT_VAR(expected_cumulative_sat_min_neg,int,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat_min_neg,int,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat_min_neg,int,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat_min_neg,int,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat_min_neg,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat_min_neg,int,32,4) = 1;
+
+void vqabs_extra()
+{
+ /* No need for 64 bits variants. */
+ DECL_VARIABLE(vector, int, 8, 8);
+ DECL_VARIABLE(vector, int, 16, 4);
+ DECL_VARIABLE(vector, int, 32, 2);
+ DECL_VARIABLE(vector, int, 8, 16);
+ DECL_VARIABLE(vector, int, 16, 8);
+ DECL_VARIABLE(vector, int, 32, 4);
+
+ DECL_VARIABLE(vector_res, int, 8, 8);
+ DECL_VARIABLE(vector_res, int, 16, 4);
+ DECL_VARIABLE(vector_res, int, 32, 2);
+ DECL_VARIABLE(vector_res, int, 8, 16);
+ DECL_VARIABLE(vector_res, int, 16, 8);
+ DECL_VARIABLE(vector_res, int, 32, 4);
+
+ clean_results ();
+
+ /* Initialize input "vector" with min negative values to check
+ saturation. */
+ VDUP(vector, , int, s, 8, 8, 0x80);
+ VDUP(vector, , int, s, 16, 4, 0x8000);
+ VDUP(vector, , int, s, 32, 2, 0x80000000);
+ VDUP(vector, q, int, s, 8, 16, 0x80);
+ VDUP(vector, q, int, s, 16, 8, 0x8000);
+ VDUP(vector, q, int, s, 32, 4, 0x80000000);
+
+#define MSG "min negative input"
+ TEST_UNARY_SAT_OP(INSN_NAME, , int, s, 8, 8, expected_cumulative_sat_min_neg, MSG);
+ TEST_UNARY_SAT_OP(INSN_NAME, , int, s, 16, 4, expected_cumulative_sat_min_neg, MSG);
+ TEST_UNARY_SAT_OP(INSN_NAME, , int, s, 32, 2, expected_cumulative_sat_min_neg, MSG);
+ TEST_UNARY_SAT_OP(INSN_NAME, q, int, s, 8, 16, expected_cumulative_sat_min_neg, MSG);
+ TEST_UNARY_SAT_OP(INSN_NAME, q, int, s, 16, 8, expected_cumulative_sat_min_neg, MSG);
+ TEST_UNARY_SAT_OP(INSN_NAME, q, int, s, 32, 4, expected_cumulative_sat_min_neg, MSG);
+
+ CHECK(TEST_MSG, int, 8, 8, PRIx8, expected_min_neg, MSG);
+ CHECK(TEST_MSG, int, 16, 4, PRIx8, expected_min_neg, MSG);
+ CHECK(TEST_MSG, int, 32, 2, PRIx8, expected_min_neg, MSG);
+ CHECK(TEST_MSG, int, 8, 16, PRIx8, expected_min_neg, MSG);
+ CHECK(TEST_MSG, int, 16, 8, PRIx8, expected_min_neg, MSG);
+ CHECK(TEST_MSG, int, 32, 4, PRIx8, expected_min_neg, MSG);
+}
--- /dev/null
+#define INSN_NAME vqadd
+#define TEST_MSG "VQADD/VQADDQ"
+
+/* Extra tests for special cases:
+ - some requiring intermediate types larger than 64 bits to
+ compute saturation flag.
+ - corner case saturations with types smaller than 64 bits.
+*/
+void vqadd_extras(void);
+#define EXTRA_TESTS vqadd_extras
+
+#include "binary_sat_op.inc"
+
+/* Expected values of cumulative_saturation flag. */
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 1;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 1;
+/* Expected results. */
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x1, 0x2, 0x3, 0x4,
+ 0x5, 0x6, 0x7, 0x8 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x12, 0x13, 0x14, 0x15 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x23, 0x24 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x34 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xffffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x1, 0x2, 0x3, 0x4,
+ 0x5, 0x6, 0x7, 0x8,
+ 0x9, 0xa, 0xb, 0xc,
+ 0xd, 0xe, 0xf, 0x10 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x12, 0x13, 0x14, 0x15,
+ 0x16, 0x17, 0x18, 0x19 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x23, 0x24, 0x25, 0x26 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x34, 0x35 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xffff, 0xffff, 0xffff, 0xffff,
+ 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffff, 0xffffffff,
+ 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffffffffffff,
+ 0xffffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333,
+ 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333,
+ 0x33333333, 0x33333333 };
+
+
+/* 64-bits types, with 0 as second input. */
+int VECT_VAR(expected_cumulative_sat_64,int,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat_64,uint,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat_64,int,64,2) = 0;
+int VECT_VAR(expected_cumulative_sat_64,uint,64,2) = 0;
+VECT_VAR_DECL(expected_64,int,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected_64,uint,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected_64,int,64,2) [] = { 0xfffffffffffffff0,
+ 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected_64,uint,64,2) [] = { 0xfffffffffffffff0,
+ 0xfffffffffffffff1 };
+
+/* 64-bits types, some cases causing cumulative saturation. */
+int VECT_VAR(expected_cumulative_sat_64_2,int,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat_64_2,uint,64,1) = 1;
+int VECT_VAR(expected_cumulative_sat_64_2,int,64,2) = 0;
+int VECT_VAR(expected_cumulative_sat_64_2,uint,64,2) = 1;
+VECT_VAR_DECL(expected_64_2,int,64,1) [] = { 0x34 };
+VECT_VAR_DECL(expected_64_2,uint,64,1) [] = { 0xffffffffffffffff };
+VECT_VAR_DECL(expected_64_2,int,64,2) [] = { 0x34, 0x35 };
+VECT_VAR_DECL(expected_64_2,uint,64,2) [] = { 0xffffffffffffffff,
+ 0xffffffffffffffff };
+
+/* 64-bits types, all causing cumulative saturation. */
+int VECT_VAR(expected_cumulative_sat_64_3,int,64,1) = 1;
+int VECT_VAR(expected_cumulative_sat_64_3,uint,64,1) = 1;
+int VECT_VAR(expected_cumulative_sat_64_3,int,64,2) = 1;
+int VECT_VAR(expected_cumulative_sat_64_3,uint,64,2) = 1;
+VECT_VAR_DECL(expected_64_3,int,64,1) [] = { 0x8000000000000000 };
+VECT_VAR_DECL(expected_64_3,uint,64,1) [] = { 0xffffffffffffffff };
+VECT_VAR_DECL(expected_64_3,int,64,2) [] = { 0x7fffffffffffffff,
+ 0x7fffffffffffffff };
+VECT_VAR_DECL(expected_64_3,uint,64,2) [] = { 0xffffffffffffffff,
+ 0xffffffffffffffff };
+
+/* smaller types, corner cases causing cumulative saturation. (1) */
+int VECT_VAR(expected_csat_lt_64_1,int,8,8) = 1;
+int VECT_VAR(expected_csat_lt_64_1,int,16,4) = 1;
+int VECT_VAR(expected_csat_lt_64_1,int,32,2) = 1;
+int VECT_VAR(expected_csat_lt_64_1,int,8,16) = 1;
+int VECT_VAR(expected_csat_lt_64_1,int,16,8) = 1;
+int VECT_VAR(expected_csat_lt_64_1,int,32,4) = 1;
+VECT_VAR_DECL(expected_lt_64_1,int,8,8) [] = { 0x80, 0x80, 0x80, 0x80,
+ 0x80, 0x80, 0x80, 0x80 };
+VECT_VAR_DECL(expected_lt_64_1,int,16,4) [] = { 0x8000, 0x8000,
+ 0x8000, 0x8000 };
+VECT_VAR_DECL(expected_lt_64_1,int,32,2) [] = { 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected_lt_64_1,int,8,16) [] = { 0x80, 0x80, 0x80, 0x80,
+ 0x80, 0x80, 0x80, 0x80,
+ 0x80, 0x80, 0x80, 0x80,
+ 0x80, 0x80, 0x80, 0x80 };
+VECT_VAR_DECL(expected_lt_64_1,int,16,8) [] = { 0x8000, 0x8000,
+ 0x8000, 0x8000,
+ 0x8000, 0x8000,
+ 0x8000, 0x8000 };
+VECT_VAR_DECL(expected_lt_64_1,int,32,4) [] = { 0x80000000, 0x80000000,
+ 0x80000000, 0x80000000 };
+
+/* smaller types, corner cases causing cumulative saturation. (2) */
+int VECT_VAR(expected_csat_lt_64_2,uint,8,8) = 1;
+int VECT_VAR(expected_csat_lt_64_2,uint,16,4) = 1;
+int VECT_VAR(expected_csat_lt_64_2,uint,32,2) = 1;
+int VECT_VAR(expected_csat_lt_64_2,uint,8,16) = 1;
+int VECT_VAR(expected_csat_lt_64_2,uint,16,8) = 1;
+int VECT_VAR(expected_csat_lt_64_2,uint,32,4) = 1;
+VECT_VAR_DECL(expected_lt_64_2,uint,8,8) [] = { 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected_lt_64_2,uint,16,4) [] = { 0xffff, 0xffff,
+ 0xffff, 0xffff };
+VECT_VAR_DECL(expected_lt_64_2,uint,32,2) [] = { 0xffffffff,
+ 0xffffffff };
+VECT_VAR_DECL(expected_lt_64_2,uint,8,16) [] = { 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff,
+ 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected_lt_64_2,uint,16,8) [] = { 0xffff, 0xffff,
+ 0xffff, 0xffff,
+ 0xffff, 0xffff,
+ 0xffff, 0xffff };
+VECT_VAR_DECL(expected_lt_64_2,uint,32,4) [] = { 0xffffffff, 0xffffffff,
+ 0xffffffff, 0xffffffff };
+
+void vqadd_extras(void)
+{
+ DECL_VARIABLE_ALL_VARIANTS(vector1);
+ DECL_VARIABLE_ALL_VARIANTS(vector2);
+ DECL_VARIABLE_ALL_VARIANTS(vector_res);
+
+ /* Initialize input "vector1" from "buffer". */
+ TEST_MACRO_ALL_VARIANTS_2_5(VLOAD, vector1, buffer);
+
+ /* Use a second vector full of 0. */
+ VDUP(vector2, , int, s, 64, 1, 0);
+ VDUP(vector2, , uint, u, 64, 1, 0);
+ VDUP(vector2, q, int, s, 64, 2, 0);
+ VDUP(vector2, q, uint, u, 64, 2, 0);
+
+#define MSG "64 bits saturation adding zero"
+ TEST_BINARY_SAT_OP(INSN_NAME, , int, s, 64, 1, expected_cumulative_sat_64, MSG);
+ TEST_BINARY_SAT_OP(INSN_NAME, , uint, u, 64, 1, expected_cumulative_sat_64, MSG);
+ TEST_BINARY_SAT_OP(INSN_NAME, q, int, s, 64, 2, expected_cumulative_sat_64, MSG);
+ TEST_BINARY_SAT_OP(INSN_NAME, q, uint, u, 64, 2, expected_cumulative_sat_64, MSG);
+
+ CHECK(TEST_MSG, int, 64, 1, PRIx64, expected_64, MSG);
+ CHECK(TEST_MSG, uint, 64, 1, PRIx64, expected_64, MSG);
+ CHECK(TEST_MSG, int, 64, 2, PRIx64, expected_64, MSG);
+ CHECK(TEST_MSG, uint, 64, 2, PRIx64, expected_64, MSG);
+
+ /* Another set of tests with non-zero values, some chosen to create
+ overflow. */
+ VDUP(vector2, , int, s, 64, 1, 0x44);
+ VDUP(vector2, , uint, u, 64, 1, 0x88);
+ VDUP(vector2, q, int, s, 64, 2, 0x44);
+ VDUP(vector2, q, uint, u, 64, 2, 0x88);
+
+#undef MSG
+#define MSG "64 bits saturation cumulative_sat (2)"
+ TEST_BINARY_SAT_OP(INSN_NAME, , int, s, 64, 1, expected_cumulative_sat_64_2, MSG);
+ TEST_BINARY_SAT_OP(INSN_NAME, , uint, u, 64, 1, expected_cumulative_sat_64_2, MSG);
+ TEST_BINARY_SAT_OP(INSN_NAME, q, int, s, 64, 2, expected_cumulative_sat_64_2, MSG);
+ TEST_BINARY_SAT_OP(INSN_NAME, q, uint, u, 64, 2, expected_cumulative_sat_64_2, MSG);
+
+ CHECK(TEST_MSG, int, 64, 1, PRIx64, expected_64_2, MSG);
+ CHECK(TEST_MSG, uint, 64, 1, PRIx64, expected_64_2, MSG);
+ CHECK(TEST_MSG, int, 64, 2, PRIx64, expected_64_2, MSG);
+ CHECK(TEST_MSG, uint, 64, 2, PRIx64, expected_64_2, MSG);
+
+ /* Another set of tests, with input values chosen to set
+ cumulative_sat in all cases. */
+ VDUP(vector2, , int, s, 64, 1, 0x8000000000000003LL);
+ VDUP(vector2, , uint, u, 64, 1, 0x88);
+ /* To check positive saturation, we need to write a positive value
+ in vector1. */
+ VDUP(vector1, q, int, s, 64, 2, 0x4000000000000000LL);
+ VDUP(vector2, q, int, s, 64, 2, 0x4000000000000000LL);
+ VDUP(vector2, q, uint, u, 64, 2, 0x22);
+
+#undef MSG
+#define MSG "64 bits saturation cumulative_sat (3)"
+ TEST_BINARY_SAT_OP(INSN_NAME, , int, s, 64, 1, expected_cumulative_sat_64_3, MSG);
+ TEST_BINARY_SAT_OP(INSN_NAME, , uint, u, 64, 1, expected_cumulative_sat_64_3, MSG);
+ TEST_BINARY_SAT_OP(INSN_NAME, q, int, s, 64, 2, expected_cumulative_sat_64_3, MSG);
+ TEST_BINARY_SAT_OP(INSN_NAME, q, uint, u, 64, 2, expected_cumulative_sat_64_3, MSG);
+
+ CHECK(TEST_MSG, int, 64, 1, PRIx64, expected_64_3, MSG);
+ CHECK(TEST_MSG, uint, 64, 1, PRIx64, expected_64_3, MSG);
+ CHECK(TEST_MSG, int, 64, 2, PRIx64, expected_64_3, MSG);
+ CHECK(TEST_MSG, uint, 64, 2, PRIx64, expected_64_3, MSG);
+
+ /* To improve coverage, check saturation with less than 64 bits
+ too. */
+ VDUP(vector2, , int, s, 8, 8, 0x81);
+ VDUP(vector2, , int, s, 16, 4, 0x8001);
+ VDUP(vector2, , int, s, 32, 2, 0x80000001);
+ VDUP(vector2, q, int, s, 8, 16, 0x81);
+ VDUP(vector2, q, int, s, 16, 8, 0x8001);
+ VDUP(vector2, q, int, s, 32, 4, 0x80000001);
+
+#undef MSG
+#define MSG "less than 64 bits saturation cumulative_sat (1)"
+ TEST_BINARY_SAT_OP(INSN_NAME, , int, s, 8, 8, expected_csat_lt_64_1, MSG);
+ TEST_BINARY_SAT_OP(INSN_NAME, , int, s, 16, 4, expected_csat_lt_64_1, MSG);
+ TEST_BINARY_SAT_OP(INSN_NAME, , int, s, 32, 2, expected_csat_lt_64_1, MSG);
+ TEST_BINARY_SAT_OP(INSN_NAME, q, int, s, 8, 16, expected_csat_lt_64_1, MSG);
+ TEST_BINARY_SAT_OP(INSN_NAME, q, int, s, 16, 8, expected_csat_lt_64_1, MSG);
+ TEST_BINARY_SAT_OP(INSN_NAME, q, int, s, 32, 4, expected_csat_lt_64_1, MSG);
+
+ CHECK(TEST_MSG, int, 8, 8, PRIx8, expected_lt_64_1, MSG);
+ CHECK(TEST_MSG, int, 16, 4, PRIx16, expected_lt_64_1, MSG);
+ CHECK(TEST_MSG, int, 32, 2, PRIx32, expected_lt_64_1, MSG);
+ CHECK(TEST_MSG, int, 8, 16, PRIx8, expected_lt_64_1, MSG);
+ CHECK(TEST_MSG, int, 16, 8, PRIx16, expected_lt_64_1, MSG);
+ CHECK(TEST_MSG, int, 32, 4, PRIx32, expected_lt_64_1, MSG);
+
+ /* Another set of tests with large vector1 values. */
+ VDUP(vector1, , uint, u, 8, 8, 0xF0);
+ VDUP(vector1, , uint, u, 16, 4, 0xFFF0);
+ VDUP(vector1, , uint, u, 32, 2, 0xFFFFFFF0);
+ VDUP(vector1, q, uint, u, 8, 16, 0xF0);
+ VDUP(vector1, q, uint, u, 16, 8, 0xFFF0);
+ VDUP(vector1, q, uint, u, 32, 4, 0xFFFFFFF0);
+
+ VDUP(vector2, , uint, u, 8, 8, 0x20);
+ VDUP(vector2, , uint, u, 16, 4, 0x20);
+ VDUP(vector2, , uint, u, 32, 2, 0x20);
+ VDUP(vector2, q, uint, u, 8, 16, 0x20);
+ VDUP(vector2, q, uint, u, 16, 8, 0x20);
+ VDUP(vector2, q, uint, u, 32, 4, 0x20);
+
+#undef MSG
+#define MSG "less than 64 bits saturation cumulative_sat (2)"
+ TEST_BINARY_SAT_OP(INSN_NAME, , uint, u, 8, 8, expected_csat_lt_64_2, MSG);
+ TEST_BINARY_SAT_OP(INSN_NAME, , uint, u, 16, 4, expected_csat_lt_64_2, MSG);
+ TEST_BINARY_SAT_OP(INSN_NAME, , uint, u, 32, 2, expected_csat_lt_64_2, MSG);
+ TEST_BINARY_SAT_OP(INSN_NAME, q, uint, u, 8, 16, expected_csat_lt_64_2, MSG);
+ TEST_BINARY_SAT_OP(INSN_NAME, q, uint, u, 16, 8, expected_csat_lt_64_2, MSG);
+ TEST_BINARY_SAT_OP(INSN_NAME, q, uint, u, 32, 4, expected_csat_lt_64_2, MSG);
+
+ CHECK(TEST_MSG, uint, 8, 8, PRIx8, expected_lt_64_2, MSG);
+ CHECK(TEST_MSG, uint, 16, 4, PRIx16, expected_lt_64_2, MSG);
+ CHECK(TEST_MSG, uint, 32, 2, PRIx32, expected_lt_64_2, MSG);
+ CHECK(TEST_MSG, uint, 8, 16, PRIx8, expected_lt_64_2, MSG);
+ CHECK(TEST_MSG, uint, 16, 8, PRIx16, expected_lt_64_2, MSG);
+ CHECK(TEST_MSG, uint, 32, 4, PRIx32, expected_lt_64_2, MSG);
+}
--- /dev/null
+#define INSN_NAME vqneg
+#define TEST_MSG "VQNEG/VQNEGQ"
+
+/* Extra tests for functions requiring corner cases tests */
+void vqneg_extra(void);
+#define EXTRA_TESTS vqneg_extra
+
+#include "unary_sat_op.inc"
+
+/* Expected results. */
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x10, 0xf, 0xe, 0xd, 0xc, 0xb, 0xa, 0x9 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x10, 0xf, 0xe, 0xd };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x10, 0xf };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x10, 0xf, 0xe, 0xd,
+ 0xc, 0xb, 0xa, 0x9,
+ 0x8, 0x7, 0x6, 0x5,
+ 0x4, 0x3, 0x2, 0x1 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x10, 0xf, 0xe, 0xd,
+ 0xc, 0xb, 0xa, 0x9 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x10, 0xf, 0xe, 0xd };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333,
+ 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333,
+ 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333,
+ 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333,
+ 0x33333333, 0x33333333 };
+
+/* Expected values of cumulative_saturation flag. */
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+
+/* Expected results when input is the min negative value of the type. */
+VECT_VAR_DECL(expected_min_neg,int,8,8) [] = { 0x7f, 0x7f, 0x7f, 0x7f,
+ 0x7f, 0x7f, 0x7f, 0x7f };
+VECT_VAR_DECL(expected_min_neg,int,16,4) [] = { 0x7fff, 0x7fff,
+ 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected_min_neg,int,32,2) [] = { 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected_min_neg,int,8,16) [] = { 0x7f, 0x7f, 0x7f, 0x7f,
+ 0x7f, 0x7f, 0x7f, 0x7f,
+ 0x7f, 0x7f, 0x7f, 0x7f,
+ 0x7f, 0x7f, 0x7f, 0x7f };
+VECT_VAR_DECL(expected_min_neg,int,16,8) [] = { 0x7fff, 0x7fff,
+ 0x7fff, 0x7fff,
+ 0x7fff, 0x7fff,
+ 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected_min_neg,int,32,4) [] = { 0x7fffffff, 0x7fffffff,
+ 0x7fffffff, 0x7fffffff };
+
+/* Expected values of cumulative_saturation flag when input is the min
+ negative value of the type. */
+int VECT_VAR(expected_cumulative_sat_min_neg,int,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat_min_neg,int,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat_min_neg,int,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat_min_neg,int,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat_min_neg,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat_min_neg,int,32,4) = 1;
+
+void vqneg_extra()
+{
+ /* No need for 64 bits variants. */
+ DECL_VARIABLE(vector, int, 8, 8);
+ DECL_VARIABLE(vector, int, 16, 4);
+ DECL_VARIABLE(vector, int, 32, 2);
+ DECL_VARIABLE(vector, int, 8, 16);
+ DECL_VARIABLE(vector, int, 16, 8);
+ DECL_VARIABLE(vector, int, 32, 4);
+
+ DECL_VARIABLE(vector_res, int, 8, 8);
+ DECL_VARIABLE(vector_res, int, 16, 4);
+ DECL_VARIABLE(vector_res, int, 32, 2);
+ DECL_VARIABLE(vector_res, int, 8, 16);
+ DECL_VARIABLE(vector_res, int, 16, 8);
+ DECL_VARIABLE(vector_res, int, 32, 4);
+
+ clean_results ();
+
+ /* Initialize input "vector" with min negative values to check
+ saturation. */
+ VDUP(vector, , int, s, 8, 8, 0x80);
+ VDUP(vector, , int, s, 16, 4, 0x8000);
+ VDUP(vector, , int, s, 32, 2, 0x80000000);
+ VDUP(vector, q, int, s, 8, 16, 0x80);
+ VDUP(vector, q, int, s, 16, 8, 0x8000);
+ VDUP(vector, q, int, s, 32, 4, 0x80000000);
+
+#define MSG "min negative input"
+ TEST_UNARY_SAT_OP(INSN_NAME, , int, s, 8, 8, expected_cumulative_sat_min_neg, MSG);
+ TEST_UNARY_SAT_OP(INSN_NAME, , int, s, 16, 4, expected_cumulative_sat_min_neg, MSG);
+ TEST_UNARY_SAT_OP(INSN_NAME, , int, s, 32, 2, expected_cumulative_sat_min_neg, MSG);
+ TEST_UNARY_SAT_OP(INSN_NAME, q, int, s, 8, 16, expected_cumulative_sat_min_neg, MSG);
+ TEST_UNARY_SAT_OP(INSN_NAME, q, int, s, 16, 8, expected_cumulative_sat_min_neg, MSG);
+ TEST_UNARY_SAT_OP(INSN_NAME, q, int, s, 32, 4, expected_cumulative_sat_min_neg, MSG);
+
+ CHECK(TEST_MSG, int, 8, 8, PRIx8, expected_min_neg, MSG);
+ CHECK(TEST_MSG, int, 16, 4, PRIx8, expected_min_neg, MSG);
+ CHECK(TEST_MSG, int, 32, 2, PRIx8, expected_min_neg, MSG);
+ CHECK(TEST_MSG, int, 8, 16, PRIx8, expected_min_neg, MSG);
+ CHECK(TEST_MSG, int, 16, 8, PRIx8, expected_min_neg, MSG);
+ CHECK(TEST_MSG, int, 32, 4, PRIx8, expected_min_neg, MSG);
+}
--- /dev/null
+#define INSN_NAME vqsub
+#define TEST_MSG "VQSUB/VQSUBQ"
+
+/* Extra tests for special cases:
+ - some requiring intermediate types larger than 64 bits to
+ compute saturation flag.
+ - corner case saturations with types smaller than 64 bits.
+*/
+void vqsub_extras(void);
+#define EXTRA_TESTS vqsub_extras
+
+#include "binary_sat_op.inc"
+
+
+/* Expected results. */
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xdf, 0xe0, 0xe1, 0xe2,
+ 0xe3, 0xe4, 0xe5, 0xe6 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xffce, 0xffcf,
+ 0xffd0, 0xffd1 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xffffffbd, 0xffffffbe };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xffffffffffffffac };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x9b, 0x9c, 0x9d, 0x9e,
+ 0x9f, 0xa0, 0xa1, 0xa2 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xff8a, 0xff8b,
+ 0xff8c, 0xff8d };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffff79, 0xffffff7a };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xffffffffffffff68 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xdf, 0xe0, 0xe1, 0xe2,
+ 0xe3, 0xe4, 0xe5, 0xe6,
+ 0xe7, 0xe8, 0xe9, 0xea,
+ 0xeb, 0xec, 0xed, 0xee };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xffce, 0xffcf, 0xffd0, 0xffd1,
+ 0xffd2, 0xffd3, 0xffd4, 0xffd5 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffffffbd, 0xffffffbe,
+ 0xffffffbf, 0xffffffc0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xffffffffffffffac,
+ 0xffffffffffffffad };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x9b, 0x9c, 0x9d, 0x9e,
+ 0x9f, 0xa0, 0xa1, 0xa2,
+ 0xa3, 0xa4, 0xa5, 0xa6,
+ 0xa7, 0xa8, 0xa9, 0xaa };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xff8a, 0xff8b, 0xff8c, 0xff8d,
+ 0xff8e, 0xff8f, 0xff90, 0xff91 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffff79, 0xffffff7a,
+ 0xffffff7b, 0xffffff7c };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffffffffff68,
+ 0xffffffffffffff69 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333,
+ 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333,
+ 0x33333333, 0x33333333 };
+
+/* Expected values of cumulative saturation flag. */
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 0;
+
+/* 64-bits types, with 0 as second input. */
+VECT_VAR_DECL(expected_64,int,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected_64,uint,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected_64,int,64,2) [] = { 0xfffffffffffffff0,
+ 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected_64,uint,64,2) [] = { 0xfffffffffffffff0,
+ 0xfffffffffffffff1 };
+int VECT_VAR(expected_cumulative_sat_64,int,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat_64,uint,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat_64,int,64,2) = 0;
+int VECT_VAR(expected_cumulative_sat_64,uint,64,2) = 0;
+
+/* 64-bits types, other cases. */
+VECT_VAR_DECL(expected_64_2,int,64,1) [] = { 0xffffffffffffffac };
+VECT_VAR_DECL(expected_64_2,uint,64,1) [] = { 0xffffffffffffff68 };
+VECT_VAR_DECL(expected_64_2,int,64,2) [] = { 0xffffffffffffffac,
+ 0xffffffffffffffad };
+VECT_VAR_DECL(expected_64_2,uint,64,2) [] = { 0xffffffffffffff68,
+ 0xffffffffffffff69 };
+int VECT_VAR(expected_cumulative_sat_64_2,int,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat_64_2,uint,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat_64_2,int,64,2) = 0;
+int VECT_VAR(expected_cumulative_sat_64_2,uint,64,2) = 0;
+
+/* 64-bits types, all causing cumulative saturation. */
+VECT_VAR_DECL(expected_64_3,int,64,1) [] = { 0x8000000000000000 };
+VECT_VAR_DECL(expected_64_3,uint,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected_64_3,int,64,2) [] = { 0x7fffffffffffffff,
+ 0x7fffffffffffffff };
+VECT_VAR_DECL(expected_64_3,uint,64,2) [] = { 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat_64_3,int,64,1) = 1;
+int VECT_VAR(expected_cumulative_sat_64_3,uint,64,1) = 1;
+int VECT_VAR(expected_cumulative_sat_64_3,int,64,2) = 1;
+int VECT_VAR(expected_cumulative_sat_64_3,uint,64,2) = 1;
+
+/* smaller types, corner cases causing cumulative saturation. (1) */
+VECT_VAR_DECL(expected_lt_64_1,int,8,8) [] = { 0x80, 0x80, 0x80, 0x80,
+ 0x80, 0x80, 0x80, 0x80 };
+VECT_VAR_DECL(expected_lt_64_1,int,16,4) [] = { 0x8000, 0x8000,
+ 0x8000, 0x8000 };
+VECT_VAR_DECL(expected_lt_64_1,int,32,2) [] = { 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected_lt_64_1,int,8,16) [] = { 0x80, 0x80, 0x80, 0x80,
+ 0x80, 0x80, 0x80, 0x80,
+ 0x80, 0x80, 0x80, 0x80,
+ 0x80, 0x80, 0x80, 0x80 };
+VECT_VAR_DECL(expected_lt_64_1,int,16,8) [] = { 0x8000, 0x8000,
+ 0x8000, 0x8000,
+ 0x8000, 0x8000,
+ 0x8000, 0x8000 };
+VECT_VAR_DECL(expected_lt_64_1,int,32,4) [] = { 0x80000000, 0x80000000,
+ 0x80000000, 0x80000000 };
+int VECT_VAR(expected_csat_lt_64_1,int,8,8) = 1;
+int VECT_VAR(expected_csat_lt_64_1,int,16,4) = 1;
+int VECT_VAR(expected_csat_lt_64_1,int,32,2) = 1;
+int VECT_VAR(expected_csat_lt_64_1,int,8,16) = 1;
+int VECT_VAR(expected_csat_lt_64_1,int,16,8) = 1;
+int VECT_VAR(expected_csat_lt_64_1,int,32,4) = 1;
+
+/* smaller types, corner cases causing cumulative saturation. (2) */
+VECT_VAR_DECL(expected_lt_64_2,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected_lt_64_2,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected_lt_64_2,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected_lt_64_2,uint,8,16) [] = { 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected_lt_64_2,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected_lt_64_2,uint,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_csat_lt_64_2,uint,8,8) = 1;
+int VECT_VAR(expected_csat_lt_64_2,uint,16,4) = 1;
+int VECT_VAR(expected_csat_lt_64_2,uint,32,2) = 1;
+int VECT_VAR(expected_csat_lt_64_2,uint,8,16) = 1;
+int VECT_VAR(expected_csat_lt_64_2,uint,16,8) = 1;
+int VECT_VAR(expected_csat_lt_64_2,uint,32,4) = 1;
+
+void vqsub_extras(void)
+{
+ DECL_VARIABLE_ALL_VARIANTS(vector1);
+ DECL_VARIABLE_ALL_VARIANTS(vector2);
+ DECL_VARIABLE_ALL_VARIANTS(vector_res);
+
+ /* Initialize input "vector1" from "buffer". */
+ TEST_MACRO_ALL_VARIANTS_2_5(VLOAD, vector1, buffer);
+
+ /* Use a second vector full of 0. */
+ VDUP(vector2, , int, s, 64, 1, 0x0);
+ VDUP(vector2, , uint, u, 64, 1, 0x0);
+ VDUP(vector2, q, int, s, 64, 2, 0x0);
+ VDUP(vector2, q, uint, u, 64, 2, 0x0);
+
+#define MSG "64 bits saturation when adding zero"
+ TEST_BINARY_SAT_OP(INSN_NAME, , int, s, 64, 1, expected_cumulative_sat_64, MSG);
+ TEST_BINARY_SAT_OP(INSN_NAME, , uint, u, 64, 1, expected_cumulative_sat_64, MSG);
+ TEST_BINARY_SAT_OP(INSN_NAME, q, int, s, 64, 2, expected_cumulative_sat_64, MSG);
+ TEST_BINARY_SAT_OP(INSN_NAME, q, uint, u, 64, 2, expected_cumulative_sat_64, MSG);
+
+ CHECK(TEST_MSG, int, 64, 1, PRIx64, expected_64, MSG);
+ CHECK(TEST_MSG, uint, 64, 1, PRIx64, expected_64, MSG);
+ CHECK(TEST_MSG, int, 64, 2, PRIx64, expected_64, MSG);
+ CHECK(TEST_MSG, uint, 64, 2, PRIx64, expected_64, MSG);
+
+ /* Another set of tests with non-zero values. */
+ VDUP(vector2, , int, s, 64, 1, 0x44);
+ VDUP(vector2, , uint, u, 64, 1, 0x88);
+ VDUP(vector2, q, int, s, 64, 2, 0x44);
+ VDUP(vector2, q, uint, u, 64, 2, 0x88);
+
+#undef MSG
+#define MSG "64 bits saturation cumulative_sat (2)"
+ TEST_BINARY_SAT_OP(INSN_NAME, , int, s, 64, 1, expected_cumulative_sat_64_2, MSG);
+ TEST_BINARY_SAT_OP(INSN_NAME, , uint, u, 64, 1, expected_cumulative_sat_64_2, MSG);
+ TEST_BINARY_SAT_OP(INSN_NAME, q, int, s, 64, 2, expected_cumulative_sat_64_2, MSG);
+ TEST_BINARY_SAT_OP(INSN_NAME, q, uint, u, 64, 2, expected_cumulative_sat_64_2, MSG);
+
+ CHECK(TEST_MSG, int, 64, 1, PRIx64, expected_64_2, MSG);
+ CHECK(TEST_MSG, uint, 64, 1, PRIx64, expected_64_2, MSG);
+ CHECK(TEST_MSG, int, 64, 2, PRIx64, expected_64_2, MSG);
+ CHECK(TEST_MSG, uint, 64, 2, PRIx64, expected_64_2, MSG);
+
+ /* Another set of tests, with input values chosen to set
+ cumulative_sat in all cases. */
+ VDUP(vector2, , int, s, 64, 1, 0x7fffffffffffffffLL);
+ VDUP(vector2, , uint, u, 64, 1, 0xffffffffffffffffULL);
+ /* To check positive saturation, we need to write a positive value
+ in vector1. */
+ VDUP(vector1, q, int, s, 64, 2, 0x3fffffffffffffffLL);
+ VDUP(vector2, q, int, s, 64, 2, 0x8000000000000000LL);
+ VDUP(vector2, q, uint, u, 64, 2, 0xffffffffffffffffULL);
+
+#undef MSG
+#define MSG "64 bits saturation cumulative_sat (3)"
+ TEST_BINARY_SAT_OP(INSN_NAME, , int, s, 64, 1, expected_cumulative_sat_64_3, MSG);
+ TEST_BINARY_SAT_OP(INSN_NAME, , uint, u, 64, 1, expected_cumulative_sat_64_3, MSG);
+ TEST_BINARY_SAT_OP(INSN_NAME, q, int, s, 64, 2, expected_cumulative_sat_64_3, MSG);
+ TEST_BINARY_SAT_OP(INSN_NAME, q, uint, u, 64, 2, expected_cumulative_sat_64_3, MSG);
+
+ CHECK(TEST_MSG, int, 64, 1, PRIx64, expected_64_3, MSG);
+ CHECK(TEST_MSG, uint, 64, 1, PRIx64, expected_64_3, MSG);
+ CHECK(TEST_MSG, int, 64, 2, PRIx64, expected_64_3, MSG);
+ CHECK(TEST_MSG, uint, 64, 2, PRIx64, expected_64_3, MSG);
+
+ /* To improve coverage, check saturation with less than 64 bits
+ too. */
+ VDUP(vector2, , int, s, 8, 8, 0x7F);
+ VDUP(vector2, , int, s, 16, 4, 0x7FFF);
+ VDUP(vector2, , int, s, 32, 2, 0x7FFFFFFF);
+ VDUP(vector2, q, int, s, 8, 16, 0x7F);
+ VDUP(vector2, q, int, s, 16, 8, 0x7FFF);
+ VDUP(vector2, q, int, s, 32, 4, 0x7FFFFFFF);
+
+#undef MSG
+#define MSG "less than 64 bits saturation cumulative_sat (1)"
+ TEST_BINARY_SAT_OP(INSN_NAME, , int, s, 8, 8, expected_csat_lt_64_1, MSG);
+ TEST_BINARY_SAT_OP(INSN_NAME, , int, s, 16, 4, expected_csat_lt_64_1, MSG);
+ TEST_BINARY_SAT_OP(INSN_NAME, , int, s, 32, 2, expected_csat_lt_64_1, MSG);
+ TEST_BINARY_SAT_OP(INSN_NAME, q, int, s, 8, 16, expected_csat_lt_64_1, MSG);
+ TEST_BINARY_SAT_OP(INSN_NAME, q, int, s, 16, 8, expected_csat_lt_64_1, MSG);
+ TEST_BINARY_SAT_OP(INSN_NAME, q, int, s, 32, 4, expected_csat_lt_64_1, MSG);
+
+ CHECK(TEST_MSG, int, 8, 8, PRIx8, expected_lt_64_1, MSG);
+ CHECK(TEST_MSG, int, 16, 4, PRIx16, expected_lt_64_1, MSG);
+ CHECK(TEST_MSG, int, 32, 2, PRIx32, expected_lt_64_1, MSG);
+ CHECK(TEST_MSG, int, 8, 16, PRIx8, expected_lt_64_1, MSG);
+ CHECK(TEST_MSG, int, 16, 8, PRIx16, expected_lt_64_1, MSG);
+ CHECK(TEST_MSG, int, 32, 4, PRIx32, expected_lt_64_1, MSG);
+
+ /* Another set of tests with vector1 values smaller than
+ vector2. */
+ VDUP(vector1, , uint, u, 8, 8, 0x10);
+ VDUP(vector1, , uint, u, 16, 4, 0x10);
+ VDUP(vector1, , uint, u, 32, 2, 0x10);
+ VDUP(vector1, q, uint, u, 8, 16, 0x10);
+ VDUP(vector1, q, uint, u, 16, 8, 0x10);
+ VDUP(vector1, q, uint, u, 32, 4, 0x10);
+
+ VDUP(vector2, , uint, u, 8, 8, 0x20);
+ VDUP(vector2, , uint, u, 16, 4, 0x20);
+ VDUP(vector2, , uint, u, 32, 2, 0x20);
+ VDUP(vector2, q, uint, u, 8, 16, 0x20);
+ VDUP(vector2, q, uint, u, 16, 8, 0x20);
+ VDUP(vector2, q, uint, u, 32, 4, 0x20);
+
+#undef MSG
+#define MSG "less than 64 bits saturation cumulative_sat (2)"
+ TEST_BINARY_SAT_OP(INSN_NAME, , uint, u, 8, 8, expected_csat_lt_64_2, MSG);
+ TEST_BINARY_SAT_OP(INSN_NAME, , uint, u, 16, 4, expected_csat_lt_64_2, MSG);
+ TEST_BINARY_SAT_OP(INSN_NAME, , uint, u, 32, 2, expected_csat_lt_64_2, MSG);
+ TEST_BINARY_SAT_OP(INSN_NAME, q, uint, u, 8, 16, expected_csat_lt_64_2, MSG);
+ TEST_BINARY_SAT_OP(INSN_NAME, q, uint, u, 16, 8, expected_csat_lt_64_2, MSG);
+ TEST_BINARY_SAT_OP(INSN_NAME, q, uint, u, 32, 4, expected_csat_lt_64_2, MSG);
+
+ CHECK(TEST_MSG, uint, 8, 8, PRIx8, expected_lt_64_2, MSG);
+ CHECK(TEST_MSG, uint, 16, 4, PRIx16, expected_lt_64_2, MSG);
+ CHECK(TEST_MSG, uint, 32, 2, PRIx32, expected_lt_64_2, MSG);
+ CHECK(TEST_MSG, uint, 8, 16, PRIx8, expected_lt_64_2, MSG);
+ CHECK(TEST_MSG, uint, 16, 8, PRIx16, expected_lt_64_2, MSG);
+ CHECK(TEST_MSG, uint, 32, 4, PRIx32, expected_lt_64_2, MSG);
+}
--- /dev/null
+#include <arm_neon.h>
+#include "arm-neon-ref.h"
+#include "compute-ref-data.h"
+
+/* Expected results. */
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xe0, 0xe2, 0xe4, 0xe6,
+ 0xe8, 0xea, 0xec, 0xee };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xff80, 0xff88, 0xff90, 0xff98 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffff000, 0xfffff100 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xffffffffffffff80 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xe0, 0xe2, 0xe4, 0xe6,
+ 0xe8, 0xea, 0xec, 0xee };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xff80, 0xff88, 0xff90, 0xff98 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffff000, 0xfffff100 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xffffffffffffff80 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333,
+ 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x20, 0x40, 0x60,
+ 0x80, 0xa0, 0xc0, 0xe0,
+ 0x0, 0x20, 0x40, 0x60,
+ 0x80, 0xa0, 0xc0, 0xe0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x1000, 0x2000, 0x3000,
+ 0x4000, 0x5000, 0x6000, 0x7000 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x40000000,
+ 0x80000000, 0xc0000000 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x0, 0x8000000000000000 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x20, 0x40, 0x60,
+ 0x80, 0xa0, 0xc0, 0xe0,
+ 0x0, 0x20, 0x40, 0x60,
+ 0x80, 0xa0, 0xc0, 0xe0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x1000, 0x2000, 0x3000,
+ 0x4000, 0x5000, 0x6000, 0x7000 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x40000000,
+ 0x80000000, 0xc0000000 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x0, 0x8000000000000000 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333,
+ 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333,
+ 0x33333333, 0x33333333 };
+
+/* Expected results with large shift amount. */
+VECT_VAR_DECL(expected_large_shift,int,8,8) [] = { 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected_large_shift,int,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected_large_shift,int,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected_large_shift,int,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected_large_shift,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected_large_shift,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected_large_shift,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected_large_shift,uint,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected_large_shift,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected_large_shift,poly,16,4) [] = { 0x3333, 0x3333,
+ 0x3333, 0x3333 };
+VECT_VAR_DECL(expected_large_shift,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected_large_shift,int,8,16) [] = { 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected_large_shift,int,16,8) [] = { 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected_large_shift,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected_large_shift,int,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected_large_shift,uint,8,16) [] = { 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected_large_shift,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected_large_shift,uint,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected_large_shift,uint,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected_large_shift,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected_large_shift,poly,16,8) [] = { 0x3333, 0x3333,
+ 0x3333, 0x3333,
+ 0x3333, 0x3333,
+ 0x3333, 0x3333 };
+VECT_VAR_DECL(expected_large_shift,hfloat,32,4) [] = { 0x33333333, 0x33333333,
+ 0x33333333, 0x33333333 };
+
+
+/* Expected results with negative shift amount. */
+VECT_VAR_DECL(expected_negative_shift,int,8,8) [] = { 0xf8, 0xf8, 0xf9, 0xf9,
+ 0xfa, 0xfa, 0xfb, 0xfb };
+VECT_VAR_DECL(expected_negative_shift,int,16,4) [] = { 0xfff8, 0xfff8,
+ 0xfff9, 0xfff9 };
+VECT_VAR_DECL(expected_negative_shift,int,32,2) [] = { 0xfffffffc, 0xfffffffc };
+VECT_VAR_DECL(expected_negative_shift,int,64,1) [] = { 0xffffffffffffffff };
+VECT_VAR_DECL(expected_negative_shift,uint,8,8) [] = { 0x78, 0x78, 0x79, 0x79,
+ 0x7a, 0x7a, 0x7b, 0x7b };
+VECT_VAR_DECL(expected_negative_shift,uint,16,4) [] = { 0x7ff8, 0x7ff8,
+ 0x7ff9, 0x7ff9 };
+VECT_VAR_DECL(expected_negative_shift,uint,32,2) [] = { 0x3ffffffc,
+ 0x3ffffffc };
+VECT_VAR_DECL(expected_negative_shift,uint,64,1) [] = { 0xfffffffffffffff };
+VECT_VAR_DECL(expected_negative_shift,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected_negative_shift,poly,16,4) [] = { 0x3333, 0x3333,
+ 0x3333, 0x3333 };
+VECT_VAR_DECL(expected_negative_shift,hfloat,32,2) [] = { 0x33333333,
+ 0x33333333 };
+VECT_VAR_DECL(expected_negative_shift,int,8,16) [] = { 0xfc, 0xfc, 0xfc, 0xfc,
+ 0xfd, 0xfd, 0xfd, 0xfd,
+ 0xfe, 0xfe, 0xfe, 0xfe,
+ 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected_negative_shift,int,16,8) [] = { 0xffff, 0xffff,
+ 0xffff, 0xffff,
+ 0xffff, 0xffff,
+ 0xffff, 0xffff };
+VECT_VAR_DECL(expected_negative_shift,int,32,4) [] = { 0xfffffffe, 0xfffffffe,
+ 0xfffffffe, 0xfffffffe };
+VECT_VAR_DECL(expected_negative_shift,int,64,2) [] = { 0xffffffffffffffff,
+ 0xffffffffffffffff };
+VECT_VAR_DECL(expected_negative_shift,uint,8,16) [] = { 0x3c, 0x3c, 0x3c, 0x3c,
+ 0x3d, 0x3d, 0x3d, 0x3d,
+ 0x3e, 0x3e, 0x3e, 0x3e,
+ 0x3f, 0x3f, 0x3f, 0x3f };
+VECT_VAR_DECL(expected_negative_shift,uint,16,8) [] = { 0x7ff, 0x7ff,
+ 0x7ff, 0x7ff,
+ 0x7ff, 0x7ff,
+ 0x7ff, 0x7ff };
+VECT_VAR_DECL(expected_negative_shift,uint,32,4) [] = { 0x1ffffffe, 0x1ffffffe,
+ 0x1ffffffe, 0x1ffffffe };
+VECT_VAR_DECL(expected_negative_shift,uint,64,2) [] = { 0x7ffffffffffffff,
+ 0x7ffffffffffffff };
+VECT_VAR_DECL(expected_negative_shift,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected_negative_shift,poly,16,8) [] = { 0x3333, 0x3333,
+ 0x3333, 0x3333,
+ 0x3333, 0x3333,
+ 0x3333, 0x3333 };
+VECT_VAR_DECL(expected_negative_shift,hfloat,32,4) [] = { 0x33333333,
+ 0x33333333,
+ 0x33333333,
+ 0x33333333 };
+
+
+#ifndef INSN_NAME
+#define INSN_NAME vshl
+#define TEST_MSG "VSHL/VSHLQ"
+#endif
+
+#define FNNAME1(NAME) exec_ ## NAME
+#define FNNAME(NAME) FNNAME1(NAME)
+
+void FNNAME (INSN_NAME) (void)
+{
+ /* Basic test: v3=vshl(v1,v2), then store the result. */
+#define TEST_VSHL(T3, Q, T1, T2, W, N) \
+ VECT_VAR(vector_res, T1, W, N) = \
+ vshl##Q##_##T2##W(VECT_VAR(vector, T1, W, N), \
+ VECT_VAR(vector_shift, T3, W, N)); \
+ vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N), VECT_VAR(vector_res, T1, W, N))
+
+ DECL_VARIABLE_ALL_VARIANTS(vector);
+ DECL_VARIABLE_ALL_VARIANTS(vector_res);
+
+ DECL_VARIABLE_SIGNED_VARIANTS(vector_shift);
+
+ clean_results ();
+
+ /* Initialize input "vector" from "buffer". */
+ TEST_MACRO_ALL_VARIANTS_2_5(VLOAD, vector, buffer);
+
+ /* Choose init value arbitrarily, will be used as shift amount. */
+ VDUP(vector_shift, , int, s, 8, 8, 1);
+ VDUP(vector_shift, , int, s, 16, 4, 3);
+ VDUP(vector_shift, , int, s, 32, 2, 8);
+ VDUP(vector_shift, , int, s, 64, 1, 3);
+ VDUP(vector_shift, q, int, s, 8, 16, 5);
+ VDUP(vector_shift, q, int, s, 16, 8, 12);
+ VDUP(vector_shift, q, int, s, 32, 4, 30);
+ VDUP(vector_shift, q, int, s, 64, 2, 63);
+
+ /* Execute the tests. */
+ TEST_MACRO_ALL_VARIANTS_1_5(TEST_VSHL, int);
+
+ CHECK_RESULTS (TEST_MSG, "");
+
+
+ /* Test large shift amount (larger or equal to the type width. */
+ VDUP(vector_shift, , int, s, 8, 8, 8);
+ VDUP(vector_shift, , int, s, 16, 4, 16);
+ VDUP(vector_shift, , int, s, 32, 2, 32);
+ VDUP(vector_shift, , int, s, 64, 1, 64);
+ VDUP(vector_shift, q, int, s, 8, 16, 8);
+ VDUP(vector_shift, q, int, s, 16, 8, 17);
+ VDUP(vector_shift, q, int, s, 32, 4, 33);
+ VDUP(vector_shift, q, int, s, 64, 2, 65);
+
+ /* Execute the tests. */
+ TEST_MACRO_ALL_VARIANTS_1_5(TEST_VSHL, int);
+
+ CHECK_RESULTS_NAMED (TEST_MSG, expected_large_shift, "(large shift amount)");
+
+
+ /* Test negative shift amount. */
+ VDUP(vector_shift, , int, s, 8, 8, -1);
+ VDUP(vector_shift, , int, s, 16, 4, -1);
+ VDUP(vector_shift, , int, s, 32, 2, -2);
+ VDUP(vector_shift, , int, s, 64, 1, -4);
+ VDUP(vector_shift, q, int, s, 8, 16, -2);
+ VDUP(vector_shift, q, int, s, 16, 8, -5);
+ VDUP(vector_shift, q, int, s, 32, 4, -3);
+ VDUP(vector_shift, q, int, s, 64, 2, -5);
+
+ /* Execute the tests. */
+ TEST_MACRO_ALL_VARIANTS_1_5(TEST_VSHL, int);
+
+ CHECK_RESULTS_NAMED (TEST_MSG, expected_negative_shift, "(negative shift amount)");
+}
+
+int main (void)
+{
+ FNNAME (INSN_NAME) ();
+
+ return 0;
+}
--- /dev/null
+#define INSN_NAME vsub
+#define TEST_MSG "VSUB/VSUBQ"
+
+/* Extra tests for functions requiring floating-point types */
+void exec_vsub_f32(void);
+#define EXTRA_TESTS exec_vsub_f32
+
+#include "binary_op.inc"
+
+/* Expected results. */
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xee, 0xef, 0xf0, 0xf1,
+ 0xf2, 0xf3, 0xf4, 0xf5 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xffffffed, 0xffffffee };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xffffffffffffff8c };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xdc, 0xdd, 0xde, 0xdf,
+ 0xe0, 0xe1, 0xe2, 0xe3 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffd2, 0xffd3, 0xffd4, 0xffd5 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffc8, 0xffffffc9 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xffffffffffffffee };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xfa, 0xfb, 0xfc, 0xfd,
+ 0xfe, 0xff, 0x0, 0x1,
+ 0x2, 0x3, 0x4, 0x5,
+ 0x6, 0x7, 0x8, 0x9 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x4, 0x5, 0x6, 0x7,
+ 0x8, 0x9, 0xa, 0xb };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xe, 0xf, 0x10, 0x11 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xffffffffffffffd8,
+ 0xffffffffffffffd9 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xe4, 0xe5, 0xe6, 0xe7,
+ 0xe8, 0xe9, 0xea, 0xeb,
+ 0xec, 0xed, 0xee, 0xef,
+ 0xf0, 0xf1, 0xf2, 0xf3};
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xffed, 0xffee, 0xffef, 0xfff0,
+ 0xfff1, 0xfff2, 0xfff3, 0xfff4 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffb9, 0xffffffba,
+ 0xffffffbb, 0xffffffbc };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffffffffffed,
+ 0xffffffffffffffee };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33,
+ 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333,
+ 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333,
+ 0x33333333, 0x33333333 };
+
+/* Expected results for float32 variants. Needs to be separated since
+ the generic test function does not test floating-point
+ versions. */
+VECT_VAR_DECL(expected_float32,hfloat,32,2) [] = { 0xc00ccccd, 0xc00ccccd };
+VECT_VAR_DECL(expected_float32,hfloat,32,4) [] = { 0xc00ccccc, 0xc00ccccc,
+ 0xc00ccccc, 0xc00ccccc };
+
+void exec_vsub_f32(void)
+{
+ DECL_VARIABLE(vector, float, 32, 2);
+ DECL_VARIABLE(vector, float, 32, 4);
+
+ DECL_VARIABLE(vector2, float, 32, 2);
+ DECL_VARIABLE(vector2, float, 32, 4);
+
+ DECL_VARIABLE(vector_res, float, 32, 2);
+ DECL_VARIABLE(vector_res, float, 32, 4);
+
+ VDUP(vector, , float, f, 32, 2, 2.3f);
+ VDUP(vector, q, float, f, 32, 4, 3.4f);
+
+ VDUP(vector2, , float, f, 32, 2, 4.5f);
+ VDUP(vector2, q, float, f, 32, 4, 5.6f);
+
+ TEST_BINARY_OP(INSN_NAME, , float, f, 32, 2);
+ TEST_BINARY_OP(INSN_NAME, q, float, f, 32, 4);
+
+ CHECK_FP(TEST_MSG, float, 32, 2, PRIx32, expected_float32, "");
+ CHECK_FP(TEST_MSG, float, 32, 4, PRIx32, expected_float32, "");
+}
--- /dev/null
+#include <arm_neon.h>
+#include "arm-neon-ref.h"
+#include "compute-ref-data.h"
+
+/* Expected results splitted in several chunks. */
+/* Chunk 0. */
+VECT_VAR_DECL(expected0,int,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3,
+ 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected0,int,16,4) [] = { 0xfff0, 0xfff1,
+ 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected0,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected0,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected0,uint,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3,
+ 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected0,uint,16,4) [] = { 0xfff0, 0xfff1,
+ 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected0,uint,32,2) [] = { 0xfffffff0,
+ 0xfffffff1 };
+VECT_VAR_DECL(expected0,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected0,poly,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3,
+ 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected0,poly,16,4) [] = { 0xfff0, 0xfff1,
+ 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected0,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected0,int,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3,
+ 0xf4, 0xf5, 0xf6, 0xf7,
+ 0xf8, 0xf9, 0xfa, 0xfb,
+ 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected0,int,16,8) [] = { 0xfff0, 0xfff1,
+ 0xfff2, 0xfff3,
+ 0xfff4, 0xfff5,
+ 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected0,int,32,4) [] = { 0xfffffff0, 0xfffffff1,
+ 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected0,int,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected0,uint,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3,
+ 0xf4, 0xf5, 0xf6, 0xf7,
+ 0xf8, 0xf9, 0xfa, 0xfb,
+ 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected0,uint,16,8) [] = { 0xfff0, 0xfff1,
+ 0xfff2, 0xfff3,
+ 0xfff4, 0xfff5,
+ 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected0,uint,32,4) [] = { 0xfffffff0, 0xfffffff1,
+ 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected0,uint,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected0,poly,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3,
+ 0xf4, 0xf5, 0xf6, 0xf7,
+ 0xf8, 0xf9, 0xfa, 0xfb,
+ 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected0,poly,16,8) [] = { 0xfff0, 0xfff1,
+ 0xfff2, 0xfff3,
+ 0xfff4, 0xfff5,
+ 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected0,hfloat,32,4) [] = { 0xc1800000, 0xc1700000,
+ 0xc1600000, 0xc1500000 };
+
+/* Chunk 1. */
+VECT_VAR_DECL(expected1,int,8,8) [] = { 0x11, 0x11, 0x11, 0x11,
+ 0x11, 0x11, 0x11, 0x11 };
+VECT_VAR_DECL(expected1,int,16,4) [] = { 0x22, 0x22, 0x22, 0x22 };
+VECT_VAR_DECL(expected1,int,32,2) [] = { 0x33, 0x33 };
+VECT_VAR_DECL(expected1,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected1,uint,8,8) [] = { 0x55, 0x55, 0x55, 0x55,
+ 0x55, 0x55, 0x55, 0x55 };
+VECT_VAR_DECL(expected1,uint,16,4) [] = { 0x66, 0x66, 0x66, 0x66 };
+VECT_VAR_DECL(expected1,uint,32,2) [] = { 0x77, 0x77 };
+VECT_VAR_DECL(expected1,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected1,poly,8,8) [] = { 0x55, 0x55, 0x55, 0x55,
+ 0x55, 0x55, 0x55, 0x55 };
+VECT_VAR_DECL(expected1,poly,16,4) [] = { 0x66, 0x66, 0x66, 0x66 };
+VECT_VAR_DECL(expected1,hfloat,32,2) [] = { 0x42066666, 0x42066666 };
+VECT_VAR_DECL(expected1,int,8,16) [] = { 0x11, 0x11, 0x11, 0x11,
+ 0x11, 0x11, 0x11, 0x11,
+ 0x11, 0x11, 0x11, 0x11,
+ 0x11, 0x11, 0x11, 0x11 };
+VECT_VAR_DECL(expected1,int,16,8) [] = { 0x22, 0x22, 0x22, 0x22,
+ 0x22, 0x22, 0x22, 0x22 };
+VECT_VAR_DECL(expected1,int,32,4) [] = { 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected1,int,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected1,uint,8,16) [] = { 0x55, 0x55, 0x55, 0x55,
+ 0x55, 0x55, 0x55, 0x55,
+ 0x55, 0x55, 0x55, 0x55,
+ 0x55, 0x55, 0x55, 0x55 };
+VECT_VAR_DECL(expected1,uint,16,8) [] = { 0x66, 0x66, 0x66, 0x66,
+ 0x66, 0x66, 0x66, 0x66 };
+VECT_VAR_DECL(expected1,uint,32,4) [] = { 0x77, 0x77, 0x77, 0x77 };
+VECT_VAR_DECL(expected1,uint,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected1,poly,8,16) [] = { 0x55, 0x55, 0x55, 0x55,
+ 0x55, 0x55, 0x55, 0x55,
+ 0x55, 0x55, 0x55, 0x55,
+ 0x55, 0x55, 0x55, 0x55 };
+VECT_VAR_DECL(expected1,poly,16,8) [] = { 0x66, 0x66, 0x66, 0x66,
+ 0x66, 0x66, 0x66, 0x66 };
+VECT_VAR_DECL(expected1,hfloat,32,4) [] = { 0x42073333, 0x42073333,
+ 0x42073333, 0x42073333 };
+
+#ifndef INSN_NAME
+#define INSN_NAME vuzp
+#define TEST_MSG "VUZP/VUZPQ"
+#endif
+
+#define FNNAME1(NAME) exec_ ## NAME
+#define FNNAME(NAME) FNNAME1(NAME)
+
+void FNNAME (INSN_NAME) (void)
+{
+ /* In this case, output variables are arrays of vectors. */
+#define DECL_VUZP(T1, W, N) \
+ VECT_ARRAY_TYPE(T1, W, N, 2) VECT_ARRAY_VAR(result_vec, T1, W, N, 2); \
+ VECT_VAR_DECL(result_bis, T1, W, N)[2 * N]
+
+ /* We need to use a temporary result buffer (result_bis), because
+ the one used for other tests is not large enough. A subset of the
+ result data is moved from result_bis to result, and it is this
+ subset which is used to check the actual behaviour. The next
+ macro enables to move another chunk of data from result_bis to
+ result. */
+#define TEST_VUZP(INSN, Q, T1, T2, W, N) \
+ VECT_ARRAY_VAR(result_vec, T1, W, N, 2) = \
+ INSN##Q##_##T2##W(VECT_VAR(vector1, T1, W, N), \
+ VECT_VAR(vector2, T1, W, N)); \
+ vst2##Q##_##T2##W(VECT_VAR(result_bis, T1, W, N), \
+ VECT_ARRAY_VAR(result_vec, T1, W, N, 2)); \
+ memcpy(VECT_VAR(result, T1, W, N), VECT_VAR(result_bis, T1, W, N), \
+ sizeof(VECT_VAR(result, T1, W, N)));
+
+ /* Overwrite "result" with the contents of "result_bis"[X]. */
+#define TEST_EXTRA_CHUNK(T1, W, N, X) \
+ memcpy(VECT_VAR(result, T1, W, N), &(VECT_VAR(result_bis, T1, W, N)[X*N]), \
+ sizeof(VECT_VAR(result, T1, W, N)));
+
+ DECL_VARIABLE_ALL_VARIANTS(vector1);
+ DECL_VARIABLE_ALL_VARIANTS(vector2);
+
+ /* We don't need 64 bits variants. */
+#define DECL_ALL_VUZP() \
+ DECL_VUZP(int, 8, 8); \
+ DECL_VUZP(int, 16, 4); \
+ DECL_VUZP(int, 32, 2); \
+ DECL_VUZP(uint, 8, 8); \
+ DECL_VUZP(uint, 16, 4); \
+ DECL_VUZP(uint, 32, 2); \
+ DECL_VUZP(poly, 8, 8); \
+ DECL_VUZP(poly, 16, 4); \
+ DECL_VUZP(float, 32, 2); \
+ DECL_VUZP(int, 8, 16); \
+ DECL_VUZP(int, 16, 8); \
+ DECL_VUZP(int, 32, 4); \
+ DECL_VUZP(uint, 8, 16); \
+ DECL_VUZP(uint, 16, 8); \
+ DECL_VUZP(uint, 32, 4); \
+ DECL_VUZP(poly, 8, 16); \
+ DECL_VUZP(poly, 16, 8); \
+ DECL_VUZP(float, 32, 4)
+
+ DECL_ALL_VUZP();
+
+ /* Initialize input "vector" from "buffer". */
+ TEST_MACRO_ALL_VARIANTS_2_5(VLOAD, vector1, buffer);
+ VLOAD(vector1, buffer, , float, f, 32, 2);
+ VLOAD(vector1, buffer, q, float, f, 32, 4);
+
+ /* Choose arbitrary initialization values. */
+ VDUP(vector2, , int, s, 8, 8, 0x11);
+ VDUP(vector2, , int, s, 16, 4, 0x22);
+ VDUP(vector2, , int, s, 32, 2, 0x33);
+ VDUP(vector2, , uint, u, 8, 8, 0x55);
+ VDUP(vector2, , uint, u, 16, 4, 0x66);
+ VDUP(vector2, , uint, u, 32, 2, 0x77);
+ VDUP(vector2, , poly, p, 8, 8, 0x55);
+ VDUP(vector2, , poly, p, 16, 4, 0x66);
+ VDUP(vector2, , float, f, 32, 2, 33.6f);
+
+ VDUP(vector2, q, int, s, 8, 16, 0x11);
+ VDUP(vector2, q, int, s, 16, 8, 0x22);
+ VDUP(vector2, q, int, s, 32, 4, 0x33);
+ VDUP(vector2, q, uint, u, 8, 16, 0x55);
+ VDUP(vector2, q, uint, u, 16, 8, 0x66);
+ VDUP(vector2, q, uint, u, 32, 4, 0x77);
+ VDUP(vector2, q, poly, p, 8, 16, 0x55);
+ VDUP(vector2, q, poly, p, 16, 8, 0x66);
+ VDUP(vector2, q, float, f, 32, 4, 33.8f);
+
+#define TEST_ALL_VUZP(INSN) \
+ TEST_VUZP(INSN, , int, s, 8, 8); \
+ TEST_VUZP(INSN, , int, s, 16, 4); \
+ TEST_VUZP(INSN, , int, s, 32, 2); \
+ TEST_VUZP(INSN, , uint, u, 8, 8); \
+ TEST_VUZP(INSN, , uint, u, 16, 4); \
+ TEST_VUZP(INSN, , uint, u, 32, 2); \
+ TEST_VUZP(INSN, , poly, p, 8, 8); \
+ TEST_VUZP(INSN, , poly, p, 16, 4); \
+ TEST_VUZP(INSN, , float, f, 32, 2); \
+ TEST_VUZP(INSN, q, int, s, 8, 16); \
+ TEST_VUZP(INSN, q, int, s, 16, 8); \
+ TEST_VUZP(INSN, q, int, s, 32, 4); \
+ TEST_VUZP(INSN, q, uint, u, 8, 16); \
+ TEST_VUZP(INSN, q, uint, u, 16, 8); \
+ TEST_VUZP(INSN, q, uint, u, 32, 4); \
+ TEST_VUZP(INSN, q, poly, p, 8, 16); \
+ TEST_VUZP(INSN, q, poly, p, 16, 8); \
+ TEST_VUZP(INSN, q, float, f, 32, 4)
+
+#define TEST_ALL_EXTRA_CHUNKS() \
+ TEST_EXTRA_CHUNK(int, 8, 8, 1); \
+ TEST_EXTRA_CHUNK(int, 16, 4, 1); \
+ TEST_EXTRA_CHUNK(int, 32, 2, 1); \
+ TEST_EXTRA_CHUNK(uint, 8, 8, 1); \
+ TEST_EXTRA_CHUNK(uint, 16, 4, 1); \
+ TEST_EXTRA_CHUNK(uint, 32, 2, 1); \
+ TEST_EXTRA_CHUNK(poly, 8, 8, 1); \
+ TEST_EXTRA_CHUNK(poly, 16, 4, 1); \
+ TEST_EXTRA_CHUNK(float, 32, 2, 1); \
+ TEST_EXTRA_CHUNK(int, 8, 16, 1); \
+ TEST_EXTRA_CHUNK(int, 16, 8, 1); \
+ TEST_EXTRA_CHUNK(int, 32, 4, 1); \
+ TEST_EXTRA_CHUNK(uint, 8, 16, 1); \
+ TEST_EXTRA_CHUNK(uint, 16, 8, 1); \
+ TEST_EXTRA_CHUNK(uint, 32, 4, 1); \
+ TEST_EXTRA_CHUNK(poly, 8, 16, 1); \
+ TEST_EXTRA_CHUNK(poly, 16, 8, 1); \
+ TEST_EXTRA_CHUNK(float, 32, 4, 1)
+
+ clean_results ();
+
+ /* Execute the tests. */
+ TEST_ALL_VUZP(INSN_NAME);
+
+ CHECK_RESULTS_NAMED (TEST_MSG, expected0, "(chunk 0)");
+
+ TEST_ALL_EXTRA_CHUNKS();
+ CHECK_RESULTS_NAMED (TEST_MSG, expected1, "(chunk 1)");
+}
+
+int main (void)
+{
+ FNNAME (INSN_NAME) ();
+
+ return 0;
+}
--- /dev/null
+#include <arm_neon.h>
+#include "arm-neon-ref.h"
+#include "compute-ref-data.h"
+
+/* Expected results splitted in several chunks. */
+/* Chunk 0. */
+VECT_VAR_DECL(expected0,int,8,8) [] = { 0xf0, 0xf4, 0x11, 0x11,
+ 0xf1, 0xf5, 0x11, 0x11 };
+VECT_VAR_DECL(expected0,int,16,4) [] = { 0xfff0, 0xfff2,
+ 0x22, 0x22 };
+VECT_VAR_DECL(expected0,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected0,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected0,uint,8,8) [] = { 0xf0, 0xf4, 0x55, 0x55,
+ 0xf1, 0xf5, 0x55, 0x55 };
+VECT_VAR_DECL(expected0,uint,16,4) [] = { 0xfff0, 0xfff2,
+ 0x66, 0x66 };
+VECT_VAR_DECL(expected0,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected0,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected0,poly,8,8) [] = { 0xf0, 0xf4, 0x55, 0x55,
+ 0xf1, 0xf5, 0x55, 0x55 };
+VECT_VAR_DECL(expected0,poly,16,4) [] = { 0xfff0, 0xfff2,
+ 0x66, 0x66 };
+VECT_VAR_DECL(expected0,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected0,int,8,16) [] = { 0xf0, 0xf8, 0x11, 0x11,
+ 0xf1, 0xf9, 0x11, 0x11,
+ 0xf2, 0xfa, 0x11, 0x11,
+ 0xf3, 0xfb, 0x11, 0x11 };
+VECT_VAR_DECL(expected0,int,16,8) [] = { 0xfff0, 0xfff4, 0x22, 0x22,
+ 0xfff1, 0xfff5, 0x22, 0x22 };
+VECT_VAR_DECL(expected0,int,32,4) [] = { 0xfffffff0, 0xfffffff2,
+ 0x33, 0x33 };
+VECT_VAR_DECL(expected0,int,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected0,uint,8,16) [] = { 0xf0, 0xf8, 0x55, 0x55,
+ 0xf1, 0xf9, 0x55, 0x55,
+ 0xf2, 0xfa, 0x55, 0x55,
+ 0xf3, 0xfb, 0x55, 0x55 };
+VECT_VAR_DECL(expected0,uint,16,8) [] = { 0xfff0, 0xfff4, 0x66, 0x66,
+ 0xfff1, 0xfff5, 0x66, 0x66 };
+VECT_VAR_DECL(expected0,uint,32,4) [] = { 0xfffffff0, 0xfffffff2,
+ 0x77, 0x77 };
+VECT_VAR_DECL(expected0,uint,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected0,poly,8,16) [] = { 0xf0, 0xf8, 0x55, 0x55,
+ 0xf1, 0xf9, 0x55, 0x55,
+ 0xf2, 0xfa, 0x55, 0x55,
+ 0xf3, 0xfb, 0x55, 0x55 };
+VECT_VAR_DECL(expected0,poly,16,8) [] = { 0xfff0, 0xfff4, 0x66, 0x66,
+ 0xfff1, 0xfff5, 0x66, 0x66 };
+VECT_VAR_DECL(expected0,hfloat,32,4) [] = { 0xc1800000, 0xc1600000,
+ 0x42073333, 0x42073333 };
+
+/* Chunk 1. */
+VECT_VAR_DECL(expected1,int,8,8) [] = { 0xf2, 0xf6, 0x11, 0x11,
+ 0xf3, 0xf7, 0x11, 0x11 };
+VECT_VAR_DECL(expected1,int,16,4) [] = { 0xfff1, 0xfff3,
+ 0x22, 0x22 };
+VECT_VAR_DECL(expected1,int,32,2) [] = { 0x33, 0x33 };
+VECT_VAR_DECL(expected1,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected1,uint,8,8) [] = { 0xf2, 0xf6, 0x55, 0x55,
+ 0xf3, 0xf7, 0x55, 0x55 };
+VECT_VAR_DECL(expected1,uint,16,4) [] = { 0xfff1, 0xfff3,
+ 0x66, 0x66 };
+VECT_VAR_DECL(expected1,uint,32,2) [] = { 0x77, 0x77 };
+VECT_VAR_DECL(expected1,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected1,poly,8,8) [] = { 0xf2, 0xf6, 0x55, 0x55,
+ 0xf3, 0xf7, 0x55, 0x55 };
+VECT_VAR_DECL(expected1,poly,16,4) [] = { 0xfff1, 0xfff3,
+ 0x66, 0x66 };
+VECT_VAR_DECL(expected1,hfloat,32,2) [] = { 0x42066666, 0x42066666 };
+VECT_VAR_DECL(expected1,int,8,16) [] = { 0xf4, 0xfc, 0x11, 0x11,
+ 0xf5, 0xfd, 0x11, 0x11,
+ 0xf6, 0xfe, 0x11, 0x11,
+ 0xf7, 0xff, 0x11, 0x11 };
+VECT_VAR_DECL(expected1,int,16,8) [] = { 0xfff2, 0xfff6, 0x22, 0x22,
+ 0xfff3, 0xfff7, 0x22, 0x22 };
+VECT_VAR_DECL(expected1,int,32,4) [] = { 0xfffffff1, 0xfffffff3,
+ 0x33, 0x33 };
+VECT_VAR_DECL(expected1,int,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected1,uint,8,16) [] = { 0xf4, 0xfc, 0x55, 0x55,
+ 0xf5, 0xfd, 0x55, 0x55,
+ 0xf6, 0xfe, 0x55, 0x55,
+ 0xf7, 0xff, 0x55, 0x55 };
+VECT_VAR_DECL(expected1,uint,16,8) [] = { 0xfff2, 0xfff6, 0x66, 0x66,
+ 0xfff3, 0xfff7, 0x66, 0x66 };
+VECT_VAR_DECL(expected1,uint,32,4) [] = { 0xfffffff1, 0xfffffff3,
+ 0x77, 0x77 };
+VECT_VAR_DECL(expected1,uint,64,2) [] = { 0x3333333333333333,
+ 0x3333333333333333 };
+VECT_VAR_DECL(expected1,poly,8,16) [] = { 0xf4, 0xfc, 0x55, 0x55,
+ 0xf5, 0xfd, 0x55, 0x55,
+ 0xf6, 0xfe, 0x55, 0x55,
+ 0xf7, 0xff, 0x55, 0x55 };
+VECT_VAR_DECL(expected1,poly,16,8) [] = { 0xfff2, 0xfff6, 0x66, 0x66,
+ 0xfff3, 0xfff7, 0x66, 0x66 };
+VECT_VAR_DECL(expected1,hfloat,32,4) [] = { 0xc1700000, 0xc1500000,
+ 0x42073333, 0x42073333 };
+
+#ifndef INSN_NAME
+#define INSN_NAME vzip
+#define TEST_MSG "VZIP/VZIPQ"
+#endif
+
+#define FNNAME1(NAME) exec_ ## NAME
+#define FNNAME(NAME) FNNAME1(NAME)
+
+void FNNAME (INSN_NAME) (void)
+{
+ /* In this case, output variables are arrays of vectors. */
+#define DECL_VZIP(T1, W, N) \
+ VECT_ARRAY_TYPE(T1, W, N, 2) VECT_ARRAY_VAR(result_vec, T1, W, N, 2); \
+ VECT_VAR_DECL(result_bis, T1, W, N)[2 * N]
+
+ /* We need to use a temporary result buffer (result_bis), because
+ the one used for other tests is not large enough. A subset of the
+ result data is moved from result_bis to result, and it is this
+ subset which is used to check the actual behaviour. The next
+ macro enables to move another chunk of data from result_bis to
+ result. */
+#define TEST_VZIP(INSN, Q, T1, T2, W, N) \
+ VECT_ARRAY_VAR(result_vec, T1, W, N, 2) = \
+ INSN##Q##_##T2##W(VECT_VAR(vector1, T1, W, N), \
+ VECT_VAR(vector2, T1, W, N)); \
+ vst2##Q##_##T2##W(VECT_VAR(result_bis, T1, W, N), \
+ VECT_ARRAY_VAR(result_vec, T1, W, N, 2)); \
+ memcpy(VECT_VAR(result, T1, W, N), VECT_VAR(result_bis, T1, W, N), \
+ sizeof(VECT_VAR(result, T1, W, N)));
+
+ /* Overwrite "result" with the contents of "result_bis"[X]. */
+#define TEST_EXTRA_CHUNK(T1, W, N, X) \
+ memcpy(VECT_VAR(result, T1, W, N), &(VECT_VAR(result_bis, T1, W, N)[X*N]), \
+ sizeof(VECT_VAR(result, T1, W, N)));
+
+ DECL_VARIABLE_ALL_VARIANTS(vector1);
+ DECL_VARIABLE_ALL_VARIANTS(vector2);
+
+ /* We don't need 64 bits variants. */
+#define DECL_ALL_VZIP() \
+ DECL_VZIP(int, 8, 8); \
+ DECL_VZIP(int, 16, 4); \
+ DECL_VZIP(int, 32, 2); \
+ DECL_VZIP(uint, 8, 8); \
+ DECL_VZIP(uint, 16, 4); \
+ DECL_VZIP(uint, 32, 2); \
+ DECL_VZIP(poly, 8, 8); \
+ DECL_VZIP(poly, 16, 4); \
+ DECL_VZIP(float, 32, 2); \
+ DECL_VZIP(int, 8, 16); \
+ DECL_VZIP(int, 16, 8); \
+ DECL_VZIP(int, 32, 4); \
+ DECL_VZIP(uint, 8, 16); \
+ DECL_VZIP(uint, 16, 8); \
+ DECL_VZIP(uint, 32, 4); \
+ DECL_VZIP(poly, 8, 16); \
+ DECL_VZIP(poly, 16, 8); \
+ DECL_VZIP(float, 32, 4)
+
+ DECL_ALL_VZIP();
+
+ /* Initialize input "vector" from "buffer". */
+ TEST_MACRO_ALL_VARIANTS_2_5(VLOAD, vector1, buffer);
+ VLOAD(vector1, buffer, , float, f, 32, 2);
+ VLOAD(vector1, buffer, q, float, f, 32, 4);
+
+ /* Choose arbitrary initialization values. */
+ VDUP(vector2, , int, s, 8, 8, 0x11);
+ VDUP(vector2, , int, s, 16, 4, 0x22);
+ VDUP(vector2, , int, s, 32, 2, 0x33);
+ VDUP(vector2, , uint, u, 8, 8, 0x55);
+ VDUP(vector2, , uint, u, 16, 4, 0x66);
+ VDUP(vector2, , uint, u, 32, 2, 0x77);
+ VDUP(vector2, , poly, p, 8, 8, 0x55);
+ VDUP(vector2, , poly, p, 16, 4, 0x66);
+ VDUP(vector2, , float, f, 32, 2, 33.6f);
+
+ VDUP(vector2, q, int, s, 8, 16, 0x11);
+ VDUP(vector2, q, int, s, 16, 8, 0x22);
+ VDUP(vector2, q, int, s, 32, 4, 0x33);
+ VDUP(vector2, q, uint, u, 8, 16, 0x55);
+ VDUP(vector2, q, uint, u, 16, 8, 0x66);
+ VDUP(vector2, q, uint, u, 32, 4, 0x77);
+ VDUP(vector2, q, poly, p, 8, 16, 0x55);
+ VDUP(vector2, q, poly, p, 16, 8, 0x66);
+ VDUP(vector2, q, float, f, 32, 4, 33.8f);
+
+#define TEST_ALL_VZIP(INSN) \
+ TEST_VZIP(INSN, , int, s, 8, 8); \
+ TEST_VZIP(INSN, , int, s, 16, 4); \
+ TEST_VZIP(INSN, , int, s, 32, 2); \
+ TEST_VZIP(INSN, , uint, u, 8, 8); \
+ TEST_VZIP(INSN, , uint, u, 16, 4); \
+ TEST_VZIP(INSN, , uint, u, 32, 2); \
+ TEST_VZIP(INSN, , poly, p, 8, 8); \
+ TEST_VZIP(INSN, , poly, p, 16, 4); \
+ TEST_VZIP(INSN, , float, f, 32, 2); \
+ TEST_VZIP(INSN, q, int, s, 8, 16); \
+ TEST_VZIP(INSN, q, int, s, 16, 8); \
+ TEST_VZIP(INSN, q, int, s, 32, 4); \
+ TEST_VZIP(INSN, q, uint, u, 8, 16); \
+ TEST_VZIP(INSN, q, uint, u, 16, 8); \
+ TEST_VZIP(INSN, q, uint, u, 32, 4); \
+ TEST_VZIP(INSN, q, poly, p, 8, 16); \
+ TEST_VZIP(INSN, q, poly, p, 16, 8); \
+ TEST_VZIP(INSN, q, float, f, 32, 4)
+
+#define TEST_ALL_EXTRA_CHUNKS() \
+ TEST_EXTRA_CHUNK(int, 8, 8, 1); \
+ TEST_EXTRA_CHUNK(int, 16, 4, 1); \
+ TEST_EXTRA_CHUNK(int, 32, 2, 1); \
+ TEST_EXTRA_CHUNK(uint, 8, 8, 1); \
+ TEST_EXTRA_CHUNK(uint, 16, 4, 1); \
+ TEST_EXTRA_CHUNK(uint, 32, 2, 1); \
+ TEST_EXTRA_CHUNK(poly, 8, 8, 1); \
+ TEST_EXTRA_CHUNK(poly, 16, 4, 1); \
+ TEST_EXTRA_CHUNK(float, 32, 2, 1); \
+ TEST_EXTRA_CHUNK(int, 8, 16, 1); \
+ TEST_EXTRA_CHUNK(int, 16, 8, 1); \
+ TEST_EXTRA_CHUNK(int, 32, 4, 1); \
+ TEST_EXTRA_CHUNK(uint, 8, 16, 1); \
+ TEST_EXTRA_CHUNK(uint, 16, 8, 1); \
+ TEST_EXTRA_CHUNK(uint, 32, 4, 1); \
+ TEST_EXTRA_CHUNK(poly, 8, 16, 1); \
+ TEST_EXTRA_CHUNK(poly, 16, 8, 1); \
+ TEST_EXTRA_CHUNK(float, 32, 4, 1)
+
+ clean_results ();
+
+ /* Execute the tests. */
+ TEST_ALL_VZIP(INSN_NAME);
+
+ CHECK_RESULTS_NAMED (TEST_MSG, expected0, "(chunk 0)");
+
+ TEST_ALL_EXTRA_CHUNKS();
+ CHECK_RESULTS_NAMED (TEST_MSG, expected1, "(chunk 1)");
+}
+
+int main (void)
+{
+ FNNAME (INSN_NAME) ();
+
+ return 0;
+}
--- /dev/null
+Advanced SIMD intrinsics tests are located in gcc.target/aarch64.
projects / platform / upstream / linaro-gcc.git / commitdiff