From f91057cbad196be09541eccf1ece5472531f63aa Mon Sep 17 00:00:00 2001 From: Marius Hillenbrand Date: Tue, 15 Sep 2020 10:54:37 +0200 Subject: [PATCH] s390x: move common vector definitions and utils into header ... to facilitate reuse beyond gemm_vec.c and avoid code duplication. Signed-off-by: Marius Hillenbrand --- kernel/zarch/gemm_vec.c | 34 ++--------------------- kernel/zarch/vector-common.h | 64 ++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 66 insertions(+), 32 deletions(-) create mode 100644 kernel/zarch/vector-common.h diff --git a/kernel/zarch/gemm_vec.c b/kernel/zarch/gemm_vec.c index ef0b1d1..30f3171 100644 --- a/kernel/zarch/gemm_vec.c +++ b/kernel/zarch/gemm_vec.c @@ -30,12 +30,13 @@ * USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. */ #include "common.h" -#include +#include "vector-common.h" #include #include #include + #ifdef COMPLEX #error "Handling for complex numbers is not supported in this kernel" #endif @@ -153,37 +154,6 @@ static const bool backwards = false; * 3, May 2008. */ -#define VLEN_BYTES 16 -#define VLEN_FLOATS (VLEN_BYTES / sizeof(FLOAT)) - -typedef FLOAT vector_float __attribute__ ((vector_size (16))); - -/** - * Load a vector into register, and hint on 8-byte alignment to improve - * performance. gcc-9 and newer will create these hints by itself. For older - * compiler versions, use inline assembly to explicitly express the hint. - * Provide explicit hex encoding to cater for binutils versions that do not know - * about vector-load with alignment hints yet. - * - * Note that, for block sizes where we apply vectorization, vectors in A will - * always be 8-byte aligned. - */ -static inline vector_float vec_load_hinted(FLOAT const *restrict a) { - vector_float const *restrict addr = (vector_float const *restrict)a; - vector_float y; - -#if __GNUC__ < 9 && !defined(__clang__) - // hex-encode vl %[out],%[addr],3 - asm(".insn vrx,0xe70000003006,%[out],%[addr],3" - : [ out ] "=v"(y) - : [ addr ] "R"(*addr)); -#else - y = *addr; -#endif - - return y; -} - /** * Calculate for a row-block in C_i of size ROWSxCOLS using vector intrinsics. * diff --git a/kernel/zarch/vector-common.h b/kernel/zarch/vector-common.h new file mode 100644 index 0000000..140d39d --- /dev/null +++ b/kernel/zarch/vector-common.h @@ -0,0 +1,64 @@ +/* + * Copyright (c) IBM Corporation 2020. + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are + * met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * 3. Neither the name of the OpenBLAS project nor the names of + * its contributors may be used to endorse or promote products + * derived from this software without specific prior written + * permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR + * SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER + * CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, + * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE + * USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#include + +#define VLEN_BYTES 16 +#define VLEN_FLOATS (VLEN_BYTES / sizeof(FLOAT)) + +typedef FLOAT vector_float __attribute__ ((vector_size (VLEN_BYTES))); + +/** + * Load a vector into register, and hint on 8-byte alignment to improve + * performance. gcc-9 and newer will create these hints by itself. For older + * compiler versions, use inline assembly to explicitly express the hint. + * Provide explicit hex encoding to cater for binutils versions that do not know + * about vector-load with alignment hints yet. + * + * Note that, for block sizes where we apply vectorization, vectors in A will + * always be 8-byte aligned. + */ +static inline vector_float vec_load_hinted(FLOAT const *restrict a) { + vector_float const *restrict addr = (vector_float const *restrict)a; + vector_float y; + +#if __GNUC__ < 9 && !defined(__clang__) + // hex-encode vl %[out],%[addr],3 + asm(".insn vrx,0xe70000003006,%[out],%[addr],3" + : [ out ] "=v"(y) + : [ addr ] "R"(*addr)); +#else + y = *addr; +#endif + + return y; +} -- 2.7.4