Enable VAES support [3/5]

gcc/
	* config/i386/i386-builtin.def (__builtin_ia32_vaesdeclast_v16qi,
	__builtin_ia32_vaesdeclast_v32qi, __builtin_ia32_vaesdeclast_v64qi): New.
	* config/i386/sse.md (vaesdeclast_<mode>): New pattern.
	* config/i386/vaesintrin.h (_mm256_aesdeclast_epi128,
	_mm512_aesdeclast_epi128, _mm_aesdeclast_epi128): New intrinsics.

gcc/testsuite/
	* gcc.target/i386/avx512f-aesdeclast-2.c: New test.
	* gcc.target/i386/avx512vl-aesdeclast-2.c
	* gcc.target/i386/avx512fvl-vaes-1.c: Handle new intrinsics.

From-SVN: r255674

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 9e38d7c..aa1d1a6 100644 (file)
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,11 @@
+2017-12-15  Julia Koval  <julia.koval@intel.com>
+
+       * config/i386/i386-builtin.def (__builtin_ia32_vaesdeclast_v16qi,
+       __builtin_ia32_vaesdeclast_v32qi, __builtin_ia32_vaesdeclast_v64qi): New.
+       * config/i386/sse.md (vaesdeclast_<mode>): New pattern.
+       * config/i386/vaesintrin.h (_mm256_aesdeclast_epi128,
+       _mm512_aesdeclast_epi128, _mm_aesdeclast_epi128): New intrinsics.
+
 2017-12-14  Bill Schmidt  <wschmidt@linux.vnet.ibm.com>
 
        * gimple-ssa-strength-reduction.c (analyze_increments):

diff --git a/gcc/config/i386/i386-builtin.def b/gcc/config/i386/i386-builtin.def
index 8cfa149..99b13cf 100644 (file)
--- a/gcc/config/i386/i386-builtin.def
+++ b/gcc/config/i386/i386-builtin.def
@@ -2767,6 +2767,9 @@ BDESC (OPTION_MASK_ISA_AVX512VNNI, CODE_FOR_vpdpwssds_v4si_maskz, "__builtin_ia3
 BDESC (OPTION_MASK_ISA_VAES, CODE_FOR_vaesdec_v16qi, "__builtin_ia32_vaesdec_v16qi", IX86_BUILTIN_VAESDEC16, UNKNOWN, (int) V16QI_FTYPE_V16QI_V16QI)
 BDESC (OPTION_MASK_ISA_VAES, CODE_FOR_vaesdec_v32qi, "__builtin_ia32_vaesdec_v32qi", IX86_BUILTIN_VAESDEC32, UNKNOWN, (int) V32QI_FTYPE_V32QI_V32QI)
 BDESC (OPTION_MASK_ISA_VAES, CODE_FOR_vaesdec_v64qi, "__builtin_ia32_vaesdec_v64qi", IX86_BUILTIN_VAESDEC64, UNKNOWN, (int) V64QI_FTYPE_V64QI_V64QI)
+BDESC (OPTION_MASK_ISA_VAES, CODE_FOR_vaesdeclast_v16qi, "__builtin_ia32_vaesdeclast_v16qi", IX86_BUILTIN_VAESDECLAST16, UNKNOWN, (int) V16QI_FTYPE_V16QI_V16QI)
+BDESC (OPTION_MASK_ISA_VAES, CODE_FOR_vaesdeclast_v32qi, "__builtin_ia32_vaesdeclast_v32qi", IX86_BUILTIN_VAESDECLAST32, UNKNOWN, (int) V32QI_FTYPE_V32QI_V32QI)
+BDESC (OPTION_MASK_ISA_VAES, CODE_FOR_vaesdeclast_v64qi, "__builtin_ia32_vaesdeclast_v64qi", IX86_BUILTIN_VAESDECLAST64, UNKNOWN, (int) V64QI_FTYPE_V64QI_V64QI)
 
 BDESC_END (ARGS2, SPECIAL_ARGS2)
 

diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
index 238a606..eedb345 100644 (file)
--- a/gcc/config/i386/sse.md
+++ b/gcc/config/i386/sse.md
@@ -175,6 +175,7 @@
 
   ;; For VAES support
   UNSPEC_VAESDEC
+  UNSPEC_VAESDECLAST
 ])
 
 (define_c_enum "unspecv" [
@@ -20465,3 +20466,13 @@
   "TARGET_VAES"
   "vaesdec\t{%2, %1, %0|%0, %1, %2}"
 )
+
+(define_insn "vaesdeclast_<mode>"
+  [(set (match_operand:VI1_AVX512VL_F 0 "register_operand" "=v")
+         (unspec:VI1_AVX512VL_F
+         [(match_operand:VI1_AVX512VL_F 1 "register_operand" "v")
+          (match_operand:VI1_AVX512VL_F 2 "vector_operand" "v")]
+         UNSPEC_VAESDECLAST))]
+  "TARGET_VAES"
+  "vaesdeclast\t{%2, %1, %0|%0, %1, %2}"
+)

diff --git a/gcc/config/i386/vaesintrin.h b/gcc/config/i386/vaesintrin.h
index 0208cc7..1159922 100644 (file)
--- a/gcc/config/i386/vaesintrin.h
+++ b/gcc/config/i386/vaesintrin.h
@@ -14,6 +14,14 @@ _mm256_aesdec_epi128 (__m256i __A, __m256i __B)
   return (__m256i)__builtin_ia32_vaesdec_v32qi ((__v32qi) __A, (__v32qi) __B);
 }
 
+extern __inline __m256i
+__attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_aesdeclast_epi128 (__m256i __A, __m256i __B)
+{
+  return (__m256i)__builtin_ia32_vaesdeclast_v32qi ((__v32qi) __A,
+                                                               (__v32qi) __B);
+}
+
 #ifdef __DISABLE_VAES__
 #undef __DISABLE_VAES__
 #pragma GCC pop_options
@@ -34,6 +42,14 @@ _mm512_aesdec_epi128 (__m512i __A, __m512i __B)
   return (__m512i)__builtin_ia32_vaesdec_v64qi ((__v64qi) __A, (__v64qi) __B);
 }
 
+extern __inline __m512i
+__attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_aesdeclast_epi128 (__m512i __A, __m512i __B)
+{
+  return (__m512i)__builtin_ia32_vaesdeclast_v64qi ((__v64qi) __A,
+                                                   (__v64qi) __B);
+}
+
 #ifdef __DISABLE_VAESF__
 #undef __DISABLE_VAESF__
 #pragma GCC pop_options
@@ -52,6 +68,14 @@ _mm_aesdec_epi128 (__m128i __A, __m128i __B)
   return (__m128i)__builtin_ia32_vaesdec_v16qi ((__v16qi) __A, (__v16qi) __B);
 }
 
+extern __inline __m128i
+__attribute__((__gnu_inline__, __always_inline__, __artificial__))
+_mm_aesdeclast_epi128 (__m128i __A, __m128i __B)
+{
+  return (__m128i)__builtin_ia32_vaesdeclast_v16qi ((__v16qi) __A,
+                                                   (__v16qi) __B);
+}
+
 #ifdef __DISABLE_VAESVL__
 #undef __DISABLE_VAESVL__
 #pragma GCC pop_options

diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index f39da0b..3a2fddb 100644 (file)
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,9 @@
+2017-12-12  Julia Koval  <julia.koval@intel.com>
+
+       * gcc.target/i386/avx512f-aesdeclast-2.c: New test.
+       * gcc.target/i386/avx512vl-aesdeclast-2.c
+       * gcc.target/i386/avx512fvl-vaes-1.c: Handle new intrinsics.
+
 2017-12-14  Bernd Edlinger  <bernd.edlinger@hotmail.de>
 
        * c-c++-common/Wcast-function-type.c: New test.

diff --git a/gcc/testsuite/gcc.target/i386/avx512f-aesdeclast-2.c b/gcc/testsuite/gcc.target/i386/avx512f-aesdeclast-2.c
new file mode 100644 (file)
index 0000000..c318eb2
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512f-aesdeclast-2.c
@@ -0,0 +1,52 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -mavx512f -mvaes" } */
+/* { dg-require-effective-target avx512f } */
+/* { dg-require-effective-target avx512vaes } */
+
+#define AVX512F
+
+#define VAES
+#include "avx512f-helper.h"
+
+#define SIZE (AVX512F_LEN / 32)
+
+#include "avx512f-mask-type.h"
+
+static void
+CALC (unsigned int *r)
+{
+  for (int i = 0; i < SIZE; i+=4)
+    {
+      r[i] = 0xa8ba9d0;
+      r[i + 1] = 0x94902ace;
+      r[i + 2] = 0xa7726929;
+      r[i + 3] = 0x654dfb35;
+    }
+}
+
+void
+TEST (void)
+{
+  int i;
+  UNION_TYPE (AVX512F_LEN, i_ud) res1, src1, src2;
+  MASK_TYPE mask = MASK_VALUE;
+  unsigned int res_ref[SIZE];
+
+  for (int i = 0; i < SIZE; i+=4)
+    {
+      src1.a[i] = 0x5d53475d;
+      src1.a[i + 1] = 0x63746f72;
+      src1.a[i + 2] = 0x73745665;
+      src1.a[i + 3] = 0x7b5b5465;
+      src2.a[i] = 0x726f6e5d;
+      src2.a[i + 1] = 0x5b477565;
+      src2.a[i + 2] = 0x68617929;
+      src2.a[i + 3] = 0x48692853;
+    }
+
+  CALC (res_ref);
+  res1.x = INTRINSIC (_aesdeclast_epi128) (src2.x, src1.x);
+
+  if (UNION_CHECK (AVX512F_LEN, i_ud) (res1, res_ref))
+    abort ();
+}

diff --git a/gcc/testsuite/gcc.target/i386/avx512fvl-vaes-1.c b/gcc/testsuite/gcc.target/i386/avx512fvl-vaes-1.c
index fc4e6bf..0ff4ce6 100644 (file)
--- a/gcc/testsuite/gcc.target/i386/avx512fvl-vaes-1.c
+++ b/gcc/testsuite/gcc.target/i386/avx512fvl-vaes-1.c
@@ -1,10 +1,13 @@
 /* { dg-do compile } */
 /* { dg-options "-mvaes -mavx512f -mavx512vl -O2" } */
 /* { dg-final { scan-assembler-times "vaesdec\[ \\t\]+\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+(?:\n|\[ \\t\]+#)"  1 } } */
+/* { dg-final { scan-assembler-times "vaesdeclast\[ \\t\]+\[^\{\n\]*%zmm\[0-9\]+\[^\{\n\]*%zmm\[0-9\]+\[^\{\n\]*%zmm\[0-9\]+(?:\n|\[ \\t\]+#)"  1 } } */
 
 /* { dg-final { scan-assembler-times "vaesdec\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+\[^\{\n\]*%ymm\[0-9\]+\[^\{\n\]*%ymm\[0-9\]+(?:\n|\[ \\t\]+#)"  1 } } */
+/* { dg-final { scan-assembler-times "vaesdeclast\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+\[^\{\n\]*%ymm\[0-9\]+\[^\{\n\]*%ymm\[0-9\]+(?:\n|\[ \\t\]+#)"  1 } } */
 
 /* { dg-final { scan-assembler-times "vaesdec\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\{\n\]*%xmm\[0-9\]+\[^\{\n\]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)"  1 } } */
+/* { dg-final { scan-assembler-times "vaesdeclast\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\{\n\]*%xmm\[0-9\]+\[^\{\n\]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)"  1 } } */
 
 #include <immintrin.h>
 
@@ -16,9 +19,11 @@ void extern
 avx512f_test (void)
 {
   x = _mm512_aesdec_epi128 (x, y);
+  x = _mm512_aesdeclast_epi128 (x, y);
 
   x256 = _mm256_aesdec_epi128 (x256, y256);
+  x256 = _mm256_aesdeclast_epi128 (x256, y256);
 
   x128 = _mm_aesdec_epi128 (x128, y128);
-
+  x128 = _mm_aesdeclast_epi128 (x128, y128);
 }

diff --git a/gcc/testsuite/gcc.target/i386/avx512vl-aesdeclast-2.c b/gcc/testsuite/gcc.target/i386/avx512vl-aesdeclast-2.c
new file mode 100644 (file)
index 0000000..b2a783a
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512vl-aesdeclast-2.c
@@ -0,0 +1,17 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -mavx512bw -mavx512vl -mvaes" } */
+/* { dg-require-effective-target avx512vl } */
+/* { dg-require-effective-target avx512bw } */
+/* { dg-require-effective-target avx512vaes } */
+
+#define AVX512VL
+#define AVX512F_LEN 256
+#define AVX512F_LEN_HALF 128
+#include "avx512f-aesdeclast-2.c"
+
+#undef AVX512F_LEN
+#undef AVX512F_LEN_HALF
+
+#define AVX512F_LEN 128
+#define AVX512F_LEN_HALF 128
+#include "avx512f-aesdeclast-2.c"