[PATCH, testsuite]: Use x86intrin.h in x86 intrinsics tests

[Uros Bizjak <ubizjak at gmail dot com>]

Hello!

This patch changes various generic x86 tests that test x86 intrinsic 
functions to use x86intrin.h.

2008-12-13  Uros Bizjak  <ubizjak@gmail.com>

   * gcc.target/i386/sse-12.c: Include x86intrin.h.
   (dg-options): Use -mavx instead of -msse4. Add -maes -mpclmul.
   * gcc.target/i386/sse-13.c: Include x86intrin.h. Define immintrin.h
   intrinsics that require immediate arguments.
   (dg-options): Use -mavx instead of -msse4.
   * gcc.target/i386/sse-14.c: Include x86intrin.h. Define immintrin.h
   intrinsics that require immediate arguments.
   (test_3): New macro.
   (dg-options): Use -mavx instead of -msse4.
   * g++.dg/other/i386-2.C: Include x86intrin.h.
   (dg-options): Use -mavx instead of -msse4.
   * g++.dg/other/i386-3.C: Include x86intrin.h.
   (dg-options): Use -mavx instead of -msse4.

Patch was teste on x86_64-pc-linux-gnu, committed to mainline.

Uros.
Index: gcc.target/i386/sse-12.c
===================================================================
--- gcc.target/i386/sse-12.c	(revision 142738)
+++ gcc.target/i386/sse-12.c	(working copy)
@@ -1,10 +1,8 @@
-/* Test that {,x,e,p,t,s,a}mmintrin.h, mm3dnow.h and mm_malloc.h are
+/* Test that {,x,e,p,t,s,w,a,b,i}mmintrin.h, mm3dnow.h and mm_malloc.h are
    usable with -O -std=c89 -pedantic-errors.  */
 /* { dg-do compile } */
-/* { dg-options "-O -std=c89 -pedantic-errors -march=k8 -m3dnow -msse4 -msse5" } */
+/* { dg-options "-O -std=c89 -pedantic-errors -march=k8 -m3dnow -mavx -msse5 -maes -mpclmul" } */
 
-#include <bmmintrin.h>
-#include <smmintrin.h>
-#include <mm3dnow.h>
+#include <x86intrin.h>
 
 int dummy;
Index: gcc.target/i386/sse-14.c
===================================================================
--- gcc.target/i386/sse-14.c	(revision 142738)
+++ gcc.target/i386/sse-14.c	(working copy)
@@ -1,5 +1,5 @@
 /* { dg-do compile } */
-/* { dg-options "-O0 -Werror-implicit-function-declaration -march=k8 -m3dnow -msse4 -msse5 -maes -mpclmul" } */
+/* { dg-options "-O0 -Werror-implicit-function-declaration -march=k8 -m3dnow -mavx -msse5 -maes -mpclmul" } */
 
 #include <mm_malloc.h>
 
@@ -11,10 +11,7 @@
 #define extern
 #define __inline
 
-#include <wmmintrin.h>
-#include <bmmintrin.h>
-#include <smmintrin.h>
-#include <mm3dnow.h>
+#include <x86intrin.h>
 
 #define _CONCAT(x,y) x ## y
 
@@ -34,6 +31,11 @@
   type _CONCAT(_,func) (op1_type A, op2_type B, int const I, int const L) \
   { return func (A, B, imm1, imm2); }
 
+#define test_3(func, type, op1_type, op2_type, op3_type, imm)		\
+  type _CONCAT(_,func) (op1_type A, op2_type B,				\
+			op3_type C, int const I)			\
+  { return func (A, B, C, imm); }
+
 #define test_4(func, type, op1_type, op2_type, op3_type, op4_type, imm)	\
   type _CONCAT(_,func) (op1_type A, op2_type B,				\
 			op3_type C, op4_type D, int const I)		\
@@ -47,6 +49,50 @@
 test_1x (_mm_extracti_si64, __m128i, __m128i, 1, 1)
 test_2x (_mm_inserti_si64, __m128i, __m128i, __m128i, 1, 1)
 
+/* immintrin.h */
+test_2 (_mm256_blend_pd, __m256d, __m256d, __m256d, 1)
+test_2 (_mm256_blend_ps, __m256, __m256, __m256, 1)
+test_2 (_mm256_dp_ps, __m256, __m256, __m256, 1)
+test_2 (_mm256_shuffle_pd, __m256d, __m256d, __m256d, 1)
+test_2 (_mm256_shuffle_ps, __m256, __m256, __m256, 1)
+test_2 (_mm_cmp_sd, __m128d, __m128d, __m128d, 1)
+test_2 (_mm_cmp_ss, __m128, __m128, __m128, 1)
+test_2 (_mm_cmp_pd, __m128d, __m128d, __m128d, 1)
+test_2 (_mm_cmp_ps, __m128, __m128, __m128, 1)
+test_2 (_mm256_cmp_pd, __m256d, __m256d, __m256d, 1)
+test_2 (_mm256_cmp_ps, __m256, __m256, __m256, 1)
+test_1 (_mm256_extractf128_pd, __m128d, __m256d, 1)
+test_1 (_mm256_extractf128_ps, __m128, __m256, 1)
+test_1 (_mm256_extractf128_si256, __m128i, __m256i, 1)
+test_1 (_mm256_extract_epi8, int, __m256i, 20)
+test_1 (_mm256_extract_epi16, int, __m256i, 13)
+test_1 (_mm256_extract_epi32, int, __m256i, 6)
+#ifdef __x86_64__
+test_1 (_mm256_extract_epi64, long long, __m256i, 2)
+#endif
+test_1 (_mm_permute_pd, __m128d, __m128d, 1)
+test_1 (_mm256_permute_pd, __m256d, __m256d, 1)
+test_1 (_mm_permute_ps, __m128, __m128, 1)
+test_1 (_mm256_permute_ps, __m256, __m256, 1)
+test_3 (_mm_permute2_pd, __m128d, __m128d, __m128d, __m128d, 1)
+test_3 (_mm256_permute2_pd, __m256d, __m256d, __m256d, __m256d, 1)
+test_3 (_mm_permute2_ps, __m128, __m128, __m128, __m128, 1)
+test_3 (_mm256_permute2_ps, __m256, __m256, __m256, __m256, 1)
+test_2 (_mm256_permute2f128_pd, __m256d, __m256d, __m256d, 1)
+test_2 (_mm256_permute2f128_ps, __m256, __m256, __m256, 1)
+test_2 (_mm256_permute2f128_si256, __m256i, __m256i, __m256i, 1)
+test_2 (_mm256_insertf128_pd, __m256d, __m256d, __m128d, 1)
+test_2 (_mm256_insertf128_ps, __m256, __m256, __m128, 1)
+test_2 (_mm256_insertf128_si256, __m256i, __m256i, __m128i, 1)
+test_2 (_mm256_insert_epi8, __m256i, __m256i, int, 30)
+test_2 (_mm256_insert_epi16, __m256i, __m256i, int, 7)
+test_2 (_mm256_insert_epi32, __m256i, __m256i, int, 3)
+#ifdef __x86_64__
+test_2 (_mm256_insert_epi64, __m256i, __m256i, long long, 1)
+#endif
+test_1 (_mm256_round_pd, __m256d, __m256d, 1)
+test_1 (_mm256_round_ps, __m256, __m256, 1)
+
 /* wmmintrin.h */
 test_1 (_mm_aeskeygenassist_si128, __m128i, __m128i, 1)
 test_2 (_mm_clmulepi64_si128, __m128i, __m128i, __m128i, 1)
Index: gcc.target/i386/sse-13.c
===================================================================
--- gcc.target/i386/sse-13.c	(revision 142738)
+++ gcc.target/i386/sse-13.c	(working copy)
@@ -1,10 +1,10 @@
 /* { dg-do compile } */
-/* { dg-options "-O2 -Werror-implicit-function-declaration -march=k8 -m3dnow -msse4 -msse5 -maes -mpclmul" } */
+/* { dg-options "-O2 -Werror-implicit-function-declaration -march=k8 -m3dnow -mavx -msse5 -maes -mpclmul" } */
 
 #include <mm_malloc.h>
 
 /* Test that the intrinsics compile with optimization.  All of them are
-   defined as inline functions in {,x,e,p,t,s,w,a,b}mmintrin.h and mm3dnow.h
+   defined as inline functions in {,x,e,p,t,s,w,a,b,i}mmintrin.h and mm3dnow.h
    that reference the proper builtin functions.  Defining away "extern" and
    "__inline" results in all of them being compiled as proper functions.  */
 
@@ -17,6 +17,38 @@
 #define __builtin_ia32_extrqi(X, I, L)  __builtin_ia32_extrqi(X, 1, 1)
 #define __builtin_ia32_insertqi(X, Y, I, L) __builtin_ia32_insertqi(X, Y, 1, 1)
 
+/* immintrin.h */
+#define __builtin_ia32_blendpd256(X, Y, M) __builtin_ia32_blendpd256(X, Y, 1)
+#define __builtin_ia32_blendps256(X, Y, M) __builtin_ia32_blendps256(X, Y, 1)
+#define __builtin_ia32_dpps256(X, Y, M) __builtin_ia32_dpps256(X, Y, 1)
+#define __builtin_ia32_shufpd256(X, Y, M) __builtin_ia32_shufpd256(X, Y, 1)
+#define __builtin_ia32_shufps256(X, Y, M) __builtin_ia32_shufps256(X, Y, 1)
+#define __builtin_ia32_cmpsd(X, Y, O) __builtin_ia32_cmpsd(X, Y, 1)
+#define __builtin_ia32_cmpss(X, Y, O) __builtin_ia32_cmpss(X, Y, 1)
+#define __builtin_ia32_cmppd(X, Y, O) __builtin_ia32_cmppd(X, Y, 1)
+#define __builtin_ia32_cmpps(X, Y, O) __builtin_ia32_cmpps(X, Y, 1)
+#define __builtin_ia32_cmppd256(X, Y, O) __builtin_ia32_cmppd256(X, Y, 1)
+#define __builtin_ia32_cmpps256(X, Y, O) __builtin_ia32_cmpps256(X, Y, 1)
+#define __builtin_ia32_vextractf128_pd256(X, N) __builtin_ia32_vextractf128_pd256(X, 1)
+#define __builtin_ia32_vextractf128_ps256(X, N) __builtin_ia32_vextractf128_ps256(X, 1)
+#define __builtin_ia32_vextractf128_si256(X, N) __builtin_ia32_vextractf128_si256(X, 1)
+#define __builtin_ia32_vpermilpd(X, N) __builtin_ia32_vpermilpd(X, 1)
+#define __builtin_ia32_vpermilpd256(X, N) __builtin_ia32_vpermilpd256(X, 1)
+#define __builtin_ia32_vpermilps(X, N) __builtin_ia32_vpermilps(X, 1)
+#define __builtin_ia32_vpermilps256(X, N) __builtin_ia32_vpermilps256(X, 1)
+#define __builtin_ia32_vpermil2pd(X, Y, C, I) __builtin_ia32_vpermil2pd(X, Y, C, 1)
+#define __builtin_ia32_vpermil2pd256(X, Y, C, I) __builtin_ia32_vpermil2pd256(X, Y, C, 1)
+#define __builtin_ia32_vpermil2ps(X, Y, C, I) __builtin_ia32_vpermil2ps(X, Y, C, 1)
+#define __builtin_ia32_vpermil2ps256(X, Y, C, I) __builtin_ia32_vpermil2ps256(X, Y, C, 1)
+#define __builtin_ia32_vperm2f128_pd256(X, Y, C) __builtin_ia32_vperm2f128_pd256(X, Y, 1)
+#define __builtin_ia32_vperm2f128_ps256(X, Y, C) __builtin_ia32_vperm2f128_ps256(X, Y, 1)
+#define __builtin_ia32_vperm2f128_si256(X, Y, C) __builtin_ia32_vperm2f128_si256(X, Y, 1)
+#define __builtin_ia32_vinsertf128_pd256(X, Y, C) __builtin_ia32_vinsertf128_pd256(X, Y, 1)
+#define __builtin_ia32_vinsertf128_ps256(X, Y, C) __builtin_ia32_vinsertf128_ps256(X, Y, 1)
+#define __builtin_ia32_vinsertf128_si256(X, Y, C) __builtin_ia32_vinsertf128_si256(X, Y, 1)
+#define __builtin_ia32_roundpd256(V, M) __builtin_ia32_roundpd256(V, 1)
+#define __builtin_ia32_roundps256(V, M) __builtin_ia32_roundps256(V, 1)
+
 /* wmmintrin.h */
 #define __builtin_ia32_aeskeygenassist128(X, C) __builtin_ia32_aeskeygenassist128(X, 1)
 #define __builtin_ia32_pclmulqdq128(X, Y, I) __builtin_ia32_pclmulqdq128(X, Y, 1)
@@ -100,7 +132,4 @@
 #define __builtin_ia32_protdi(A, B) __builtin_ia32_protdi(A,1)
 #define __builtin_ia32_protqi(A, B) __builtin_ia32_protqi(A,1)
 
-#include <wmmintrin.h>
-#include <bmmintrin.h>
-#include <smmintrin.h>
-#include <mm3dnow.h>
+#include <x86intrin.h>
Index: g++.dg/other/i386-2.C
===================================================================
--- g++.dg/other/i386-2.C	(revision 142738)
+++ g++.dg/other/i386-2.C	(working copy)
@@ -1,11 +1,8 @@
-/* Test that {,x,e,p,t,s,w,a,b}mmintrin.h, mm3dnow.h and mm_malloc.h are
+/* Test that {,x,e,p,t,s,w,a,b,i}mmintrin.h, mm3dnow.h and mm_malloc.h are
    usable with -O -pedantic-errors.  */
 /* { dg-do compile { target i?86-*-* x86_64-*-* } } */
-/* { dg-options "-O -pedantic-errors -march=k8 -m3dnow -msse4 -msse5 -maes -mpclmul" } */
+/* { dg-options "-O -pedantic-errors -march=k8 -m3dnow -mavx -msse5 -maes -mpclmul" } */
 
-#include <wmmintrin.h>
-#include <bmmintrin.h>
-#include <smmintrin.h>
-#include <mm3dnow.h>
+#include <x86intrin.h>
 
 int dummy;
Index: g++.dg/other/i386-3.C
===================================================================
--- g++.dg/other/i386-3.C	(revision 142738)
+++ g++.dg/other/i386-3.C	(working copy)
@@ -1,9 +1,6 @@
-/* Test that {,x,e,p,t,s,w,a,b}mmintrin.h, mm3dnow.h and mm_malloc.h are
+/* Test that {,x,e,p,t,s,w,a,b,i}mmintrin.h, mm3dnow.h and mm_malloc.h are
    usable with -O -fkeep-inline-functions.  */
 /* { dg-do compile { target i?86-*-* x86_64-*-* } } */
-/* { dg-options "-O -fkeep-inline-functions -march=k8 -m3dnow -maes -mpclmul -msse4 -msse5" } */
+/* { dg-options "-O -fkeep-inline-functions -march=k8 -m3dnow -mavx -msse5 -maes -mpclmul" } */
 
-#include <wmmintrin.h>
-#include <bmmintrin.h>
-#include <smmintrin.h>
-#include <mm3dnow.h>
+#include <x86intrin.h>