[AVX]: 4 AVX intrinsic tests

["H.J. Lu" <hjl dot tools at gmail dot com>]

This patch has 4 AVX intrinsic tests.


H.J.
---
2008-04-09  H.J. Lu  <hongjiu.lu@intel.com>

	* g++.dg/other/i386-4.C: New.
	* g++.dg/other/i386-5.C: Likewise.
	* gcc.target/i386/avx-1.c: Likewise.
	* gcc.target/i386/avx-2.c: Likewise.

Index: g++.dg/other/i386-4.C
===================================================================
--- g++.dg/other/i386-4.C	(revision 0)
+++ g++.dg/other/i386-4.C	(revision 0)
@@ -0,0 +1,11 @@
+/* Test that {,x,e,p,t,s,w,g,a,b}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 -mavx -msse5 -maes -mpclmul" } */
+
+#include <wmmintrin.h>
+#include <bmmintrin.h>
+#include <gmmintrin.h>
+#include <mm3dnow.h>
+
+int dummy;
Index: g++.dg/other/i386-5.C
===================================================================
--- g++.dg/other/i386-5.C	(revision 0)
+++ g++.dg/other/i386-5.C	(revision 0)
@@ -0,0 +1,9 @@
+/* Test that {,x,e,p,t,s,w,g,a,b}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 -mavx -msse5" } */
+
+#include <wmmintrin.h>
+#include <bmmintrin.h>
+#include <gmmintrin.h>
+#include <mm3dnow.h>
Index: gcc.target/i386/avx-1.c
===================================================================
--- gcc.target/i386/avx-1.c	(revision 0)
+++ gcc.target/i386/avx-1.c	(revision 0)
@@ -0,0 +1,118 @@
+/* { dg-do compile } */
+/* { 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,g,a,b}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.  */
+
+#define extern
+#define __inline
+
+/* Following intrinsics require immediate arguments. */
+
+/* ammintrin.h */
+#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)
+
+/* gmmintrin.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)
+
+/* 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)
+
+/* smmintrin.h */
+#define __builtin_ia32_pblendw128(X, Y, M) __builtin_ia32_pblendw128 (X, Y, 1)
+#define __builtin_ia32_blendps(X, Y, M) __builtin_ia32_blendps(X, Y, 1)
+#define __builtin_ia32_blendpd(X, Y, M) __builtin_ia32_blendpd(X, Y, 1)
+#define __builtin_ia32_dpps(X, Y, M) __builtin_ia32_dpps(X, Y, 1)
+#define __builtin_ia32_dppd(X, Y, M) __builtin_ia32_dppd(X, Y, 1)
+#define __builtin_ia32_insertps128(D, S, N) __builtin_ia32_insertps128(D, S, 1)
+#define __builtin_ia32_vec_ext_v4sf(X, N) __builtin_ia32_vec_ext_v4sf(X, 1)
+#define __builtin_ia32_vec_set_v16qi(D, S, N) __builtin_ia32_vec_set_v16qi(D, S, 1)
+#define __builtin_ia32_vec_set_v4si(D, S, N) __builtin_ia32_vec_set_v4si(D, S, 1)
+#define __builtin_ia32_vec_set_v2di(D, S, N) __builtin_ia32_vec_set_v2di(D, S, 1)
+#define __builtin_ia32_vec_ext_v16qi(X, N) __builtin_ia32_vec_ext_v16qi(X, 1)
+#define __builtin_ia32_vec_ext_v4si(X, N) __builtin_ia32_vec_ext_v4si(X, 1)
+#define __builtin_ia32_vec_ext_v2di(X, N) __builtin_ia32_vec_ext_v2di(X, 1)
+#define __builtin_ia32_roundpd(V, M) __builtin_ia32_roundpd(V, 1)
+#define __builtin_ia32_roundsd(D, V, M) __builtin_ia32_roundsd(D, V, 1)
+#define __builtin_ia32_roundps(V, M) __builtin_ia32_roundps(V, 1)
+#define __builtin_ia32_roundss(D, V, M) __builtin_ia32_roundss(D, V, 1)
+#define __builtin_ia32_mpsadbw128(X, Y, M) __builtin_ia32_mpsadbw128(X, Y, 1)
+#define __builtin_ia32_pcmpistrm128(X, Y, M) \
+  __builtin_ia32_pcmpistrm128(X, Y, 1)
+#define __builtin_ia32_pcmpistri128(X, Y, M) \
+  __builtin_ia32_pcmpistri128(X, Y, 1)
+#define __builtin_ia32_pcmpestrm128(X, LX, Y, LY, M) \
+  __builtin_ia32_pcmpestrm128(X, LX, Y, LY, 1)
+#define __builtin_ia32_pcmpestri128(X, LX, Y, LY, M) \
+  __builtin_ia32_pcmpestri128(X, LX, Y, LY, 1)
+#define __builtin_ia32_pcmpistria128(X, Y, M) \
+  __builtin_ia32_pcmpistria128(X, Y, 1)
+#define __builtin_ia32_pcmpistric128(X, Y, M) \
+  __builtin_ia32_pcmpistric128(X, Y, 1)
+#define __builtin_ia32_pcmpistrio128(X, Y, M) \
+  __builtin_ia32_pcmpistrio128(X, Y, 1)
+#define __builtin_ia32_pcmpistris128(X, Y, M) \
+  __builtin_ia32_pcmpistris128(X, Y, 1)
+#define __builtin_ia32_pcmpistriz128(X, Y, M) \
+  __builtin_ia32_pcmpistriz128(X, Y, 1)
+#define __builtin_ia32_pcmpestria128(X, LX, Y, LY, M) \
+  __builtin_ia32_pcmpestria128(X, LX, Y, LY, 1)
+#define __builtin_ia32_pcmpestric128(X, LX, Y, LY, M) \
+  __builtin_ia32_pcmpestric128(X, LX, Y, LY, 1)
+#define __builtin_ia32_pcmpestrio128(X, LX, Y, LY, M) \
+  __builtin_ia32_pcmpestrio128(X, LX, Y, LY, 1)
+#define __builtin_ia32_pcmpestris128(X, LX, Y, LY, M) \
+  __builtin_ia32_pcmpestris128(X, LX, Y, LY, 1)
+#define __builtin_ia32_pcmpestriz128(X, LX, Y, LY, M) \
+  __builtin_ia32_pcmpestriz128(X, LX, Y, LY, 1)
+
+/* tmmintrin.h */
+#define __builtin_ia32_palignr128(X, Y, N) __builtin_ia32_palignr128(X, Y, 8)
+#define __builtin_ia32_palignr(X, Y, N) __builtin_ia32_palignr(X, Y, 8)
+
+/* emmintrin.h */
+#define __builtin_ia32_psrldqi128(A, B) __builtin_ia32_psrldqi128(A, 8)
+#define __builtin_ia32_pslldqi128(A, B) __builtin_ia32_pslldqi128(A, 8)
+#define __builtin_ia32_pshufhw(A, N) __builtin_ia32_pshufhw(A, 0)
+#define __builtin_ia32_pshuflw(A, N) __builtin_ia32_pshuflw(A, 0)
+#define __builtin_ia32_pshufd(A, N) __builtin_ia32_pshufd(A, 0)
+#define __builtin_ia32_vec_set_v8hi(A, D, N) \
+  __builtin_ia32_vec_set_v8hi(A, D, 0)
+#define __builtin_ia32_vec_ext_v8hi(A, N) __builtin_ia32_vec_ext_v8hi(A, 0)
+#define __builtin_ia32_shufpd(A, B, N) __builtin_ia32_shufpd(A, B, 0)
+
+/* xmmintrin.h */
+#define __builtin_prefetch(P, A, I) __builtin_prefetch(P, A, _MM_HINT_NTA)
+#define __builtin_ia32_pshufw(A, N) __builtin_ia32_pshufw(A, 0)
+#define __builtin_ia32_vec_set_v4hi(A, D, N) \
+  __builtin_ia32_vec_set_v4hi(A, D, 0)
+#define __builtin_ia32_vec_ext_v4hi(A, N) __builtin_ia32_vec_ext_v4hi(A, 0)
+#define __builtin_ia32_shufps(A, B, N) __builtin_ia32_shufps(A, B, 0)
+
+/* bmmintrin.h */
+#define __builtin_ia32_protbi(A, B) __builtin_ia32_protbi(A,1)
+#define __builtin_ia32_protwi(A, B) __builtin_ia32_protwi(A,1)
+#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 <gmmintrin.h>
+#include <mm3dnow.h>
Index: gcc.target/i386/avx-2.c
===================================================================
--- gcc.target/i386/avx-2.c	(revision 0)
+++ gcc.target/i386/avx-2.c	(revision 0)
@@ -0,0 +1,130 @@
+/* { dg-do compile } */
+/* { dg-options "-O0 -Werror-implicit-function-declaration -march=k8 -m3dnow -mavx -msse5 -maes -mpclmul" } */
+
+#include <mm_malloc.h>
+
+/* Test that the intrinsics compile without optimization.  All of them are
+   defined as inline functions in {,x,e,p,t,s,w,g,a,b}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.  */
+
+#define extern
+#define __inline
+
+#include <wmmintrin.h>
+#include <bmmintrin.h>
+#include <gmmintrin.h>
+#include <mm3dnow.h>
+
+#define _CONCAT(x,y) x ## y
+
+#define test_1(func, type, op1_type, imm)				\
+  type _CONCAT(_,func) (op1_type A, int const I)			\
+  { return func (A, imm); }
+
+#define test_1x(func, type, op1_type, imm1, imm2)			\
+  type _CONCAT(_,func) (op1_type A, int const I, int const L)		\
+  { return func (A, imm1, imm2); }
+
+#define test_2(func, type, op1_type, op2_type, imm)			\
+  type _CONCAT(_,func) (op1_type A, op2_type B, int const I)		\
+  { return func (A, B, imm); }
+
+#define test_2x(func, type, op1_type, op2_type, imm1, imm2)		\
+  type _CONCAT(_,func) (op1_type A, op2_type B, int const I, int const L) \
+  { return func (A, B, imm1, imm2); }
+
+#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)		\
+  { return func (A, B, C, D, imm); }
+
+
+/* Following intrinsics require immediate arguments.  They
+   are defined as macros for non-optimized compilations. */
+
+/* ammintrin.h */
+test_1x (_mm_extracti_si64, __m128i, __m128i, 1, 1)
+test_2x (_mm_inserti_si64, __m128i, __m128i, __m128i, 1, 1)
+
+/* gmmintrin.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)
+
+/* wmmintrin.h */
+test_1 (_mm_aeskeygenassist_si128, __m128i, __m128i, 1)
+test_2 (_mm_clmulepi64_si128, __m128i, __m128i, __m128i, 1)
+
+/* smmintrin.h */
+test_2 (_mm_blend_epi16, __m128i, __m128i, __m128i, 1)
+test_2 (_mm_blend_ps, __m128, __m128, __m128, 1)
+test_2 (_mm_blend_pd, __m128d, __m128d, __m128d, 1)
+test_2 (_mm_dp_ps, __m128, __m128, __m128, 1)
+test_2 (_mm_dp_pd, __m128d, __m128d, __m128d, 1)
+test_2 (_mm_insert_ps, __m128, __m128, __m128, 1)
+test_1 (_mm_extract_ps, int, __m128, 1)
+test_2 (_mm_insert_epi8, __m128i, __m128i, int, 1)
+test_2 (_mm_insert_epi32, __m128i, __m128i, int, 1)
+#ifdef __x86_64__
+test_2 (_mm_insert_epi64, __m128i, __m128i, long long, 1)
+#endif
+test_1 (_mm_extract_epi8, int, __m128i, 1)
+test_1 (_mm_extract_epi32, int, __m128i, 1)
+#ifdef __x86_64__
+test_1 (_mm_extract_epi64, long long, __m128i, 1)
+#endif
+test_2 (_mm_mpsadbw_epu8, __m128i, __m128i, __m128i, 1)
+test_2 (_mm_cmpistrm, __m128i, __m128i, __m128i, 1)
+test_2 (_mm_cmpistri, int, __m128i, __m128i, 1)
+test_4 (_mm_cmpestrm, __m128i, __m128i, int, __m128i, int, 1)
+test_4 (_mm_cmpestri, int, __m128i, int, __m128i, int, 1)
+test_2 (_mm_cmpistra, int, __m128i, __m128i, 1)
+test_2 (_mm_cmpistrc, int, __m128i, __m128i, 1)
+test_2 (_mm_cmpistro, int, __m128i, __m128i, 1)
+test_2 (_mm_cmpistrs, int, __m128i, __m128i, 1)
+test_2 (_mm_cmpistrz, int, __m128i, __m128i, 1)
+test_4 (_mm_cmpestra, int, __m128i, int, __m128i, int, 1)
+test_4 (_mm_cmpestrc, int, __m128i, int, __m128i, int, 1)
+test_4 (_mm_cmpestro, int, __m128i, int, __m128i, int, 1)
+test_4 (_mm_cmpestrs, int, __m128i, int, __m128i, int, 1)
+test_4 (_mm_cmpestrz, int, __m128i, int, __m128i, int, 1)
+
+/* tmmintrin.h */
+test_2 (_mm_alignr_epi8, __m128i, __m128i, __m128i, 1)
+test_2 (_mm_alignr_pi8, __m64, __m64, __m64, 1)
+
+/* emmintrin.h */
+test_2 (_mm_shuffle_pd, __m128d, __m128d, __m128d, 1)
+test_1 (_mm_srli_si128, __m128i, __m128i, 1)
+test_1 (_mm_slli_si128, __m128i, __m128i, 1)
+test_1 (_mm_extract_epi16, int, __m128i, 1)
+test_2 (_mm_insert_epi16, __m128i, __m128i, int, 1)
+test_1 (_mm_shufflehi_epi16, __m128i, __m128i, 1)
+test_1 (_mm_shufflelo_epi16, __m128i, __m128i, 1)
+test_1 (_mm_shuffle_epi32, __m128i, __m128i, 1)
+
+/* xmmintrin.h */
+test_2 (_mm_shuffle_ps, __m128, __m128, __m128, 1)
+test_1 (_mm_extract_pi16, int, __m64, 1)
+test_1 (_m_pextrw, int, __m64, 1)
+test_2 (_mm_insert_pi16, __m64, __m64, int, 1)
+test_2 (_m_pinsrw, __m64, __m64, int, 1)
+test_1 (_mm_shuffle_pi16, __m64, __m64, 1)
+test_1 (_m_pshufw, __m64, __m64, 1)
+test_1 (_mm_prefetch, void, void *, _MM_HINT_NTA)
+
+/* bmmintrin.h */
+test_1 (_mm_roti_epi8, __m128i, __m128i, 1)
+test_1 (_mm_roti_epi16, __m128i, __m128i, 1)
+test_1 (_mm_roti_epi32, __m128i, __m128i, 1)
+test_1 (_mm_roti_epi64, __m128i, __m128i, 1)