From 3d996e269b2a4c446a67d89d9d8b1c510168169b Mon Sep 17 00:00:00 2001 From: Simon Pilgrim Date: Tue, 17 May 2016 22:03:31 +0000 Subject: [PATCH] [X86][SSE] Tidied up MMX/SSE/SSE2 builtin tests to the correct test file git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@269852 91177308-0d34-0410-b5e6-96231b3b80d8 --- test/CodeGen/mmx-builtins.c | 10 +- test/CodeGen/sse-builtins.c | 343 +++++------------------------------ test/CodeGen/sse2-builtins.c | 54 ++++++ 3 files changed, 101 insertions(+), 306 deletions(-) diff --git a/test/CodeGen/mmx-builtins.c b/test/CodeGen/mmx-builtins.c index 44d1ea4d57..e2761f4e36 100644 --- a/test/CodeGen/mmx-builtins.c +++ b/test/CodeGen/mmx-builtins.c @@ -44,8 +44,8 @@ __m64 test_mm_add_pi32(__m64 a, __m64 b) { __m64 test_mm_add_si64(__m64 a, __m64 b) { // CHECK-LABEL: test_mm_add_si64 - // CHECK: call x86_mmx @llvm.x86.mmx.padd.q - return __builtin_ia32_paddq(a, b); + // CHECK: call x86_mmx @llvm.x86.mmx.padd.q(x86_mmx %{{.*}}, x86_mmx %{{.*}}) + return _mm_add_si64(a, b); } __m64 test_mm_adds_pi8(__m64 a, __m64 b) { @@ -315,7 +315,7 @@ int test_mm_movemask_pi8(__m64 a) { __m64 test_mm_mul_su32(__m64 a, __m64 b) { // CHECK-LABEL: test_mm_mul_su32 - // CHECK: call x86_mmx @llvm.x86.mmx.pmulu.dq + // CHECK: call x86_mmx @llvm.x86.mmx.pmulu.dq(x86_mmx %{{.*}}, x86_mmx %{{.*}}) return _mm_mul_su32(a, b); } @@ -525,8 +525,8 @@ __m64 test_mm_sub_pi32(__m64 a, __m64 b) { __m64 test_mm_sub_si64(__m64 a, __m64 b) { // CHECK-LABEL: test_mm_sub_si64 - // CHECK: call x86_mmx @llvm.x86.mmx.psub.q - return __builtin_ia32_psubq(a, b); + // CHECK: call x86_mmx @llvm.x86.mmx.psub.q(x86_mmx %{{.*}}, x86_mmx %{{.*}}) + return _mm_sub_si64(a, b); } __m64 test_mm_subs_pi8(__m64 a, __m64 b) { diff --git a/test/CodeGen/sse-builtins.c b/test/CodeGen/sse-builtins.c index 5814532dc5..51ff87f4d6 100644 --- a/test/CodeGen/sse-builtins.c +++ b/test/CodeGen/sse-builtins.c @@ -4,6 +4,48 @@ #include #include +__m128 test_mm_add_ps(__m128 A, __m128 B) { + // CHECK-LABEL: test_mm_add_ps + // CHECK: fadd <4 x float> + return _mm_add_ps(A, B); +} + +__m128 test_mm_and_ps(__m128 A, __m128 B) { + // CHECK-LABEL: test_mm_and_ps + // CHECK: and <4 x i32> %{{.*}}, %{{.*}} + return _mm_and_ps(A, B); +} + +__m128 test_mm_div_ps(__m128 A, __m128 B) { + // CHECK-LABEL: test_mm_div_ps + // CHECK: fdiv <4 x float> + return _mm_div_ps(A, B); +} + +__m128 test_mm_mul_ps(__m128 A, __m128 B) { + // CHECK-LABEL: test_mm_mul_ps + // CHECK: fmul <4 x float> + return _mm_mul_ps(A, B); +} + +__m128 test_mm_or_ps(__m128 A, __m128 B) { + // CHECK-LABEL: test_mm_or_ps + // CHECK: or <4 x i32> %{{.*}}, %{{.*}} + return _mm_or_ps(A, B); +} + +__m128 test_mm_sub_ps(__m128 A, __m128 B) { + // CHECK-LABEL: test_mm_sub_ps + // CHECK: fsub <4 x float> + return _mm_sub_ps(A, B); +} + +__m128 test_mm_xor_ps(__m128 A, __m128 B) { + // CHECK-LABEL: test_mm_xor_ps + // CHECK: xor <4 x i32> %{{.*}}, %{{.*}} + return _mm_xor_ps(A, B); +} + __m128 test_rsqrt_ss(__m128 x) { // CHECK: define {{.*}} @test_rsqrt_ss // CHECK: call <4 x float> @llvm.x86.sse.rsqrt.ss @@ -68,104 +110,6 @@ void test_store_ss(__m128 x, void* y) { _mm_store_ss(y, x); } -__m128d test_load1_pd(__m128 x, void* y) { - // CHECK: define {{.*}} @test_load1_pd - // CHECK: load double, double* {{.*}}, align 1{{$}} - return _mm_load1_pd(y); -} - -__m128d test_loadr_pd(__m128 x, void* y) { - // CHECK: define {{.*}} @test_loadr_pd - // CHECK: load <2 x double>, <2 x double>* {{.*}}, align 16{{$}} - return _mm_loadr_pd(y); -} - -__m128d test_load_sd(void* y) { - // CHECK: define {{.*}} @test_load_sd - // CHECK: load double, double* {{.*}}, align 1{{$}} - return _mm_load_sd(y); -} - -__m128d test_loadh_pd(__m128d x, void* y) { - // CHECK: define {{.*}} @test_loadh_pd - // CHECK: load double, double* {{.*}}, align 1{{$}} - return _mm_loadh_pd(x, y); -} - -__m128d test_loadl_pd(__m128d x, void* y) { - // CHECK: define {{.*}} @test_loadl_pd - // CHECK: load double, double* {{.*}}, align 1{{$}} - return _mm_loadl_pd(x, y); -} - -void test_store_sd(__m128d x, void* y) { - // CHECK-LABEL: define void @test_store_sd - // CHECK: store {{.*}} double* {{.*}}, align 1{{$}} - _mm_store_sd(y, x); -} - -void test_store1_pd(__m128d x, void* y) { - // CHECK-LABEL: define void @test_store1_pd - // CHECK: store {{.*}} double* {{.*}}, align 1{{$}} - // CHECK: store {{.*}} double* {{.*}}, align 1{{$}} - _mm_store1_pd(y, x); -} - -void test_storer_pd(__m128d x, void* y) { - // CHECK-LABEL: define void @test_storer_pd - // CHECK: store {{.*}} <2 x double>* {{.*}}, align 16{{$}} - _mm_storer_pd(y, x); -} - -void test_storeh_pd(__m128d x, void* y) { - // CHECK-LABEL: define void @test_storeh_pd - // CHECK: store {{.*}} double* {{.*}}, align 1{{$}} - _mm_storeh_pd(y, x); -} - -void test_storel_pd(__m128d x, void* y) { - // CHECK-LABEL: define void @test_storel_pd - // CHECK: store {{.*}} double* {{.*}}, align 1{{$}} - _mm_storel_pd(y, x); -} - -__m128i test_loadl_epi64(void* y) { - // CHECK: define {{.*}} @test_loadl_epi64 - // CHECK: load i64, i64* {{.*}}, align 1{{$}} - return _mm_loadl_epi64(y); -} - -void test_storel_epi64(__m128i x, void* y) { - // CHECK-LABEL: define void @test_storel_epi64 - // CHECK: store {{.*}} i64* {{.*}}, align 1{{$}} - _mm_storel_epi64(y, x); -} - -void test_stream_si32(int x, void *y) { - // CHECK-LABEL: define void @test_stream_si32 - // CHECK: store {{.*}} i32* {{.*}}, align 1, !nontemporal - _mm_stream_si32(y, x); -} - -void test_stream_si64(long long x, void *y) { - // CHECK-LABEL: define void @test_stream_si64 - // CHECK: store {{.*}} i64* {{.*}}, align 1, !nontemporal - _mm_stream_si64(y, x); -} - -void test_stream_si128(__m128i x, void *y) { - // CHECK-LABEL: define void @test_stream_si128 - // CHECK: store {{.*}} <2 x i64>* {{.*}}, align 16, !nontemporal - _mm_stream_si128(y, x); -} - -void test_extract_epi16(__m128i __a) { - // CHECK-LABEL: define void @test_extract_epi16 - // CHECK: [[x:%.*]] = and i32 %{{.*}}, 7 - // CHECK: extractelement <8 x i16> %{{.*}}, i32 [[x]] - _mm_extract_epi16(__a, 8); -} - __m128 test_mm_cmpeq_ss(__m128 __a, __m128 __b) { // CHECK-LABEL: @test_mm_cmpeq_ss // CHECK: @llvm.x86.sse.cmp.ss(<4 x float> %{{.*}}, <4 x float> %{{.*}}, i8 0) @@ -310,212 +254,9 @@ __m128 test_mm_cmpnge_ps(__m128 __a, __m128 __b) { return _mm_cmpnge_ps(__a, __b); } -__m128d test_mm_cmpeq_sd(__m128d __a, __m128d __b) { - // CHECK-LABEL: @test_mm_cmpeq_sd - // CHECK: @llvm.x86.sse2.cmp.sd(<2 x double> %{{.*}}, <2 x double> %{{.*}}, i8 0) - return _mm_cmpeq_sd(__a, __b); -} - -__m128d test_mm_cmplt_sd(__m128d __a, __m128d __b) { - // CHECK-LABEL: @test_mm_cmplt_sd - // CHECK: @llvm.x86.sse2.cmp.sd(<2 x double> %{{.*}}, <2 x double> %{{.*}}, i8 1) - return _mm_cmplt_sd(__a, __b); -} - -__m128d test_mm_cmple_sd(__m128d __a, __m128d __b) { - // CHECK-LABEL: @test_mm_cmple_sd - // CHECK: @llvm.x86.sse2.cmp.sd(<2 x double> %{{.*}}, <2 x double> %{{.*}}, i8 2) - return _mm_cmple_sd(__a, __b); -} - -__m128d test_mm_cmpunord_sd(__m128d __a, __m128d __b) { - // CHECK-LABEL: @test_mm_cmpunord_sd - // CHECK: @llvm.x86.sse2.cmp.sd(<2 x double> %{{.*}}, <2 x double> %{{.*}}, i8 3) - return _mm_cmpunord_sd(__a, __b); -} - -__m128d test_mm_cmpneq_sd(__m128d __a, __m128d __b) { - // CHECK-LABEL: @test_mm_cmpneq_sd - // CHECK: @llvm.x86.sse2.cmp.sd(<2 x double> %{{.*}}, <2 x double> %{{.*}}, i8 4) - return _mm_cmpneq_sd(__a, __b); -} - -__m128d test_mm_cmpnlt_sd(__m128d __a, __m128d __b) { - // CHECK-LABEL: @test_mm_cmpnlt_sd - // CHECK: @llvm.x86.sse2.cmp.sd(<2 x double> %{{.*}}, <2 x double> %{{.*}}, i8 5) - return _mm_cmpnlt_sd(__a, __b); -} - -__m128d test_mm_cmpnle_sd(__m128d __a, __m128d __b) { - // CHECK-LABEL: @test_mm_cmpnle_sd - // CHECK: @llvm.x86.sse2.cmp.sd(<2 x double> %{{.*}}, <2 x double> %{{.*}}, i8 6) - return _mm_cmpnle_sd(__a, __b); -} - -__m128d test_mm_cmpord_sd(__m128d __a, __m128d __b) { - // CHECK-LABEL: @test_mm_cmpord_sd - // CHECK: @llvm.x86.sse2.cmp.sd(<2 x double> %{{.*}}, <2 x double> %{{.*}}, i8 7) - return _mm_cmpord_sd(__a, __b); -} - -__m128d test_mm_cmpgt_sd(__m128d __a, __m128d __b) { - // CHECK-LABEL: @test_mm_cmpgt_sd - // CHECK: @llvm.x86.sse2.cmp.sd(<2 x double> %{{.*}}, <2 x double> %{{.*}}, i8 1) - return _mm_cmpgt_sd(__a, __b); -} - -__m128d test_mm_cmpge_sd(__m128d __a, __m128d __b) { - // CHECK-LABEL: @test_mm_cmpge_sd - // CHECK: @llvm.x86.sse2.cmp.sd(<2 x double> %{{.*}}, <2 x double> %{{.*}}, i8 2) - return _mm_cmpge_sd(__a, __b); -} - -__m128d test_mm_cmpngt_sd(__m128d __a, __m128d __b) { - // CHECK-LABEL: @test_mm_cmpngt_sd - // CHECK: @llvm.x86.sse2.cmp.sd(<2 x double> %{{.*}}, <2 x double> %{{.*}}, i8 5) - return _mm_cmpngt_sd(__a, __b); -} - -__m128d test_mm_cmpnge_sd(__m128d __a, __m128d __b) { - // CHECK-LABEL: @test_mm_cmpnge_sd - // CHECK: @llvm.x86.sse2.cmp.sd(<2 x double> %{{.*}}, <2 x double> %{{.*}}, i8 6) - return _mm_cmpnge_sd(__a, __b); -} - -__m128d test_mm_cmpeq_pd(__m128d __a, __m128d __b) { - // CHECK-LABEL: @test_mm_cmpeq_pd - // CHECK: @llvm.x86.sse2.cmp.pd(<2 x double> %{{.*}}, <2 x double> %{{.*}}, i8 0) - return _mm_cmpeq_pd(__a, __b); -} - -__m128d test_mm_cmplt_pd(__m128d __a, __m128d __b) { - // CHECK-LABEL: @test_mm_cmplt_pd - // CHECK: @llvm.x86.sse2.cmp.pd(<2 x double> %{{.*}}, <2 x double> %{{.*}}, i8 1) - return _mm_cmplt_pd(__a, __b); -} - -__m128d test_mm_cmple_pd(__m128d __a, __m128d __b) { - // CHECK-LABEL: @test_mm_cmple_pd - // CHECK: @llvm.x86.sse2.cmp.pd(<2 x double> %{{.*}}, <2 x double> %{{.*}}, i8 2) - return _mm_cmple_pd(__a, __b); -} - -__m128d test_mm_cmpunord_pd(__m128d __a, __m128d __b) { - // CHECK-LABEL: @test_mm_cmpunord_pd - // CHECK: @llvm.x86.sse2.cmp.pd(<2 x double> %{{.*}}, <2 x double> %{{.*}}, i8 3) - return _mm_cmpunord_pd(__a, __b); -} - -__m128d test_mm_cmpneq_pd(__m128d __a, __m128d __b) { - // CHECK-LABEL: @test_mm_cmpneq_pd - // CHECK: @llvm.x86.sse2.cmp.pd(<2 x double> %{{.*}}, <2 x double> %{{.*}}, i8 4) - return _mm_cmpneq_pd(__a, __b); -} - -__m128d test_mm_cmpnlt_pd(__m128d __a, __m128d __b) { - // CHECK-LABEL: @test_mm_cmpnlt_pd - // CHECK: @llvm.x86.sse2.cmp.pd(<2 x double> %{{.*}}, <2 x double> %{{.*}}, i8 5) - return _mm_cmpnlt_pd(__a, __b); -} - -__m128d test_mm_cmpnle_pd(__m128d __a, __m128d __b) { - // CHECK-LABEL: @test_mm_cmpnle_pd - // CHECK: @llvm.x86.sse2.cmp.pd(<2 x double> %{{.*}}, <2 x double> %{{.*}}, i8 6) - return _mm_cmpnle_pd(__a, __b); -} - -__m128d test_mm_cmpord_pd(__m128d __a, __m128d __b) { - // CHECK-LABEL: @test_mm_cmpord_pd - // CHECK: @llvm.x86.sse2.cmp.pd(<2 x double> %{{.*}}, <2 x double> %{{.*}}, i8 7) - return _mm_cmpord_pd(__a, __b); -} - -__m128d test_mm_cmpgt_pd(__m128d __a, __m128d __b) { - // CHECK-LABEL: @test_mm_cmpgt_pd - // CHECK: @llvm.x86.sse2.cmp.pd(<2 x double> %{{.*}}, <2 x double> %{{.*}}, i8 1) - return _mm_cmpgt_pd(__a, __b); -} - -__m128d test_mm_cmpge_pd(__m128d __a, __m128d __b) { - // CHECK-LABEL: @test_mm_cmpge_pd - // CHECK: @llvm.x86.sse2.cmp.pd(<2 x double> %{{.*}}, <2 x double> %{{.*}}, i8 2) - return _mm_cmpge_pd(__a, __b); -} - -__m128d test_mm_cmpngt_pd(__m128d __a, __m128d __b) { - // CHECK-LABEL: @test_mm_cmpngt_pd - // CHECK: @llvm.x86.sse2.cmp.pd(<2 x double> %{{.*}}, <2 x double> %{{.*}}, i8 5) - return _mm_cmpngt_pd(__a, __b); -} - -__m128d test_mm_cmpnge_pd(__m128d __a, __m128d __b) { - // CHECK-LABEL: @test_mm_cmpnge_pd - // CHECK: @llvm.x86.sse2.cmp.pd(<2 x double> %{{.*}}, <2 x double> %{{.*}}, i8 6) - return _mm_cmpnge_pd(__a, __b); -} - -__m128i test_mm_slli_si128(__m128 a) { - // CHECK-LABEL: @test_mm_slli_si128 - // CHECK: shufflevector <16 x i8> {{.*}}, <16 x i8> {{.*}}, <16 x i32> - return _mm_slli_si128(a, 5); -} - -__m128i test_mm_bslli_si128(__m128 a) { - // CHECK-LABEL: @test_mm_bslli_si128 - // CHECK: shufflevector <16 x i8> {{.*}}, <16 x i8> {{.*}}, <16 x i32> - return _mm_bslli_si128(a, 5); -} - -__m128i test_mm_srli_si128(__m128 a) { - // CHECK-LABEL: @test_mm_srli_si128 - // CHECK: shufflevector <16 x i8> {{.*}}, <16 x i8> {{.*}}, <16 x i32> - return _mm_srli_si128(a, 5); -} - -__m128i test_mm_bsrli_si128(__m128 a) { - // CHECK-LABEL: @test_mm_bsrli_si128 - // CHECK: shufflevector <16 x i8> {{.*}}, <16 x i8> {{.*}}, <16 x i32> - return _mm_bsrli_si128(a, 5); -} - __m128 test_mm_undefined_ps() { // CHECK-LABEL: @test_mm_undefined_ps // CHECK: ret <4 x float> undef return _mm_undefined_ps(); } -__m128d test_mm_undefined_pd() { - // CHECK-LABEL: @test_mm_undefined_pd - // CHECK: ret <2 x double> undef - return _mm_undefined_pd(); -} - -__m128i test_mm_undefined_si128() { - // CHECK-LABEL: @test_mm_undefined_si128 - // CHECK: ret <2 x i64> undef - return _mm_undefined_si128(); -} - -__m64 test_mm_add_si64(__m64 __a, __m64 __b) { - // CHECK-LABEL: @test_mm_add_si64 - // CHECK @llvm.x86.mmx.padd.q(x86_mmx %{{.*}}, x86_mmx %{{.*}}) - return _mm_add_si64(__a, __b); -} - -__m64 test_mm_sub_si64(__m64 __a, __m64 __b) { - // CHECK-LABEL: @test_mm_sub_si64 - // CHECK @llvm.x86.mmx.psub.q(x86_mmx %{{.*}}, x86_mmx %{{.*}}) - return _mm_sub_si64(__a, __b); -} - -__m64 test_mm_mul_su32(__m64 __a, __m64 __b) { - // CHECK-LABEL: @test_mm_mul_su32 - // CHECK @llvm.x86.mmx.pmulu.dq(x86_mmx %{{.*}}, x86_mmx %{{.*}}) - return _mm_mul_su32(__a, __b); -} - -void test_mm_pause() { - // CHECK-LABEL: @test_mm_pause - // CHECK @llvm.x86.sse2.pause() - return _mm_pause(); -} diff --git a/test/CodeGen/sse2-builtins.c b/test/CodeGen/sse2-builtins.c index 4ceb93abfc..0caa4bfca3 100644 --- a/test/CodeGen/sse2-builtins.c +++ b/test/CodeGen/sse2-builtins.c @@ -536,9 +536,27 @@ __m128d test_mm_load1_pd(double const* A) { __m128d test_mm_loadh_pd(__m128d x, void* y) { // CHECK-LABEL: test_mm_loadh_pd // CHECK: load double, double* %{{.*}}, align 1{{$}} + // CHECK: insertelement <2 x double> %{{.*}}, double %{{.*}}, i32 1 return _mm_loadh_pd(x, y); } +__m128i test_mm_loadl_epi64(__m128i* y) { + // CHECK: test_mm_loadl_epi64 + // CHECK: load i64, i64* {{.*}}, align 1{{$}} + // CHECK: insertelement <2 x i64> undef, i64 {{.*}}, i32 0 + // CHECK: insertelement <2 x i64> {{.*}}, i64 0, i32 1 + return _mm_loadl_epi64(y); +} + +__m128d test_mm_loadl_pd(__m128d x, void* y) { + // CHECK-LABEL: test_mm_loadl_pd + // CHECK: load double, double* %{{.*}}, align 1{{$}} + // CHECK: insertelement <2 x double> undef, double %{{.*}}, i32 0 + // CHECK: extractelement <2 x double> %{{.*}}, i32 1 + // CHECK: insertelement <2 x double> %{{.*}}, double %{{.*}}, i32 1 + return _mm_loadl_pd(x, y); +} + __m128d test_mm_loadr_pd(double const* A) { // CHECK-LABEL: test_mm_loadr_pd // CHECK: load <2 x double>, <2 x double>* %{{.*}}, align 16 @@ -888,18 +906,42 @@ void test_mm_store_si128(__m128i* A, __m128i B) { _mm_store_si128(A, B); } +void test_mm_store1_pd(__m128d x, void* y) { + // CHECK-LABEL: test_mm_store1_pd + // CHECK: extractelement <2 x double> %{{.*}}, i32 0 + // CHECK: store {{.*}} double* {{.*}}, align 1{{$}} + // CHECK: store {{.*}} double* {{.*}}, align 1{{$}} + _mm_store1_pd(y, x); +} + void test_mm_storeh_pd(double* A, __m128d B) { // CHECK-LABEL: test_mm_storeh_pd + // CHECK: extractelement <2 x double> %{{.*}}, i32 1 // CHECK: store double %{{.*}}, double* %{{.*}}, align 1 _mm_storeh_pd(A, B); } +void test_mm_storel_epi64(__m128i x, void* y) { + // CHECK-LABEL: test_mm_storel_epi64 + // CHECK: extractelement <2 x i64> %{{.*}}, i32 0 + // CHECK: store {{.*}} i64* {{.*}}, align 1{{$}} + _mm_storel_epi64(y, x); +} + void test_mm_storel_pd(double* A, __m128d B) { // CHECK-LABEL: test_mm_storel_pd + // CHECK: extractelement <2 x double> %{{.*}}, i32 0 // CHECK: store double %{{.*}}, double* %{{.*}}, align 1 _mm_storel_pd(A, B); } +void test_mm_storer_pd(__m128d A, double* B) { + // CHECK-LABEL: test_mm_storer_pd + // CHECK: shufflevector <2 x double> {{.*}}, <2 x double> {{.*}}, <2 x i32> + // CHECK: store {{.*}} <2 x double>* {{.*}}, align 16{{$}} + _mm_storer_pd(B, A); +} + void test_mm_storeu_pd(double* A, __m128d B) { // CHECK-LABEL: test_mm_storeu_pd // CHECK: store <2 x double> %{{.*}}, <2 x double>* %{{.*}}, align 1 @@ -1032,6 +1074,18 @@ int test_mm_ucomineq_sd(__m128d A, __m128d B) { return _mm_ucomineq_sd(A, B); } +__m128d test_mm_undefined_pd() { + // CHECK-LABEL: @test_mm_undefined_pd + // CHECK: ret <2 x double> undef + return _mm_undefined_pd(); +} + +__m128i test_mm_undefined_si128() { + // CHECK-LABEL: @test_mm_undefined_si128 + // CHECK: ret <2 x i64> undef + return _mm_undefined_si128(); +} + __m128i test_mm_unpackhi_epi8(__m128i A, __m128i B) { // CHECK-LABEL: test_mm_unpackhi_epi8 // CHECK: shufflevector <16 x i8> %{{.*}}, <16 x i8> %{{.*}}, <16 x i32> -- 2.40.0