r248092 - [X86][SSE] Replace 128-bit SSE41 PMOVSX intrinsics with native IR
Simon Pilgrim via cfe-commits
cfe-commits at lists.llvm.org
Sat Sep 19 08:12:39 PDT 2015
Author: rksimon
Date: Sat Sep 19 10:12:38 2015
New Revision: 248092
URL: http://llvm.org/viewvc/llvm-project?rev=248092&view=rev
Log:
[X86][SSE] Replace 128-bit SSE41 PMOVSX intrinsics with native IR
128-bit vector integer sign extensions correctly lower to the pmovsx instructions even for debug builds.
This patch removes the builtins and reimplements the _mm_cvtepi*_epi* intrinsics __using builtin_shufflevector (to extract the bottom most subvector) and __builtin_convertvector (to actually perform the sign extension).
Differential Revision: http://reviews.llvm.org/D12835
Modified:
cfe/trunk/include/clang/Basic/BuiltinsX86.def
cfe/trunk/lib/Headers/smmintrin.h
cfe/trunk/test/CodeGen/builtins-x86.c
cfe/trunk/test/CodeGen/sse41-builtins.c
Modified: cfe/trunk/include/clang/Basic/BuiltinsX86.def
URL: http://llvm.org/viewvc/llvm-project/cfe/trunk/include/clang/Basic/BuiltinsX86.def?rev=248092&r1=248091&r2=248092&view=diff
==============================================================================
--- cfe/trunk/include/clang/Basic/BuiltinsX86.def (original)
+++ cfe/trunk/include/clang/Basic/BuiltinsX86.def Sat Sep 19 10:12:38 2015
@@ -376,12 +376,6 @@ TARGET_BUILTIN(__builtin_ia32_pminsb128,
TARGET_BUILTIN(__builtin_ia32_pminsd128, "V4iV4iV4i", "", "sse4.1")
TARGET_BUILTIN(__builtin_ia32_pminud128, "V4iV4iV4i", "", "sse4.1")
TARGET_BUILTIN(__builtin_ia32_pminuw128, "V8sV8sV8s", "", "sse4.1")
-TARGET_BUILTIN(__builtin_ia32_pmovsxbd128, "V4iV16c", "", "sse4.1")
-TARGET_BUILTIN(__builtin_ia32_pmovsxbq128, "V2LLiV16c", "", "sse4.1")
-TARGET_BUILTIN(__builtin_ia32_pmovsxbw128, "V8sV16c", "", "sse4.1")
-TARGET_BUILTIN(__builtin_ia32_pmovsxdq128, "V2LLiV4i", "", "sse4.1")
-TARGET_BUILTIN(__builtin_ia32_pmovsxwd128, "V4iV8s", "", "sse4.1")
-TARGET_BUILTIN(__builtin_ia32_pmovsxwq128, "V2LLiV8s", "", "sse4.1")
TARGET_BUILTIN(__builtin_ia32_pmovzxbd128, "V4iV16c", "", "sse4.1")
TARGET_BUILTIN(__builtin_ia32_pmovzxbq128, "V2LLiV16c", "", "sse4.1")
TARGET_BUILTIN(__builtin_ia32_pmovzxbw128, "V8sV16c", "", "sse4.1")
Modified: cfe/trunk/lib/Headers/smmintrin.h
URL: http://llvm.org/viewvc/llvm-project/cfe/trunk/lib/Headers/smmintrin.h?rev=248092&r1=248091&r2=248092&view=diff
==============================================================================
--- cfe/trunk/lib/Headers/smmintrin.h (original)
+++ cfe/trunk/lib/Headers/smmintrin.h Sat Sep 19 10:12:38 2015
@@ -286,37 +286,37 @@ _mm_cmpeq_epi64(__m128i __V1, __m128i __
static __inline__ __m128i __DEFAULT_FN_ATTRS
_mm_cvtepi8_epi16(__m128i __V)
{
- return (__m128i) __builtin_ia32_pmovsxbw128((__v16qi) __V);
+ return (__m128i)__builtin_convertvector(__builtin_shufflevector((__v16qi)__V, (__v16qi)__V, 0, 1, 2, 3, 4, 5, 6, 7), __v8hi);
}
static __inline__ __m128i __DEFAULT_FN_ATTRS
_mm_cvtepi8_epi32(__m128i __V)
{
- return (__m128i) __builtin_ia32_pmovsxbd128((__v16qi) __V);
+ return (__m128i)__builtin_convertvector(__builtin_shufflevector((__v16qi)__V, (__v16qi)__V, 0, 1, 2, 3), __v4si);
}
static __inline__ __m128i __DEFAULT_FN_ATTRS
_mm_cvtepi8_epi64(__m128i __V)
{
- return (__m128i) __builtin_ia32_pmovsxbq128((__v16qi) __V);
+ return (__m128i)__builtin_convertvector(__builtin_shufflevector((__v16qi)__V, (__v16qi)__V, 0, 1), __v2di);
}
static __inline__ __m128i __DEFAULT_FN_ATTRS
_mm_cvtepi16_epi32(__m128i __V)
{
- return (__m128i) __builtin_ia32_pmovsxwd128((__v8hi) __V);
+ return (__m128i)__builtin_convertvector(__builtin_shufflevector((__v8hi)__V, (__v8hi)__V, 0, 1, 2, 3), __v4si);
}
static __inline__ __m128i __DEFAULT_FN_ATTRS
_mm_cvtepi16_epi64(__m128i __V)
{
- return (__m128i) __builtin_ia32_pmovsxwq128((__v8hi)__V);
+ return (__m128i)__builtin_convertvector(__builtin_shufflevector((__v8hi)__V, (__v8hi)__V, 0, 1), __v2di);
}
static __inline__ __m128i __DEFAULT_FN_ATTRS
_mm_cvtepi32_epi64(__m128i __V)
{
- return (__m128i) __builtin_ia32_pmovsxdq128((__v4si)__V);
+ return (__m128i)__builtin_convertvector(__builtin_shufflevector((__v4si)__V, (__v4si)__V, 0, 1), __v2di);
}
/* SSE4 Packed Integer Zero-Extension. */
Modified: cfe/trunk/test/CodeGen/builtins-x86.c
URL: http://llvm.org/viewvc/llvm-project/cfe/trunk/test/CodeGen/builtins-x86.c?rev=248092&r1=248091&r2=248092&view=diff
==============================================================================
--- cfe/trunk/test/CodeGen/builtins-x86.c (original)
+++ cfe/trunk/test/CodeGen/builtins-x86.c Sat Sep 19 10:12:38 2015
@@ -372,12 +372,6 @@ void f0() {
tmp_V4i = __builtin_ia32_pminsd128(tmp_V4i, tmp_V4i);
tmp_V4i = __builtin_ia32_pminud128(tmp_V4i, tmp_V4i);
tmp_V8s = __builtin_ia32_pminuw128(tmp_V8s, tmp_V8s);
- tmp_V4i = __builtin_ia32_pmovsxbd128(tmp_V16c);
- tmp_V2LLi = __builtin_ia32_pmovsxbq128(tmp_V16c);
- tmp_V8s = __builtin_ia32_pmovsxbw128(tmp_V16c);
- tmp_V2LLi = __builtin_ia32_pmovsxdq128(tmp_V4i);
- tmp_V4i = __builtin_ia32_pmovsxwd128(tmp_V8s);
- tmp_V2LLi = __builtin_ia32_pmovsxwq128(tmp_V8s);
tmp_V4i = __builtin_ia32_pmovzxbd128(tmp_V16c);
tmp_V2LLi = __builtin_ia32_pmovzxbq128(tmp_V16c);
tmp_V8s = __builtin_ia32_pmovzxbw128(tmp_V16c);
Modified: cfe/trunk/test/CodeGen/sse41-builtins.c
URL: http://llvm.org/viewvc/llvm-project/cfe/trunk/test/CodeGen/sse41-builtins.c?rev=248092&r1=248091&r2=248092&view=diff
==============================================================================
--- cfe/trunk/test/CodeGen/sse41-builtins.c (original)
+++ cfe/trunk/test/CodeGen/sse41-builtins.c Sat Sep 19 10:12:38 2015
@@ -86,42 +86,42 @@ __m128i test_mm_cmpeq_epi64(__m128i A, _
__m128i test_mm_cvtepi8_epi16(__m128i a) {
// CHECK-LABEL: test_mm_cvtepi8_epi16
- // CHECK: call <8 x i16> @llvm.x86.sse41.pmovsxbw(<16 x i8> {{.*}})
+ // CHECK: sext <8 x i8> {{.*}} to <8 x i16>
// CHECK-ASM: pmovsxbw %xmm{{.*}}, %xmm{{.*}}
return _mm_cvtepi8_epi16(a);
}
__m128i test_mm_cvtepi8_epi32(__m128i a) {
// CHECK-LABEL: test_mm_cvtepi8_epi32
- // CHECK: call <4 x i32> @llvm.x86.sse41.pmovsxbd(<16 x i8> {{.*}})
+ // CHECK: sext <4 x i8> {{.*}} to <4 x i32>
// CHECK-ASM: pmovsxbd %xmm{{.*}}, %xmm{{.*}}
return _mm_cvtepi8_epi32(a);
}
__m128i test_mm_cvtepi8_epi64(__m128i a) {
// CHECK-LABEL: test_mm_cvtepi8_epi64
- // CHECK: call <2 x i64> @llvm.x86.sse41.pmovsxbq(<16 x i8> {{.*}})
+ // CHECK: sext <2 x i8> {{.*}} to <2 x i64>
// CHECK-ASM: pmovsxbq %xmm{{.*}}, %xmm{{.*}}
return _mm_cvtepi8_epi64(a);
}
__m128i test_mm_cvtepi16_epi32(__m128i a) {
// CHECK-LABEL: test_mm_cvtepi16_epi32
- // CHECK: call <4 x i32> @llvm.x86.sse41.pmovsxwd(<8 x i16> {{.*}})
+ // CHECK: sext <4 x i16> {{.*}} to <4 x i32>
// CHECK-ASM: pmovsxwd %xmm{{.*}}, %xmm{{.*}}
return _mm_cvtepi16_epi32(a);
}
__m128i test_mm_cvtepi16_epi64(__m128i a) {
// CHECK-LABEL: test_mm_cvtepi16_epi64
- // CHECK: call <2 x i64> @llvm.x86.sse41.pmovsxwq(<8 x i16> {{.*}})
+ // CHECK: sext <2 x i16> {{.*}} to <2 x i64>
// CHECK-ASM: pmovsxwq %xmm{{.*}}, %xmm{{.*}}
return _mm_cvtepi16_epi64(a);
}
__m128i test_mm_cvtepi32_epi64(__m128i a) {
// CHECK-LABEL: test_mm_cvtepi32_epi64
- // CHECK: call <2 x i64> @llvm.x86.sse41.pmovsxdq(<4 x i32> {{.*}})
+ // CHECK: sext <2 x i32> {{.*}} to <2 x i64>
// CHECK-ASM: pmovsxdq %xmm{{.*}}, %xmm{{.*}}
return _mm_cvtepi32_epi64(a);
}
More information about the cfe-commits
mailing list