diff options
| author | Simon Pilgrim <llvm-dev@redking.me.uk> | 2016-05-23 22:13:02 +0000 |
|---|---|---|
| committer | Simon Pilgrim <llvm-dev@redking.me.uk> | 2016-05-23 22:13:02 +0000 |
| commit | 90770c7c76574b72c5807c5af87bfc6bec7078d4 (patch) | |
| tree | 12fdc931d2696a1ca603047445e916f5e088be1a /clang/test/CodeGen/builtins-x86.c | |
| parent | adcaef72382e367dcc6a12ab3980baa60b162489 (diff) | |
| download | bcm5719-llvm-90770c7c76574b72c5807c5af87bfc6bec7078d4.tar.gz bcm5719-llvm-90770c7c76574b72c5807c5af87bfc6bec7078d4.zip | |
[X86][SSE] Replace lossless i32/f32 to f64 conversion intrinsics with generic IR
Both the (V)CVTDQ2PD(Y) (i32 to f64) and (V)CVTPS2PD(Y) (f32 to f64) conversion instructions are lossless and can be safely represented as generic __builtin_convertvector calls instead of x86 intrinsics without affecting final codegen.
This patch removes the clang builtins and their use in the sse2/avx headers - a future patch will deal with removing the llvm intrinsics, but that will require a bit more work.
Differential Revision: http://reviews.llvm.org/D20528
llvm-svn: 270499
Diffstat (limited to 'clang/test/CodeGen/builtins-x86.c')
| -rw-r--r-- | clang/test/CodeGen/builtins-x86.c | 4 |
1 files changed, 0 insertions, 4 deletions
diff --git a/clang/test/CodeGen/builtins-x86.c b/clang/test/CodeGen/builtins-x86.c index 67084b4b654..8b53c631544 100644 --- a/clang/test/CodeGen/builtins-x86.c +++ b/clang/test/CodeGen/builtins-x86.c @@ -325,7 +325,6 @@ void f0() { tmp_V2LLi = __builtin_ia32_psadbw128(tmp_V16c, tmp_V16c); tmp_V2d = __builtin_ia32_sqrtpd(tmp_V2d); tmp_V2d = __builtin_ia32_sqrtsd(tmp_V2d); - tmp_V2d = __builtin_ia32_cvtdq2pd(tmp_V4i); tmp_V4f = __builtin_ia32_cvtdq2ps(tmp_V4i); tmp_V2LLi = __builtin_ia32_cvtpd2dq(tmp_V2d); tmp_V2i = __builtin_ia32_cvtpd2pi(tmp_V2d); @@ -338,7 +337,6 @@ void f0() { tmp_LLi = __builtin_ia32_cvtsd2si64(tmp_V2d); #endif tmp_V4i = __builtin_ia32_cvtps2dq(tmp_V4f); - tmp_V2d = __builtin_ia32_cvtps2pd(tmp_V4f); tmp_V4i = __builtin_ia32_cvttps2dq(tmp_V4f); (void) __builtin_ia32_clflush(tmp_vCp); (void) __builtin_ia32_lfence(); @@ -423,11 +421,9 @@ void f0() { tmp_V8f = __builtin_ia32_dpps256(tmp_V8f, tmp_V8f, 0x7); tmp_V4d = __builtin_ia32_cmppd256(tmp_V4d, tmp_V4d, 0); tmp_V8f = __builtin_ia32_cmpps256(tmp_V8f, tmp_V8f, 0); - tmp_V4d = __builtin_ia32_cvtdq2pd256(tmp_V4i); tmp_V8f = __builtin_ia32_cvtdq2ps256(tmp_V8i); tmp_V4f = __builtin_ia32_cvtpd2ps256(tmp_V4d); tmp_V8i = __builtin_ia32_cvtps2dq256(tmp_V8f); - tmp_V4d = __builtin_ia32_cvtps2pd256(tmp_V4f); tmp_V4i = __builtin_ia32_cvttpd2dq256(tmp_V4d); tmp_V4i = __builtin_ia32_cvtpd2dq256(tmp_V4d); tmp_V8i = __builtin_ia32_cvttps2dq256(tmp_V8f); |
