diff options
author | Bruno Cardoso Lopes <bruno.cardoso@gmail.com> | 2011-08-15 21:45:54 +0000 |
---|---|---|
committer | Bruno Cardoso Lopes <bruno.cardoso@gmail.com> | 2011-08-15 21:45:54 +0000 |
commit | cbe7feeab99395287ecafbca05a1f45e798d43f2 (patch) | |
tree | 78e99f4d4f8f24702fd51735318529455c49a454 /llvm/test/CodeGen/X86/avx-vinsertf128.ll | |
parent | 5ef35b7ce2fa88f2886f0d0a8d9c40c1e5dee09b (diff) | |
download | bcm5719-llvm-cbe7feeab99395287ecafbca05a1f45e798d43f2.tar.gz bcm5719-llvm-cbe7feeab99395287ecafbca05a1f45e798d43f2.zip |
Fix PR10656. It's only profitable to use 128-bit inserts and extracts
when AVX mode is one. Otherwise is just more work for the type
legalizer.
llvm-svn: 137661
Diffstat (limited to 'llvm/test/CodeGen/X86/avx-vinsertf128.ll')
-rw-r--r-- | llvm/test/CodeGen/X86/avx-vinsertf128.ll | 20 |
1 files changed, 20 insertions, 0 deletions
diff --git a/llvm/test/CodeGen/X86/avx-vinsertf128.ll b/llvm/test/CodeGen/X86/avx-vinsertf128.ll index b54b57b8d15..a6f258513a5 100644 --- a/llvm/test/CodeGen/X86/avx-vinsertf128.ll +++ b/llvm/test/CodeGen/X86/avx-vinsertf128.ll @@ -1,4 +1,5 @@ ; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=corei7-avx -mattr=+avx | FileCheck %s +; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=corei7-avx -mattr=+avx | FileCheck -check-prefix=CHECK-SSE %s ; CHECK-NOT: vunpck ; CHECK: vinsertf128 $1 @@ -16,3 +17,22 @@ entry: ret <4 x double> %shuffle } +declare <2 x double> @llvm.x86.sse2.min.pd(<2 x double>, <2 x double>) nounwind readnone + +declare <2 x double> @llvm.x86.sse2.min.sd(<2 x double>, <2 x double>) nounwind readnone + +; Just check that no crash happens +; CHECK-SSE: _insert_crash +define void @insert_crash() nounwind { +allocas: + %v1.i.i451 = shufflevector <4 x double> zeroinitializer, <4 x double> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef> + %ret_0a.i.i.i452 = shufflevector <4 x double> %v1.i.i451, <4 x double> undef, <2 x i32> <i32 0, i32 1> + %vret_0.i.i.i454 = tail call <2 x double> @llvm.x86.sse2.min.pd(<2 x double> %ret_0a.i.i.i452, <2 x double> undef) nounwind + %ret_val.i.i.i463 = tail call <2 x double> @llvm.x86.sse2.min.sd(<2 x double> %vret_0.i.i.i454, <2 x double> undef) nounwind + %ret.i1.i.i464 = extractelement <2 x double> %ret_val.i.i.i463, i32 0 + %double2float = fptrunc double %ret.i1.i.i464 to float + %smearinsert50 = insertelement <4 x float> undef, float %double2float, i32 3 + %blendAsInt.i503 = bitcast <4 x float> %smearinsert50 to <4 x i32> + store <4 x i32> %blendAsInt.i503, <4 x i32>* undef, align 4 + ret void +} |