llvm-6502/test/CodeGen/X86/avx-vinsertf128.ll
Bruno Cardoso Lopes 50b37c7920 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.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@137661 91177308-0d34-0410-b5e6-96231b3b80d8
2011-08-15 21:45:54 +00:00

39 lines
1.8 KiB
LLVM

; 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
define <8 x float> @A(<8 x float> %a) nounwind uwtable readnone ssp {
entry:
%shuffle = shufflevector <8 x float> %a, <8 x float> undef, <8 x i32> <i32 8, i32 8, i32 8, i32 8, i32 0, i32 1, i32 2, i32 3>
ret <8 x float> %shuffle
}
; CHECK-NOT: vunpck
; CHECK: vinsertf128 $1
define <4 x double> @B(<4 x double> %a) nounwind uwtable readnone ssp {
entry:
%shuffle = shufflevector <4 x double> %a, <4 x double> undef, <4 x i32> <i32 4, i32 4, i32 0, i32 1>
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
}