maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[X86][AVX1] Regenerate checks and add i686 triple tests for folded logical ops 

llvm-svn: 302144
This commit is contained in:
Simon Pilgrim 2017-05-04 13:00:30 +00:00
parent 6cf800a6f7
commit fbaaf25739
1 changed files with 71 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

83
llvm/test/CodeGen/X86/avx1-logical-load-folding.ll
View File

@ -1,10 +1,26 @@
; RUN: llc -O3 -disable-peephole -mcpu=corei7-avx -mattr=+avx < %s | FileCheck %s
target datalayout = "e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-apple-macosx10.9.0"
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -O3 -disable-peephole -mtriple=i686-apple-macosx10.9.0 -mcpu=corei7-avx -mattr=+avx | FileCheck %s --check-prefix=X86
; RUN: llc < %s -O3 -disable-peephole -mtriple=x86_64-apple-macosx10.9.0 -mcpu=corei7-avx -mattr=+avx | FileCheck %s --check-prefix=X64
; Function Attrs: nounwind ssp uwtable
define void @test1(float* %A, float* %C) #0 {
; X86-LABEL: test1:
; X86: ## BB#0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: vmovaps (%ecx), %ymm0
; X86-NEXT: vandps LCPI0_0, %ymm0, %ymm0
; X86-NEXT: vmovss %xmm0, (%eax)
; X86-NEXT: vzeroupper
; X86-NEXT: retl
;
; X64-LABEL: test1:
; X64: ## BB#0:
; X64-NEXT: vmovaps (%rdi), %ymm0
; X64-NEXT: vandps {{.*}}(%rip), %ymm0, %ymm0
; X64-NEXT: vmovss %xmm0, (%rsi)
; X64-NEXT: vzeroupper
; X64-NEXT: retq
%tmp1 = bitcast float* %A to <8 x float>*
%tmp2 = load <8 x float>, <8 x float>* %tmp1, align 32
%tmp3 = bitcast <8 x float> %tmp2 to <8 x i32>
@ -13,12 +29,27 @@ define void @test1(float* %A, float* %C) #0 {
%tmp6 = extractelement <8 x float> %tmp5, i32 0
store float %tmp6, float* %C
ret void
; CHECK: vandps LCPI0_0(%rip), %ymm0, %ymm0
}
; Function Attrs: nounwind ssp uwtable
define void @test2(float* %A, float* %C) #0 {
; X86-LABEL: test2:
; X86: ## BB#0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: vmovaps (%ecx), %ymm0
; X86-NEXT: vorps LCPI1_0, %ymm0, %ymm0
; X86-NEXT: vmovss %xmm0, (%eax)
; X86-NEXT: vzeroupper
; X86-NEXT: retl
;
; X64-LABEL: test2:
; X64: ## BB#0:
; X64-NEXT: vmovaps (%rdi), %ymm0
; X64-NEXT: vorps {{.*}}(%rip), %ymm0, %ymm0
; X64-NEXT: vmovss %xmm0, (%rsi)
; X64-NEXT: vzeroupper
; X64-NEXT: retq
%tmp1 = bitcast float* %A to <8 x float>*
%tmp2 = load <8 x float>, <8 x float>* %tmp1, align 32
%tmp3 = bitcast <8 x float> %tmp2 to <8 x i32>
@ -27,12 +58,27 @@ define void @test2(float* %A, float* %C) #0 {
%tmp6 = extractelement <8 x float> %tmp5, i32 0
store float %tmp6, float* %C
ret void
; CHECK: vorps LCPI1_0(%rip), %ymm0, %ymm0
}
; Function Attrs: nounwind ssp uwtable
define void @test3(float* %A, float* %C) #0 {
; X86-LABEL: test3:
; X86: ## BB#0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: vmovaps (%ecx), %ymm0
; X86-NEXT: vxorps LCPI2_0, %ymm0, %ymm0
; X86-NEXT: vmovss %xmm0, (%eax)
; X86-NEXT: vzeroupper
; X86-NEXT: retl
;
; X64-LABEL: test3:
; X64: ## BB#0:
; X64-NEXT: vmovaps (%rdi), %ymm0
; X64-NEXT: vxorps {{.*}}(%rip), %ymm0, %ymm0
; X64-NEXT: vmovss %xmm0, (%rsi)
; X64-NEXT: vzeroupper
; X64-NEXT: retq
%tmp1 = bitcast float* %A to <8 x float>*
%tmp2 = load <8 x float>, <8 x float>* %tmp1, align 32
%tmp3 = bitcast <8 x float> %tmp2 to <8 x i32>
@ -41,11 +87,26 @@ define void @test3(float* %A, float* %C) #0 {
%tmp6 = extractelement <8 x float> %tmp5, i32 0
store float %tmp6, float* %C
ret void
; CHECK: vxorps LCPI2_0(%rip), %ymm0, %ymm0
}
define void @test4(float* %A, float* %C) #0 {
; X86-LABEL: test4:
; X86: ## BB#0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: vmovaps (%ecx), %ymm0
; X86-NEXT: vandnps LCPI3_0, %ymm0, %ymm0
; X86-NEXT: vmovss %xmm0, (%eax)
; X86-NEXT: vzeroupper
; X86-NEXT: retl
;
; X64-LABEL: test4:
; X64: ## BB#0:
; X64-NEXT: vmovaps (%rdi), %ymm0
; X64-NEXT: vandnps {{.*}}(%rip), %ymm0, %ymm0
; X64-NEXT: vmovss %xmm0, (%rsi)
; X64-NEXT: vzeroupper
; X64-NEXT: retq
%tmp1 = bitcast float* %A to <8 x float>*
%tmp2 = load <8 x float>, <8 x float>* %tmp1, align 32
%tmp3 = bitcast <8 x float> %tmp2 to <8 x i32>
@ -55,6 +116,4 @@ define void @test4(float* %A, float* %C) #0 {
%tmp7 = extractelement <8 x float> %tmp6, i32 0
store float %tmp7, float * %C
ret void
;CHECK: vandnps LCPI3_0(%rip), %ymm0, %ymm0
}