llvm-project/llvm/test/CodeGen/X86/avx1-logical-load-folding.ll

120 lines
4.5 KiB
LLVM

; 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>
%tmp4 = and <8 x i32> %tmp3, <i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647>
%tmp5 = bitcast <8 x i32> %tmp4 to <8 x float>
%tmp6 = extractelement <8 x float> %tmp5, i32 0
store float %tmp6, float* %C
ret void
}
; 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>
%tmp4 = or <8 x i32> %tmp3, <i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647>
%tmp5 = bitcast <8 x i32> %tmp4 to <8 x float>
%tmp6 = extractelement <8 x float> %tmp5, i32 0
store float %tmp6, float* %C
ret void
}
; 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>
%tmp4 = xor <8 x i32> %tmp3, <i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647>
%tmp5 = bitcast <8 x i32> %tmp4 to <8 x float>
%tmp6 = extractelement <8 x float> %tmp5, i32 0
store float %tmp6, float* %C
ret void
}
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>
%tmp4 = xor <8 x i32> %tmp3, <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1>
%tmp5 = and <8 x i32> %tmp4, <i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647>
%tmp6 = bitcast <8 x i32> %tmp5 to <8 x float>
%tmp7 = extractelement <8 x float> %tmp6, i32 0
store float %tmp7, float * %C
ret void
}