llvm-6502/test/CodeGen/X86/vselect-2.ll
Andrea Di Biagio a1e1f01699 [X86] Improved target specific combine on VSELECT dag nodes.
This patch teaches function 'transformVSELECTtoBlendVECTOR_SHUFFLE' how to
convert VSELECT dag nodes to shuffles on targets that do not have SSE4.1.
On pre-SSE4.1 targets, we can still perform blend operations using movss/movsd.

Also, removed a target specific combine that performed a premature lowering of
VSELECT nodes to target specific MOVSS/MOVSD nodes.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@222647 91177308-0d34-0410-b5e6-96231b3b80d8
2014-11-24 12:23:15 +00:00

61 lines
1.9 KiB
LLVM

; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse2 | FileCheck %s --check-prefix=SSE2
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse4.1 | FileCheck %s --check-prefix=SSE41
define <4 x i32> @test1(<4 x i32> %A, <4 x i32> %B) {
; SSE2-LABEL: test1
; SSE2: # BB#0:
; SSE2-NEXT: movsd %xmm0, %xmm1
; SSE2-NEXT: movaps %xmm1, %xmm0
; SSE2-NEXT: retq
;
; SSE41-LABEL: test1
; SSE41: # BB#0:
; SSE41-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7]
; SSE41-NEXT: retq
%select = select <4 x i1><i1 true, i1 true, i1 false, i1 false>, <4 x i32> %A, <4 x i32> %B
ret <4 x i32> %select
}
define <4 x i32> @test2(<4 x i32> %A, <4 x i32> %B) {
; SSE2-LABEL: test2
; SSE2: # BB#0:
; SSE2-NEXT: movsd %xmm1, %xmm0
; SSE2-NEXT: retq
;
; SSE41-LABEL: test2
; SSE41: # BB#0:
; SSE41-NEXT: pblendw {{.*#+}} xmm0 = xmm1[0,1,2,3],xmm0[4,5,6,7]
; SSE41-NEXT: retq
%select = select <4 x i1><i1 false, i1 false, i1 true, i1 true>, <4 x i32> %A, <4 x i32> %B
ret <4 x i32> %select
}
define <4 x float> @test3(<4 x float> %A, <4 x float> %B) {
; SSE2-LABEL: test3
; SSE2: # BB#0:
; SSE2-NEXT: movsd %xmm0, %xmm1
; SSE2-NEXT: movaps %xmm1, %xmm0
; SSE2-NEXT: retq
;
; SSE41-LABEL: test3
; SSE41: # BB#0:
; SSE41-NEXT: blendpd {{.*#+}} xmm0 = xmm0[0],xmm1[1]
; SSE41-NEXT: retq
%select = select <4 x i1><i1 true, i1 true, i1 false, i1 false>, <4 x float> %A, <4 x float> %B
ret <4 x float> %select
}
define <4 x float> @test4(<4 x float> %A, <4 x float> %B) {
; SSE2-LABEL: test4
; SSE2: # BB#0:
; SSE2-NEXT: movsd %xmm1, %xmm0
; SSE2-NEXT: retq
;
; SSE41-LABEL: test4
; SSE41: # BB#0:
; SSE41-NEXT: blendpd {{.*#+}} xmm0 = xmm1[0],xmm0[1]
; SSE41-NEXT: retq
%select = select <4 x i1><i1 false, i1 false, i1 true, i1 true>, <4 x float> %A, <4 x float> %B
ret <4 x float> %select
}