058602372e
Reduces codesize - make use of free PS<->PD domain transfers (like we do in many other places) and replace a suitable BLENDPS mask with MOVSD if OptSize or the scheduler prefers it
72 lines
2.4 KiB
LLVM
72 lines
2.4 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse2 | FileCheck %s --check-prefixes=SSE,SSE2
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse4.1 | FileCheck %s --check-prefixes=SSE,SSE41
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s --check-prefixes=AVX
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefixes=AVX
|
|
|
|
define <4 x i32> @test1(<4 x i32> %A, <4 x i32> %B) {
|
|
; SSE2-LABEL: test1:
|
|
; SSE2: # %bb.0:
|
|
; SSE2-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3]
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; SSE41-LABEL: test1:
|
|
; SSE41: # %bb.0:
|
|
; SSE41-NEXT: blendps {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3]
|
|
; SSE41-NEXT: retq
|
|
;
|
|
; AVX-LABEL: test1:
|
|
; AVX: # %bb.0:
|
|
; AVX-NEXT: vblendps {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3]
|
|
; AVX-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) {
|
|
; SSE-LABEL: test2:
|
|
; SSE: # %bb.0:
|
|
; SSE-NEXT: movsd {{.*#+}} xmm0 = xmm1[0],xmm0[1]
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX-LABEL: test2:
|
|
; AVX: # %bb.0:
|
|
; AVX-NEXT: vblendps {{.*#+}} xmm0 = xmm1[0,1],xmm0[2,3]
|
|
; AVX-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: shufps {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3]
|
|
; SSE2-NEXT: retq
|
|
;
|
|
; SSE41-LABEL: test3:
|
|
; SSE41: # %bb.0:
|
|
; SSE41-NEXT: blendps {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3]
|
|
; SSE41-NEXT: retq
|
|
;
|
|
; AVX-LABEL: test3:
|
|
; AVX: # %bb.0:
|
|
; AVX-NEXT: vmovsd {{.*#+}} xmm0 = xmm0[0],xmm1[1]
|
|
; AVX-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) {
|
|
; SSE-LABEL: test4:
|
|
; SSE: # %bb.0:
|
|
; SSE-NEXT: movsd {{.*#+}} xmm0 = xmm1[0],xmm0[1]
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX-LABEL: test4:
|
|
; AVX: # %bb.0:
|
|
; AVX-NEXT: vmovsd {{.*#+}} xmm0 = xmm1[0],xmm0[1]
|
|
; AVX-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
|
|
}
|