OSchip
/
llvm-project
mirror of https://github.com/THU-DSP-LAB/llvm-project.git
13
0
Fork 6
Code Issues Packages Projects Releases Wiki Activity

[x86] regenerate checks; NFC 

llvm-svn: 296883
This commit is contained in:
Sanjay Patel 2017-03-03 16:58:51 +00:00
parent e938a152c5
commit 1716aa45f1
1 changed files with 24 additions and 32 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

56
llvm/test/CodeGen/X86/sse41.ll
View File

@ -1,3 +1,4 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=i686-apple-darwin9 -mattr=sse4.1 -mcpu=penryn | FileCheck %s --check-prefix=X32
; RUN: llc < %s -mtriple=x86_64-apple-darwin9 -mattr=sse4.1 -mcpu=penryn | FileCheck %s --check-prefix=X64
@ -793,12 +794,12 @@ define <4 x float> @insertps_from_vector_load(<4 x float> %a, <4 x float>* nocap
; X32-LABEL: insertps_from_vector_load:
; X32: ## BB#0:
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; X32-NEXT: insertps $48, (%{{...}}), {{.*#+}} xmm0 = xmm0[0,1,2],mem[0]
; X32-NEXT: insertps {{.*#+}} xmm0 = xmm0[0,1,2],mem[0]
; X32-NEXT: retl
;
; X64-LABEL: insertps_from_vector_load:
; X64: ## BB#0:
; X64-NEXT: insertps $48, (%{{...}}), {{.*#+}} xmm0 = xmm0[0,1,2],mem[0]
; X64-NEXT: insertps {{.*#+}} xmm0 = xmm0[0,1,2],mem[0]
; X64-NEXT: retq
%1 = load <4 x float>, <4 x float>* %pb, align 16
%2 = tail call <4 x float> @llvm.x86.sse41.insertps(<4 x float> %a, <4 x float> %1, i32 48)
@ -811,12 +812,12 @@ define <4 x float> @insertps_from_vector_load_offset(<4 x float> %a, <4 x float>
; X32-LABEL: insertps_from_vector_load_offset:
; X32: ## BB#0:
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; X32-NEXT: insertps $32, 4(%{{...}}), {{.*#+}} xmm0 = xmm0[0,1],mem[0],xmm0[3]
; X32-NEXT: insertps {{.*#+}} xmm0 = xmm0[0,1],mem[0],xmm0[3]
; X32-NEXT: retl
;
; X64-LABEL: insertps_from_vector_load_offset:
; X64: ## BB#0:
; X64-NEXT: insertps $32, 4(%{{...}}), {{.*#+}} xmm0 = xmm0[0,1],mem[0],xmm0[3]
; X64-NEXT: insertps {{.*#+}} xmm0 = xmm0[0,1],mem[0],xmm0[3]
; X64-NEXT: retq
%1 = load <4 x float>, <4 x float>* %pb, align 16
%2 = tail call <4 x float> @llvm.x86.sse41.insertps(<4 x float> %a, <4 x float> %1, i32 96)
@ -830,13 +831,13 @@ define <4 x float> @insertps_from_vector_load_offset_2(<4 x float> %a, <4 x floa
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; X32-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X32-NEXT: shll $4, %ecx
; X32-NEXT: insertps $0, 12(%{{...}},%{{...}}), {{.*#+}} xmm0 = mem[0],xmm0[1,2,3]
; X32-NEXT: insertps {{.*#+}} xmm0 = mem[0],xmm0[1,2,3]
; X32-NEXT: retl
;
; X64-LABEL: insertps_from_vector_load_offset_2:
; X64: ## BB#0:
; X64-NEXT: shlq $4, %rsi
; X64-NEXT: insertps $0, 12(%{{...}},%{{...}}), {{.*#+}} xmm0 = mem[0],xmm0[1,2,3]
; X64-NEXT: insertps {{.*#+}} xmm0 = mem[0],xmm0[1,2,3]
; X64-NEXT: retq
%1 = getelementptr inbounds <4 x float>, <4 x float>* %pb, i64 %index
%2 = load <4 x float>, <4 x float>* %1, align 16
@ -992,15 +993,14 @@ define void @insertps_pr20411(<4 x i32> %shuffle109, <4 x i32> %shuffle116, i32*
define <4 x float> @insertps_4(<4 x float> %A, <4 x float> %B) {
; X32-LABEL: insertps_4:
; X32: ## BB#0: ## %entry
; X32: ## BB#0:
; X32-NEXT: insertps {{.*#+}} xmm0 = xmm0[0],zero,xmm1[2],zero
; X32-NEXT: retl
;
; X64-LABEL: insertps_4:
; X64: ## BB#0: ## %entry
; X64: ## BB#0:
; X64-NEXT: insertps {{.*#+}} xmm0 = xmm0[0],zero,xmm1[2],zero
; X64-NEXT: retq
entry:
%vecext = extractelement <4 x float> %A, i32 0
%vecinit = insertelement <4 x float> undef, float %vecext, i32 0
%vecinit1 = insertelement <4 x float> %vecinit, float 0.000000e+00, i32 1
@ -1012,15 +1012,14 @@ entry:
define <4 x float> @insertps_5(<4 x float> %A, <4 x float> %B) {
; X32-LABEL: insertps_5:
; X32: ## BB#0: ## %entry
; X32: ## BB#0:
; X32-NEXT: insertps {{.*#+}} xmm0 = xmm0[0],xmm1[1],zero,zero
; X32-NEXT: retl
;
; X64-LABEL: insertps_5:
; X64: ## BB#0: ## %entry
; X64: ## BB#0:
; X64-NEXT: insertps {{.*#+}} xmm0 = xmm0[0],xmm1[1],zero,zero
; X64-NEXT: retq
entry:
%vecext = extractelement <4 x float> %A, i32 0
%vecinit = insertelement <4 x float> undef, float %vecext, i32 0
%vecext1 = extractelement <4 x float> %B, i32 1
@ -1032,15 +1031,14 @@ entry:
define <4 x float> @insertps_6(<4 x float> %A, <4 x float> %B) {
; X32-LABEL: insertps_6:
; X32: ## BB#0: ## %entry
; X32: ## BB#0:
; X32-NEXT: insertps {{.*#+}} xmm0 = zero,xmm0[1],xmm1[2],zero
; X32-NEXT: retl
;
; X64-LABEL: insertps_6:
; X64: ## BB#0: ## %entry
; X64: ## BB#0:
; X64-NEXT: insertps {{.*#+}} xmm0 = zero,xmm0[1],xmm1[2],zero
; X64-NEXT: retq
entry:
%vecext = extractelement <4 x float> %A, i32 1
%vecinit = insertelement <4 x float> <float 0.000000e+00, float undef, float undef, float undef>, float %vecext, i32 1
%vecext1 = extractelement <4 x float> %B, i32 2
@ -1051,15 +1049,14 @@ entry:
define <4 x float> @insertps_7(<4 x float> %A, <4 x float> %B) {
; X32-LABEL: insertps_7:
; X32: ## BB#0: ## %entry
; X32: ## BB#0:
; X32-NEXT: insertps {{.*#+}} xmm0 = xmm0[0],zero,xmm1[1],zero
; X32-NEXT: retl
;
; X64-LABEL: insertps_7:
; X64: ## BB#0: ## %entry
; X64: ## BB#0:
; X64-NEXT: insertps {{.*#+}} xmm0 = xmm0[0],zero,xmm1[1],zero
; X64-NEXT: retq
entry:
%vecext = extractelement <4 x float> %A, i32 0
%vecinit = insertelement <4 x float> undef, float %vecext, i32 0
%vecinit1 = insertelement <4 x float> %vecinit, float 0.000000e+00, i32 1
@ -1071,15 +1068,14 @@ entry:
define <4 x float> @insertps_8(<4 x float> %A, <4 x float> %B) {
; X32-LABEL: insertps_8:
; X32: ## BB#0: ## %entry
; X32: ## BB#0:
; X32-NEXT: insertps {{.*#+}} xmm0 = xmm0[0],xmm1[0],zero,zero
; X32-NEXT: retl
;
; X64-LABEL: insertps_8:
; X64: ## BB#0: ## %entry
; X64: ## BB#0:
; X64-NEXT: insertps {{.*#+}} xmm0 = xmm0[0],xmm1[0],zero,zero
; X64-NEXT: retq
entry:
%vecext = extractelement <4 x float> %A, i32 0
%vecinit = insertelement <4 x float> undef, float %vecext, i32 0
%vecext1 = extractelement <4 x float> %B, i32 0
@ -1091,17 +1087,16 @@ entry:
define <4 x float> @insertps_9(<4 x float> %A, <4 x float> %B) {
; X32-LABEL: insertps_9:
; X32: ## BB#0: ## %entry
; X32: ## BB#0:
; X32-NEXT: insertps {{.*#+}} xmm1 = zero,xmm0[0],xmm1[2],zero
; X32-NEXT: movaps %xmm1, %xmm0
; X32-NEXT: retl
;
; X64-LABEL: insertps_9:
; X64: ## BB#0: ## %entry
; X64: ## BB#0:
; X64-NEXT: insertps {{.*#+}} xmm1 = zero,xmm0[0],xmm1[2],zero
; X64-NEXT: movaps %xmm1, %xmm0
; X64-NEXT: retq
entry:
%vecext = extractelement <4 x float> %A, i32 0
%vecinit = insertelement <4 x float> <float 0.000000e+00, float undef, float undef, float undef>, float %vecext, i32 1
%vecext1 = extractelement <4 x float> %B, i32 2
@ -1110,7 +1105,7 @@ entry:
ret <4 x float> %vecinit3
}
define <4 x float> @insertps_10(<4 x float> %A)
define <4 x float> @insertps_10(<4 x float> %A) {
; X32-LABEL: insertps_10:
; X32: ## BB#0:
; X32-NEXT: insertps {{.*#+}} xmm0 = xmm0[0],zero,xmm0[0],zero
@ -1120,7 +1115,6 @@ define <4 x float> @insertps_10(<4 x float> %A)
; X64: ## BB#0:
; X64-NEXT: insertps {{.*#+}} xmm0 = xmm0[0],zero,xmm0[0],zero
; X64-NEXT: retq
{
%vecext = extractelement <4 x float> %A, i32 0
%vecbuild1 = insertelement <4 x float> <float 0.000000e+00, float 0.000000e+00, float 0.000000e+00, float 0.000000e+00>, float %vecext, i32 0
%vecbuild2 = insertelement <4 x float> %vecbuild1, float %vecext, i32 2
@ -1129,17 +1123,16 @@ define <4 x float> @insertps_10(<4 x float> %A)
define <4 x float> @build_vector_to_shuffle_1(<4 x float> %A) {
; X32-LABEL: build_vector_to_shuffle_1:
; X32: ## BB#0: ## %entry
; X32: ## BB#0:
; X32-NEXT: xorps %xmm1, %xmm1
; X32-NEXT: blendps {{.*#+}} xmm0 = xmm1[0],xmm0[1],xmm1[2],xmm0[3]
; X32-NEXT: retl
;
; X64-LABEL: build_vector_to_shuffle_1:
; X64: ## BB#0: ## %entry
; X64: ## BB#0:
; X64-NEXT: xorps %xmm1, %xmm1
; X64-NEXT: blendps {{.*#+}} xmm0 = xmm1[0],xmm0[1],xmm1[2],xmm0[3]
; X64-NEXT: retq
entry:
%vecext = extractelement <4 x float> %A, i32 1
%vecinit = insertelement <4 x float> zeroinitializer, float %vecext, i32 1
%vecinit1 = insertelement <4 x float> %vecinit, float 0.0, i32 2
@ -1149,17 +1142,16 @@ entry:
define <4 x float> @build_vector_to_shuffle_2(<4 x float> %A) {
; X32-LABEL: build_vector_to_shuffle_2:
; X32: ## BB#0: ## %entry
; X32: ## BB#0:
; X32-NEXT: xorps %xmm1, %xmm1
; X32-NEXT: blendps {{.*#+}} xmm0 = xmm1[0],xmm0[1],xmm1[2,3]
; X32-NEXT: retl
;
; X64-LABEL: build_vector_to_shuffle_2:
; X64: ## BB#0: ## %entry
; X64: ## BB#0:
; X64-NEXT: xorps %xmm1, %xmm1
; X64-NEXT: blendps {{.*#+}} xmm0 = xmm1[0],xmm0[1],xmm1[2,3]
; X64-NEXT: retq
entry:
%vecext = extractelement <4 x float> %A, i32 1
%vecinit = insertelement <4 x float> zeroinitializer, float %vecext, i32 1
%vecinit1 = insertelement <4 x float> %vecinit, float 0.0, i32 2