6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2025-11-01 00:17:01 +00:00
Code Issues Projects Releases Wiki Activity

SLP Vectorizer: Canonicalize tree operands of commutitive binary operands.

Browse Source 
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@214338 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Chad Rosier
2014-07-30 21:07:56 +00:00
parent 7fef5a3d19
commit 7f6a685444
2 changed files with 107 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

75
test/Transforms/SLPVectorizer/AArch64/commute.ll Normal file
View File

@@ -0,0 +1,75 @@
; RUN: opt -S -slp-vectorizer %s | FileCheck %s
target datalayout = "e-m:e-i64:64-i128:128-n32:64-S128"
target triple = "aarch64--linux-gnu"
%structA = type { [2 x float] }
define void @test1(%structA* nocapture readonly %J, i32 %xmin, i32 %ymin) {
; CHECK-LABEL: test1
; CHECK: %arrayidx4 = getelementptr inbounds %structA* %J, i64 0, i32 0, i64 0
; CHECK: %arrayidx9 = getelementptr inbounds %structA* %J, i64 0, i32 0, i64 1
; CHECK: %3 = bitcast float* %arrayidx4 to <2 x float>*
; CHECK: %4 = load <2 x float>* %3, align 4
; CHECK: %5 = fsub <2 x float> %2, %4
; CHECK: %6 = fmul <2 x float> %5, %5
; CHECK: %7 = extractelement <2 x float> %6, i32 0
; CHECK: %8 = extractelement <2 x float> %6, i32 1
; CHECK: %add = fadd fast float %7, %8
; CHECK: %cmp = fcmp oeq float %add, 0.000000e+00
entry:
br label %for.body3.lr.ph
for.body3.lr.ph:
%conv5 = sitofp i32 %ymin to float
%conv = sitofp i32 %xmin to float
%arrayidx4 = getelementptr inbounds %structA* %J, i64 0, i32 0, i64 0
%0 = load float* %arrayidx4, align 4
%sub = fsub fast float %conv, %0
%arrayidx9 = getelementptr inbounds %structA* %J, i64 0, i32 0, i64 1
%1 = load float* %arrayidx9, align 4
%sub10 = fsub fast float %conv5, %1
%mul11 = fmul fast float %sub, %sub
%mul12 = fmul fast float %sub10, %sub10
%add = fadd fast float %mul11, %mul12
%cmp = fcmp oeq float %add, 0.000000e+00
br i1 %cmp, label %for.body3.lr.ph, label %for.end27
for.end27:
ret void
}
define void @test2(%structA* nocapture readonly %J, i32 %xmin, i32 %ymin) {
; CHECK-LABEL: test2
; CHECK: %arrayidx4 = getelementptr inbounds %structA* %J, i64 0, i32 0, i64 0
; CHECK: %arrayidx9 = getelementptr inbounds %structA* %J, i64 0, i32 0, i64 1
; CHECK: %3 = bitcast float* %arrayidx4 to <2 x float>*
; CHECK: %4 = load <2 x float>* %3, align 4
; CHECK: %5 = fsub <2 x float> %2, %4
; CHECK: %6 = fmul <2 x float> %5, %5
; CHECK: %7 = extractelement <2 x float> %6, i32 0
; CHECK: %8 = extractelement <2 x float> %6, i32 1
; CHECK: %add = fadd fast float %8, %7
; CHECK: %cmp = fcmp oeq float %add, 0.000000e+00
entry:
br label %for.body3.lr.ph
for.body3.lr.ph:
%conv5 = sitofp i32 %ymin to float
%conv = sitofp i32 %xmin to float
%arrayidx4 = getelementptr inbounds %structA* %J, i64 0, i32 0, i64 0
%0 = load float* %arrayidx4, align 4
%sub = fsub fast float %conv, %0
%arrayidx9 = getelementptr inbounds %structA* %J, i64 0, i32 0, i64 1
%1 = load float* %arrayidx9, align 4
%sub10 = fsub fast float %conv5, %1
%mul11 = fmul fast float %sub, %sub
%mul12 = fmul fast float %sub10, %sub10
%add = fadd fast float %mul12, %mul11 ;;;<---- Operands commuted!!
%cmp = fcmp oeq float %add, 0.000000e+00
br i1 %cmp, label %for.body3.lr.ph, label %for.end27
for.end27:
ret void
}