RPCSX/llvm
1
0
Fork 0
mirror of https://github.com/RPCSX/llvm.git synced 2024-12-04 18:06:49 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Loop vectorization with uniform load

Browse Source 
Vectorization cost of uniform load wasn't correctly calculated.
As a result, a simple loop that loads a uniform value wasn't vectorized.

Differential Revision: http://reviews.llvm.org/D18940



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@265901 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Elena Demikhovsky 2016-04-10 16:53:19 +00:00
parent a6346264ce
commit 9f62954aaa
2 changed files with 56 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
lib/Transforms/Vectorize/LoopVectorize.cpp
View File

@ -5819,6 +5819,15 @@ LoopVectorizationCostModel::getInstructionCost(Instruction *I, unsigned VF,
return TTI.getAddressComputationCost(VectorTy) + return TTI.getAddressComputationCost(VectorTy) +
TTI.getMemoryOpCost(I->getOpcode(), VectorTy, Alignment, AS); TTI.getMemoryOpCost(I->getOpcode(), VectorTy, Alignment, AS);
if (LI && Legal->isUniform(Ptr)) {
// Scalar load + broadcast
unsigned Cost = TTI.getAddressComputationCost(ValTy->getScalarType());
Cost += TTI.getMemoryOpCost(I->getOpcode(), ValTy->getScalarType(),
Alignment, AS);
return Cost + TTI.getShuffleCost(TargetTransformInfo::SK_Broadcast,
ValTy);
}
// For an interleaved access, calculate the total cost of the whole // For an interleaved access, calculate the total cost of the whole
// interleave group. // interleave group.
if (Legal->isAccessInterleaved(I)) { if (Legal->isAccessInterleaved(I)) {

47
test/Transforms/LoopVectorize/X86/uniform_load.ll Normal file
View File

@ -0,0 +1,47 @@
; RUN: opt -basicaa -loop-vectorize -S -mcpu=core-avx2 < %s | FileCheck %s
;float inc = 0.5;
;void foo(float *A, unsigned N) {
;
; for (unsigned i=0; i<N; i++){
; A[i] += inc;
; }
;}
; CHECK-LABEL: foo
; CHECK: vector.body
; CHECK: load <8 x float>
; CHECK: fadd <8 x float>
; CHECK: store <8 x float>
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"
@inc = global float 5.000000e-01, align 4
define void @foo(float* nocapture %A, i32 %N) #0 {
entry:
%cmp3 = icmp eq i32 %N, 0
br i1 %cmp3, label %for.end, label %for.body.preheader
for.body.preheader: ; preds = %entry
br label %for.body
for.body: ; preds = %for.body.preheader, %for.body
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %for.body.preheader ]
%0 = load float, float* @inc, align 4
%arrayidx = getelementptr inbounds float, float* %A, i64 %indvars.iv
%1 = load float, float* %arrayidx, align 4
%add = fadd float %0, %1
store float %add, float* %arrayidx, align 4
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %N
br i1 %exitcond, label %for.end.loopexit, label %for.body
for.end.loopexit: ; preds = %for.body
br label %for.end
for.end: ; preds = %for.end.loopexit, %entry
ret void
}