maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

SLP Vectorizer: Extract cost will only be added once even if the scalar has multiple external uses. 

llvm-svn: 195406
This commit is contained in:
Yi Jiang 2013-11-22 01:57:02 +00:00
parent ae215951a9
commit 79a2b0a6d1
2 changed files with 34 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
View File

@ -1082,9 +1082,13 @@ int BoUpSLP::getTreeCost() {
Cost += C; Cost += C;
} }
SmallSet<Value *, 16> ExtractCostCalculated;
int ExtractCost = 0; int ExtractCost = 0;
for (UserList::iterator I = ExternalUses.begin(), E = ExternalUses.end(); for (UserList::iterator I = ExternalUses.begin(), E = ExternalUses.end();
I != E; ++I) { I != E; ++I) {
// We only add extract cost once for the same scalar.
if (!ExtractCostCalculated.insert(I->Scalar))
continue;
VectorType *VecTy = VectorType::get(I->Scalar->getType(), BundleWidth); VectorType *VecTy = VectorType::get(I->Scalar->getType(), BundleWidth);
ExtractCost += TTI->getVectorInstrCost(Instruction::ExtractElement, VecTy, ExtractCost += TTI->getVectorInstrCost(Instruction::ExtractElement, VecTy,

30
llvm/test/Transforms/SLPVectorizer/X86/extractcost.ll Normal file
View File

@ -0,0 +1,30 @@
; RUN: opt < %s -basicaa -slp-vectorizer -dce -S -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx | FileCheck %s
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
target triple = "x86_64-apple-macosx10.8.0"
;CHECK-LABEL: @foo(
;CHECK: store <4 x i32>
;CHECK: ret
define i32 @foo(i32* nocapture %A, i32 %n, i32 %m) {
entry:
%mul = mul nsw i32 %n, 5
%add = add nsw i32 %mul, 9
store i32 %add, i32* %A, align 4
%mul1 = mul nsw i32 %n, 9
%add2 = add nsw i32 %mul1, 9
%arrayidx3 = getelementptr inbounds i32* %A, i64 1
store i32 %add2, i32* %arrayidx3, align 4
%mul4 = shl i32 %n, 3
%add5 = add nsw i32 %mul4, 9
%arrayidx6 = getelementptr inbounds i32* %A, i64 2
store i32 %add5, i32* %arrayidx6, align 4
%mul7 = mul nsw i32 %n, 10
%add8 = add nsw i32 %mul7, 9
%arrayidx9 = getelementptr inbounds i32* %A, i64 3
store i32 %add8, i32* %arrayidx9, align 4
%externaluse1 = add nsw i32 %add, %m
%externaluse2 = mul nsw i32 %add, %m ; we should add the extract cost only once and the store will be vectorized
%add10 = add nsw i32 %externaluse1, %externaluse2
ret i32 %add10
}