RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-22 18:54:02 +01:00
Code Issues Projects Releases Wiki Activity

[SLPVectorizer] Pass the right type argument to getCmpSelInstrCost()

Browse Source 
In getEntryCost(), make the scalar type for a compare instruction that of the
operands, not i1. This is needed in order to call getCmpSelInstrCost() for a
compare in a sensible way, the same way as the LoopVectorizer does.

New test: test/Transforms/SLPVectorizer/SystemZ/SLP-cmp-cost-query.ll

Review: Matthew Simpson
https://reviews.llvm.org/D31601

llvm-svn: 300061
This commit is contained in:
Jonas Paulsson 2017-04-12 13:29:25 +00:00
parent 467066b926
commit eedad8c536
2 changed files with 38 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
lib/Transforms/Vectorize/SLPVectorizer.cpp
View File

@ -1702,6 +1702,8 @@ int BoUpSLP::getEntryCost(TreeEntry *E) {
Type *ScalarTy = VL[0]->getType();
if (StoreInst *SI = dyn_cast<StoreInst>(VL[0]))
ScalarTy = SI->getValueOperand()->getType();
else if (CmpInst *CI = dyn_cast<CmpInst>(VL[0]))
ScalarTy = CI->getOperand(0)->getType();
VectorType *VecTy = VectorType::get(ScalarTy, VL.size());
// If we have computed a smaller type for the expression, update VecTy so

36
test/Transforms/SLPVectorizer/SystemZ/SLP-cmp-cost-query.ll Normal file
View File

@ -0,0 +1,36 @@
; REQUIRES: asserts
; RUN: opt -mtriple=systemz-unknown -mcpu=z13 -slp-vectorizer -debug-only=SLP \
; RUN: -S -disable-output < %s |& FileCheck %s
;
; Check that SLP vectorizer gets the right cost difference for a compare
; node.
; Function Attrs: norecurse nounwind readonly
define void @fun(i8* nocapture, i32 zeroext) local_unnamed_addr #0 {
.lr.ph.preheader:
br label %.lr.ph
.lr.ph: ; preds = %.lr.ph.preheader, %.lr.ph
%2 = phi i32 [ %., %.lr.ph ], [ undef, %.lr.ph.preheader ]
%3 = phi i32 [ %.9, %.lr.ph ], [ undef, %.lr.ph.preheader ]
%4 = icmp ult i32 %2, %1
%5 = select i1 %4, i32 0, i32 %1
%. = sub i32 %2, %5
%6 = icmp ult i32 %3, %1
%7 = select i1 %6, i32 0, i32 %1
%.9 = sub i32 %3, %7
%8 = zext i32 %. to i64
%9 = getelementptr inbounds i8, i8* %0, i64 %8
%10 = load i8, i8* %9, align 1
%11 = zext i32 %.9 to i64
%12 = getelementptr inbounds i8, i8* %0, i64 %11
%13 = load i8, i8* %12, align 1
%14 = icmp eq i8 %10, %13
br i1 %14, label %.lr.ph, label %._crit_edge
._crit_edge: ; preds = %.lr.ph
ret void
; CHECK: SLP: Adding cost -1 for bundle that starts with %4 = icmp ult i32 %2, %1.
}