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

[LV] Avoid potentential division by zero when selecting IC 

llvm-svn: 303174
This commit is contained in:
Matthew Simpson 2017-05-16 14:43:55 +00:00
parent afb555473e
commit b7b5d55c38
2 changed files with 35 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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

@ -6550,8 +6550,8 @@ unsigned LoopVectorizationCostModel::selectInterleaveCount(bool OptForSize,
// We assume that the cost overhead is 1 and we use the cost model
// to estimate the cost of the loop and interleave until the cost of the
// loop overhead is about 5% of the cost of the loop.
unsigned SmallIC =
std::min(IC, (unsigned)PowerOf2Floor(SmallLoopCost / LoopCost));
unsigned SmallIC = std::min(
IC, (unsigned)PowerOf2Floor(SmallLoopCost / LoopCost ? LoopCost : 1));
// Interleave until store/load ports (estimated by max interleave count) are
// saturated.

33
llvm/test/Transforms/LoopVectorize/interleave_count.ll Normal file
View File

@ -0,0 +1,33 @@
; RUN: opt < %s -loop-vectorize -force-target-instruction-cost=0 -force-vector-width=2 -instcombine -S | FileCheck %s
target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
; CHECK-LABEL: @copy(
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %vector.ph ], [ [[INDEX_NEXT:%.*]], %vector.body ]
; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds i64, i64* %a, i64 [[INDEX]]
; CHECK-NEXT: [[TMP3:%.*]] = getelementptr inbounds i64, i64* %b, i64 [[INDEX]]
; CHECK-NEXT: [[TMP4:%.*]] = bitcast i64* [[TMP3]] to <2 x i64>*
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <2 x i64>, <2 x i64>* [[TMP4]], align 8
; CHECK-NEXT: [[TMP5:%.*]] = bitcast i64* [[TMP2]] to <2 x i64>*
; CHECK-NEXT: store <2 x i64> [[WIDE_LOAD]], <2 x i64>* [[TMP5]], align 8
; CHECK-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], 2
; CHECK: br i1 {{.*}}, label %middle.block, label %vector.body
;
define void @copy(i64* %a, i64* %b, i64 %n) {
entry:
br label %for.body
for.body:
%i = phi i64 [ %i.next, %for.body ], [ 0, %entry ]
%tmp0 = getelementptr inbounds i64, i64* %a, i64 %i
%tmp1 = getelementptr inbounds i64, i64* %b, i64 %i
%tmp3 = load i64, i64* %tmp1, align 8
store i64 %tmp3, i64* %tmp0, align 8
%i.next = add nuw nsw i64 %i, 1
%cond = icmp slt i64 %i.next, %n
br i1 %cond, label %for.body, label %for.end
for.end:
ret void
}