[PATCH] D17332: [LV] Fix PR26600: avoid out of bounds loads for interleaved access vectorization
silviu.baranga@arm.com via llvm-commits
llvm-commits at lists.llvm.org
Fri Feb 19 07:50:37 PST 2016
This revision was automatically updated to reflect the committed changes.
Closed by commit rL261331: [LV] Fix PR26600: avoid out of bounds loads for interleaved access vectorization (authored by sbaranga).
Changed prior to commit:
http://reviews.llvm.org/D17332?vs=48174&id=48495#toc
Repository:
rL LLVM
http://reviews.llvm.org/D17332
Files:
llvm/trunk/lib/Transforms/Vectorize/LoopVectorize.cpp
llvm/trunk/test/Transforms/LoopVectorize/PowerPC/stride-vectorization.ll
llvm/trunk/test/Transforms/LoopVectorize/interleaved-accesses.ll
Index: llvm/trunk/test/Transforms/LoopVectorize/interleaved-accesses.ll
===================================================================
--- llvm/trunk/test/Transforms/LoopVectorize/interleaved-accesses.ll
+++ llvm/trunk/test/Transforms/LoopVectorize/interleaved-accesses.ll
@@ -292,10 +292,8 @@
; }
; CHECK-LABEL: @even_load(
-; CHECK: %wide.vec = load <8 x i32>, <8 x i32>* %{{.*}}, align 4
-; CHECK: %strided.vec = shufflevector <8 x i32> %wide.vec, <8 x i32> undef, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
-; CHECK-NOT: shufflevector <8 x i32> %wide.vec, <8 x i32> undef, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
-; CHECK: shl nsw <4 x i32> %strided.vec, <i32 1, i32 1, i32 1, i32 1>
+; CHECK-NOT: %wide.vec = load <8 x i32>, <8 x i32>* %{{.*}}, align 4
+; CHECK-NOT: %strided.vec = shufflevector <8 x i32> %wide.vec, <8 x i32> undef, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
define void @even_load(i32* noalias nocapture readonly %A, i32* noalias nocapture %B) {
entry:
Index: llvm/trunk/test/Transforms/LoopVectorize/PowerPC/stride-vectorization.ll
===================================================================
--- llvm/trunk/test/Transforms/LoopVectorize/PowerPC/stride-vectorization.ll
+++ llvm/trunk/test/Transforms/LoopVectorize/PowerPC/stride-vectorization.ll
@@ -16,9 +16,15 @@
for.body: ; preds = %for.body, %entry
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
%0 = shl nsw i64 %indvars.iv, 1
+ %odd.idx = add nsw i64 %0, 1
+
%arrayidx = getelementptr inbounds double, double* %b, i64 %0
+ %arrayidx.odd = getelementptr inbounds double, double* %b, i64 %odd.idx
+
%1 = load double, double* %arrayidx, align 8
- %add = fadd double %1, 1.000000e+00
+ %2 = load double, double* %arrayidx.odd, align 8
+
+ %add = fadd double %1, %2
%arrayidx2 = getelementptr inbounds double, double* %a, i64 %indvars.iv
store double %add, double* %arrayidx2, align 8
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
Index: llvm/trunk/lib/Transforms/Vectorize/LoopVectorize.cpp
===================================================================
--- llvm/trunk/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ llvm/trunk/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -4719,6 +4719,8 @@
// Holds all interleaved store groups temporarily.
SmallSetVector<InterleaveGroup *, 4> StoreGroups;
+ // Holds all interleaved load groups temporarily.
+ SmallSetVector<InterleaveGroup *, 4> LoadGroups;
// Search the load-load/write-write pair B-A in bottom-up order and try to
// insert B into the interleave group of A according to 3 rules:
@@ -4746,6 +4748,8 @@
if (A->mayWriteToMemory())
StoreGroups.insert(Group);
+ else
+ LoadGroups.insert(Group);
for (auto II = std::next(I); II != E; ++II) {
Instruction *B = II->first;
@@ -4793,6 +4797,12 @@
for (InterleaveGroup *Group : StoreGroups)
if (Group->getNumMembers() != Group->getFactor())
releaseGroup(Group);
+
+ // Remove interleaved load groups that don't have the first and last member.
+ // This guarantees that we won't do speculative out of bounds loads.
+ for (InterleaveGroup *Group : LoadGroups)
+ if (!Group->getMember(0) || !Group->getMember(Group->getFactor() - 1))
+ releaseGroup(Group);
}
LoopVectorizationCostModel::VectorizationFactor
-------------- next part --------------
A non-text attachment was scrubbed...
Name: D17332.48495.patch
Type: text/x-patch
Size: 3371 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20160219/587cda1e/attachment.bin>
More information about the llvm-commits
mailing list