1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2025-01-31 20:51:52 +01:00

[LV] Unroll factor is expected to be > 0

LV fails with assertion checking that UF > 0. We already set UF to 1 if it is 0 except the case when IC > MaxInterleaveCount. The fix is to set UF to 1 for that case as well.

Reviewed By: fhahn

Differential Revision: https://reviews.llvm.org/D87679
This commit is contained in:
Evgeniy Brevnov 2020-09-15 17:09:47 +07:00
parent 0ca876f471
commit b0957e3eb4
2 changed files with 39 additions and 8 deletions

View File

@ -5598,12 +5598,28 @@ unsigned LoopVectorizationCostModel::selectInterleaveCount(ElementCount VF,
}
// If trip count is known or estimated compile time constant, limit the
// interleave count to be less than the trip count divided by VF.
// interleave count to be less than the trip count divided by VF, provided it
// is at least 1.
if (BestKnownTC) {
MaxInterleaveCount =
std::min(*BestKnownTC / VF.getKnownMinValue(), MaxInterleaveCount);
// Make sure MaxInterleaveCount is greater than 0.
MaxInterleaveCount = std::max(1u, MaxInterleaveCount);
}
assert(MaxInterleaveCount > 0 &&
"Maximum interleave count must be greater than 0");
// Clamp the calculated IC to be between the 1 and the max interleave count
// that the target and trip count allows.
if (IC > MaxInterleaveCount)
IC = MaxInterleaveCount;
else
// Make sure IC is greater than 0.
IC = std::max(1u, IC);
assert(IC > 0 && "Interleave count must be greater than 0.");
// If we did not calculate the cost for VF (because the user selected the VF)
// then we calculate the cost of VF here.
if (LoopCost == 0)
@ -5611,13 +5627,6 @@ unsigned LoopVectorizationCostModel::selectInterleaveCount(ElementCount VF,
assert(LoopCost && "Non-zero loop cost expected");
// Clamp the calculated IC to be between the 1 and the max interleave count
// that the target and trip count allows.
if (IC > MaxInterleaveCount)
IC = MaxInterleaveCount;
else if (IC < 1)
IC = 1;
// Interleave if we vectorized this loop and there is a reduction that could
// benefit from interleaving.
if (VF.isVector() && HasReductions) {

View File

@ -0,0 +1,22 @@
; RUN: opt -S -loop-vectorize -mtriple=s390x-linux-gnu -tiny-trip-count-interleave-threshold=4 -vectorizer-min-trip-count=8 < %s | FileCheck %s
; RUN: opt -S -passes=loop-vectorize -mtriple=s390x-linux-gnu -tiny-trip-count-interleave-threshold=4 -vectorizer-min-trip-count=8 < %s | FileCheck %s
define i32 @main(i32 %arg, i8** nocapture readnone %arg1) #0 {
;CHECK: vector.body:
entry:
%0 = alloca i8, align 1
br label %loop
loop:
%storemerge.i.i = phi i8 [ 0, %entry ], [ %tmp12.i.i, %loop ]
store i8 %storemerge.i.i, i8* %0, align 2
%tmp8.i.i = icmp ult i8 %storemerge.i.i, 8
%tmp12.i.i = add nuw nsw i8 %storemerge.i.i, 1
br i1 %tmp8.i.i, label %loop, label %ret
ret:
ret i32 0
}
attributes #0 = { "target-cpu"="z13" }