[llvm-branch-commits] [llvm] b0536b5 - [LV] Do not try to sink dead instructions.
Hans Wennborg via llvm-branch-commits
llvm-branch-commits at lists.llvm.org
Wed Jan 29 13:04:47 PST 2020
Author: Florian Hahn
Date: 2020-01-29T22:02:52+01:00
New Revision: b0536b58c1b40ac946bb653d13a63e4372c2ca17
URL: https://github.com/llvm/llvm-project/commit/b0536b58c1b40ac946bb653d13a63e4372c2ca17
DIFF: https://github.com/llvm/llvm-project/commit/b0536b58c1b40ac946bb653d13a63e4372c2ca17.diff
LOG: [LV] Do not try to sink dead instructions.
Dead instructions do not need to be sunk. Currently we try and record
the recipies for them, but there are no recipes emitted for them and
there's nothing to sink. They can be removed from SinkAfter while
marking them for recording.
Fixes PR44634.
Reviewers: rengolin, hsaito, fhahn, Ayal, gilr
Reviewed By: gilr
Differential Revision: https://reviews.llvm.org/D73423
(cherry picked from commit a911fef3dd79e0a04b241be7b476dde7e99744c4)
Added:
Modified:
llvm/lib/Transforms/Vectorize/LoopVectorizationPlanner.h
llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
llvm/test/Transforms/LoopVectorize/first-order-recurrence.ll
Removed:
################################################################################
diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorizationPlanner.h b/llvm/lib/Transforms/Vectorize/LoopVectorizationPlanner.h
index c3ca43fcd492..e5edd305d3d5 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorizationPlanner.h
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorizationPlanner.h
@@ -279,9 +279,10 @@ class LoopVectorizationPlanner {
/// Build a VPlan using VPRecipes according to the information gather by
/// Legal. This method is only used for the legacy inner loop vectorizer.
- VPlanPtr
- buildVPlanWithVPRecipes(VFRange &Range, SmallPtrSetImpl<Value *> &NeedDef,
- SmallPtrSetImpl<Instruction *> &DeadInstructions);
+ VPlanPtr buildVPlanWithVPRecipes(
+ VFRange &Range, SmallPtrSetImpl<Value *> &NeedDef,
+ SmallPtrSetImpl<Instruction *> &DeadInstructions,
+ const DenseMap<Instruction *, Instruction *> &SinkAfter);
/// Build VPlans for power-of-2 VF's between \p MinVF and \p MaxVF inclusive,
/// according to the information gathered by Legal when it checked if it is
diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
index 684a3098e564..c99b930a61f9 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -7118,25 +7118,29 @@ void LoopVectorizationPlanner::buildVPlansWithVPRecipes(unsigned MinVF,
SmallPtrSet<Instruction *, 4> DeadInstructions;
collectTriviallyDeadInstructions(DeadInstructions);
+ DenseMap<Instruction *, Instruction *> &SinkAfter = Legal->getSinkAfter();
+ // Dead instructions do not need sinking. Remove them from SinkAfter.
+ for (Instruction *I : DeadInstructions)
+ SinkAfter.erase(I);
+
for (unsigned VF = MinVF; VF < MaxVF + 1;) {
VFRange SubRange = {VF, MaxVF + 1};
- VPlans.push_back(
- buildVPlanWithVPRecipes(SubRange, NeedDef, DeadInstructions));
+ VPlans.push_back(buildVPlanWithVPRecipes(SubRange, NeedDef,
+ DeadInstructions, SinkAfter));
VF = SubRange.End;
}
}
VPlanPtr LoopVectorizationPlanner::buildVPlanWithVPRecipes(
VFRange &Range, SmallPtrSetImpl<Value *> &NeedDef,
- SmallPtrSetImpl<Instruction *> &DeadInstructions) {
+ SmallPtrSetImpl<Instruction *> &DeadInstructions,
+ const DenseMap<Instruction *, Instruction *> &SinkAfter) {
// Hold a mapping from predicated instructions to their recipes, in order to
// fix their AlsoPack behavior if a user is determined to replicate and use a
// scalar instead of vector value.
DenseMap<Instruction *, VPReplicateRecipe *> PredInst2Recipe;
- DenseMap<Instruction *, Instruction *> &SinkAfter = Legal->getSinkAfter();
-
SmallPtrSet<const InterleaveGroup<Instruction> *, 1> InterleaveGroups;
VPRecipeBuilder RecipeBuilder(OrigLoop, TLI, Legal, CM, Builder);
diff --git a/llvm/test/Transforms/LoopVectorize/first-order-recurrence.ll b/llvm/test/Transforms/LoopVectorize/first-order-recurrence.ll
index f86dcd7e2e7c..5a250984b1f0 100644
--- a/llvm/test/Transforms/LoopVectorize/first-order-recurrence.ll
+++ b/llvm/test/Transforms/LoopVectorize/first-order-recurrence.ll
@@ -607,3 +607,41 @@ cond.end: ; preds = %for.body4, %cond.tr
for.end12.loopexit: ; preds = %cond.end
ret void
}
+
+; Dead instructions, like the exit condition are not part of the actual VPlan
+; and do not need to be sunk. PR44634.
+define void @sink_dead_inst() {
+; SINK-AFTER-LABEL: define void @sink_dead_inst(
+; SINK-AFTER-LABEL: vector.body: ; preds = %vector.body, %vector.ph
+; SINK-AFTER-NEXT: %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
+; SINK-AFTER-NEXT: %vec.ind = phi <4 x i16> [ <i16 -27, i16 -26, i16 -25, i16 -24>, %vector.ph ], [ %vec.ind.next, %vector.body ]
+; SINK-AFTER-NEXT: %vector.recur = phi <4 x i16> [ <i16 undef, i16 undef, i16 undef, i16 0>, %vector.ph ], [ %3, %vector.body ]
+; SINK-AFTER-NEXT: %vector.recur2 = phi <4 x i32> [ <i32 undef, i32 undef, i32 undef, i32 -27>, %vector.ph ], [ %1, %vector.body ]
+; SINK-AFTER-NEXT: %0 = add <4 x i16> %vec.ind, <i16 1, i16 1, i16 1, i16 1>
+; SINK-AFTER-NEXT: %1 = zext <4 x i16> %0 to <4 x i32>
+; SINK-AFTER-NEXT: %2 = shufflevector <4 x i32> %vector.recur2, <4 x i32> %1, <4 x i32> <i32 3, i32 4, i32 5, i32 6>
+; SINK-AFTER-NEXT: %3 = add <4 x i16> %0, <i16 5, i16 5, i16 5, i16 5>
+; SINK-AFTER-NEXT: %4 = shufflevector <4 x i16> %vector.recur, <4 x i16> %3, <4 x i32> <i32 3, i32 4, i32 5, i32 6>
+; SINK-AFTER-NEXT: %5 = sub <4 x i16> %4, <i16 10, i16 10, i16 10, i16 10>
+; SINK-AFTER-NEXT: %index.next = add i32 %index, 4
+; SINK-AFTER-NEXT: %vec.ind.next = add <4 x i16> %vec.ind, <i16 4, i16 4, i16 4, i16 4>
+; SINK-AFTER-NEXT: %6 = icmp eq i32 %index.next, 40
+; SINK-AFTER-NEXT: br i1 %6, label %middle.block, label %vector.body, !llvm.loop !43
+;
+entry:
+ br label %for.cond
+
+for.cond:
+ %iv = phi i16 [ -27, %entry ], [ %iv.next, %for.cond ]
+ %rec.1 = phi i16 [ 0, %entry ], [ %rec.1.prev, %for.cond ]
+ %rec.2 = phi i32 [ -27, %entry ], [ %rec.2.prev, %for.cond ]
+ %use.rec.1 = sub i16 %rec.1, 10
+ %cmp = icmp eq i32 %rec.2, 15
+ %iv.next = add i16 %iv, 1
+ %rec.2.prev = zext i16 %iv.next to i32
+ %rec.1.prev = add i16 %iv.next, 5
+ br i1 %cmp, label %for.end, label %for.cond
+
+for.end:
+ ret void
+}
More information about the llvm-branch-commits
mailing list