[llvm] [VPlan] Add initial loop-invariant code motion transform. (PR #107894)

via llvm-commits llvm-commits at lists.llvm.org
Mon Sep 9 10:47:07 PDT 2024


llvmbot wrote:


<!--LLVM PR SUMMARY COMMENT-->

@llvm/pr-subscribers-llvm-transforms

Author: Florian Hahn (fhahn)

<details>
<summary>Changes</summary>

Add initial transform to move out loop-invariant recipes.

This also helps to fix a divergence between legacy and VPlan-based cost model due to legacy using ScalarEvolution::isLoopInvariant in some cases.

Fixes https://github.com/llvm/llvm-project/issues/107501.

NOTE: Some tests still need updating.

---

Patch is 46.15 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/107894.diff


24 Files Affected:

- (modified) llvm/lib/Transforms/Vectorize/LoopVectorize.cpp (+3-2) 
- (modified) llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp (+20) 
- (modified) llvm/lib/Transforms/Vectorize/VPlanTransforms.h (+3) 
- (modified) llvm/test/Transforms/LoopVectorize/AArch64/induction-costs.ll (+1-1) 
- (modified) llvm/test/Transforms/LoopVectorize/RISCV/divrem.ll (+2-2) 
- (modified) llvm/test/Transforms/LoopVectorize/RISCV/pr88802.ll (+2-2) 
- (modified) llvm/test/Transforms/LoopVectorize/RISCV/truncate-to-minimal-bitwidth-cost.ll (+2-2) 
- (modified) llvm/test/Transforms/LoopVectorize/SystemZ/pr47665.ll (+1-1) 
- (modified) llvm/test/Transforms/LoopVectorize/X86/cost-model.ll (+4-4) 
- (modified) llvm/test/Transforms/LoopVectorize/X86/divs-with-tail-folding.ll (+1-1) 
- (modified) llvm/test/Transforms/LoopVectorize/X86/invariant-load-gather.ll (+2-2) 
- (modified) llvm/test/Transforms/LoopVectorize/blend-in-header.ll (+1-1) 
- (modified) llvm/test/Transforms/LoopVectorize/first-order-recurrence-sink-replicate-region.ll (+3-3) 
- (modified) llvm/test/Transforms/LoopVectorize/pr55167-fold-tail-live-out.ll (+3-3) 
- (modified) llvm/test/Transforms/LoopVectorize/reduction-inloop-uf4.ll (+6-6) 
- (modified) llvm/test/Transforms/LoopVectorize/scalable-trunc-min-bitwidth.ll (+1-1) 
- (modified) llvm/test/Transforms/LoopVectorize/skeleton-lcssa-crash.ll (+1-1) 
- (modified) llvm/test/Transforms/LoopVectorize/trunc-extended-icmps.ll (+1-1) 
- (modified) llvm/test/Transforms/LoopVectorize/trunc-loads-p16.ll (+1-1) 
- (modified) llvm/test/Transforms/LoopVectorize/trunc-shifts.ll (+3-3) 
- (modified) llvm/test/Transforms/LoopVectorize/vector-geps.ll (+3-3) 
- (modified) llvm/test/Transforms/LoopVectorize/version-stride-with-integer-casts.ll (+1-1) 
- (modified) llvm/test/Transforms/LoopVectorize/vplan-sink-scalars-and-merge.ll (+1-1) 
- (modified) llvm/test/Transforms/LoopVectorize/widen-gep-all-indices-invariant.ll (+3-3) 


``````````diff
diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
index dd4d42b68b5661..22bd5d9cd77ac2 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -2382,7 +2382,8 @@ void InnerLoopVectorizer::scalarizeInstruction(const Instruction *Instr,
     AC->registerAssumption(II);
 
   // End if-block.
-  bool IfPredicateInstr = RepRecipe->getParent()->getParent()->isReplicator();
+  VPRegionBlock *Parent = RepRecipe->getParent()->getParent();
+  bool IfPredicateInstr = Parent ? Parent->isReplicator() : false;
   if (IfPredicateInstr)
     PredicatedInstructions.push_back(Cloned);
 }
@@ -7294,7 +7295,7 @@ static bool planContainsAdditionalSimplifications(VPlan &Plan,
   };
 
   DenseSet<Instruction *> SeenInstrs;
-  auto Iter = vp_depth_first_deep(Plan.getEntry());
+  auto Iter = vp_depth_first_deep(Plan.getVectorLoopRegion()->getEntry());
   for (VPBasicBlock *VPBB : VPBlockUtils::blocksOnly<VPBasicBlock>(Iter)) {
     for (VPRecipeBase &R : *VPBB) {
       if (auto *IR = dyn_cast<VPInterleaveRecipe>(&R)) {
diff --git a/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp b/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp
index eaf54464457d5e..6b298749981ab4 100644
--- a/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp
+++ b/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp
@@ -1127,6 +1127,7 @@ void VPlanTransforms::optimize(VPlan &Plan, ScalarEvolution &SE) {
   removeRedundantInductionCasts(Plan);
 
   simplifyRecipes(Plan, SE.getContext());
+  licm(Plan);
   legalizeAndOptimizeInductions(Plan, SE);
   removeDeadRecipes(Plan);
 
@@ -1586,3 +1587,22 @@ void VPlanTransforms::createInterleaveGroups(
       }
   }
 }
+
+void VPlanTransforms::licm(VPlan &Plan) {
+  VPRegionBlock *LoopRegion = Plan.getVectorLoopRegion();
+  VPBasicBlock *Preheader =
+      cast<VPBasicBlock>(LoopRegion->getSinglePredecessor());
+  // Hoist any loop invariant recipes from the vector loop region to the
+  // preheader.
+  for (VPBasicBlock *VPBB : VPBlockUtils::blocksOnly<VPBasicBlock>(
+           vp_depth_first_shallow(LoopRegion->getEntry()))) {
+    for (VPRecipeBase &R : make_early_inc_range(*VPBB)) {
+      if (R.mayHaveSideEffects() || R.mayReadFromMemory() || R.isPhi() ||
+          any_of(R.operands(), [](VPValue *Op) {
+            return !Op->isDefinedOutsideVectorRegions();
+          }))
+        continue;
+      R.moveBefore(*Preheader, Preheader->end());
+    }
+  }
+}
diff --git a/llvm/lib/Transforms/Vectorize/VPlanTransforms.h b/llvm/lib/Transforms/Vectorize/VPlanTransforms.h
index e714f69eeff1ab..ec4bd17819d9c1 100644
--- a/llvm/lib/Transforms/Vectorize/VPlanTransforms.h
+++ b/llvm/lib/Transforms/Vectorize/VPlanTransforms.h
@@ -114,6 +114,9 @@ struct VPlanTransforms {
   static void createInterleaveGroups(
       const SmallPtrSetImpl<const InterleaveGroup<Instruction> *> &InterleaveGroups,
       VPRecipeBuilder &RecipeBuilder, bool ScalarEpilogueAllowed);
+
+  /// Move loop-invariant recipes out of vector loop regions.
+  static void licm(VPlan &Plan);
 };
 
 } // namespace llvm
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/induction-costs.ll b/llvm/test/Transforms/LoopVectorize/AArch64/induction-costs.ll
index 2e7205ee8b3c4a..dd3ebeb2cbf21b 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/induction-costs.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/induction-costs.ll
@@ -18,6 +18,7 @@ define i32 @multi_exit_iv_uniform(i32 %a, i64 %N, ptr %dst) {
 ; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[TMP0]], [[TMP2]]
 ; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i32> poison, i32 [[A]], i64 0
 ; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT]], <4 x i32> poison, <4 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP7:%.*]] = zext <4 x i32> [[BROADCAST_SPLAT]] to <4 x i64>
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
@@ -27,7 +28,6 @@ define i32 @multi_exit_iv_uniform(i32 %a, i64 %N, ptr %dst) {
 ; CHECK-NEXT:    [[TMP4:%.*]] = add i64 [[INDEX]], 4
 ; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr i64, ptr [[DST]], i64 [[TMP3]]
 ; CHECK-NEXT:    [[TMP6:%.*]] = getelementptr i64, ptr [[DST]], i64 [[TMP4]]
-; CHECK-NEXT:    [[TMP7:%.*]] = zext <4 x i32> [[BROADCAST_SPLAT]] to <4 x i64>
 ; CHECK-NEXT:    [[TMP8:%.*]] = getelementptr i64, ptr [[TMP5]], i32 0
 ; CHECK-NEXT:    [[TMP9:%.*]] = getelementptr i64, ptr [[TMP5]], i32 4
 ; CHECK-NEXT:    store <4 x i64> [[TMP7]], ptr [[TMP8]], align 8
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/divrem.ll b/llvm/test/Transforms/LoopVectorize/RISCV/divrem.ll
index 7ca1b5395dd013..b8fb7eb177ed3c 100644
--- a/llvm/test/Transforms/LoopVectorize/RISCV/divrem.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/divrem.ll
@@ -439,6 +439,7 @@ define void @predicated_udiv(ptr noalias nocapture %a, i64 %v, i64 %n) {
 ; CHECK-NEXT:    [[TMP5:%.*]] = mul i64 [[TMP4]], 2
 ; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[V:%.*]], i64 0
 ; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 2 x i64> [[BROADCAST_SPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP9:%.*]] = icmp ne <vscale x 2 x i64> [[BROADCAST_SPLAT]], zeroinitializer
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
@@ -446,7 +447,6 @@ define void @predicated_udiv(ptr noalias nocapture %a, i64 %v, i64 %n) {
 ; CHECK-NEXT:    [[TMP7:%.*]] = getelementptr inbounds i64, ptr [[A:%.*]], i64 [[TMP6]]
 ; CHECK-NEXT:    [[TMP8:%.*]] = getelementptr inbounds i64, ptr [[TMP7]], i32 0
 ; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <vscale x 2 x i64>, ptr [[TMP8]], align 8
-; CHECK-NEXT:    [[TMP9:%.*]] = icmp ne <vscale x 2 x i64> [[BROADCAST_SPLAT]], zeroinitializer
 ; CHECK-NEXT:    [[TMP10:%.*]] = select <vscale x 2 x i1> [[TMP9]], <vscale x 2 x i64> [[BROADCAST_SPLAT]], <vscale x 2 x i64> shufflevector (<vscale x 2 x i64> insertelement (<vscale x 2 x i64> poison, i64 1, i64 0), <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer)
 ; CHECK-NEXT:    [[TMP11:%.*]] = udiv <vscale x 2 x i64> [[WIDE_LOAD]], [[TMP10]]
 ; CHECK-NEXT:    [[PREDPHI:%.*]] = select <vscale x 2 x i1> [[TMP9]], <vscale x 2 x i64> [[TMP11]], <vscale x 2 x i64> [[WIDE_LOAD]]
@@ -570,6 +570,7 @@ define void @predicated_sdiv(ptr noalias nocapture %a, i64 %v, i64 %n) {
 ; CHECK-NEXT:    [[TMP5:%.*]] = mul i64 [[TMP4]], 2
 ; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[V:%.*]], i64 0
 ; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 2 x i64> [[BROADCAST_SPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP9:%.*]] = icmp ne <vscale x 2 x i64> [[BROADCAST_SPLAT]], zeroinitializer
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
@@ -577,7 +578,6 @@ define void @predicated_sdiv(ptr noalias nocapture %a, i64 %v, i64 %n) {
 ; CHECK-NEXT:    [[TMP7:%.*]] = getelementptr inbounds i64, ptr [[A:%.*]], i64 [[TMP6]]
 ; CHECK-NEXT:    [[TMP8:%.*]] = getelementptr inbounds i64, ptr [[TMP7]], i32 0
 ; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <vscale x 2 x i64>, ptr [[TMP8]], align 8
-; CHECK-NEXT:    [[TMP9:%.*]] = icmp ne <vscale x 2 x i64> [[BROADCAST_SPLAT]], zeroinitializer
 ; CHECK-NEXT:    [[TMP10:%.*]] = select <vscale x 2 x i1> [[TMP9]], <vscale x 2 x i64> [[BROADCAST_SPLAT]], <vscale x 2 x i64> shufflevector (<vscale x 2 x i64> insertelement (<vscale x 2 x i64> poison, i64 1, i64 0), <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer)
 ; CHECK-NEXT:    [[TMP11:%.*]] = sdiv <vscale x 2 x i64> [[WIDE_LOAD]], [[TMP10]]
 ; CHECK-NEXT:    [[PREDPHI:%.*]] = select <vscale x 2 x i1> [[TMP9]], <vscale x 2 x i64> [[TMP11]], <vscale x 2 x i64> [[WIDE_LOAD]]
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/pr88802.ll b/llvm/test/Transforms/LoopVectorize/RISCV/pr88802.ll
index a91f92348ab261..1990590252ea6c 100644
--- a/llvm/test/Transforms/LoopVectorize/RISCV/pr88802.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/pr88802.ll
@@ -9,8 +9,10 @@ define void @test(ptr %p, i64 %a, i8 %b) {
 ; CHECK:       vector.ph:
 ; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i64> poison, i64 [[A]], i64 0
 ; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> poison, <4 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP2:%.*]] = shl <4 x i64> [[BROADCAST_SPLAT]], <i64 48, i64 48, i64 48, i64 48>
 ; CHECK-NEXT:    [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <4 x i8> poison, i8 [[B]], i64 0
 ; CHECK-NEXT:    [[BROADCAST_SPLAT2:%.*]] = shufflevector <4 x i8> [[BROADCAST_SPLATINSERT1]], <4 x i8> poison, <4 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP6:%.*]] = zext <4 x i8> [[BROADCAST_SPLAT2]] to <4 x i32>
 ; CHECK-NEXT:    br label [[VECTOR_BODY1:%.*]]
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[PRED_STORE_CONTINUE8:%.*]] ]
@@ -18,11 +20,9 @@ define void @test(ptr %p, i64 %a, i8 %b) {
 ; CHECK-NEXT:    [[TMP0:%.*]] = add i32 [[INDEX]], 0
 ; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 [[TMP0]], i32 3)
 ; CHECK-NEXT:    [[TMP1:%.*]] = icmp slt <4 x i32> [[VEC_IND]], <i32 2, i32 2, i32 2, i32 2>
-; CHECK-NEXT:    [[TMP2:%.*]] = shl <4 x i64> [[BROADCAST_SPLAT]], <i64 48, i64 48, i64 48, i64 48>
 ; CHECK-NEXT:    [[TMP3:%.*]] = ashr <4 x i64> [[TMP2]], <i64 52, i64 52, i64 52, i64 52>
 ; CHECK-NEXT:    [[TMP4:%.*]] = trunc <4 x i64> [[TMP3]] to <4 x i32>
 ; CHECK-NEXT:    [[TMP5:%.*]] = select <4 x i1> [[ACTIVE_LANE_MASK]], <4 x i1> [[TMP1]], <4 x i1> zeroinitializer
-; CHECK-NEXT:    [[TMP6:%.*]] = zext <4 x i8> [[BROADCAST_SPLAT2]] to <4 x i32>
 ; CHECK-NEXT:    [[PREDPHI:%.*]] = select <4 x i1> [[TMP5]], <4 x i32> [[TMP6]], <4 x i32> [[TMP4]]
 ; CHECK-NEXT:    [[TMP7:%.*]] = shl <4 x i32> [[PREDPHI]], <i32 8, i32 8, i32 8, i32 8>
 ; CHECK-NEXT:    [[TMP8:%.*]] = trunc <4 x i32> [[TMP7]] to <4 x i8>
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/truncate-to-minimal-bitwidth-cost.ll b/llvm/test/Transforms/LoopVectorize/RISCV/truncate-to-minimal-bitwidth-cost.ll
index a2c3f2bfa274c1..315064a474a2f6 100644
--- a/llvm/test/Transforms/LoopVectorize/RISCV/truncate-to-minimal-bitwidth-cost.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/truncate-to-minimal-bitwidth-cost.ll
@@ -288,6 +288,8 @@ define void @icmp_only_first_op_truncated(ptr noalias %dst, i32 %x, i64 %N, i64
 ; CHECK-NEXT:    [[TMP6:%.*]] = mul i64 [[TMP5]], 2
 ; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[N]], i64 0
 ; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 2 x i64> [[BROADCAST_SPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP7:%.*]] = trunc <vscale x 2 x i64> [[BROADCAST_SPLAT]] to <vscale x 2 x i32>
+; CHECK-NEXT:    [[TMP9:%.*]] = zext i32 [[X]] to i64
 ; CHECK-NEXT:    [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <vscale x 2 x i32> poison, i32 [[T]], i64 0
 ; CHECK-NEXT:    [[BROADCAST_SPLAT2:%.*]] = shufflevector <vscale x 2 x i32> [[BROADCAST_SPLATINSERT1]], <vscale x 2 x i32> poison, <vscale x 2 x i32> zeroinitializer
 ; CHECK-NEXT:    [[BROADCAST_SPLATINSERT5:%.*]] = insertelement <vscale x 2 x ptr> poison, ptr [[DST]], i64 0
@@ -295,9 +297,7 @@ define void @icmp_only_first_op_truncated(ptr noalias %dst, i32 %x, i64 %N, i64
 ; CHECK-NEXT:    br label %[[VECTOR_BODY:.*]]
 ; CHECK:       [[VECTOR_BODY]]:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
-; CHECK-NEXT:    [[TMP7:%.*]] = trunc <vscale x 2 x i64> [[BROADCAST_SPLAT]] to <vscale x 2 x i32>
 ; CHECK-NEXT:    [[TMP8:%.*]] = icmp eq <vscale x 2 x i32> [[TMP7]], [[BROADCAST_SPLAT2]]
-; CHECK-NEXT:    [[TMP9:%.*]] = zext i32 [[X]] to i64
 ; CHECK-NEXT:    [[TMP10:%.*]] = getelementptr double, ptr [[SRC]], i64 [[TMP9]]
 ; CHECK-NEXT:    [[BROADCAST_SPLATINSERT3:%.*]] = insertelement <vscale x 2 x ptr> poison, ptr [[TMP10]], i64 0
 ; CHECK-NEXT:    [[BROADCAST_SPLAT4:%.*]] = shufflevector <vscale x 2 x ptr> [[BROADCAST_SPLATINSERT3]], <vscale x 2 x ptr> poison, <vscale x 2 x i32> zeroinitializer
diff --git a/llvm/test/Transforms/LoopVectorize/SystemZ/pr47665.ll b/llvm/test/Transforms/LoopVectorize/SystemZ/pr47665.ll
index 07a1cca1bc21e7..b9a6235db6fa60 100644
--- a/llvm/test/Transforms/LoopVectorize/SystemZ/pr47665.ll
+++ b/llvm/test/Transforms/LoopVectorize/SystemZ/pr47665.ll
@@ -9,6 +9,7 @@ define void @test(ptr %p, i40 %a) {
 ; CHECK:       vector.ph:
 ; CHECK-NEXT:    [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <16 x i40> poison, i40 [[A]], i64 0
 ; CHECK-NEXT:    [[BROADCAST_SPLAT2:%.*]] = shufflevector <16 x i40> [[BROADCAST_SPLATINSERT1]], <16 x i40> poison, <16 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP1:%.*]] = shl <16 x i40> [[BROADCAST_SPLAT2]], <i40 24, i40 24, i40 24, i40 24, i40 24, i40 24, i40 24, i40 24, i40 24, i40 24, i40 24, i40 24, i40 24, i40 24, i40 24, i40 24>
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[PRED_STORE_CONTINUE32:%.*]] ]
@@ -16,7 +17,6 @@ define void @test(ptr %p, i40 %a) {
 ; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <16 x i32> [[BROADCAST_SPLATINSERT]], <16 x i32> poison, <16 x i32> zeroinitializer
 ; CHECK-NEXT:    [[VEC_IV:%.*]] = add <16 x i32> [[BROADCAST_SPLAT]], <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
 ; CHECK-NEXT:    [[TMP0:%.*]] = icmp ule <16 x i32> [[VEC_IV]], <i32 9, i32 9, i32 9, i32 9, i32 9, i32 9, i32 9, i32 9, i32 9, i32 9, i32 9, i32 9, i32 9, i32 9, i32 9, i32 9>
-; CHECK-NEXT:    [[TMP1:%.*]] = shl <16 x i40> [[BROADCAST_SPLAT2]], <i40 24, i40 24, i40 24, i40 24, i40 24, i40 24, i40 24, i40 24, i40 24, i40 24, i40 24, i40 24, i40 24, i40 24, i40 24, i40 24>
 ; CHECK-NEXT:    [[TMP2:%.*]] = ashr <16 x i40> [[TMP1]], <i40 28, i40 28, i40 28, i40 28, i40 28, i40 28, i40 28, i40 28, i40 28, i40 28, i40 28, i40 28, i40 28, i40 28, i40 28, i40 28>
 ; CHECK-NEXT:    [[TMP3:%.*]] = trunc <16 x i40> [[TMP2]] to <16 x i32>
 ; CHECK-NEXT:    [[TMP4:%.*]] = trunc <16 x i32> [[TMP3]] to <16 x i1>
diff --git a/llvm/test/Transforms/LoopVectorize/X86/cost-model.ll b/llvm/test/Transforms/LoopVectorize/X86/cost-model.ll
index 8877e65a0d9d73..12259d4c011b3e 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/cost-model.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/cost-model.ll
@@ -782,6 +782,10 @@ define i64 @cost_assume(ptr %end, i64 %N) {
 ; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[TMP2]], [[N_MOD_VF]]
 ; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <2 x i64> poison, i64 [[N:%.*]], i64 0
 ; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <2 x i64> [[BROADCAST_SPLATINSERT]], <2 x i64> poison, <2 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP7:%.*]] = icmp ne <2 x i64> [[BROADCAST_SPLAT]], zeroinitializer
+; CHECK-NEXT:    [[TMP8:%.*]] = icmp ne <2 x i64> [[BROADCAST_SPLAT]], zeroinitializer
+; CHECK-NEXT:    [[TMP9:%.*]] = icmp ne <2 x i64> [[BROADCAST_SPLAT]], zeroinitializer
+; CHECK-NEXT:    [[TMP10:%.*]] = icmp ne <2 x i64> [[BROADCAST_SPLAT]], zeroinitializer
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
@@ -793,10 +797,6 @@ define i64 @cost_assume(ptr %end, i64 %N) {
 ; CHECK-NEXT:    [[TMP4]] = add <2 x i64> [[VEC_PHI2]], <i64 1, i64 1>
 ; CHECK-NEXT:    [[TMP5]] = add <2 x i64> [[VEC_PHI3]], <i64 1, i64 1>
 ; CHECK-NEXT:    [[TMP6]] = add <2 x i64> [[VEC_PHI4]], <i64 1, i64 1>
-; CHECK-NEXT:    [[TMP7:%.*]] = icmp ne <2 x i64> [[BROADCAST_SPLAT]], zeroinitializer
-; CHECK-NEXT:    [[TMP8:%.*]] = icmp ne <2 x i64> [[BROADCAST_SPLAT]], zeroinitializer
-; CHECK-NEXT:    [[TMP9:%.*]] = icmp ne <2 x i64> [[BROADCAST_SPLAT]], zeroinitializer
-; CHECK-NEXT:    [[TMP10:%.*]] = icmp ne <2 x i64> [[BROADCAST_SPLAT]], zeroinitializer
 ; CHECK-NEXT:    [[TMP11:%.*]] = extractelement <2 x i1> [[TMP7]], i32 0
 ; CHECK-NEXT:    tail call void @llvm.assume(i1 [[TMP11]])
 ; CHECK-NEXT:    [[TMP12:%.*]] = extractelement <2 x i1> [[TMP7]], i32 1
diff --git a/llvm/test/Transforms/LoopVectorize/X86/divs-with-tail-folding.ll b/llvm/test/Transforms/LoopVectorize/X86/divs-with-tail-folding.ll
index 32964d650ea0f7..7566844ff39df8 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/divs-with-tail-folding.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/divs-with-tail-folding.ll
@@ -19,6 +19,7 @@ define void @sdiv_feeding_gep(ptr %dst, i32 %x, i64 %M, i64 %conv6, i64 %N) {
 ; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], 4
 ; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
 ; CHECK-NEXT:    [[TRIP_COUNT_MINUS_1:%.*]] = sub i64 [[N]], 1
+; CHECK-NEXT:    [[TMP17:%.*]] = sdiv i64 [[M]], [[CONV6]]
 ; CHECK-NEXT:    [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <4 x i64> poison, i64 [[TRIP_COUNT_MINUS_1]], i64 0
 ; CHECK-NEXT:    [[BROADCAST_SPLAT2:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT1]], <4 x i64> poison, <4 x i32> zeroinitializer
 ; CHECK-NEXT:    br label %[[VECTOR_BODY:.*]]
@@ -29,7 +30,6 @@ define void @sdiv_feeding_gep(ptr %dst, i32 %x, i64 %M, i64 %conv6, i64 %N) {
 ; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> poison, <4 x i32> zeroinitializer
 ; CHECK-NEXT:    [[VEC_IV:%.*]] = add <4 x i64> [[BROADCAST_SPLAT]], <i64 0, i64 1, i64 2, i64 3>
 ; CHECK-NEXT:    [[TMP6:%.*]] = icmp ule <4 x i64> [[VEC_IV]], [[BROADCAST_SPLAT2]]
-; CHECK-NEXT:    [[TMP17:%.*]] = sdiv i64 [[M]], [[CONV6]]
 ; CHECK-NEXT:    [[TMP19:%.*]] = trunc i64 [[TMP17]] to i32
 ; CHECK-NEXT:    [[TMP20:%.*]] = mul i64 [[TMP17]], [[CONV61]]
 ; CHECK-NEXT:    [[TMP21:%.*]] = sub i64 [[TMP5]], [[TMP20]]
diff --git a/llvm/test/Transforms/LoopVectorize/X86/invariant-load-gather.ll b/llvm/test/Transforms/LoopVectorize/X86/invariant-load-gather.ll
index 9f9db3ad859911..c9a47a60866f17 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/invariant-load-gather.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/invariant-load-gather.ll
@@ -26,6 +26,7 @@ define i32 @inv_load_conditional(ptr %a, i64 %n, ptr %b, i32 %k) {
 ; CHECK-NEXT:    [[N_VEC:%.*]] = and i64 [[SMAX2]], 9223372036854775792
 ; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <16 x ptr> poison, ptr [[A]], i64 0
 ; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <16 x ptr> [[BROADCAST_SPLATINSERT]], <16 x ptr> poison, <16 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP3:%.*]] = icmp ne <16 x ptr> [[BROADCAST_SPLAT]], zeroinitializer
 ; CHECK-NEXT:    [[BROADCAST_SPLATINSERT4:%.*]] = insertelement <16 x i32> poison, i32 [[NTRUNC]], i64 0
 ; CHECK-NEXT:    [[BROADCAST_SPLAT5:%.*]] = shufflevector <16 x i32> [[BROADCAST_SPLATINSERT4]], <16 x i32> poison, <16 x i32> zeroinitializer
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
@@ -37,7 +38,6 @@ define i32 @inv_load_conditional(ptr %a, i64 %n, ptr %b, i32 %k) {
 ; CHECK-NEXT:    [[TMP2:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
 ; CHECK-NEXT:    br i1 [[TMP2]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
 ; CHECK:       middle.block:
-; CHECK-NEXT:    [[TMP3:%.*]] = icmp ne <16 x ptr> [[BROADCAST_SPLAT]], zeroinitializer
 ; CHECK-NEXT:    [[WIDE_MASKED_GATHER:%.*]] = call <16 x i32> @llvm.masked.gather.v16i32.v16p0(<16 x ptr> [[BROADCAST_SPLAT]], i32 4, <16 x i1> [[TMP3]], <16 x i32> poison), !alias.scope [[META3]]
 ; CHECK-NEXT:    [[PREDPHI:%.*]] = select <16 x i1> [[TMP3]], <16 x i32> [[WIDE_MASKED_GATHER]], <16 x i32> <i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison,...
[truncated]

``````````

</details>


https://github.com/llvm/llvm-project/pull/107894


More information about the llvm-commits mailing list