[llvm] ba40a7b - [LoopVectorize] Vectorize fixed-order recurrence with vscale x 1. (#142772)
via llvm-commits
llvm-commits at lists.llvm.org
Wed Jun 18 01:03:24 PDT 2025
Author: Mel Chen
Date: 2025-06-18T16:03:20+08:00
New Revision: ba40a7bc2e65be86ac23c9cf6038ac085dda77eb
URL: https://github.com/llvm/llvm-project/commit/ba40a7bc2e65be86ac23c9cf6038ac085dda77eb
DIFF: https://github.com/llvm/llvm-project/commit/ba40a7bc2e65be86ac23c9cf6038ac085dda77eb.diff
LOG: [LoopVectorize] Vectorize fixed-order recurrence with vscale x 1. (#142772)
When the fixed-order recurrence phi is live-out from the loop, the
vectorizer uses VPInstruction::ExtractPenultimateElement to extract the
penultimate element from the recurrence vector. However, this is not
feasible when the VF is vscale x 1, since vscale could be 1, making the
vector contain only one element.
This patch changes the behavior for vscale x 1 by extracting the last
element from the vector produced by splicing the recurrence phi and the
previous value. This ensures we can still determine the correct live-out
value of the recurrence phi.
Added:
Modified:
llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp
llvm/test/Transforms/LoopVectorize/RISCV/first-order-recurrence-scalable-vf1.ll
llvm/test/Transforms/LoopVectorize/first-order-recurrence-scalable-vf1.ll
Removed:
################################################################################
diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
index f887b34e76422..16d48b06dce41 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -6163,11 +6163,6 @@ LoopVectorizationCostModel::getInstructionCost(Instruction *I,
// First-order recurrences are replaced by vector shuffles inside the loop.
if (VF.isVector() && Legal->isFixedOrderRecurrence(Phi)) {
- // For <vscale x 1 x i64>, if vscale = 1 we are unable to extract the
- // penultimate value of the recurrence.
- // TODO: Consider vscale_range info.
- if (VF.isScalable() && VF.getKnownMinValue() == 1)
- return InstructionCost::getInvalid();
SmallVector<int> Mask(VF.getKnownMinValue());
std::iota(Mask.begin(), Mask.end(), VF.getKnownMinValue() - 1);
return TTI.getShuffleCost(TargetTransformInfo::SK_Splice,
@@ -8556,13 +8551,17 @@ addUsersInExitBlocks(VPlan &Plan,
/// users in the original exit block using the VPIRInstruction wrapping to the
/// LCSSA phi.
static void addExitUsersForFirstOrderRecurrences(
- VPlan &Plan, SetVector<VPIRInstruction *> &ExitUsersToFix) {
+ VPlan &Plan, SetVector<VPIRInstruction *> &ExitUsersToFix, VFRange &Range) {
VPRegionBlock *VectorRegion = Plan.getVectorLoopRegion();
auto *ScalarPHVPBB = Plan.getScalarPreheader();
auto *MiddleVPBB = Plan.getMiddleBlock();
VPBuilder ScalarPHBuilder(ScalarPHVPBB);
VPBuilder MiddleBuilder(MiddleVPBB, MiddleVPBB->getFirstNonPhi());
+ auto IsScalableOne = [](ElementCount VF) -> bool {
+ return VF == ElementCount::getScalable(1);
+ };
+
for (auto &HeaderPhi : VectorRegion->getEntryBasicBlock()->phis()) {
auto *FOR = dyn_cast<VPFirstOrderRecurrencePHIRecipe>(&HeaderPhi);
if (!FOR)
@@ -8644,6 +8643,15 @@ static void addExitUsersForFirstOrderRecurrences(
for (VPIRInstruction *ExitIRI : ExitUsersToFix) {
if (ExitIRI->getOperand(0) != FOR)
continue;
+ // For VF vscale x 1, if vscale = 1, we are unable to extract the
+ // penultimate value of the recurrence. Instead, we rely on function
+ // addUsersInExitBlocks to extract the last element from the result of
+ // VPInstruction::FirstOrderRecurrenceSplice by leaving the user of the
+ // recurrence phi in ExitUsersToFix.
+ // TODO: Consider vscale_range info and UF.
+ if (LoopVectorizationPlanner::getDecisionAndClampRange(IsScalableOne,
+ Range))
+ return;
VPValue *PenultimateElement = MiddleBuilder.createNaryOp(
VPInstruction::ExtractPenultimateElement, {FOR->getBackedgeValue()},
{}, "vector.recur.extract.for.phi");
@@ -8858,7 +8866,7 @@ VPlanPtr LoopVectorizationPlanner::tryToBuildVPlanWithVPRecipes(
addScalarResumePhis(RecipeBuilder, *Plan, IVEndValues);
SetVector<VPIRInstruction *> ExitUsersToFix =
collectUsersInLatchExitBlock(*Plan);
- addExitUsersForFirstOrderRecurrences(*Plan, ExitUsersToFix);
+ addExitUsersForFirstOrderRecurrences(*Plan, ExitUsersToFix, Range);
addUsersInExitBlocks(*Plan, ExitUsersToFix);
// ---------------------------------------------------------------------------
diff --git a/llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp b/llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp
index 1ed0b97849a8d..f3b5c8cfa9885 100644
--- a/llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp
+++ b/llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp
@@ -3680,9 +3680,6 @@ VPFirstOrderRecurrencePHIRecipe::computeCost(ElementCount VF,
if (VF.isScalar())
return Ctx.TTI.getCFInstrCost(Instruction::PHI, Ctx.CostKind);
- if (VF == ElementCount::getScalable(1))
- return InstructionCost::getInvalid();
-
return 0;
}
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/first-order-recurrence-scalable-vf1.ll b/llvm/test/Transforms/LoopVectorize/RISCV/first-order-recurrence-scalable-vf1.ll
index d340985457168..e3f9540ff3df7 100644
--- a/llvm/test/Transforms/LoopVectorize/RISCV/first-order-recurrence-scalable-vf1.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/first-order-recurrence-scalable-vf1.ll
@@ -1,56 +1,63 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
-; RUN: opt -p loop-vectorize -S %s | FileCheck %s
+; RUN: opt -p loop-vectorize -scalable-vectorization=on -S %s | FileCheck %s
target datalayout = "e-m:e-p:64:64-i64:64-i128:128-n32:64-S128"
target triple = "riscv64-unknown-linux-gnu"
-; Make sure we do not pick <vscale x 1 x i64> as VF for a loop with a
-; first-order recurrence.
define i64 @pr97452_scalable_vf1_for(ptr %src, ptr noalias %dst) #0 {
; CHECK-LABEL: define i64 @pr97452_scalable_vf1_for(
; CHECK-SAME: ptr [[SRC:%.*]], ptr noalias [[DST:%.*]]) #[[ATTR0:[0-9]+]] {
; CHECK-NEXT: [[ENTRY:.*]]:
-; CHECK-NEXT: br i1 false, label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
+; CHECK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 23, [[TMP0]]
+; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
; CHECK: [[VECTOR_PH]]:
+; CHECK-NEXT: [[TMP1:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 23, [[TMP1]]
+; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 23, [[N_MOD_VF]]
+; CHECK-NEXT: [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT: [[TMP3:%.*]] = call i32 @llvm.vscale.i32()
+; CHECK-NEXT: [[TMP4:%.*]] = sub i32 [[TMP3]], 1
+; CHECK-NEXT: [[VECTOR_RECUR_INIT:%.*]] = insertelement <vscale x 1 x i64> poison, i64 0, i32 [[TMP4]]
; CHECK-NEXT: br label %[[VECTOR_BODY:.*]]
; CHECK: [[VECTOR_BODY]]:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
-; CHECK-NEXT: [[VECTOR_RECUR:%.*]] = phi <4 x i64> [ <i64 poison, i64 poison, i64 poison, i64 0>, %[[VECTOR_PH]] ], [ [[WIDE_LOAD1:%.*]], %[[VECTOR_BODY]] ]
-; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds i64, ptr [[SRC]], i64 [[INDEX]]
-; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds i64, ptr [[TMP2]], i32 0
-; CHECK-NEXT: [[TMP5:%.*]] = getelementptr inbounds i64, ptr [[TMP2]], i32 4
-; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <4 x i64>, ptr [[TMP1]], align 8
-; CHECK-NEXT: [[WIDE_LOAD1]] = load <4 x i64>, ptr [[TMP5]], align 8
-; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <4 x i64> [[VECTOR_RECUR]], <4 x i64> [[WIDE_LOAD]], <4 x i32> <i32 3, i32 4, i32 5, i32 6>
-; CHECK-NEXT: [[TMP4:%.*]] = shufflevector <4 x i64> [[WIDE_LOAD]], <4 x i64> [[WIDE_LOAD1]], <4 x i32> <i32 3, i32 4, i32 5, i32 6>
+; CHECK-NEXT: [[VECTOR_RECUR:%.*]] = phi <vscale x 1 x i64> [ [[VECTOR_RECUR_INIT]], %[[VECTOR_PH]] ], [ [[WIDE_LOAD:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT: [[TMP5:%.*]] = getelementptr inbounds i64, ptr [[SRC]], i64 [[INDEX]]
+; CHECK-NEXT: [[TMP6:%.*]] = getelementptr inbounds i64, ptr [[TMP5]], i32 0
+; CHECK-NEXT: [[WIDE_LOAD]] = load <vscale x 1 x i64>, ptr [[TMP6]], align 8
+; CHECK-NEXT: [[TMP7:%.*]] = call <vscale x 1 x i64> @llvm.vector.splice.nxv1i64(<vscale x 1 x i64> [[VECTOR_RECUR]], <vscale x 1 x i64> [[WIDE_LOAD]], i32 -1)
; CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds i64, ptr [[DST]], i64 [[INDEX]]
; CHECK-NEXT: [[TMP9:%.*]] = getelementptr inbounds i64, ptr [[TMP8]], i32 0
-; CHECK-NEXT: [[TMP7:%.*]] = getelementptr inbounds i64, ptr [[TMP8]], i32 4
-; CHECK-NEXT: store <4 x i64> [[TMP3]], ptr [[TMP9]], align 8
-; CHECK-NEXT: store <4 x i64> [[TMP4]], ptr [[TMP7]], align 8
-; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 8
-; CHECK-NEXT: [[TMP6:%.*]] = icmp eq i64 [[INDEX_NEXT]], 16
-; CHECK-NEXT: br i1 [[TMP6]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
+; CHECK-NEXT: store <vscale x 1 x i64> [[TMP7]], ptr [[TMP9]], align 8
+; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP2]]
+; CHECK-NEXT: [[TMP10:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT: br i1 [[TMP10]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK: [[MIDDLE_BLOCK]]:
-; CHECK-NEXT: [[VECTOR_RECUR_EXTRACT_FOR_PHI:%.*]] = extractelement <4 x i64> [[WIDE_LOAD1]], i32 2
-; CHECK-NEXT: [[VECTOR_RECUR_EXTRACT:%.*]] = extractelement <4 x i64> [[WIDE_LOAD1]], i32 3
-; CHECK-NEXT: br i1 false, label %[[EXIT:.*]], label %[[SCALAR_PH]]
+; CHECK-NEXT: [[TMP11:%.*]] = call i32 @llvm.vscale.i32()
+; CHECK-NEXT: [[TMP12:%.*]] = sub i32 [[TMP11]], 1
+; CHECK-NEXT: [[TMP13:%.*]] = extractelement <vscale x 1 x i64> [[TMP7]], i32 [[TMP12]]
+; CHECK-NEXT: [[TMP14:%.*]] = call i32 @llvm.vscale.i32()
+; CHECK-NEXT: [[TMP15:%.*]] = sub i32 [[TMP14]], 1
+; CHECK-NEXT: [[VECTOR_RECUR_EXTRACT:%.*]] = extractelement <vscale x 1 x i64> [[WIDE_LOAD]], i32 [[TMP15]]
+; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 23, [[N_VEC]]
+; CHECK-NEXT: br i1 [[CMP_N]], label %[[EXIT:.*]], label %[[SCALAR_PH]]
; CHECK: [[SCALAR_PH]]:
; CHECK-NEXT: [[SCALAR_RECUR_INIT:%.*]] = phi i64 [ [[VECTOR_RECUR_EXTRACT]], %[[MIDDLE_BLOCK]] ], [ 0, %[[ENTRY]] ]
-; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ 16, %[[MIDDLE_BLOCK]] ], [ 0, %[[ENTRY]] ]
+; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], %[[MIDDLE_BLOCK]] ], [ 0, %[[ENTRY]] ]
; CHECK-NEXT: br label %[[LOOP:.*]]
; CHECK: [[LOOP]]:
; CHECK-NEXT: [[FOR:%.*]] = phi i64 [ [[SCALAR_RECUR_INIT]], %[[SCALAR_PH]] ], [ [[L:%.*]], %[[LOOP]] ]
; CHECK-NEXT: [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], %[[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], %[[LOOP]] ]
; CHECK-NEXT: [[IV_NEXT]] = add i64 [[IV]], 1
-; CHECK-NEXT: [[GEP:%.*]] = getelementptr inbounds i64, ptr [[SRC]], i64 [[IV]]
-; CHECK-NEXT: [[L]] = load i64, ptr [[GEP]], align 8
+; CHECK-NEXT: [[GEP_SRC:%.*]] = getelementptr inbounds i64, ptr [[SRC]], i64 [[IV]]
+; CHECK-NEXT: [[L]] = load i64, ptr [[GEP_SRC]], align 8
; CHECK-NEXT: [[GEP_DST:%.*]] = getelementptr inbounds i64, ptr [[DST]], i64 [[IV]]
; CHECK-NEXT: store i64 [[FOR]], ptr [[GEP_DST]], align 8
; CHECK-NEXT: [[EC:%.*]] = icmp eq i64 [[IV]], 22
; CHECK-NEXT: br i1 [[EC]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP3:![0-9]+]]
; CHECK: [[EXIT]]:
-; CHECK-NEXT: [[RES:%.*]] = phi i64 [ [[FOR]], %[[LOOP]] ], [ [[VECTOR_RECUR_EXTRACT_FOR_PHI]], %[[MIDDLE_BLOCK]] ]
+; CHECK-NEXT: [[RES:%.*]] = phi i64 [ [[FOR]], %[[LOOP]] ], [ [[TMP13]], %[[MIDDLE_BLOCK]] ]
; CHECK-NEXT: ret i64 [[RES]]
;
entry:
diff --git a/llvm/test/Transforms/LoopVectorize/first-order-recurrence-scalable-vf1.ll b/llvm/test/Transforms/LoopVectorize/first-order-recurrence-scalable-vf1.ll
index 98a942a501077..b20d59bd5760e 100644
--- a/llvm/test/Transforms/LoopVectorize/first-order-recurrence-scalable-vf1.ll
+++ b/llvm/test/Transforms/LoopVectorize/first-order-recurrence-scalable-vf1.ll
@@ -8,17 +8,51 @@ define i64 @pr97452_scalable_vf1_for_live_out(ptr %src) {
; CHECK-LABEL: define i64 @pr97452_scalable_vf1_for_live_out(
; CHECK-SAME: ptr [[SRC:%.*]]) {
; CHECK-NEXT: [[ENTRY:.*]]:
+; CHECK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 23, [[TMP0]]
+; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
+; CHECK: [[VECTOR_PH]]:
+; CHECK-NEXT: [[TMP1:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 23, [[TMP1]]
+; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 23, [[N_MOD_VF]]
+; CHECK-NEXT: [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT: [[TMP3:%.*]] = call i32 @llvm.vscale.i32()
+; CHECK-NEXT: [[TMP4:%.*]] = sub i32 [[TMP3]], 1
+; CHECK-NEXT: [[VECTOR_RECUR_INIT:%.*]] = insertelement <vscale x 1 x i64> poison, i64 0, i32 [[TMP4]]
+; CHECK-NEXT: br label %[[VECTOR_BODY:.*]]
+; CHECK: [[VECTOR_BODY]]:
+; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT: [[VECTOR_RECUR:%.*]] = phi <vscale x 1 x i64> [ [[VECTOR_RECUR_INIT]], %[[VECTOR_PH]] ], [ [[WIDE_LOAD:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT: [[TMP5:%.*]] = getelementptr inbounds i64, ptr [[SRC]], i64 [[INDEX]]
+; CHECK-NEXT: [[TMP6:%.*]] = getelementptr inbounds i64, ptr [[TMP5]], i32 0
+; CHECK-NEXT: [[WIDE_LOAD]] = load <vscale x 1 x i64>, ptr [[TMP6]], align 8
+; CHECK-NEXT: [[TMP7:%.*]] = call <vscale x 1 x i64> @llvm.vector.splice.nxv1i64(<vscale x 1 x i64> [[VECTOR_RECUR]], <vscale x 1 x i64> [[WIDE_LOAD]], i32 -1)
+; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP2]]
+; CHECK-NEXT: [[TMP8:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT: br i1 [[TMP8]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
+; CHECK: [[MIDDLE_BLOCK]]:
+; CHECK-NEXT: [[TMP9:%.*]] = call i32 @llvm.vscale.i32()
+; CHECK-NEXT: [[TMP10:%.*]] = sub i32 [[TMP9]], 1
+; CHECK-NEXT: [[TMP11:%.*]] = extractelement <vscale x 1 x i64> [[TMP7]], i32 [[TMP10]]
+; CHECK-NEXT: [[TMP12:%.*]] = call i32 @llvm.vscale.i32()
+; CHECK-NEXT: [[TMP13:%.*]] = sub i32 [[TMP12]], 1
+; CHECK-NEXT: [[VECTOR_RECUR_EXTRACT:%.*]] = extractelement <vscale x 1 x i64> [[WIDE_LOAD]], i32 [[TMP13]]
+; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 23, [[N_VEC]]
+; CHECK-NEXT: br i1 [[CMP_N]], label %[[EXIT:.*]], label %[[SCALAR_PH]]
+; CHECK: [[SCALAR_PH]]:
+; CHECK-NEXT: [[SCALAR_RECUR_INIT:%.*]] = phi i64 [ [[VECTOR_RECUR_EXTRACT]], %[[MIDDLE_BLOCK]] ], [ 0, %[[ENTRY]] ]
+; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], %[[MIDDLE_BLOCK]] ], [ 0, %[[ENTRY]] ]
; CHECK-NEXT: br label %[[LOOP:.*]]
; CHECK: [[LOOP]]:
-; CHECK-NEXT: [[FOR:%.*]] = phi i64 [ 0, %[[ENTRY]] ], [ [[L:%.*]], %[[LOOP]] ]
-; CHECK-NEXT: [[IV:%.*]] = phi i64 [ 0, %[[ENTRY]] ], [ [[IV_NEXT:%.*]], %[[LOOP]] ]
+; CHECK-NEXT: [[FOR:%.*]] = phi i64 [ [[SCALAR_RECUR_INIT]], %[[SCALAR_PH]] ], [ [[L:%.*]], %[[LOOP]] ]
+; CHECK-NEXT: [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], %[[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], %[[LOOP]] ]
; CHECK-NEXT: [[IV_NEXT]] = add i64 [[IV]], 1
; CHECK-NEXT: [[GEP:%.*]] = getelementptr inbounds i64, ptr [[SRC]], i64 [[IV]]
; CHECK-NEXT: [[L]] = load i64, ptr [[GEP]], align 8
; CHECK-NEXT: [[EC:%.*]] = icmp eq i64 [[IV]], 22
-; CHECK-NEXT: br i1 [[EC]], label %[[EXIT:.*]], label %[[LOOP]]
+; CHECK-NEXT: br i1 [[EC]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP3:![0-9]+]]
; CHECK: [[EXIT]]:
-; CHECK-NEXT: [[RES:%.*]] = phi i64 [ [[FOR]], %[[LOOP]] ]
+; CHECK-NEXT: [[RES:%.*]] = phi i64 [ [[FOR]], %[[LOOP]] ], [ [[TMP11]], %[[MIDDLE_BLOCK]] ]
; CHECK-NEXT: ret i64 [[RES]]
;
entry:
@@ -43,17 +77,51 @@ define void @pr97452_scalable_vf1_for_no_live_out(ptr %src, ptr noalias %dst) {
; CHECK-LABEL: define void @pr97452_scalable_vf1_for_no_live_out(
; CHECK-SAME: ptr [[SRC:%.*]], ptr noalias [[DST:%.*]]) {
; CHECK-NEXT: [[ENTRY:.*]]:
+; CHECK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 23, [[TMP0]]
+; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
+; CHECK: [[VECTOR_PH]]:
+; CHECK-NEXT: [[TMP1:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 23, [[TMP1]]
+; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 23, [[N_MOD_VF]]
+; CHECK-NEXT: [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT: [[TMP3:%.*]] = call i32 @llvm.vscale.i32()
+; CHECK-NEXT: [[TMP4:%.*]] = sub i32 [[TMP3]], 1
+; CHECK-NEXT: [[VECTOR_RECUR_INIT:%.*]] = insertelement <vscale x 1 x i64> poison, i64 0, i32 [[TMP4]]
+; CHECK-NEXT: br label %[[VECTOR_BODY:.*]]
+; CHECK: [[VECTOR_BODY]]:
+; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT: [[VECTOR_RECUR:%.*]] = phi <vscale x 1 x i64> [ [[VECTOR_RECUR_INIT]], %[[VECTOR_PH]] ], [ [[WIDE_LOAD:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT: [[TMP5:%.*]] = getelementptr inbounds i64, ptr [[SRC]], i64 [[INDEX]]
+; CHECK-NEXT: [[TMP6:%.*]] = getelementptr inbounds i64, ptr [[TMP5]], i32 0
+; CHECK-NEXT: [[WIDE_LOAD]] = load <vscale x 1 x i64>, ptr [[TMP6]], align 8
+; CHECK-NEXT: [[TMP7:%.*]] = call <vscale x 1 x i64> @llvm.vector.splice.nxv1i64(<vscale x 1 x i64> [[VECTOR_RECUR]], <vscale x 1 x i64> [[WIDE_LOAD]], i32 -1)
+; CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds i64, ptr [[DST]], i64 [[INDEX]]
+; CHECK-NEXT: [[TMP9:%.*]] = getelementptr inbounds i64, ptr [[TMP8]], i32 0
+; CHECK-NEXT: store <vscale x 1 x i64> [[TMP7]], ptr [[TMP9]], align 8
+; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP2]]
+; CHECK-NEXT: [[TMP10:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT: br i1 [[TMP10]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
+; CHECK: [[MIDDLE_BLOCK]]:
+; CHECK-NEXT: [[TMP11:%.*]] = call i32 @llvm.vscale.i32()
+; CHECK-NEXT: [[TMP12:%.*]] = sub i32 [[TMP11]], 1
+; CHECK-NEXT: [[VECTOR_RECUR_EXTRACT:%.*]] = extractelement <vscale x 1 x i64> [[WIDE_LOAD]], i32 [[TMP12]]
+; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 23, [[N_VEC]]
+; CHECK-NEXT: br i1 [[CMP_N]], label %[[EXIT:.*]], label %[[SCALAR_PH]]
+; CHECK: [[SCALAR_PH]]:
+; CHECK-NEXT: [[SCALAR_RECUR_INIT:%.*]] = phi i64 [ [[VECTOR_RECUR_EXTRACT]], %[[MIDDLE_BLOCK]] ], [ 0, %[[ENTRY]] ]
+; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], %[[MIDDLE_BLOCK]] ], [ 0, %[[ENTRY]] ]
; CHECK-NEXT: br label %[[LOOP:.*]]
; CHECK: [[LOOP]]:
-; CHECK-NEXT: [[FOR:%.*]] = phi i64 [ 0, %[[ENTRY]] ], [ [[L:%.*]], %[[LOOP]] ]
-; CHECK-NEXT: [[IV:%.*]] = phi i64 [ 0, %[[ENTRY]] ], [ [[IV_NEXT:%.*]], %[[LOOP]] ]
+; CHECK-NEXT: [[FOR:%.*]] = phi i64 [ [[SCALAR_RECUR_INIT]], %[[SCALAR_PH]] ], [ [[L:%.*]], %[[LOOP]] ]
+; CHECK-NEXT: [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], %[[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], %[[LOOP]] ]
; CHECK-NEXT: [[IV_NEXT]] = add i64 [[IV]], 1
; CHECK-NEXT: [[GEP:%.*]] = getelementptr inbounds i64, ptr [[SRC]], i64 [[IV]]
; CHECK-NEXT: [[L]] = load i64, ptr [[GEP]], align 8
; CHECK-NEXT: [[GEP_DST:%.*]] = getelementptr inbounds i64, ptr [[DST]], i64 [[IV]]
; CHECK-NEXT: store i64 [[FOR]], ptr [[GEP_DST]], align 8
; CHECK-NEXT: [[EC:%.*]] = icmp eq i64 [[IV]], 22
-; CHECK-NEXT: br i1 [[EC]], label %[[EXIT:.*]], label %[[LOOP]]
+; CHECK-NEXT: br i1 [[EC]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP5:![0-9]+]]
; CHECK: [[EXIT]]:
; CHECK-NEXT: ret void
;
@@ -74,3 +142,11 @@ loop:
exit:
ret void
}
+;.
+; CHECK: [[LOOP0]] = distinct !{[[LOOP0]], [[META1:![0-9]+]], [[META2:![0-9]+]]}
+; CHECK: [[META1]] = !{!"llvm.loop.isvectorized", i32 1}
+; CHECK: [[META2]] = !{!"llvm.loop.unroll.runtime.disable"}
+; CHECK: [[LOOP3]] = distinct !{[[LOOP3]], [[META2]], [[META1]]}
+; CHECK: [[LOOP4]] = distinct !{[[LOOP4]], [[META1]], [[META2]]}
+; CHECK: [[LOOP5]] = distinct !{[[LOOP5]], [[META2]], [[META1]]}
+;.
More information about the llvm-commits
mailing list