Skip to content

[VPlan] Create AVL as a phi from TC -> 0 with EVL tail folding #151481

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 5 commits into from
Aug 1, 2025
Merged

[VPlan] Create AVL as a phi from TC -> 0 with EVL tail folding #151481

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
5b480e0
[VPlan] Create AVL as a phi from TC -> 0 with EVL tail folding
lukel97 Jul 31, 2025
360b65f
Update vplan debug output tests
lukel97 Jul 31, 2025
b4cc0f1
Address review comments
lukel97 Jul 31, 2025
9dc9ef5
Update tryAddExplicitVectorLength comment
lukel97 Jul 31, 2025
055c142
Merge branch 'main' of github.com:llvm/llvm-project into loop-vectori…
lukel97 Aug 1, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
34 changes: 23 additions & 11 deletions llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1483,11 +1483,11 @@ static bool simplifyBranchConditionForVFAndUF(VPlan &Plan, ElementCount BestVF,
auto *CanIVTy = Plan.getCanonicalIV()->getScalarType();
if (all_of(Header->phis(),
IsaPred<VPCanonicalIVPHIRecipe, VPEVLBasedIVPHIRecipe,
VPFirstOrderRecurrencePHIRecipe>)) {
VPFirstOrderRecurrencePHIRecipe, VPPhi>)) {
for (VPRecipeBase &HeaderR : make_early_inc_range(Header->phis())) {
auto *HeaderPhiR = cast<VPHeaderPHIRecipe>(&HeaderR);
HeaderPhiR->replaceAllUsesWith(HeaderPhiR->getStartValue());
HeaderPhiR->eraseFromParent();
auto *Phi = cast<VPPhiAccessors>(&HeaderR);
HeaderR.getVPSingleValue()->replaceAllUsesWith(Phi->getIncomingValue(0));
HeaderR.eraseFromParent();
}

VPBlockBase *Preheader = VectorRegion->getSinglePredecessor();
Expand Down Expand Up @@ -2292,10 +2292,12 @@ static void transformRecipestoEVLRecipes(VPlan &Plan, VPValue &EVL) {
/// ...
/// %EVLPhi = EXPLICIT-VECTOR-LENGTH-BASED-IV-PHI [ %StartV, %vector.ph ],
/// [ %NextEVLIV, %vector.body ]
/// %AVL = sub original TC, %EVLPhi
/// %AVL = phi [ trip-count, %vector.ph ], [ %NextAVL, %vector.body ]
/// %VPEVL = EXPLICIT-VECTOR-LENGTH %AVL
/// ...
/// %NextEVLIV = add IVSize (cast i32 %VPEVVL to IVSize), %EVLPhi
/// %OpEVL = cast i32 %VPEVL to IVSize
/// %NextEVLIV = add IVSize %OpEVL, %EVLPhi
/// %NextAVL = sub IVSize nuw %AVL, %OpEVL
/// ...
///
/// If MaxSafeElements is provided, the function adds the following recipes:
Expand All @@ -2306,12 +2308,14 @@ static void transformRecipestoEVLRecipes(VPlan &Plan, VPValue &EVL) {
/// ...
/// %EVLPhi = EXPLICIT-VECTOR-LENGTH-BASED-IV-PHI [ %StartV, %vector.ph ],
/// [ %NextEVLIV, %vector.body ]
/// %AVL = sub original TC, %EVLPhi
/// %AVL = phi [ trip-count, %vector.ph ], [ %NextAVL, %vector.body ]
/// %cmp = cmp ult %AVL, MaxSafeElements
/// %SAFE_AVL = select %cmp, %AVL, MaxSafeElements
/// %VPEVL = EXPLICIT-VECTOR-LENGTH %SAFE_AVL
/// ...
/// %NextEVLIV = add IVSize (cast i32 %VPEVL to IVSize), %EVLPhi
/// %OpEVL = cast i32 %VPEVL to IVSize
/// %NextEVLIV = add IVSize %OpEVL, %EVLPhi
/// %NextAVL = sub IVSize nuw %AVL, %OpEVL
/// ...
///
bool VPlanTransforms::tryAddExplicitVectorLength(
Expand All @@ -2333,9 +2337,12 @@ bool VPlanTransforms::tryAddExplicitVectorLength(
auto *EVLPhi = new VPEVLBasedIVPHIRecipe(StartV, DebugLoc());
EVLPhi->insertAfter(CanonicalIVPHI);
VPBuilder Builder(Header, Header->getFirstNonPhi());
// Compute original TC - IV as the AVL (application vector length).
VPValue *AVL = Builder.createNaryOp(
Instruction::Sub, {Plan.getTripCount(), EVLPhi}, DebugLoc(), "avl");
// Create the AVL (application vector length), starting from TC -> 0 in steps
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The comment for tryAddExplicitVectorLength still needs updating I think, as it has the old style of AVL

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Updated, thanks

// of EVL.
VPPhi *AVLPhi = Builder.createScalarPhi(
{Plan.getTripCount()}, DebugLoc::getCompilerGenerated(), "avl");
VPValue *AVL = AVLPhi;

if (MaxSafeElements) {
// Support for MaxSafeDist for correct loop emission.
VPValue *AVLSafe =
Expand All @@ -2362,6 +2369,11 @@ bool VPlanTransforms::tryAddExplicitVectorLength(
CanonicalIVIncrement->getDebugLoc(), "index.evl.next");
EVLPhi->addOperand(NextEVLIV);

VPValue *NextAVL = Builder.createOverflowingOp(
Instruction::Sub, {AVLPhi, OpVPEVL}, {/*hasNUW=*/true, /*hasNSW=*/false},
DebugLoc::getCompilerGenerated(), "avl.next");
AVLPhi->addOperand(NextAVL);

transformRecipestoEVLRecipes(Plan, *VPEVL);

// Replace all uses of VPCanonicalIVPHIRecipe by
Expand Down
3 changes: 2 additions & 1 deletion llvm/lib/Transforms/Vectorize/VPlanVerifier.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -172,7 +172,8 @@ bool VPlanVerifier::verifyEVLRecipe(const VPInstruction &EVL) const {
[&](const VPInstructionWithType *S) { return VerifyEVLUse(*S, 0); })
.Case<VPInstruction>([&](const VPInstruction *I) {
if (I->getOpcode() == Instruction::PHI ||
I->getOpcode() == Instruction::ICmp)
I->getOpcode() == Instruction::ICmp ||
I->getOpcode() == Instruction::Sub)
return VerifyEVLUse(*I, 1);
switch (I->getOpcode()) {
case Instruction::Add:
Expand Down
3 changes: 2 additions & 1 deletion llvm/test/Transforms/LoopVectorize/RISCV/evl-compatible-loops.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@ define void @test_wide_integer_induction(ptr noalias %a, i64 %N) {
; CHECK: vector.body:
; CHECK-NEXT: [[EVL_BASED_IV:%.*]] = phi i64 [ 0, [[ENTRY]] ], [ [[INDEX_EVL_NEXT:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT: [[VEC_IND:%.*]] = phi <vscale x 2 x i64> [ [[INDUCTION]], [[ENTRY]] ], [ [[VEC_IND_NEXT:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT: [[AVL:%.*]] = sub i64 [[N]], [[EVL_BASED_IV]]
; CHECK-NEXT: [[AVL:%.*]] = phi i64 [ [[N]], [[ENTRY]] ], [ [[AVL_NEXT:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT: [[TMP11:%.*]] = call i32 @llvm.experimental.get.vector.length.i64(i64 [[AVL]], i32 2, i1 true)
; CHECK-NEXT: [[TMP12:%.*]] = zext i32 [[TMP11]] to i64
; CHECK-NEXT: [[TMP13:%.*]] = mul i64 1, [[TMP12]]
Expand All @@ -35,6 +35,7 @@ define void @test_wide_integer_induction(ptr noalias %a, i64 %N) {
; CHECK-NEXT: call void @llvm.vp.store.nxv2i64.p0(<vscale x 2 x i64> [[VEC_IND]], ptr align 8 [[TMP14]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP11]])
; CHECK-NEXT: [[TMP16:%.*]] = zext i32 [[TMP11]] to i64
; CHECK-NEXT: [[INDEX_EVL_NEXT]] = add i64 [[TMP16]], [[EVL_BASED_IV]]
; CHECK-NEXT: [[AVL_NEXT]] = sub nuw i64 [[AVL]], [[TMP16]]
; CHECK-NEXT: [[VEC_IND_NEXT]] = add <vscale x 2 x i64> [[VEC_IND]], [[BROADCAST_SPLAT]]
; CHECK-NEXT: [[TMP17:%.*]] = icmp eq i64 [[INDEX_EVL_NEXT]], [[N]]
; CHECK-NEXT: br i1 [[TMP17]], label [[MIDDLE_BLOCK:%.*]], label [[FOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
Expand Down
12 changes: 8 additions & 4 deletions llvm/test/Transforms/LoopVectorize/RISCV/inloop-reduction.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -132,14 +132,15 @@ define i32 @add_i16_i32(ptr nocapture readonly %x, i32 %n) {
; IF-EVL-OUTLOOP: vector.body:
; IF-EVL-OUTLOOP-NEXT: [[EVL_BASED_IV:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_EVL_NEXT:%.*]], [[VECTOR_BODY]] ]
; IF-EVL-OUTLOOP-NEXT: [[VEC_PHI:%.*]] = phi <vscale x 4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP10:%.*]], [[VECTOR_BODY]] ]
; IF-EVL-OUTLOOP-NEXT: [[AVL:%.*]] = sub i32 [[N]], [[EVL_BASED_IV]]
; IF-EVL-OUTLOOP-NEXT: [[AVL:%.*]] = phi i32 [ [[N]], [[VECTOR_PH]] ], [ [[AVL_NEXT:%.*]], [[VECTOR_BODY]] ]
; IF-EVL-OUTLOOP-NEXT: [[TMP5:%.*]] = call i32 @llvm.experimental.get.vector.length.i32(i32 [[AVL]], i32 4, i1 true)
; IF-EVL-OUTLOOP-NEXT: [[TMP7:%.*]] = getelementptr inbounds i16, ptr [[X:%.*]], i32 [[EVL_BASED_IV]]
; IF-EVL-OUTLOOP-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 4 x i16> @llvm.vp.load.nxv4i16.p0(ptr align 2 [[TMP7]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP5]])
; IF-EVL-OUTLOOP-NEXT: [[TMP9:%.*]] = sext <vscale x 4 x i16> [[VP_OP_LOAD]] to <vscale x 4 x i32>
; IF-EVL-OUTLOOP-NEXT: [[VP_OP:%.*]] = add <vscale x 4 x i32> [[VEC_PHI]], [[TMP9]]
; IF-EVL-OUTLOOP-NEXT: [[TMP10]] = call <vscale x 4 x i32> @llvm.vp.merge.nxv4i32(<vscale x 4 x i1> splat (i1 true), <vscale x 4 x i32> [[VP_OP]], <vscale x 4 x i32> [[VEC_PHI]], i32 [[TMP5]])
; IF-EVL-OUTLOOP-NEXT: [[INDEX_EVL_NEXT]] = add nuw i32 [[TMP5]], [[EVL_BASED_IV]]
; IF-EVL-OUTLOOP-NEXT: [[AVL_NEXT]] = sub nuw i32 [[AVL]], [[TMP5]]
; IF-EVL-OUTLOOP-NEXT: [[TMP11:%.*]] = icmp eq i32 [[INDEX_EVL_NEXT]], [[N]]
; IF-EVL-OUTLOOP-NEXT: br i1 [[TMP11]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; IF-EVL-OUTLOOP: middle.block:
Expand Down Expand Up @@ -185,14 +186,15 @@ define i32 @add_i16_i32(ptr nocapture readonly %x, i32 %n) {
; IF-EVL-INLOOP: vector.body:
; IF-EVL-INLOOP-NEXT: [[EVL_BASED_IV:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_EVL_NEXT:%.*]], [[VECTOR_BODY]] ]
; IF-EVL-INLOOP-NEXT: [[VEC_PHI:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[TMP11:%.*]], [[VECTOR_BODY]] ]
; IF-EVL-INLOOP-NEXT: [[TMP5:%.*]] = sub i32 [[N]], [[EVL_BASED_IV]]
; IF-EVL-INLOOP-NEXT: [[TMP5:%.*]] = phi i32 [ [[N]], [[VECTOR_PH]] ], [ [[AVL_NEXT:%.*]], [[VECTOR_BODY]] ]
; IF-EVL-INLOOP-NEXT: [[TMP6:%.*]] = call i32 @llvm.experimental.get.vector.length.i32(i32 [[TMP5]], i32 8, i1 true)
; IF-EVL-INLOOP-NEXT: [[TMP8:%.*]] = getelementptr inbounds i16, ptr [[X:%.*]], i32 [[EVL_BASED_IV]]
; IF-EVL-INLOOP-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 8 x i16> @llvm.vp.load.nxv8i16.p0(ptr align 2 [[TMP8]], <vscale x 8 x i1> splat (i1 true), i32 [[TMP6]])
; IF-EVL-INLOOP-NEXT: [[TMP14:%.*]] = sext <vscale x 8 x i16> [[VP_OP_LOAD]] to <vscale x 8 x i32>
; IF-EVL-INLOOP-NEXT: [[TMP10:%.*]] = call i32 @llvm.vp.reduce.add.nxv8i32(i32 0, <vscale x 8 x i32> [[TMP14]], <vscale x 8 x i1> splat (i1 true), i32 [[TMP6]])
; IF-EVL-INLOOP-NEXT: [[TMP11]] = add i32 [[TMP10]], [[VEC_PHI]]
; IF-EVL-INLOOP-NEXT: [[INDEX_EVL_NEXT]] = add nuw i32 [[TMP6]], [[EVL_BASED_IV]]
; IF-EVL-INLOOP-NEXT: [[AVL_NEXT]] = sub nuw i32 [[TMP5]], [[TMP6]]
; IF-EVL-INLOOP-NEXT: [[TMP12:%.*]] = icmp eq i32 [[INDEX_EVL_NEXT]], [[N]]
; IF-EVL-INLOOP-NEXT: br i1 [[TMP12]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; IF-EVL-INLOOP: middle.block:
Expand Down Expand Up @@ -350,7 +352,7 @@ define i32 @smin(ptr %a, i64 %n, i32 %start) {
; IF-EVL-OUTLOOP: vector.body:
; IF-EVL-OUTLOOP-NEXT: [[EVL_BASED_IV:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_EVL_NEXT:%.*]], [[VECTOR_BODY]] ]
; IF-EVL-OUTLOOP-NEXT: [[VEC_PHI:%.*]] = phi <vscale x 4 x i32> [ [[BROADCAST_SPLAT]], [[VECTOR_PH]] ], [ [[TMP15:%.*]], [[VECTOR_BODY]] ]
; IF-EVL-OUTLOOP-NEXT: [[AVL:%.*]] = sub i64 [[N]], [[EVL_BASED_IV]]
; IF-EVL-OUTLOOP-NEXT: [[AVL:%.*]] = phi i64 [ [[N]], [[VECTOR_PH]] ], [ [[AVL_NEXT:%.*]], [[VECTOR_BODY]] ]
; IF-EVL-OUTLOOP-NEXT: [[TMP9:%.*]] = call i32 @llvm.experimental.get.vector.length.i64(i64 [[AVL]], i32 4, i1 true)
; IF-EVL-OUTLOOP-NEXT: [[TMP11:%.*]] = getelementptr inbounds i32, ptr [[A:%.*]], i64 [[EVL_BASED_IV]]
; IF-EVL-OUTLOOP-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.vp.load.nxv4i32.p0(ptr align 4 [[TMP11]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP9]])
Expand All @@ -359,6 +361,7 @@ define i32 @smin(ptr %a, i64 %n, i32 %start) {
; IF-EVL-OUTLOOP-NEXT: [[TMP15]] = call <vscale x 4 x i32> @llvm.vp.merge.nxv4i32(<vscale x 4 x i1> splat (i1 true), <vscale x 4 x i32> [[TMP14]], <vscale x 4 x i32> [[VEC_PHI]], i32 [[TMP9]])
; IF-EVL-OUTLOOP-NEXT: [[TMP16:%.*]] = zext i32 [[TMP9]] to i64
; IF-EVL-OUTLOOP-NEXT: [[INDEX_EVL_NEXT]] = add i64 [[TMP16]], [[EVL_BASED_IV]]
; IF-EVL-OUTLOOP-NEXT: [[AVL_NEXT]] = sub nuw i64 [[AVL]], [[TMP16]]
; IF-EVL-OUTLOOP-NEXT: [[TMP17:%.*]] = icmp eq i64 [[INDEX_EVL_NEXT]], [[N]]
; IF-EVL-OUTLOOP-NEXT: br i1 [[TMP17]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
; IF-EVL-OUTLOOP: middle.block:
Expand Down Expand Up @@ -398,14 +401,15 @@ define i32 @smin(ptr %a, i64 %n, i32 %start) {
; IF-EVL-INLOOP: vector.body:
; IF-EVL-INLOOP-NEXT: [[EVL_BASED_IV:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_EVL_NEXT:%.*]], [[VECTOR_BODY]] ]
; IF-EVL-INLOOP-NEXT: [[VEC_PHI:%.*]] = phi i32 [ [[START:%.*]], [[VECTOR_PH]] ], [ [[RDX_MINMAX:%.*]], [[VECTOR_BODY]] ]
; IF-EVL-INLOOP-NEXT: [[AVL:%.*]] = sub i64 [[N]], [[EVL_BASED_IV]]
; IF-EVL-INLOOP-NEXT: [[AVL:%.*]] = phi i64 [ [[N]], [[VECTOR_PH]] ], [ [[AVL_NEXT:%.*]], [[VECTOR_BODY]] ]
; IF-EVL-INLOOP-NEXT: [[TMP9:%.*]] = call i32 @llvm.experimental.get.vector.length.i64(i64 [[AVL]], i32 4, i1 true)
; IF-EVL-INLOOP-NEXT: [[TMP11:%.*]] = getelementptr inbounds i32, ptr [[A:%.*]], i64 [[EVL_BASED_IV]]
; IF-EVL-INLOOP-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.vp.load.nxv4i32.p0(ptr align 4 [[TMP11]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP9]])
; IF-EVL-INLOOP-NEXT: [[TMP13:%.*]] = call i32 @llvm.vp.reduce.smin.nxv4i32(i32 2147483647, <vscale x 4 x i32> [[VP_OP_LOAD]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP9]])
; IF-EVL-INLOOP-NEXT: [[RDX_MINMAX]] = call i32 @llvm.smin.i32(i32 [[TMP13]], i32 [[VEC_PHI]])
; IF-EVL-INLOOP-NEXT: [[TMP14:%.*]] = zext i32 [[TMP9]] to i64
; IF-EVL-INLOOP-NEXT: [[INDEX_EVL_NEXT]] = add i64 [[TMP14]], [[EVL_BASED_IV]]
; IF-EVL-INLOOP-NEXT: [[AVL_NEXT]] = sub nuw i64 [[AVL]], [[TMP14]]
; IF-EVL-INLOOP-NEXT: [[TMP10:%.*]] = icmp eq i64 [[INDEX_EVL_NEXT]], [[N]]
; IF-EVL-INLOOP-NEXT: br i1 [[TMP10]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
; IF-EVL-INLOOP: middle.block:
Expand Down
6 changes: 4 additions & 2 deletions llvm/test/Transforms/LoopVectorize/RISCV/interleaved-masked-access.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -117,7 +117,7 @@ define void @masked_strided_factor2(ptr noalias nocapture readonly %p, ptr noali
; PREDICATED_DATA-WITH-EVL: vector.body:
; PREDICATED_DATA-WITH-EVL-NEXT: [[EVL_BASED_IV:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_EVL_NEXT:%.*]], [[VECTOR_BODY]] ]
; PREDICATED_DATA-WITH-EVL-NEXT: [[VEC_IND:%.*]] = phi <vscale x 16 x i32> [ [[TMP0]], [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[VECTOR_BODY]] ]
; PREDICATED_DATA-WITH-EVL-NEXT: [[AVL:%.*]] = sub i32 1024, [[EVL_BASED_IV]]
; PREDICATED_DATA-WITH-EVL-NEXT: [[AVL:%.*]] = phi i32 [ 1024, [[VECTOR_PH]] ], [ [[AVL_NEXT:%.*]], [[VECTOR_BODY]] ]
; PREDICATED_DATA-WITH-EVL-NEXT: [[TMP1:%.*]] = call i32 @llvm.experimental.get.vector.length.i32(i32 [[AVL]], i32 16, i1 true)
; PREDICATED_DATA-WITH-EVL-NEXT: [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <vscale x 16 x i32> poison, i32 [[TMP1]], i64 0
; PREDICATED_DATA-WITH-EVL-NEXT: [[BROADCAST_SPLAT2:%.*]] = shufflevector <vscale x 16 x i32> [[BROADCAST_SPLATINSERT1]], <vscale x 16 x i32> poison, <vscale x 16 x i32> zeroinitializer
Expand All @@ -139,6 +139,7 @@ define void @masked_strided_factor2(ptr noalias nocapture readonly %p, ptr noali
; PREDICATED_DATA-WITH-EVL-NEXT: [[TMP14:%.*]] = getelementptr inbounds i8, ptr [[Q]], <vscale x 16 x i64> [[TMP13]]
; PREDICATED_DATA-WITH-EVL-NEXT: call void @llvm.vp.scatter.nxv16i8.nxv16p0(<vscale x 16 x i8> [[TMP12]], <vscale x 16 x ptr> align 1 [[TMP14]], <vscale x 16 x i1> [[TMP2]], i32 [[TMP1]])
; PREDICATED_DATA-WITH-EVL-NEXT: [[INDEX_EVL_NEXT]] = add nuw i32 [[TMP1]], [[EVL_BASED_IV]]
; PREDICATED_DATA-WITH-EVL-NEXT: [[AVL_NEXT]] = sub nuw i32 [[AVL]], [[TMP1]]
; PREDICATED_DATA-WITH-EVL-NEXT: [[VEC_IND_NEXT]] = add <vscale x 16 x i32> [[VEC_IND]], [[BROADCAST_SPLAT2]]
; PREDICATED_DATA-WITH-EVL-NEXT: [[TMP15:%.*]] = icmp eq i32 [[INDEX_EVL_NEXT]], 1024
; PREDICATED_DATA-WITH-EVL-NEXT: br i1 [[TMP15]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
Expand Down Expand Up @@ -325,7 +326,7 @@ define void @masked_strided_factor4(ptr noalias nocapture readonly %p, ptr noali
; PREDICATED_DATA-WITH-EVL: vector.body:
; PREDICATED_DATA-WITH-EVL-NEXT: [[EVL_BASED_IV:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_EVL_NEXT:%.*]], [[VECTOR_BODY]] ]
; PREDICATED_DATA-WITH-EVL-NEXT: [[VEC_IND:%.*]] = phi <vscale x 16 x i32> [ [[TMP0]], [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[VECTOR_BODY]] ]
; PREDICATED_DATA-WITH-EVL-NEXT: [[AVL:%.*]] = sub i32 1024, [[EVL_BASED_IV]]
; PREDICATED_DATA-WITH-EVL-NEXT: [[AVL:%.*]] = phi i32 [ 1024, [[VECTOR_PH]] ], [ [[AVL_NEXT:%.*]], [[VECTOR_BODY]] ]
; PREDICATED_DATA-WITH-EVL-NEXT: [[TMP1:%.*]] = call i32 @llvm.experimental.get.vector.length.i32(i32 [[AVL]], i32 16, i1 true)
; PREDICATED_DATA-WITH-EVL-NEXT: [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <vscale x 16 x i32> poison, i32 [[TMP1]], i64 0
; PREDICATED_DATA-WITH-EVL-NEXT: [[BROADCAST_SPLAT2:%.*]] = shufflevector <vscale x 16 x i32> [[BROADCAST_SPLATINSERT1]], <vscale x 16 x i32> poison, <vscale x 16 x i32> zeroinitializer
Expand Down Expand Up @@ -363,6 +364,7 @@ define void @masked_strided_factor4(ptr noalias nocapture readonly %p, ptr noali
; PREDICATED_DATA-WITH-EVL-NEXT: [[TMP26:%.*]] = getelementptr inbounds i8, ptr [[Q]], <vscale x 16 x i64> [[TMP25]]
; PREDICATED_DATA-WITH-EVL-NEXT: call void @llvm.vp.scatter.nxv16i8.nxv16p0(<vscale x 16 x i8> [[TMP18]], <vscale x 16 x ptr> align 1 [[TMP26]], <vscale x 16 x i1> [[TMP2]], i32 [[TMP1]])
; PREDICATED_DATA-WITH-EVL-NEXT: [[INDEX_EVL_NEXT]] = add nuw i32 [[TMP1]], [[EVL_BASED_IV]]
; PREDICATED_DATA-WITH-EVL-NEXT: [[AVL_NEXT]] = sub nuw i32 [[AVL]], [[TMP1]]
; PREDICATED_DATA-WITH-EVL-NEXT: [[VEC_IND_NEXT]] = add <vscale x 16 x i32> [[VEC_IND]], [[BROADCAST_SPLAT2]]
; PREDICATED_DATA-WITH-EVL-NEXT: [[TMP27:%.*]] = icmp eq i32 [[INDEX_EVL_NEXT]], 1024
; PREDICATED_DATA-WITH-EVL-NEXT: br i1 [[TMP27]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
Expand Down
3 changes: 2 additions & 1 deletion llvm/test/Transforms/LoopVectorize/RISCV/pr88802.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,7 +32,7 @@ define void @test(ptr %p, i64 %a, i8 %b) {
; CHECK: vector.body:
; CHECK-NEXT: [[EVL_BASED_IV:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_EVL_NEXT:%.*]], [[FOR_COND]] ]
; CHECK-NEXT: [[VEC_IND:%.*]] = phi <vscale x 2 x i32> [ [[INDUCTION]], [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[FOR_COND]] ]
; CHECK-NEXT: [[AVL:%.*]] = sub i32 9, [[EVL_BASED_IV]]
; CHECK-NEXT: [[AVL:%.*]] = phi i32 [ 9, [[VECTOR_PH]] ], [ [[AVL_NEXT:%.*]], [[FOR_COND]] ]
; CHECK-NEXT: [[TMP11:%.*]] = call i32 @llvm.experimental.get.vector.length.i32(i32 [[AVL]], i32 2, i1 true)
; CHECK-NEXT: [[BROADCAST_SPLATINSERT5:%.*]] = insertelement <vscale x 2 x i32> poison, i32 [[TMP11]], i64 0
; CHECK-NEXT: [[BROADCAST_SPLAT6:%.*]] = shufflevector <vscale x 2 x i32> [[BROADCAST_SPLATINSERT5]], <vscale x 2 x i32> poison, <vscale x 2 x i32> zeroinitializer
Expand All @@ -48,6 +48,7 @@ define void @test(ptr %p, i64 %a, i8 %b) {
; CHECK-NEXT: [[TMP17:%.*]] = trunc <vscale x 2 x i32> [[TMP16]] to <vscale x 2 x i8>
; CHECK-NEXT: call void @llvm.vp.scatter.nxv2i8.nxv2p0(<vscale x 2 x i8> [[TMP17]], <vscale x 2 x ptr> align 1 [[BROADCAST_SPLAT4]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP11]])
; CHECK-NEXT: [[INDEX_EVL_NEXT]] = add nuw i32 [[TMP11]], [[EVL_BASED_IV]]
; CHECK-NEXT: [[AVL_NEXT]] = sub nuw i32 [[AVL]], [[TMP11]]
; CHECK-NEXT: [[VEC_IND_NEXT]] = add <vscale x 2 x i32> [[VEC_IND]], [[BROADCAST_SPLAT8]]
; CHECK-NEXT: [[TMP18:%.*]] = icmp eq i32 [[INDEX_EVL_NEXT]], 9
; CHECK-NEXT: br i1 [[TMP18]], label [[MIDDLE_BLOCK:%.*]], label [[FOR_COND]], !llvm.loop [[LOOP0:![0-9]+]]
Expand Down
Loading