Skip to content

[VPlan] Don't convert VPWidenSelectRecipes to vp.select in EVL transform #146695

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 2 commits into from
Jul 3, 2025
Merged

[VPlan] Don't convert VPWidenSelectRecipes to vp.select in EVL transform #146695

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
f3734e7
[VPlan] Don't convert VPWidenSelectRecipes to vp.select in EVL transform
lukel97 Jul 2, 2025
03f331c
Merge branch 'main' into loop-vectorize/vpwidenselect-no-evl
lukel97 Jul 3, 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
7 changes: 0 additions & 7 deletions llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2152,13 +2152,6 @@ static VPRecipeBase *createEVLRecipe(VPValue *HeaderMask,
VPValue *NewMask = GetNewMask(Red->getCondOp());
return new VPReductionEVLRecipe(*Red, EVL, NewMask);
})
.Case<VPWidenSelectRecipe>([&](VPWidenSelectRecipe *Sel) {
SmallVector<VPValue *> Ops(Sel->operands());
Ops.push_back(&EVL);
return new VPWidenIntrinsicRecipe(Intrinsic::vp_select, Ops,
TypeInfo.inferScalarType(Sel),
Sel->getDebugLoc());
})
.Case<VPInstruction>([&](VPInstruction *VPI) -> VPRecipeBase * {
if (VPI->getOpcode() == VPInstruction::FirstOrderRecurrenceSplice) {
assert(PrevEVL && "Fixed-order recurrences require previous EVL");
Expand Down
2 changes: 1 addition & 1 deletion 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 @@ -367,7 +367,7 @@ define i32 @smin(ptr %a, i64 %n, i32 %start) {
; IF-EVL-OUTLOOP-NEXT: [[TMP12:%.*]] = getelementptr inbounds i32, ptr [[TMP11]], i32 0
; IF-EVL-OUTLOOP-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.vp.load.nxv4i32.p0(ptr align 4 [[TMP12]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP9]])
; IF-EVL-OUTLOOP-NEXT: [[TMP13:%.*]] = icmp slt <vscale x 4 x i32> [[VP_OP_LOAD]], [[VEC_PHI]]
; IF-EVL-OUTLOOP-NEXT: [[TMP14:%.*]] = call <vscale x 4 x i32> @llvm.vp.select.nxv4i32(<vscale x 4 x i1> [[TMP13]], <vscale x 4 x i32> [[VP_OP_LOAD]], <vscale x 4 x i32> [[VEC_PHI]], i32 [[TMP9]])
; IF-EVL-OUTLOOP-NEXT: [[TMP14:%.*]] = select <vscale x 4 x i1> [[TMP13]], <vscale x 4 x i32> [[VP_OP_LOAD]], <vscale x 4 x i32> [[VEC_PHI]]
; 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]]
Expand Down
49 changes: 23 additions & 26 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 @@ -138,20 +138,19 @@ define void @masked_strided_factor2(ptr noalias nocapture readonly %p, ptr noali
; PREDICATED_EVL-NEXT: [[TMP11:%.*]] = zext nneg <vscale x 16 x i32> [[TMP10]] to <vscale x 16 x i64>
; PREDICATED_EVL-NEXT: [[TMP12:%.*]] = getelementptr inbounds i8, ptr [[P]], <vscale x 16 x i64> [[TMP11]]
; PREDICATED_EVL-NEXT: [[WIDE_MASKED_GATHER3:%.*]] = call <vscale x 16 x i8> @llvm.vp.gather.nxv16i8.nxv16p0(<vscale x 16 x ptr> align 1 [[TMP12]], <vscale x 16 x i1> [[TMP6]], i32 [[TMP5]])
; PREDICATED_EVL-NEXT: [[TMP13:%.*]] = icmp slt <vscale x 16 x i8> [[WIDE_MASKED_GATHER]], [[WIDE_MASKED_GATHER3]]
; PREDICATED_EVL-NEXT: [[TMP14:%.*]] = call <vscale x 16 x i8> @llvm.vp.select.nxv16i8(<vscale x 16 x i1> [[TMP13]], <vscale x 16 x i8> [[WIDE_MASKED_GATHER3]], <vscale x 16 x i8> [[WIDE_MASKED_GATHER]], i32 [[TMP5]])
; PREDICATED_EVL-NEXT: [[TMP15:%.*]] = zext nneg <vscale x 16 x i32> [[TMP7]] to <vscale x 16 x i64>
; PREDICATED_EVL-NEXT: [[TMP16:%.*]] = getelementptr inbounds i8, ptr [[Q]], <vscale x 16 x i64> [[TMP15]]
; PREDICATED_EVL-NEXT: call void @llvm.vp.scatter.nxv16i8.nxv16p0(<vscale x 16 x i8> [[TMP14]], <vscale x 16 x ptr> align 1 [[TMP16]], <vscale x 16 x i1> [[TMP6]], i32 [[TMP5]])
; PREDICATED_EVL-NEXT: [[TMP17:%.*]] = sub <vscale x 16 x i8> zeroinitializer, [[TMP14]]
; PREDICATED_EVL-NEXT: [[TMP18:%.*]] = zext nneg <vscale x 16 x i32> [[TMP10]] to <vscale x 16 x i64>
; PREDICATED_EVL-NEXT: [[TMP19:%.*]] = getelementptr inbounds i8, ptr [[Q]], <vscale x 16 x i64> [[TMP18]]
; PREDICATED_EVL-NEXT: call void @llvm.vp.scatter.nxv16i8.nxv16p0(<vscale x 16 x i8> [[TMP17]], <vscale x 16 x ptr> align 1 [[TMP19]], <vscale x 16 x i1> [[TMP6]], i32 [[TMP5]])
; PREDICATED_EVL-NEXT: [[TMP13:%.*]] = call <vscale x 16 x i8> @llvm.smax.nxv16i8(<vscale x 16 x i8> [[WIDE_MASKED_GATHER]], <vscale x 16 x i8> [[WIDE_MASKED_GATHER3]])
; PREDICATED_EVL-NEXT: [[TMP14:%.*]] = zext nneg <vscale x 16 x i32> [[TMP7]] to <vscale x 16 x i64>
Comment on lines +141 to +142
Copy link
Contributor Author

Choose a reason for hiding this comment

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

An example of an optimisation InstCombine can do with a regular select. As a side note, should these tests be running instcombine to begin with?

; PREDICATED_EVL-NEXT: [[TMP15:%.*]] = getelementptr inbounds i8, ptr [[Q]], <vscale x 16 x i64> [[TMP14]]
; PREDICATED_EVL-NEXT: call void @llvm.vp.scatter.nxv16i8.nxv16p0(<vscale x 16 x i8> [[TMP13]], <vscale x 16 x ptr> align 1 [[TMP15]], <vscale x 16 x i1> [[TMP6]], i32 [[TMP5]])
; PREDICATED_EVL-NEXT: [[TMP16:%.*]] = sub <vscale x 16 x i8> zeroinitializer, [[TMP13]]
; PREDICATED_EVL-NEXT: [[TMP17:%.*]] = zext nneg <vscale x 16 x i32> [[TMP10]] to <vscale x 16 x i64>
; PREDICATED_EVL-NEXT: [[TMP18:%.*]] = getelementptr inbounds i8, ptr [[Q]], <vscale x 16 x i64> [[TMP17]]
; PREDICATED_EVL-NEXT: call void @llvm.vp.scatter.nxv16i8.nxv16p0(<vscale x 16 x i8> [[TMP16]], <vscale x 16 x ptr> align 1 [[TMP18]], <vscale x 16 x i1> [[TMP6]], i32 [[TMP5]])
; PREDICATED_EVL-NEXT: [[INDEX_EVL_NEXT]] = add nuw i32 [[TMP5]], [[EVL_BASED_IV]]
; PREDICATED_EVL-NEXT: [[INDEX_NEXT]] = add nuw i32 [[INDEX]], [[TMP3]]
; PREDICATED_EVL-NEXT: [[VEC_IND_NEXT]] = add <vscale x 16 x i32> [[VEC_IND]], [[BROADCAST_SPLAT2]]
; PREDICATED_EVL-NEXT: [[TMP20:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; PREDICATED_EVL-NEXT: br i1 [[TMP20]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; PREDICATED_EVL-NEXT: [[TMP19:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; PREDICATED_EVL-NEXT: br i1 [[TMP19]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; PREDICATED_EVL: middle.block:
; PREDICATED_EVL-NEXT: br label [[FOR_END:%.*]]
; PREDICATED_EVL: scalar.ph:
Expand Down Expand Up @@ -364,29 +363,27 @@ define void @masked_strided_factor4(ptr noalias nocapture readonly %p, ptr noali
; PREDICATED_EVL-NEXT: [[TMP17:%.*]] = zext nneg <vscale x 16 x i32> [[TMP10]] to <vscale x 16 x i64>
; PREDICATED_EVL-NEXT: [[TMP18:%.*]] = getelementptr inbounds i8, ptr [[P]], <vscale x 16 x i64> [[TMP17]]
; PREDICATED_EVL-NEXT: [[WIDE_MASKED_GATHER5:%.*]] = call <vscale x 16 x i8> @llvm.vp.gather.nxv16i8.nxv16p0(<vscale x 16 x ptr> align 1 [[TMP18]], <vscale x 16 x i1> [[TMP6]], i32 [[TMP5]])
; PREDICATED_EVL-NEXT: [[TMP19:%.*]] = icmp slt <vscale x 16 x i8> [[WIDE_MASKED_GATHER]], [[WIDE_MASKED_GATHER3]]
; PREDICATED_EVL-NEXT: [[TMP20:%.*]] = call <vscale x 16 x i8> @llvm.vp.select.nxv16i8(<vscale x 16 x i1> [[TMP19]], <vscale x 16 x i8> [[WIDE_MASKED_GATHER3]], <vscale x 16 x i8> [[WIDE_MASKED_GATHER]], i32 [[TMP5]])
; PREDICATED_EVL-NEXT: [[TMP21:%.*]] = sub <vscale x 16 x i8> zeroinitializer, [[TMP20]]
; PREDICATED_EVL-NEXT: [[TMP22:%.*]] = icmp slt <vscale x 16 x i8> [[WIDE_MASKED_GATHER4]], [[WIDE_MASKED_GATHER5]]
; PREDICATED_EVL-NEXT: [[TMP23:%.*]] = call <vscale x 16 x i8> @llvm.vp.select.nxv16i8(<vscale x 16 x i1> [[TMP22]], <vscale x 16 x i8> [[WIDE_MASKED_GATHER5]], <vscale x 16 x i8> [[WIDE_MASKED_GATHER4]], i32 [[TMP5]])
; PREDICATED_EVL-NEXT: [[TMP24:%.*]] = sub <vscale x 16 x i8> zeroinitializer, [[TMP23]]
; PREDICATED_EVL-NEXT: [[TMP25:%.*]] = zext nneg <vscale x 16 x i32> [[TMP7]] to <vscale x 16 x i64>
; PREDICATED_EVL-NEXT: [[TMP19:%.*]] = call <vscale x 16 x i8> @llvm.smax.nxv16i8(<vscale x 16 x i8> [[WIDE_MASKED_GATHER]], <vscale x 16 x i8> [[WIDE_MASKED_GATHER3]])
; PREDICATED_EVL-NEXT: [[TMP20:%.*]] = sub <vscale x 16 x i8> zeroinitializer, [[TMP19]]
; PREDICATED_EVL-NEXT: [[TMP21:%.*]] = call <vscale x 16 x i8> @llvm.smax.nxv16i8(<vscale x 16 x i8> [[WIDE_MASKED_GATHER4]], <vscale x 16 x i8> [[WIDE_MASKED_GATHER5]])
; PREDICATED_EVL-NEXT: [[TMP22:%.*]] = sub <vscale x 16 x i8> zeroinitializer, [[TMP21]]
; PREDICATED_EVL-NEXT: [[TMP23:%.*]] = zext nneg <vscale x 16 x i32> [[TMP7]] to <vscale x 16 x i64>
; PREDICATED_EVL-NEXT: [[TMP24:%.*]] = getelementptr inbounds i8, ptr [[Q]], <vscale x 16 x i64> [[TMP23]]
; PREDICATED_EVL-NEXT: call void @llvm.vp.scatter.nxv16i8.nxv16p0(<vscale x 16 x i8> [[TMP19]], <vscale x 16 x ptr> align 1 [[TMP24]], <vscale x 16 x i1> [[TMP6]], i32 [[TMP5]])
; PREDICATED_EVL-NEXT: [[TMP25:%.*]] = zext nneg <vscale x 16 x i32> [[TMP8]] to <vscale x 16 x i64>
; PREDICATED_EVL-NEXT: [[TMP26:%.*]] = getelementptr inbounds i8, ptr [[Q]], <vscale x 16 x i64> [[TMP25]]
; PREDICATED_EVL-NEXT: call void @llvm.vp.scatter.nxv16i8.nxv16p0(<vscale x 16 x i8> [[TMP20]], <vscale x 16 x ptr> align 1 [[TMP26]], <vscale x 16 x i1> [[TMP6]], i32 [[TMP5]])
; PREDICATED_EVL-NEXT: [[TMP27:%.*]] = zext nneg <vscale x 16 x i32> [[TMP8]] to <vscale x 16 x i64>
; PREDICATED_EVL-NEXT: [[TMP27:%.*]] = zext nneg <vscale x 16 x i32> [[TMP9]] to <vscale x 16 x i64>
; PREDICATED_EVL-NEXT: [[TMP28:%.*]] = getelementptr inbounds i8, ptr [[Q]], <vscale x 16 x i64> [[TMP27]]
; PREDICATED_EVL-NEXT: call void @llvm.vp.scatter.nxv16i8.nxv16p0(<vscale x 16 x i8> [[TMP21]], <vscale x 16 x ptr> align 1 [[TMP28]], <vscale x 16 x i1> [[TMP6]], i32 [[TMP5]])
; PREDICATED_EVL-NEXT: [[TMP29:%.*]] = zext nneg <vscale x 16 x i32> [[TMP9]] to <vscale x 16 x i64>
; PREDICATED_EVL-NEXT: [[TMP29:%.*]] = zext nneg <vscale x 16 x i32> [[TMP10]] to <vscale x 16 x i64>
; PREDICATED_EVL-NEXT: [[TMP30:%.*]] = getelementptr inbounds i8, ptr [[Q]], <vscale x 16 x i64> [[TMP29]]
; PREDICATED_EVL-NEXT: call void @llvm.vp.scatter.nxv16i8.nxv16p0(<vscale x 16 x i8> [[TMP23]], <vscale x 16 x ptr> align 1 [[TMP30]], <vscale x 16 x i1> [[TMP6]], i32 [[TMP5]])
; PREDICATED_EVL-NEXT: [[TMP31:%.*]] = zext nneg <vscale x 16 x i32> [[TMP10]] to <vscale x 16 x i64>
; PREDICATED_EVL-NEXT: [[TMP32:%.*]] = getelementptr inbounds i8, ptr [[Q]], <vscale x 16 x i64> [[TMP31]]
; PREDICATED_EVL-NEXT: call void @llvm.vp.scatter.nxv16i8.nxv16p0(<vscale x 16 x i8> [[TMP24]], <vscale x 16 x ptr> align 1 [[TMP32]], <vscale x 16 x i1> [[TMP6]], i32 [[TMP5]])
; PREDICATED_EVL-NEXT: call void @llvm.vp.scatter.nxv16i8.nxv16p0(<vscale x 16 x i8> [[TMP22]], <vscale x 16 x ptr> align 1 [[TMP30]], <vscale x 16 x i1> [[TMP6]], i32 [[TMP5]])
; PREDICATED_EVL-NEXT: [[INDEX_EVL_NEXT]] = add nuw i32 [[TMP5]], [[EVL_BASED_IV]]
; PREDICATED_EVL-NEXT: [[INDEX_NEXT]] = add nuw i32 [[INDEX]], [[TMP3]]
; PREDICATED_EVL-NEXT: [[VEC_IND_NEXT]] = add <vscale x 16 x i32> [[VEC_IND]], [[BROADCAST_SPLAT2]]
; PREDICATED_EVL-NEXT: [[TMP33:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; PREDICATED_EVL-NEXT: br i1 [[TMP33]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
; PREDICATED_EVL-NEXT: [[TMP31:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; PREDICATED_EVL-NEXT: br i1 [[TMP31]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
; PREDICATED_EVL: middle.block:
; PREDICATED_EVL-NEXT: br label [[FOR_END:%.*]]
; PREDICATED_EVL: scalar.ph:
Expand Down
2 changes: 1 addition & 1 deletion llvm/test/Transforms/LoopVectorize/RISCV/preserve-dbg-loc.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,7 @@
define void @vp_select(ptr %a, ptr %b, ptr %c, i64 %N) {
; DEBUGLOC-LABEL: define void @vp_select(
; DEBUGLOC: vector.body:
; DEBUGLOC: = call <vscale x 4 x i32> @llvm.vp.select.nxv4i32(<vscale x 4 x i1> %{{.+}}, <vscale x 4 x i32> %{{.+}}, <vscale x 4 x i32> %{{.+}}, i32 %{{.+}}), !dbg ![[SELLOC:[0-9]+]]
; DEBUGLOC: = select <vscale x 4 x i1> %{{.+}}, <vscale x 4 x i32> %{{.+}}, <vscale x 4 x i32> %{{.+}}, !dbg ![[SELLOC:[0-9]+]]
; DEBUGLOC: loop:
; DEBUGLOC: = select i1 %{{.+}}, i32 %{{.+}}, i32 %{{.+}}, !dbg ![[SELLOC]]
;
Expand Down
2 changes: 1 addition & 1 deletion llvm/test/Transforms/LoopVectorize/RISCV/type-info-cache-evl-crash.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -44,7 +44,7 @@ define void @type_info_cache_clobber(ptr %dstv, ptr %src, i64 %wide.trip.count)
; CHECK-NEXT: [[TMP23:%.*]] = ashr <vscale x 8 x i32> [[TMP15]], zeroinitializer
; CHECK-NEXT: [[VP_OP3:%.*]] = or <vscale x 8 x i32> [[TMP23]], zeroinitializer
; CHECK-NEXT: [[TMP16:%.*]] = icmp ult <vscale x 8 x i32> [[TMP15]], zeroinitializer
; CHECK-NEXT: [[TMP17:%.*]] = call <vscale x 8 x i32> @llvm.vp.select.nxv8i32(<vscale x 8 x i1> [[TMP16]], <vscale x 8 x i32> [[VP_OP3]], <vscale x 8 x i32> zeroinitializer, i32 [[TMP11]])
; CHECK-NEXT: [[TMP17:%.*]] = select <vscale x 8 x i1> [[TMP16]], <vscale x 8 x i32> [[VP_OP3]], <vscale x 8 x i32> zeroinitializer
; CHECK-NEXT: [[TMP24:%.*]] = trunc <vscale x 8 x i32> [[TMP17]] to <vscale x 8 x i8>
; CHECK-NEXT: call void @llvm.vp.scatter.nxv8i8.nxv8p0(<vscale x 8 x i8> [[TMP24]], <vscale x 8 x ptr> align 1 [[BROADCAST_SPLAT]], <vscale x 8 x i1> splat (i1 true), i32 [[TMP11]]), !alias.scope [[META3:![0-9]+]], !noalias [[META0]]
; CHECK-NEXT: [[TMP19:%.*]] = trunc <vscale x 8 x i32> [[VP_OP]] to <vscale x 8 x i16>
Expand Down
8 changes: 4 additions & 4 deletions llvm/test/Transforms/LoopVectorize/RISCV/vectorize-force-tail-with-evl-cond-reduction.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,7 +47,7 @@ define i32 @cond_add(ptr %a, i64 %n, i32 %start) {
; IF-EVL-OUTLOOP-NEXT: [[TMP17:%.*]] = getelementptr inbounds i32, ptr [[TMP16]], i32 0
; IF-EVL-OUTLOOP-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.vp.load.nxv4i32.p0(ptr align 4 [[TMP17]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP11]])
; IF-EVL-OUTLOOP-NEXT: [[TMP18:%.*]] = icmp sgt <vscale x 4 x i32> [[VP_OP_LOAD]], splat (i32 3)
; IF-EVL-OUTLOOP-NEXT: [[TMP19:%.*]] = call <vscale x 4 x i32> @llvm.vp.select.nxv4i32(<vscale x 4 x i1> [[TMP18]], <vscale x 4 x i32> [[VP_OP_LOAD]], <vscale x 4 x i32> zeroinitializer, i32 [[TMP11]])
; IF-EVL-OUTLOOP-NEXT: [[TMP19:%.*]] = select <vscale x 4 x i1> [[TMP18]], <vscale x 4 x i32> [[VP_OP_LOAD]], <vscale x 4 x i32> zeroinitializer
; IF-EVL-OUTLOOP-NEXT: [[VP_OP:%.*]] = add <vscale x 4 x i32> [[TMP19]], [[VEC_PHI]]
; IF-EVL-OUTLOOP-NEXT: [[TMP20]] = 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 [[TMP11]])
; IF-EVL-OUTLOOP-NEXT: [[TMP22:%.*]] = zext i32 [[TMP11]] to i64
Expand Down Expand Up @@ -101,7 +101,7 @@ define i32 @cond_add(ptr %a, i64 %n, i32 %start) {
; IF-EVL-INLOOP-NEXT: [[TMP18:%.*]] = getelementptr inbounds i32, ptr [[TMP17]], i32 0
; IF-EVL-INLOOP-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.vp.load.nxv4i32.p0(ptr align 4 [[TMP18]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP12]])
; IF-EVL-INLOOP-NEXT: [[TMP19:%.*]] = icmp sgt <vscale x 4 x i32> [[VP_OP_LOAD]], splat (i32 3)
; IF-EVL-INLOOP-NEXT: [[TMP20:%.*]] = call <vscale x 4 x i32> @llvm.vp.select.nxv4i32(<vscale x 4 x i1> [[TMP19]], <vscale x 4 x i32> [[VP_OP_LOAD]], <vscale x 4 x i32> zeroinitializer, i32 [[TMP12]])
; IF-EVL-INLOOP-NEXT: [[TMP20:%.*]] = select <vscale x 4 x i1> [[TMP19]], <vscale x 4 x i32> [[VP_OP_LOAD]], <vscale x 4 x i32> zeroinitializer
; IF-EVL-INLOOP-NEXT: [[TMP21:%.*]] = call i32 @llvm.vp.reduce.add.nxv4i32(i32 0, <vscale x 4 x i32> [[TMP20]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP12]])
; IF-EVL-INLOOP-NEXT: [[TMP22]] = add i32 [[TMP21]], [[VEC_PHI]]
; IF-EVL-INLOOP-NEXT: [[TMP23:%.*]] = zext i32 [[TMP12]] to i64
Expand Down Expand Up @@ -543,7 +543,7 @@ define i32 @step_cond_add(ptr %a, i64 %n, i32 %start) {
; IF-EVL-OUTLOOP-NEXT: [[TMP15:%.*]] = getelementptr inbounds i32, ptr [[TMP14]], i32 0
; IF-EVL-OUTLOOP-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.vp.load.nxv4i32.p0(ptr align 4 [[TMP15]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP12]])
; IF-EVL-OUTLOOP-NEXT: [[TMP16:%.*]] = icmp sgt <vscale x 4 x i32> [[VP_OP_LOAD]], [[VEC_IND]]
; IF-EVL-OUTLOOP-NEXT: [[TMP17:%.*]] = call <vscale x 4 x i32> @llvm.vp.select.nxv4i32(<vscale x 4 x i1> [[TMP16]], <vscale x 4 x i32> [[VP_OP_LOAD]], <vscale x 4 x i32> zeroinitializer, i32 [[TMP12]])
; IF-EVL-OUTLOOP-NEXT: [[TMP17:%.*]] = select <vscale x 4 x i1> [[TMP16]], <vscale x 4 x i32> [[VP_OP_LOAD]], <vscale x 4 x i32> zeroinitializer
; IF-EVL-OUTLOOP-NEXT: [[TMP18:%.*]] = add <vscale x 4 x i32> [[TMP17]], [[VEC_PHI]]
; IF-EVL-OUTLOOP-NEXT: [[TMP19]] = call <vscale x 4 x i32> @llvm.vp.merge.nxv4i32(<vscale x 4 x i1> splat (i1 true), <vscale x 4 x i32> [[TMP18]], <vscale x 4 x i32> [[VEC_PHI]], i32 [[TMP12]])
; IF-EVL-OUTLOOP-NEXT: [[TMP20:%.*]] = zext i32 [[TMP12]] to i64
Expand Down Expand Up @@ -606,7 +606,7 @@ define i32 @step_cond_add(ptr %a, i64 %n, i32 %start) {
; IF-EVL-INLOOP-NEXT: [[TMP14:%.*]] = getelementptr inbounds i32, ptr [[TMP13]], i32 0
; IF-EVL-INLOOP-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.vp.load.nxv4i32.p0(ptr align 4 [[TMP14]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP11]])
; IF-EVL-INLOOP-NEXT: [[TMP15:%.*]] = icmp sgt <vscale x 4 x i32> [[VP_OP_LOAD]], [[VEC_IND]]
; IF-EVL-INLOOP-NEXT: [[TMP16:%.*]] = call <vscale x 4 x i32> @llvm.vp.select.nxv4i32(<vscale x 4 x i1> [[TMP15]], <vscale x 4 x i32> [[VP_OP_LOAD]], <vscale x 4 x i32> zeroinitializer, i32 [[TMP11]])
; IF-EVL-INLOOP-NEXT: [[TMP16:%.*]] = select <vscale x 4 x i1> [[TMP15]], <vscale x 4 x i32> [[VP_OP_LOAD]], <vscale x 4 x i32> zeroinitializer
; IF-EVL-INLOOP-NEXT: [[TMP17:%.*]] = call i32 @llvm.vp.reduce.add.nxv4i32(i32 0, <vscale x 4 x i32> [[TMP16]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP11]])
; IF-EVL-INLOOP-NEXT: [[ADD]] = add i32 [[TMP17]], [[RDX]]
; IF-EVL-INLOOP-NEXT: [[TMP19:%.*]] = zext i32 [[TMP11]] to i64
Expand Down
Loading
Loading