[llvm] [RISCV][LoopVectorize] Use DataWithEVL as the preferred tail folding style (PR #148686)
Luke Lau via llvm-commits
llvm-commits at lists.llvm.org
Mon Jul 14 10:39:21 PDT 2025
https://github.com/lukel97 created https://github.com/llvm/llvm-project/pull/148686
In preparation to eventually make EVL tail folding the default, this patch sets DataWithEVL as the preferred tail folding style for RISC-V, but doesn't enable tail folding by default.
And although tail folding isn't enabled by default, the loop vectorizer will actually tail fold loops with a small trip count, so this will cause some EVL vectorized loops to be generated in the default configuration.
The EVL tail folding work is still not complete, e.g. we still need to handle interleave groups etc., see #123069, but a lot of these missing features also apply to the data (masked) tail folding strategy, which is the default anyway.
The actual overall performance picture is much better, on TSVC EVL tail folding is faster than data on every benchmark on the spacemit-x60[^1]: https://lnt.lukelau.me/db_default/v4/nts/755?compare_to=756
And on SPEC CPU 2017 we see a geomean improvement[^2]: https://lnt.lukelau.me/db_default/v4/nts/751?compare_to=753
This is likely due to masked instructions generally being less performant on the spacemit-x60, up to twice as slow: https://camel-cdr.github.io/rvv-bench-results/bpi_f3/index.html
We should probably wait until the LLVM 21 branch is cut before landing this, but with that said I don't expect this to affect a lot of loops so I wouldn't be overly worried if it does make it in.
[^1]: These benchmarks don't exactly give the same performance numbers as this patch, but it's a good indicator that EVL tail folding is generally faster than masked tail folding.
[^2]: The large code size increase in 505.mcf_r is due to a function being inlined now
>From ce7d64f3d29ff051ea027b37dc1ee38758515a74 Mon Sep 17 00:00:00 2001
From: Luke Lau <luke at igalia.com>
Date: Tue, 15 Jul 2025 01:18:17 +0800
Subject: [PATCH] [RISCV][LoopVectorize] Use DataWithEVL as the preferred tail
folding style
In preparation to eventually make EVL tail folding the default, this patch sets DataWithEVL as the preferred tail folding style for RISC-V, but doesn't enable tail folding by default.
And although tail folding isn't enabled by default, the loop vectorizer will actually tail fold loops with a small trip count, so this will cause some EVL vectorized loops to be generated in the default configuration.
On TSVC EVL tail folding is faster than regular data (masked) tail folding on every benchmark on the spacemit-x60^[1]: https://lnt.lukelau.me/db_default/v4/nts/755?compare_to=756
And on SPEC CPU 2017 we see a geomean improvement^[2]: https://lnt.lukelau.me/db_default/v4/nts/751?compare_to=753
This is likely due to masked instructions generally being less performant on the spacemit-x60, up to twice as slow: https://camel-cdr.github.io/rvv-bench-results/bpi_f3/index.html
[1]: These benchmarks don't exactly give the same performance numbers as this patch, but it's a good indicator that EVL tail folding is generally faster than masked tail folding.
[2]: The large code size increase in 505.mcf_r is due to a function being inlined now
---
.../Target/RISCV/RISCVTargetTransformInfo.h | 3 +-
.../RISCV/interleaved-masked-access.ll | 50 +-
.../LoopVectorize/RISCV/low-trip-count.ll | 37 +-
.../Transforms/LoopVectorize/RISCV/pr88802.ll | 69 ++-
.../LoopVectorize/RISCV/scalable-tailfold.ll | 96 ++--
.../LoopVectorize/RISCV/tail-folding-cost.ll | 16 +-
.../truncate-to-minimal-bitwidth-cost.ll | 29 +-
.../LoopVectorize/RISCV/uniform-load-store.ll | 445 ++++--------------
8 files changed, 261 insertions(+), 484 deletions(-)
diff --git a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.h b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.h
index 12bf8c1b4de70..0351cd823f3ee 100644
--- a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.h
+++ b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.h
@@ -116,8 +116,7 @@ class RISCVTTIImpl final : public BasicTTIImplBase<RISCVTTIImpl> {
}
TailFoldingStyle
getPreferredTailFoldingStyle(bool IVUpdateMayOverflow) const override {
- return ST->hasVInstructions() ? TailFoldingStyle::Data
- : TailFoldingStyle::DataWithoutLaneMask;
+ return TailFoldingStyle::DataWithEVL;
}
std::optional<unsigned> getMaxVScale() const override;
std::optional<unsigned> getVScaleForTuning() const override;
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/interleaved-masked-access.ll b/llvm/test/Transforms/LoopVectorize/RISCV/interleaved-masked-access.ll
index 45357dd6bf0d6..8ff46975bd035 100644
--- a/llvm/test/Transforms/LoopVectorize/RISCV/interleaved-masked-access.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/interleaved-masked-access.ll
@@ -71,31 +71,33 @@ define void @masked_strided_factor2(ptr noalias nocapture readonly %p, ptr noali
; PREDICATED_TAIL_FOLDING-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 16 x i32> poison, i32 [[CONV]], i64 0
; PREDICATED_TAIL_FOLDING-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 16 x i32> [[BROADCAST_SPLATINSERT]], <vscale x 16 x i32> poison, <vscale x 16 x i32> zeroinitializer
; PREDICATED_TAIL_FOLDING-NEXT: [[TMP4:%.*]] = call <vscale x 16 x i32> @llvm.stepvector.nxv16i32()
-; PREDICATED_TAIL_FOLDING-NEXT: [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <vscale x 16 x i32> poison, i32 [[TMP3]], i64 0
-; PREDICATED_TAIL_FOLDING-NEXT: [[BROADCAST_SPLAT2:%.*]] = shufflevector <vscale x 16 x i32> [[BROADCAST_SPLATINSERT1]], <vscale x 16 x i32> poison, <vscale x 16 x i32> zeroinitializer
; PREDICATED_TAIL_FOLDING-NEXT: br label [[VECTOR_BODY:%.*]]
; PREDICATED_TAIL_FOLDING: vector.body:
; PREDICATED_TAIL_FOLDING-NEXT: [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; PREDICATED_TAIL_FOLDING-NEXT: [[EVL_BASED_IV:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_EVL_NEXT:%.*]], [[VECTOR_BODY]] ]
; PREDICATED_TAIL_FOLDING-NEXT: [[VEC_IND:%.*]] = phi <vscale x 16 x i32> [ [[TMP4]], [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[VECTOR_BODY]] ]
-; PREDICATED_TAIL_FOLDING-NEXT: [[ACTIVE_LANE_MASK:%.*]] = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i32(i32 [[INDEX]], i32 1024)
-; PREDICATED_TAIL_FOLDING-NEXT: [[TMP5:%.*]] = icmp ugt <vscale x 16 x i32> [[VEC_IND]], [[BROADCAST_SPLAT]]
-; PREDICATED_TAIL_FOLDING-NEXT: [[TMP6:%.*]] = select <vscale x 16 x i1> [[ACTIVE_LANE_MASK]], <vscale x 16 x i1> [[TMP5]], <vscale x 16 x i1> zeroinitializer
+; PREDICATED_TAIL_FOLDING-NEXT: [[AVL:%.*]] = sub i32 1024, [[EVL_BASED_IV]]
+; PREDICATED_TAIL_FOLDING-NEXT: [[TMP5:%.*]] = call i32 @llvm.experimental.get.vector.length.i32(i32 [[AVL]], i32 16, i1 true)
+; PREDICATED_TAIL_FOLDING-NEXT: [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <vscale x 16 x i32> poison, i32 [[TMP5]], i64 0
+; PREDICATED_TAIL_FOLDING-NEXT: [[BROADCAST_SPLAT2:%.*]] = shufflevector <vscale x 16 x i32> [[BROADCAST_SPLATINSERT1]], <vscale x 16 x i32> poison, <vscale x 16 x i32> zeroinitializer
+; PREDICATED_TAIL_FOLDING-NEXT: [[TMP6:%.*]] = icmp ugt <vscale x 16 x i32> [[VEC_IND]], [[BROADCAST_SPLAT]]
; PREDICATED_TAIL_FOLDING-NEXT: [[TMP7:%.*]] = shl nuw nsw <vscale x 16 x i32> [[VEC_IND]], splat (i32 1)
; PREDICATED_TAIL_FOLDING-NEXT: [[TMP8:%.*]] = zext nneg <vscale x 16 x i32> [[TMP7]] to <vscale x 16 x i64>
; PREDICATED_TAIL_FOLDING-NEXT: [[TMP9:%.*]] = getelementptr inbounds i8, ptr [[P]], <vscale x 16 x i64> [[TMP8]]
-; PREDICATED_TAIL_FOLDING-NEXT: [[WIDE_MASKED_GATHER:%.*]] = call <vscale x 16 x i8> @llvm.masked.gather.nxv16i8.nxv16p0(<vscale x 16 x ptr> [[TMP9]], i32 1, <vscale x 16 x i1> [[TMP6]], <vscale x 16 x i8> poison)
+; PREDICATED_TAIL_FOLDING-NEXT: [[WIDE_MASKED_GATHER:%.*]] = call <vscale x 16 x i8> @llvm.vp.gather.nxv16i8.nxv16p0(<vscale x 16 x ptr> align 1 [[TMP9]], <vscale x 16 x i1> [[TMP6]], i32 [[TMP5]])
; PREDICATED_TAIL_FOLDING-NEXT: [[TMP10:%.*]] = or disjoint <vscale x 16 x i32> [[TMP7]], splat (i32 1)
; PREDICATED_TAIL_FOLDING-NEXT: [[TMP11:%.*]] = zext nneg <vscale x 16 x i32> [[TMP10]] to <vscale x 16 x i64>
; PREDICATED_TAIL_FOLDING-NEXT: [[TMP12:%.*]] = getelementptr inbounds i8, ptr [[P]], <vscale x 16 x i64> [[TMP11]]
-; PREDICATED_TAIL_FOLDING-NEXT: [[WIDE_MASKED_GATHER3:%.*]] = call <vscale x 16 x i8> @llvm.masked.gather.nxv16i8.nxv16p0(<vscale x 16 x ptr> [[TMP12]], i32 1, <vscale x 16 x i1> [[TMP6]], <vscale x 16 x i8> poison)
+; PREDICATED_TAIL_FOLDING-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_TAIL_FOLDING-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_TAIL_FOLDING-NEXT: [[TMP14:%.*]] = zext nneg <vscale x 16 x i32> [[TMP7]] to <vscale x 16 x i64>
; PREDICATED_TAIL_FOLDING-NEXT: [[TMP15:%.*]] = getelementptr inbounds i8, ptr [[Q]], <vscale x 16 x i64> [[TMP14]]
-; PREDICATED_TAIL_FOLDING-NEXT: call void @llvm.masked.scatter.nxv16i8.nxv16p0(<vscale x 16 x i8> [[TMP13]], <vscale x 16 x ptr> [[TMP15]], i32 1, <vscale x 16 x i1> [[TMP6]])
+; PREDICATED_TAIL_FOLDING-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_TAIL_FOLDING-NEXT: [[TMP16:%.*]] = sub <vscale x 16 x i8> zeroinitializer, [[TMP13]]
; PREDICATED_TAIL_FOLDING-NEXT: [[TMP17:%.*]] = zext nneg <vscale x 16 x i32> [[TMP10]] to <vscale x 16 x i64>
; PREDICATED_TAIL_FOLDING-NEXT: [[TMP18:%.*]] = getelementptr inbounds i8, ptr [[Q]], <vscale x 16 x i64> [[TMP17]]
-; PREDICATED_TAIL_FOLDING-NEXT: call void @llvm.masked.scatter.nxv16i8.nxv16p0(<vscale x 16 x i8> [[TMP16]], <vscale x 16 x ptr> [[TMP18]], i32 1, <vscale x 16 x i1> [[TMP6]])
+; PREDICATED_TAIL_FOLDING-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_TAIL_FOLDING-NEXT: [[INDEX_EVL_NEXT]] = add nuw i32 [[TMP5]], [[EVL_BASED_IV]]
; PREDICATED_TAIL_FOLDING-NEXT: [[INDEX_NEXT]] = add nuw i32 [[INDEX]], [[TMP3]]
; PREDICATED_TAIL_FOLDING-NEXT: [[VEC_IND_NEXT]] = add <vscale x 16 x i32> [[VEC_IND]], [[BROADCAST_SPLAT2]]
; PREDICATED_TAIL_FOLDING-NEXT: [[TMP19:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
@@ -272,51 +274,53 @@ define void @masked_strided_factor4(ptr noalias nocapture readonly %p, ptr noali
; PREDICATED_TAIL_FOLDING-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 16 x i32> poison, i32 [[CONV]], i64 0
; PREDICATED_TAIL_FOLDING-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 16 x i32> [[BROADCAST_SPLATINSERT]], <vscale x 16 x i32> poison, <vscale x 16 x i32> zeroinitializer
; PREDICATED_TAIL_FOLDING-NEXT: [[TMP4:%.*]] = call <vscale x 16 x i32> @llvm.stepvector.nxv16i32()
-; PREDICATED_TAIL_FOLDING-NEXT: [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <vscale x 16 x i32> poison, i32 [[TMP3]], i64 0
-; PREDICATED_TAIL_FOLDING-NEXT: [[BROADCAST_SPLAT2:%.*]] = shufflevector <vscale x 16 x i32> [[BROADCAST_SPLATINSERT1]], <vscale x 16 x i32> poison, <vscale x 16 x i32> zeroinitializer
; PREDICATED_TAIL_FOLDING-NEXT: br label [[VECTOR_BODY:%.*]]
; PREDICATED_TAIL_FOLDING: vector.body:
; PREDICATED_TAIL_FOLDING-NEXT: [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; PREDICATED_TAIL_FOLDING-NEXT: [[EVL_BASED_IV:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_EVL_NEXT:%.*]], [[VECTOR_BODY]] ]
; PREDICATED_TAIL_FOLDING-NEXT: [[VEC_IND:%.*]] = phi <vscale x 16 x i32> [ [[TMP4]], [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[VECTOR_BODY]] ]
-; PREDICATED_TAIL_FOLDING-NEXT: [[ACTIVE_LANE_MASK:%.*]] = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i32(i32 [[INDEX]], i32 1024)
-; PREDICATED_TAIL_FOLDING-NEXT: [[TMP5:%.*]] = icmp ugt <vscale x 16 x i32> [[VEC_IND]], [[BROADCAST_SPLAT]]
-; PREDICATED_TAIL_FOLDING-NEXT: [[TMP6:%.*]] = select <vscale x 16 x i1> [[ACTIVE_LANE_MASK]], <vscale x 16 x i1> [[TMP5]], <vscale x 16 x i1> zeroinitializer
+; PREDICATED_TAIL_FOLDING-NEXT: [[AVL:%.*]] = sub i32 1024, [[EVL_BASED_IV]]
+; PREDICATED_TAIL_FOLDING-NEXT: [[TMP5:%.*]] = call i32 @llvm.experimental.get.vector.length.i32(i32 [[AVL]], i32 16, i1 true)
+; PREDICATED_TAIL_FOLDING-NEXT: [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <vscale x 16 x i32> poison, i32 [[TMP5]], i64 0
+; PREDICATED_TAIL_FOLDING-NEXT: [[BROADCAST_SPLAT2:%.*]] = shufflevector <vscale x 16 x i32> [[BROADCAST_SPLATINSERT1]], <vscale x 16 x i32> poison, <vscale x 16 x i32> zeroinitializer
+; PREDICATED_TAIL_FOLDING-NEXT: [[TMP6:%.*]] = icmp ugt <vscale x 16 x i32> [[VEC_IND]], [[BROADCAST_SPLAT]]
; PREDICATED_TAIL_FOLDING-NEXT: [[TMP7:%.*]] = shl nuw nsw <vscale x 16 x i32> [[VEC_IND]], splat (i32 2)
; PREDICATED_TAIL_FOLDING-NEXT: [[TMP8:%.*]] = or disjoint <vscale x 16 x i32> [[TMP7]], splat (i32 1)
; PREDICATED_TAIL_FOLDING-NEXT: [[TMP9:%.*]] = or disjoint <vscale x 16 x i32> [[TMP7]], splat (i32 2)
; PREDICATED_TAIL_FOLDING-NEXT: [[TMP10:%.*]] = or disjoint <vscale x 16 x i32> [[TMP7]], splat (i32 3)
; PREDICATED_TAIL_FOLDING-NEXT: [[TMP11:%.*]] = zext nneg <vscale x 16 x i32> [[TMP7]] to <vscale x 16 x i64>
; PREDICATED_TAIL_FOLDING-NEXT: [[TMP12:%.*]] = getelementptr inbounds i8, ptr [[P]], <vscale x 16 x i64> [[TMP11]]
-; PREDICATED_TAIL_FOLDING-NEXT: [[WIDE_MASKED_GATHER:%.*]] = call <vscale x 16 x i8> @llvm.masked.gather.nxv16i8.nxv16p0(<vscale x 16 x ptr> [[TMP12]], i32 1, <vscale x 16 x i1> [[TMP6]], <vscale x 16 x i8> poison)
+; PREDICATED_TAIL_FOLDING-NEXT: [[WIDE_MASKED_GATHER:%.*]] = 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_TAIL_FOLDING-NEXT: [[TMP13:%.*]] = zext nneg <vscale x 16 x i32> [[TMP8]] to <vscale x 16 x i64>
; PREDICATED_TAIL_FOLDING-NEXT: [[TMP14:%.*]] = getelementptr inbounds i8, ptr [[P]], <vscale x 16 x i64> [[TMP13]]
-; PREDICATED_TAIL_FOLDING-NEXT: [[WIDE_MASKED_GATHER3:%.*]] = call <vscale x 16 x i8> @llvm.masked.gather.nxv16i8.nxv16p0(<vscale x 16 x ptr> [[TMP14]], i32 1, <vscale x 16 x i1> [[TMP6]], <vscale x 16 x i8> poison)
+; PREDICATED_TAIL_FOLDING-NEXT: [[WIDE_MASKED_GATHER3:%.*]] = call <vscale x 16 x i8> @llvm.vp.gather.nxv16i8.nxv16p0(<vscale x 16 x ptr> align 1 [[TMP14]], <vscale x 16 x i1> [[TMP6]], i32 [[TMP5]])
; PREDICATED_TAIL_FOLDING-NEXT: [[TMP15:%.*]] = zext nneg <vscale x 16 x i32> [[TMP9]] to <vscale x 16 x i64>
; PREDICATED_TAIL_FOLDING-NEXT: [[TMP16:%.*]] = getelementptr inbounds i8, ptr [[P]], <vscale x 16 x i64> [[TMP15]]
-; PREDICATED_TAIL_FOLDING-NEXT: [[WIDE_MASKED_GATHER4:%.*]] = call <vscale x 16 x i8> @llvm.masked.gather.nxv16i8.nxv16p0(<vscale x 16 x ptr> [[TMP16]], i32 1, <vscale x 16 x i1> [[TMP6]], <vscale x 16 x i8> poison)
+; PREDICATED_TAIL_FOLDING-NEXT: [[WIDE_MASKED_GATHER4:%.*]] = call <vscale x 16 x i8> @llvm.vp.gather.nxv16i8.nxv16p0(<vscale x 16 x ptr> align 1 [[TMP16]], <vscale x 16 x i1> [[TMP6]], i32 [[TMP5]])
; PREDICATED_TAIL_FOLDING-NEXT: [[TMP17:%.*]] = zext nneg <vscale x 16 x i32> [[TMP10]] to <vscale x 16 x i64>
; PREDICATED_TAIL_FOLDING-NEXT: [[TMP18:%.*]] = getelementptr inbounds i8, ptr [[P]], <vscale x 16 x i64> [[TMP17]]
-; PREDICATED_TAIL_FOLDING-NEXT: [[WIDE_MASKED_GATHER5:%.*]] = call <vscale x 16 x i8> @llvm.masked.gather.nxv16i8.nxv16p0(<vscale x 16 x ptr> [[TMP18]], i32 1, <vscale x 16 x i1> [[TMP6]], <vscale x 16 x i8> poison)
+; PREDICATED_TAIL_FOLDING-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_TAIL_FOLDING-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_TAIL_FOLDING-NEXT: [[TMP20:%.*]] = sub <vscale x 16 x i8> zeroinitializer, [[TMP19]]
; PREDICATED_TAIL_FOLDING-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_TAIL_FOLDING-NEXT: [[TMP22:%.*]] = sub <vscale x 16 x i8> zeroinitializer, [[TMP21]]
; PREDICATED_TAIL_FOLDING-NEXT: [[TMP23:%.*]] = zext nneg <vscale x 16 x i32> [[TMP7]] to <vscale x 16 x i64>
; PREDICATED_TAIL_FOLDING-NEXT: [[TMP24:%.*]] = getelementptr inbounds i8, ptr [[Q]], <vscale x 16 x i64> [[TMP23]]
-; PREDICATED_TAIL_FOLDING-NEXT: call void @llvm.masked.scatter.nxv16i8.nxv16p0(<vscale x 16 x i8> [[TMP19]], <vscale x 16 x ptr> [[TMP24]], i32 1, <vscale x 16 x i1> [[TMP6]])
+; PREDICATED_TAIL_FOLDING-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_TAIL_FOLDING-NEXT: [[TMP25:%.*]] = zext nneg <vscale x 16 x i32> [[TMP8]] to <vscale x 16 x i64>
; PREDICATED_TAIL_FOLDING-NEXT: [[TMP26:%.*]] = getelementptr inbounds i8, ptr [[Q]], <vscale x 16 x i64> [[TMP25]]
-; PREDICATED_TAIL_FOLDING-NEXT: call void @llvm.masked.scatter.nxv16i8.nxv16p0(<vscale x 16 x i8> [[TMP20]], <vscale x 16 x ptr> [[TMP26]], i32 1, <vscale x 16 x i1> [[TMP6]])
+; PREDICATED_TAIL_FOLDING-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_TAIL_FOLDING-NEXT: [[TMP27:%.*]] = zext nneg <vscale x 16 x i32> [[TMP9]] to <vscale x 16 x i64>
; PREDICATED_TAIL_FOLDING-NEXT: [[TMP28:%.*]] = getelementptr inbounds i8, ptr [[Q]], <vscale x 16 x i64> [[TMP27]]
-; PREDICATED_TAIL_FOLDING-NEXT: call void @llvm.masked.scatter.nxv16i8.nxv16p0(<vscale x 16 x i8> [[TMP21]], <vscale x 16 x ptr> [[TMP28]], i32 1, <vscale x 16 x i1> [[TMP6]])
+; PREDICATED_TAIL_FOLDING-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_TAIL_FOLDING-NEXT: [[TMP29:%.*]] = zext nneg <vscale x 16 x i32> [[TMP10]] to <vscale x 16 x i64>
; PREDICATED_TAIL_FOLDING-NEXT: [[TMP30:%.*]] = getelementptr inbounds i8, ptr [[Q]], <vscale x 16 x i64> [[TMP29]]
-; PREDICATED_TAIL_FOLDING-NEXT: call void @llvm.masked.scatter.nxv16i8.nxv16p0(<vscale x 16 x i8> [[TMP22]], <vscale x 16 x ptr> [[TMP30]], i32 1, <vscale x 16 x i1> [[TMP6]])
+; PREDICATED_TAIL_FOLDING-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_TAIL_FOLDING-NEXT: [[INDEX_EVL_NEXT]] = add nuw i32 [[TMP5]], [[EVL_BASED_IV]]
; PREDICATED_TAIL_FOLDING-NEXT: [[INDEX_NEXT]] = add nuw i32 [[INDEX]], [[TMP3]]
; PREDICATED_TAIL_FOLDING-NEXT: [[VEC_IND_NEXT]] = add <vscale x 16 x i32> [[VEC_IND]], [[BROADCAST_SPLAT2]]
; PREDICATED_TAIL_FOLDING-NEXT: [[TMP31:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
-; PREDICATED_TAIL_FOLDING-NEXT: br i1 [[TMP31]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
+; PREDICATED_TAIL_FOLDING-NEXT: br i1 [[TMP31]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
; PREDICATED_TAIL_FOLDING: middle.block:
; PREDICATED_TAIL_FOLDING-NEXT: br label [[FOR_END:%.*]]
; PREDICATED_TAIL_FOLDING: scalar.ph:
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/low-trip-count.ll b/llvm/test/Transforms/LoopVectorize/RISCV/low-trip-count.ll
index 6c57d2f2f00e6..c5144645269da 100644
--- a/llvm/test/Transforms/LoopVectorize/RISCV/low-trip-count.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/low-trip-count.ll
@@ -133,16 +133,23 @@ define void @trip8_i8(ptr noalias nocapture noundef %dst, ptr noalias nocapture
; CHECK-NEXT: [[TMP4:%.*]] = mul nuw i64 [[TMP3]], 4
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
-; CHECK-NEXT: [[ACTIVE_LANE_MASK:%.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 0, i64 8)
-; CHECK-NEXT: [[TMP9:%.*]] = getelementptr inbounds i8, ptr [[TMP8:%.*]], i32 0
-; CHECK-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 4 x i8> @llvm.masked.load.nxv4i8.p0(ptr [[TMP9]], i32 1, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x i8> poison)
+; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT: [[EVL_BASED_IV:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_EVL_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT: [[AVL:%.*]] = sub i64 8, [[EVL_BASED_IV]]
+; CHECK-NEXT: [[TMP5:%.*]] = call i32 @llvm.experimental.get.vector.length.i64(i64 [[AVL]], i32 4, i1 true)
+; CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds i8, ptr [[SRC:%.*]], i64 [[EVL_BASED_IV]]
+; CHECK-NEXT: [[TMP9:%.*]] = getelementptr inbounds i8, ptr [[TMP8]], i32 0
+; CHECK-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 4 x i8> @llvm.vp.load.nxv4i8.p0(ptr align 1 [[TMP9]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP5]])
; CHECK-NEXT: [[TMP10:%.*]] = shl <vscale x 4 x i8> [[WIDE_MASKED_LOAD]], splat (i8 1)
-; CHECK-NEXT: [[TMP12:%.*]] = getelementptr inbounds i8, ptr [[TMP11:%.*]], i32 0
-; CHECK-NEXT: [[WIDE_MASKED_LOAD1:%.*]] = call <vscale x 4 x i8> @llvm.masked.load.nxv4i8.p0(ptr [[TMP12]], i32 1, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x i8> poison)
+; CHECK-NEXT: [[TMP11:%.*]] = getelementptr inbounds i8, ptr [[DST:%.*]], i64 [[EVL_BASED_IV]]
+; CHECK-NEXT: [[TMP12:%.*]] = getelementptr inbounds i8, ptr [[TMP11]], i32 0
+; CHECK-NEXT: [[WIDE_MASKED_LOAD1:%.*]] = call <vscale x 4 x i8> @llvm.vp.load.nxv4i8.p0(ptr align 1 [[TMP12]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP5]])
; CHECK-NEXT: [[TMP13:%.*]] = add <vscale x 4 x i8> [[TMP10]], [[WIDE_MASKED_LOAD1]]
-; CHECK-NEXT: [[TMP14:%.*]] = getelementptr inbounds i8, ptr [[TMP11]], i32 0
-; CHECK-NEXT: call void @llvm.masked.store.nxv4i8.p0(<vscale x 4 x i8> [[TMP13]], ptr [[TMP14]], i32 1, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]])
-; CHECK-NEXT: br label [[MIDDLE_BLOCK:%.*]]
+; CHECK-NEXT: call void @llvm.vp.store.nxv4i8.p0(<vscale x 4 x i8> [[TMP13]], ptr align 1 [[TMP12]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP5]])
+; CHECK-NEXT: [[TMP14:%.*]] = zext i32 [[TMP5]] to i64
+; CHECK-NEXT: [[INDEX_EVL_NEXT]] = add nuw i64 [[TMP14]], [[EVL_BASED_IV]]
+; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP4]]
+; CHECK-NEXT: br i1 true, label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK: middle.block:
; CHECK-NEXT: br label [[FOR_END:%.*]]
; CHECK: scalar.ph:
@@ -150,16 +157,16 @@ define void @trip8_i8(ptr noalias nocapture noundef %dst, ptr noalias nocapture
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[I_08:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INC:%.*]], [[FOR_BODY]] ]
-; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i8, ptr [[TMP8]], i64 [[I_08]]
+; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i8, ptr [[SRC]], i64 [[I_08]]
; CHECK-NEXT: [[TMP15:%.*]] = load i8, ptr [[ARRAYIDX]], align 1
; CHECK-NEXT: [[MUL:%.*]] = shl i8 [[TMP15]], 1
-; CHECK-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i8, ptr [[TMP11]], i64 [[I_08]]
+; CHECK-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i8, ptr [[DST]], i64 [[I_08]]
; CHECK-NEXT: [[TMP16:%.*]] = load i8, ptr [[ARRAYIDX1]], align 1
; CHECK-NEXT: [[ADD:%.*]] = add i8 [[MUL]], [[TMP16]]
; CHECK-NEXT: store i8 [[ADD]], ptr [[ARRAYIDX1]], align 1
; CHECK-NEXT: [[INC]] = add nuw nsw i64 [[I_08]], 1
; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INC]], 8
-; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
+; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
; CHECK: for.end:
; CHECK-NEXT: ret void
;
@@ -215,7 +222,7 @@ define void @trip16_i8(ptr noalias nocapture noundef %dst, ptr noalias nocapture
; CHECK-NEXT: store i8 [[ADD]], ptr [[ARRAYIDX1]], align 1
; CHECK-NEXT: [[INC]] = add nuw nsw i64 [[I_08]], 1
; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INC]], 16
-; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
+; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
; CHECK: for.end:
; CHECK-NEXT: ret void
;
@@ -272,7 +279,7 @@ define void @trip32_i8(ptr noalias nocapture noundef %dst, ptr noalias nocapture
; CHECK-NEXT: store i8 [[ADD]], ptr [[ARRAYIDX1]], align 1
; CHECK-NEXT: [[INC]] = add nuw nsw i64 [[I_08]], 1
; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INC]], 32
-; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
+; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
; CHECK: for.end:
; CHECK-NEXT: ret void
;
@@ -315,7 +322,7 @@ define void @trip24_i8(ptr noalias nocapture noundef %dst, ptr noalias nocapture
; CHECK-NEXT: store <8 x i8> [[TMP6]], ptr [[TMP5]], align 1
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 8
; CHECK-NEXT: [[TMP7:%.*]] = icmp eq i64 [[INDEX_NEXT]], 24
-; CHECK-NEXT: br i1 [[TMP7]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
+; CHECK-NEXT: br i1 [[TMP7]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP7:![0-9]+]]
; CHECK: middle.block:
; CHECK-NEXT: br i1 true, label [[FOR_END:%.*]], label [[SCALAR_PH]]
; CHECK: scalar.ph:
@@ -332,7 +339,7 @@ define void @trip24_i8(ptr noalias nocapture noundef %dst, ptr noalias nocapture
; CHECK-NEXT: store i8 [[ADD]], ptr [[ARRAYIDX1]], align 1
; CHECK-NEXT: [[INC]] = add nuw nsw i64 [[I_08]], 1
; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INC]], 24
-; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
+; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
; CHECK: for.end:
; CHECK-NEXT: ret void
;
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/pr88802.ll b/llvm/test/Transforms/LoopVectorize/RISCV/pr88802.ll
index a1201dcfbdf57..02288112f3389 100644
--- a/llvm/test/Transforms/LoopVectorize/RISCV/pr88802.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/pr88802.ll
@@ -7,29 +7,49 @@ define void @test(ptr %p, i64 %a, i8 %b) {
; CHECK-NEXT: entry:
; CHECK-NEXT: br i1 false, label [[SCALAR_PH1:%.*]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
-; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <16 x i8> poison, i8 [[B]], i64 0
-; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <16 x i8> [[BROADCAST_SPLATINSERT]], <16 x i8> poison, <16 x i32> zeroinitializer
-; CHECK-NEXT: [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <16 x i64> poison, i64 [[A]], i64 0
-; CHECK-NEXT: [[BROADCAST_SPLAT2:%.*]] = shufflevector <16 x i64> [[BROADCAST_SPLATINSERT1]], <16 x i64> poison, <16 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP0:%.*]] = shl <16 x i64> [[BROADCAST_SPLAT2]], splat (i64 48)
-; CHECK-NEXT: [[TMP1:%.*]] = ashr <16 x i64> [[TMP0]], splat (i64 52)
-; CHECK-NEXT: [[TMP2:%.*]] = trunc <16 x i64> [[TMP1]] to <16 x i32>
-; CHECK-NEXT: [[TMP3:%.*]] = zext <16 x i8> [[BROADCAST_SPLAT]] to <16 x i32>
+; CHECK-NEXT: [[TMP0:%.*]] = call i32 @llvm.vscale.i32()
+; CHECK-NEXT: [[TMP1:%.*]] = mul nuw i32 [[TMP0]], 2
+; CHECK-NEXT: [[TMP2:%.*]] = sub i32 [[TMP1]], 1
+; CHECK-NEXT: [[N_RND_UP:%.*]] = add i32 9, [[TMP2]]
+; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i32 [[N_RND_UP]], [[TMP1]]
+; CHECK-NEXT: [[N_VEC:%.*]] = sub i32 [[N_RND_UP]], [[N_MOD_VF]]
+; CHECK-NEXT: [[TMP3:%.*]] = call i32 @llvm.vscale.i32()
+; CHECK-NEXT: [[TMP4:%.*]] = mul nuw i32 [[TMP3]], 2
+; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 2 x i8> poison, i8 [[B]], i64 0
+; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 2 x i8> [[BROADCAST_SPLATINSERT]], <vscale x 2 x i8> poison, <vscale x 2 x i32> zeroinitializer
+; CHECK-NEXT: [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[A]], i64 0
+; CHECK-NEXT: [[BROADCAST_SPLAT2:%.*]] = shufflevector <vscale x 2 x i64> [[BROADCAST_SPLATINSERT1]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP5:%.*]] = shl <vscale x 2 x i64> [[BROADCAST_SPLAT2]], splat (i64 48)
+; CHECK-NEXT: [[TMP6:%.*]] = ashr <vscale x 2 x i64> [[TMP5]], splat (i64 52)
+; CHECK-NEXT: [[TMP7:%.*]] = trunc <vscale x 2 x i64> [[TMP6]] to <vscale x 2 x i32>
+; CHECK-NEXT: [[TMP8:%.*]] = zext <vscale x 2 x i8> [[BROADCAST_SPLAT]] to <vscale x 2 x i32>
+; CHECK-NEXT: [[BROADCAST_SPLATINSERT3:%.*]] = insertelement <vscale x 2 x ptr> poison, ptr [[P]], 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
+; CHECK-NEXT: [[TMP9:%.*]] = call <vscale x 2 x i32> @llvm.stepvector.nxv2i32()
+; CHECK-NEXT: [[TMP10:%.*]] = mul <vscale x 2 x i32> [[TMP9]], splat (i32 1)
+; CHECK-NEXT: [[INDUCTION:%.*]] = add <vscale x 2 x i32> zeroinitializer, [[TMP10]]
; CHECK-NEXT: br label [[FOR_COND:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[FOR_COND]] ]
-; CHECK-NEXT: [[VEC_IND:%.*]] = phi <16 x i32> [ <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>, [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[FOR_COND]] ]
-; CHECK-NEXT: [[ACTIVE_LANE_MASK:%.*]] = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32 [[INDEX]], i32 9)
-; CHECK-NEXT: [[TMP4:%.*]] = icmp sge <16 x i32> [[VEC_IND]], splat (i32 2)
-; CHECK-NEXT: [[TMP5:%.*]] = select <16 x i1> [[ACTIVE_LANE_MASK]], <16 x i1> [[TMP4]], <16 x i1> zeroinitializer
-; CHECK-NEXT: [[PREDPHI:%.*]] = select <16 x i1> [[TMP5]], <16 x i32> [[TMP2]], <16 x i32> [[TMP3]]
-; CHECK-NEXT: [[TMP6:%.*]] = shl <16 x i32> [[PREDPHI]], splat (i32 8)
-; CHECK-NEXT: [[TMP8:%.*]] = trunc <16 x i32> [[TMP6]] to <16 x i8>
-; CHECK-NEXT: [[TMP40:%.*]] = extractelement <16 x i8> [[TMP8]], i32 15
-; CHECK-NEXT: store i8 [[TMP40]], ptr [[P]], align 1
-; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 16
-; CHECK-NEXT: [[VEC_IND_NEXT]] = add <16 x i32> [[VEC_IND]], splat (i32 16)
-; CHECK-NEXT: br i1 true, label [[MIDDLE_BLOCK:%.*]], label [[FOR_COND]], !llvm.loop [[LOOP0:![0-9]+]]
+; 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: [[TMP11:%.*]] = call i32 @llvm.experimental.get.vector.length.i32(i32 [[AVL]], i32 2, i1 true)
+; CHECK-NEXT: [[TMP12:%.*]] = mul i32 1, [[TMP11]]
+; CHECK-NEXT: [[BROADCAST_SPLATINSERT5:%.*]] = insertelement <vscale x 2 x i32> poison, i32 [[TMP12]], 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
+; CHECK-NEXT: [[TMP13:%.*]] = icmp ule <vscale x 2 x i32> [[VEC_IND]], splat (i32 8)
+; CHECK-NEXT: [[TMP14:%.*]] = icmp sge <vscale x 2 x i32> [[VEC_IND]], splat (i32 2)
+; CHECK-NEXT: [[TMP15:%.*]] = select <vscale x 2 x i1> [[TMP13]], <vscale x 2 x i1> [[TMP14]], <vscale x 2 x i1> zeroinitializer
+; CHECK-NEXT: [[PREDPHI:%.*]] = select <vscale x 2 x i1> [[TMP15]], <vscale x 2 x i32> [[TMP7]], <vscale x 2 x i32> [[TMP8]]
+; CHECK-NEXT: [[TMP16:%.*]] = shl <vscale x 2 x i32> [[PREDPHI]], splat (i32 8)
+; 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: [[INDEX_NEXT]] = add nuw i32 [[INDEX]], [[TMP4]]
+; CHECK-NEXT: [[VEC_IND_NEXT]] = add <vscale x 2 x i32> [[VEC_IND]], [[BROADCAST_SPLAT6]]
+; CHECK-NEXT: [[TMP18:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT: br i1 [[TMP18]], label [[MIDDLE_BLOCK:%.*]], label [[FOR_COND]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK: middle.block:
; CHECK-NEXT: br label [[EXIT1:%.*]]
; CHECK: scalar.ph:
@@ -52,7 +72,7 @@ define void @test(ptr %p, i64 %a, i8 %b) {
; CHECK-NEXT: [[TRUNC:%.*]] = trunc i32 [[SHL_I32]] to i8
; CHECK-NEXT: store i8 [[TRUNC]], ptr [[P]], align 1
; CHECK-NEXT: [[CMP:%.*]] = icmp slt i32 [[IV]], 8
-; CHECK-NEXT: br i1 [[CMP]], label [[FOR_COND1]], label [[EXIT1]], !llvm.loop [[LOOP3:![0-9]+]]
+; CHECK-NEXT: br i1 [[CMP]], label [[FOR_COND1]], label [[EXIT1]], !llvm.loop [[LOOP4:![0-9]+]]
; CHECK: exit:
; CHECK-NEXT: ret void
;
@@ -84,8 +104,9 @@ exit: ; preds = %for.body
ret void
}
;.
-; CHECK: [[LOOP0]] = distinct !{[[LOOP0]], [[META1:![0-9]+]], [[META2:![0-9]+]]}
+; CHECK: [[LOOP0]] = distinct !{[[LOOP0]], [[META1:![0-9]+]], [[META2:![0-9]+]], [[META3:![0-9]+]]}
; CHECK: [[META1]] = !{!"llvm.loop.isvectorized", i32 1}
-; CHECK: [[META2]] = !{!"llvm.loop.unroll.runtime.disable"}
-; CHECK: [[LOOP3]] = distinct !{[[LOOP3]], [[META2]], [[META1]]}
+; CHECK: [[META2]] = !{!"llvm.loop.isvectorized.tailfoldingstyle", !"evl"}
+; CHECK: [[META3]] = !{!"llvm.loop.unroll.runtime.disable"}
+; CHECK: [[LOOP4]] = distinct !{[[LOOP4]], [[META3]], [[META1]]}
;.
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/scalable-tailfold.ll b/llvm/test/Transforms/LoopVectorize/RISCV/scalable-tailfold.ll
index ff9c58525e51c..b046f61e4d50e 100644
--- a/llvm/test/Transforms/LoopVectorize/RISCV/scalable-tailfold.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/scalable-tailfold.ll
@@ -24,12 +24,16 @@ define void @vector_add(ptr noalias nocapture %a, i64 %v, i64 %n) {
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT: [[ACTIVE_LANE_MASK:%.*]] = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 [[INDEX]], i64 1025)
-; CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds i64, ptr [[A:%.*]], i64 [[INDEX]]
+; CHECK-NEXT: [[EVL_BASED_IV:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_EVL_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT: [[AVL:%.*]] = sub i64 1025, [[EVL_BASED_IV]]
+; CHECK-NEXT: [[TMP7:%.*]] = call i32 @llvm.experimental.get.vector.length.i64(i64 [[AVL]], i32 2, i1 true)
+; CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds i64, ptr [[A:%.*]], i64 [[EVL_BASED_IV]]
; CHECK-NEXT: [[TMP9:%.*]] = getelementptr inbounds i64, ptr [[TMP8]], i32 0
-; CHECK-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 2 x i64> @llvm.masked.load.nxv2i64.p0(ptr [[TMP9]], i32 8, <vscale x 2 x i1> [[ACTIVE_LANE_MASK]], <vscale x 2 x i64> poison)
+; CHECK-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 2 x i64> @llvm.vp.load.nxv2i64.p0(ptr align 8 [[TMP9]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP7]])
; CHECK-NEXT: [[TMP10:%.*]] = add <vscale x 2 x i64> [[WIDE_MASKED_LOAD]], [[BROADCAST_SPLAT]]
-; CHECK-NEXT: call void @llvm.masked.store.nxv2i64.p0(<vscale x 2 x i64> [[TMP10]], ptr [[TMP9]], i32 8, <vscale x 2 x i1> [[ACTIVE_LANE_MASK]])
+; CHECK-NEXT: call void @llvm.vp.store.nxv2i64.p0(<vscale x 2 x i64> [[TMP10]], ptr align 8 [[TMP9]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP7]])
+; CHECK-NEXT: [[TMP12:%.*]] = zext i32 [[TMP7]] to i64
+; CHECK-NEXT: [[INDEX_EVL_NEXT]] = add nuw i64 [[TMP12]], [[EVL_BASED_IV]]
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP6]]
; CHECK-NEXT: [[TMP11:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT: br i1 [[TMP11]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
@@ -46,7 +50,7 @@ define void @vector_add(ptr noalias nocapture %a, i64 %v, i64 %n) {
; CHECK-NEXT: store i64 [[ADD]], ptr [[ARRAYIDX]], align 8
; CHECK-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], 1025
-; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
+; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
; CHECK: for.end:
; CHECK-NEXT: ret void
;
@@ -87,15 +91,19 @@ define void @indexed_store(ptr noalias nocapture %a, ptr noalias nocapture %b, i
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT: [[ACTIVE_LANE_MASK:%.*]] = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 [[INDEX]], i64 1025)
-; CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds i64, ptr [[B:%.*]], i64 [[INDEX]]
+; CHECK-NEXT: [[EVL_BASED_IV:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_EVL_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT: [[AVL:%.*]] = sub i64 1025, [[EVL_BASED_IV]]
+; CHECK-NEXT: [[TMP7:%.*]] = call i32 @llvm.experimental.get.vector.length.i64(i64 [[AVL]], i32 2, i1 true)
+; CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds i64, ptr [[B:%.*]], i64 [[EVL_BASED_IV]]
; CHECK-NEXT: [[TMP9:%.*]] = getelementptr inbounds i64, ptr [[TMP8]], i32 0
-; CHECK-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 2 x i64> @llvm.masked.load.nxv2i64.p0(ptr [[TMP9]], i32 8, <vscale x 2 x i1> [[ACTIVE_LANE_MASK]], <vscale x 2 x i64> poison)
+; CHECK-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 2 x i64> @llvm.vp.load.nxv2i64.p0(ptr align 8 [[TMP9]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP7]])
; CHECK-NEXT: [[TMP10:%.*]] = getelementptr inbounds i64, ptr [[A:%.*]], <vscale x 2 x i64> [[WIDE_MASKED_LOAD]]
-; CHECK-NEXT: call void @llvm.masked.scatter.nxv2i64.nxv2p0(<vscale x 2 x i64> [[BROADCAST_SPLAT]], <vscale x 2 x ptr> [[TMP10]], i32 8, <vscale x 2 x i1> [[ACTIVE_LANE_MASK]])
+; CHECK-NEXT: call void @llvm.vp.scatter.nxv2i64.nxv2p0(<vscale x 2 x i64> [[BROADCAST_SPLAT]], <vscale x 2 x ptr> align 8 [[TMP10]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP7]])
+; CHECK-NEXT: [[TMP12:%.*]] = zext i32 [[TMP7]] to i64
+; CHECK-NEXT: [[INDEX_EVL_NEXT]] = add nuw i64 [[TMP12]], [[EVL_BASED_IV]]
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP6]]
; CHECK-NEXT: [[TMP11:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
-; CHECK-NEXT: br i1 [[TMP11]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
+; CHECK-NEXT: br i1 [[TMP11]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
; CHECK: middle.block:
; CHECK-NEXT: br label [[FOR_END:%.*]]
; CHECK: scalar.ph:
@@ -109,7 +117,7 @@ define void @indexed_store(ptr noalias nocapture %a, ptr noalias nocapture %b, i
; CHECK-NEXT: store i64 [[V]], ptr [[AADDR]], align 8
; CHECK-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], 1025
-; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
+; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
; CHECK: for.end:
; CHECK-NEXT: ret void
;
@@ -146,20 +154,24 @@ define i64 @indexed_load(ptr noalias nocapture %a, ptr noalias nocapture %b, i64
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT: [[EVL_BASED_IV:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_EVL_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[VEC_PHI:%.*]] = phi <vscale x 2 x i64> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP11:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT: [[ACTIVE_LANE_MASK:%.*]] = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 [[INDEX]], i64 1025)
-; CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds i64, ptr [[B:%.*]], i64 [[INDEX]]
+; CHECK-NEXT: [[AVL:%.*]] = sub i64 1025, [[EVL_BASED_IV]]
+; CHECK-NEXT: [[TMP7:%.*]] = call i32 @llvm.experimental.get.vector.length.i64(i64 [[AVL]], i32 2, i1 true)
+; CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds i64, ptr [[B:%.*]], i64 [[EVL_BASED_IV]]
; CHECK-NEXT: [[TMP9:%.*]] = getelementptr inbounds i64, ptr [[TMP8]], i32 0
-; CHECK-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 2 x i64> @llvm.masked.load.nxv2i64.p0(ptr [[TMP9]], i32 8, <vscale x 2 x i1> [[ACTIVE_LANE_MASK]], <vscale x 2 x i64> poison)
+; CHECK-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 2 x i64> @llvm.vp.load.nxv2i64.p0(ptr align 8 [[TMP9]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP7]])
; CHECK-NEXT: [[TMP10:%.*]] = getelementptr inbounds i64, ptr [[A:%.*]], <vscale x 2 x i64> [[WIDE_MASKED_LOAD]]
-; CHECK-NEXT: [[WIDE_MASKED_GATHER:%.*]] = call <vscale x 2 x i64> @llvm.masked.gather.nxv2i64.nxv2p0(<vscale x 2 x ptr> [[TMP10]], i32 8, <vscale x 2 x i1> [[ACTIVE_LANE_MASK]], <vscale x 2 x i64> poison)
-; CHECK-NEXT: [[TMP11]] = add <vscale x 2 x i64> [[VEC_PHI]], [[WIDE_MASKED_GATHER]]
-; CHECK-NEXT: [[TMP12:%.*]] = select <vscale x 2 x i1> [[ACTIVE_LANE_MASK]], <vscale x 2 x i64> [[TMP11]], <vscale x 2 x i64> [[VEC_PHI]]
+; CHECK-NEXT: [[WIDE_MASKED_GATHER:%.*]] = call <vscale x 2 x i64> @llvm.vp.gather.nxv2i64.nxv2p0(<vscale x 2 x ptr> align 8 [[TMP10]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP7]])
+; CHECK-NEXT: [[TMP12:%.*]] = add <vscale x 2 x i64> [[VEC_PHI]], [[WIDE_MASKED_GATHER]]
+; CHECK-NEXT: [[TMP11]] = call <vscale x 2 x i64> @llvm.vp.merge.nxv2i64(<vscale x 2 x i1> splat (i1 true), <vscale x 2 x i64> [[TMP12]], <vscale x 2 x i64> [[VEC_PHI]], i32 [[TMP7]])
+; CHECK-NEXT: [[TMP15:%.*]] = zext i32 [[TMP7]] to i64
+; CHECK-NEXT: [[INDEX_EVL_NEXT]] = add nuw i64 [[TMP15]], [[EVL_BASED_IV]]
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP6]]
; CHECK-NEXT: [[TMP13:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
-; CHECK-NEXT: br i1 [[TMP13]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
+; CHECK-NEXT: br i1 [[TMP13]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP7:![0-9]+]]
; CHECK: middle.block:
-; CHECK-NEXT: [[TMP14:%.*]] = call i64 @llvm.vector.reduce.add.nxv2i64(<vscale x 2 x i64> [[TMP12]])
+; CHECK-NEXT: [[TMP14:%.*]] = call i64 @llvm.vector.reduce.add.nxv2i64(<vscale x 2 x i64> [[TMP11]])
; CHECK-NEXT: br label [[FOR_END:%.*]]
; CHECK: scalar.ph:
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ]
@@ -175,7 +187,7 @@ define i64 @indexed_load(ptr noalias nocapture %a, ptr noalias nocapture %b, i64
; CHECK-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; CHECK-NEXT: [[SUM_NEXT]] = add i64 [[SUM]], [[ELEM]]
; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], 1025
-; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP7:![0-9]+]]
+; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
; CHECK: for.end:
; CHECK-NEXT: [[SUM_NEXT_LCSSA:%.*]] = phi i64 [ [[SUM_NEXT]], [[FOR_BODY]] ], [ [[TMP14]], [[MIDDLE_BLOCK]] ]
; CHECK-NEXT: ret i64 [[SUM_NEXT_LCSSA]]
@@ -217,13 +229,17 @@ define void @splat_int(ptr noalias nocapture %a, i64 %v, i64 %n) {
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT: [[ACTIVE_LANE_MASK:%.*]] = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 [[INDEX]], i64 1025)
-; CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds i64, ptr [[A:%.*]], i64 [[INDEX]]
+; CHECK-NEXT: [[EVL_BASED_IV:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_EVL_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT: [[AVL:%.*]] = sub i64 1025, [[EVL_BASED_IV]]
+; CHECK-NEXT: [[TMP7:%.*]] = call i32 @llvm.experimental.get.vector.length.i64(i64 [[AVL]], i32 2, i1 true)
+; CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds i64, ptr [[A:%.*]], i64 [[EVL_BASED_IV]]
; CHECK-NEXT: [[TMP9:%.*]] = getelementptr inbounds i64, ptr [[TMP8]], i32 0
-; CHECK-NEXT: call void @llvm.masked.store.nxv2i64.p0(<vscale x 2 x i64> [[BROADCAST_SPLAT]], ptr [[TMP9]], i32 8, <vscale x 2 x i1> [[ACTIVE_LANE_MASK]])
+; CHECK-NEXT: call void @llvm.vp.store.nxv2i64.p0(<vscale x 2 x i64> [[BROADCAST_SPLAT]], ptr align 8 [[TMP9]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP7]])
+; CHECK-NEXT: [[TMP11:%.*]] = zext i32 [[TMP7]] to i64
+; CHECK-NEXT: [[INDEX_EVL_NEXT]] = add nuw i64 [[TMP11]], [[EVL_BASED_IV]]
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP6]]
; CHECK-NEXT: [[TMP10:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
-; CHECK-NEXT: br i1 [[TMP10]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
+; CHECK-NEXT: br i1 [[TMP10]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP9:![0-9]+]]
; CHECK: middle.block:
; CHECK-NEXT: br label [[FOR_END:%.*]]
; CHECK: scalar.ph:
@@ -235,7 +251,7 @@ define void @splat_int(ptr noalias nocapture %a, i64 %v, i64 %n) {
; CHECK-NEXT: store i64 [[V]], ptr [[ARRAYIDX]], align 8
; CHECK-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], 1025
-; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP9:![0-9]+]]
+; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP10:![0-9]+]]
; CHECK: for.end:
; CHECK-NEXT: ret void
;
@@ -272,14 +288,18 @@ define void @uniform_store(ptr noalias nocapture %a, ptr noalias nocapture %b, i
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT: [[ACTIVE_LANE_MASK:%.*]] = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 [[INDEX]], i64 1025)
+; CHECK-NEXT: [[EVL_BASED_IV:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_EVL_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT: [[AVL:%.*]] = sub i64 1025, [[EVL_BASED_IV]]
+; CHECK-NEXT: [[TMP7:%.*]] = call i32 @llvm.experimental.get.vector.length.i64(i64 [[AVL]], i32 2, i1 true)
; CHECK-NEXT: store i64 [[V]], ptr [[B:%.*]], align 8
-; CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds i64, ptr [[A:%.*]], i64 [[INDEX]]
+; CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds i64, ptr [[A:%.*]], i64 [[EVL_BASED_IV]]
; CHECK-NEXT: [[TMP9:%.*]] = getelementptr inbounds i64, ptr [[TMP8]], i32 0
-; CHECK-NEXT: call void @llvm.masked.store.nxv2i64.p0(<vscale x 2 x i64> [[BROADCAST_SPLAT]], ptr [[TMP9]], i32 8, <vscale x 2 x i1> [[ACTIVE_LANE_MASK]])
+; CHECK-NEXT: call void @llvm.vp.store.nxv2i64.p0(<vscale x 2 x i64> [[BROADCAST_SPLAT]], ptr align 8 [[TMP9]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP7]])
+; CHECK-NEXT: [[TMP11:%.*]] = zext i32 [[TMP7]] to i64
+; CHECK-NEXT: [[INDEX_EVL_NEXT]] = add nuw i64 [[TMP11]], [[EVL_BASED_IV]]
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP6]]
; CHECK-NEXT: [[TMP10:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
-; CHECK-NEXT: br i1 [[TMP10]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP10:![0-9]+]]
+; CHECK-NEXT: br i1 [[TMP10]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP11:![0-9]+]]
; CHECK: middle.block:
; CHECK-NEXT: br label [[FOR_END:%.*]]
; CHECK: scalar.ph:
@@ -292,7 +312,7 @@ define void @uniform_store(ptr noalias nocapture %a, ptr noalias nocapture %b, i
; CHECK-NEXT: store i64 [[V]], ptr [[ARRAYIDX]], align 8
; CHECK-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], 1025
-; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP11:![0-9]+]]
+; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP12:![0-9]+]]
; CHECK: for.end:
; CHECK-NEXT: ret void
;
@@ -363,15 +383,19 @@ define void @vector_add_trip1024(ptr noalias nocapture %a, i64 %v, i64 %n) {
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT: [[ACTIVE_LANE_MASK:%.*]] = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 [[INDEX]], i64 1024)
-; CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds i64, ptr [[A:%.*]], i64 [[INDEX]]
+; CHECK-NEXT: [[EVL_BASED_IV:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_EVL_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT: [[AVL:%.*]] = sub i64 1024, [[EVL_BASED_IV]]
+; CHECK-NEXT: [[TMP7:%.*]] = call i32 @llvm.experimental.get.vector.length.i64(i64 [[AVL]], i32 2, i1 true)
+; CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds i64, ptr [[A:%.*]], i64 [[EVL_BASED_IV]]
; CHECK-NEXT: [[TMP9:%.*]] = getelementptr inbounds i64, ptr [[TMP8]], i32 0
-; CHECK-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 2 x i64> @llvm.masked.load.nxv2i64.p0(ptr [[TMP9]], i32 8, <vscale x 2 x i1> [[ACTIVE_LANE_MASK]], <vscale x 2 x i64> poison)
+; CHECK-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 2 x i64> @llvm.vp.load.nxv2i64.p0(ptr align 8 [[TMP9]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP7]])
; CHECK-NEXT: [[TMP10:%.*]] = add <vscale x 2 x i64> [[WIDE_MASKED_LOAD]], [[BROADCAST_SPLAT]]
-; CHECK-NEXT: call void @llvm.masked.store.nxv2i64.p0(<vscale x 2 x i64> [[TMP10]], ptr [[TMP9]], i32 8, <vscale x 2 x i1> [[ACTIVE_LANE_MASK]])
+; CHECK-NEXT: call void @llvm.vp.store.nxv2i64.p0(<vscale x 2 x i64> [[TMP10]], ptr align 8 [[TMP9]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP7]])
+; CHECK-NEXT: [[TMP12:%.*]] = zext i32 [[TMP7]] to i64
+; CHECK-NEXT: [[INDEX_EVL_NEXT]] = add nuw i64 [[TMP12]], [[EVL_BASED_IV]]
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP6]]
; CHECK-NEXT: [[TMP11:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
-; CHECK-NEXT: br i1 [[TMP11]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP12:![0-9]+]]
+; CHECK-NEXT: br i1 [[TMP11]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP13:![0-9]+]]
; CHECK: middle.block:
; CHECK-NEXT: br label [[FOR_END:%.*]]
; CHECK: scalar.ph:
@@ -385,7 +409,7 @@ define void @vector_add_trip1024(ptr noalias nocapture %a, i64 %v, i64 %n) {
; CHECK-NEXT: store i64 [[ADD]], ptr [[ARRAYIDX]], align 8
; CHECK-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], 1024
-; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP13:![0-9]+]]
+; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP14:![0-9]+]]
; CHECK: for.end:
; CHECK-NEXT: ret void
;
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/tail-folding-cost.ll b/llvm/test/Transforms/LoopVectorize/RISCV/tail-folding-cost.ll
index b4afdd7cf7d54..cd53ea0263649 100644
--- a/llvm/test/Transforms/LoopVectorize/RISCV/tail-folding-cost.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/tail-folding-cost.ll
@@ -1,17 +1,17 @@
; REQUIRES: asserts
-; RUN: opt < %s -passes=loop-vectorize -prefer-predicate-over-epilogue=predicate-else-scalar-epilogue \
-; RUN: -mtriple riscv64-linux-gnu -mattr=+v,+f -S -disable-output -debug-only=loop-vectorize 2>&1 | FileCheck %s
+; RUN: opt < %s -passes=loop-vectorize -prefer-predicate-over-epilogue=predicate-else-scalar-epilogue -force-tail-folding-style=data \
+; RUN: -mtriple riscv64-linux-gnu -mattr=+v,+f -S -disable-output -debug-only=loop-vectorize 2>&1 | FileCheck %s --check-prefix=DATA
; RUN: opt < %s -passes=loop-vectorize -prefer-predicate-over-epilogue=predicate-else-scalar-epilogue \
; RUN: -mtriple riscv64-linux-gnu -force-tail-folding-style=data-with-evl -mattr=+v,+f -S \
; RUN: -disable-output -debug-only=loop-vectorize 2>&1 | FileCheck %s --check-prefix=EVL
-; CHECK: Cost of 2 for VF 2: EMIT{{.*}} = active lane mask
-; CHECK: Cost of 4 for VF 4: EMIT{{.*}} = active lane mask
-; CHECK: Cost of 8 for VF 8: EMIT{{.*}} = active lane mask
-; CHECK: Cost of 2 for VF vscale x 1: EMIT{{.*}} = active lane mask
-; CHECK: Cost of 4 for VF vscale x 2: EMIT{{.*}} = active lane mask
-; CHECK: Cost of 8 for VF vscale x 4: EMIT{{.*}} = active lane mask
+; DATA: Cost of 2 for VF 2: EMIT{{.*}} = active lane mask
+; DATA: Cost of 4 for VF 4: EMIT{{.*}} = active lane mask
+; DATA: Cost of 8 for VF 8: EMIT{{.*}} = active lane mask
+; DATA: Cost of 2 for VF vscale x 1: EMIT{{.*}} = active lane mask
+; DATA: Cost of 4 for VF vscale x 2: EMIT{{.*}} = active lane mask
+; DATA: Cost of 8 for VF vscale x 4: EMIT{{.*}} = active lane mask
; EVL: Cost of 1 for VF vscale x 1: EMIT{{.*}} = EXPLICIT-VECTOR-LENGTH
; EVL: Cost of 1 for VF vscale x 2: EMIT{{.*}} = EXPLICIT-VECTOR-LENGTH
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 528cec077d8a9..b56e7128af4c2 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
@@ -170,15 +170,11 @@ define void @truncate_to_i1_used_by_branch(i8 %x, ptr %dst) #0 {
; CHECK-NEXT: br label %[[VECTOR_BODY:.*]]
; CHECK: [[VECTOR_BODY]]:
; CHECK-NEXT: [[INDEX:%.*]] = phi i32 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
-; CHECK-NEXT: [[BROADCAST_SPLATINSERT3:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[INDEX]], i64 0
-; CHECK-NEXT: [[BROADCAST_SPLAT4:%.*]] = shufflevector <vscale x 4 x i32> [[BROADCAST_SPLATINSERT3]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP13:%.*]] = call <vscale x 4 x i32> @llvm.stepvector.nxv4i32()
-; CHECK-NEXT: [[TMP14:%.*]] = add <vscale x 4 x i32> zeroinitializer, [[TMP13]]
-; CHECK-NEXT: [[VEC_IV:%.*]] = add <vscale x 4 x i32> [[BROADCAST_SPLAT4]], [[TMP14]]
-; CHECK-NEXT: [[TMP15:%.*]] = extractelement <vscale x 4 x i32> [[VEC_IV]], i32 0
-; CHECK-NEXT: [[ACTIVE_LANE_MASK:%.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i32(i32 [[TMP15]], i32 9)
-; CHECK-NEXT: [[TMP11:%.*]] = select <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x i1> splat (i1 true), <vscale x 4 x i1> zeroinitializer
-; CHECK-NEXT: call void @llvm.masked.scatter.nxv4i8.nxv4p0(<vscale x 4 x i8> zeroinitializer, <vscale x 4 x ptr> [[BROADCAST_SPLAT2]], i32 1, <vscale x 4 x i1> [[TMP11]])
+; CHECK-NEXT: [[EVL_BASED_IV:%.*]] = phi i32 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_EVL_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT: [[AVL:%.*]] = sub i32 9, [[EVL_BASED_IV]]
+; CHECK-NEXT: [[TMP6:%.*]] = call i32 @llvm.experimental.get.vector.length.i32(i32 [[AVL]], i32 4, i1 true)
+; CHECK-NEXT: call void @llvm.vp.scatter.nxv4i8.nxv4p0(<vscale x 4 x i8> zeroinitializer, <vscale x 4 x ptr> align 1 [[BROADCAST_SPLAT2]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP6]])
+; CHECK-NEXT: [[INDEX_EVL_NEXT]] = add nuw i32 [[TMP6]], [[EVL_BASED_IV]]
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i32 [[INDEX]], [[TMP5]]
; CHECK-NEXT: [[TMP9:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT: br i1 [[TMP9]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
@@ -199,7 +195,7 @@ define void @truncate_to_i1_used_by_branch(i8 %x, ptr %dst) #0 {
; CHECK-NEXT: [[ADD]] = add i8 [[F_039]], 1
; CHECK-NEXT: [[CONV:%.*]] = sext i8 [[F_039]] to i32
; CHECK-NEXT: [[CMP:%.*]] = icmp slt i32 [[CONV]], 8
-; CHECK-NEXT: br i1 [[CMP]], label %[[LOOP_HEADER]], label %[[EXIT]], !llvm.loop [[LOOP7:![0-9]+]]
+; CHECK-NEXT: br i1 [[CMP]], label %[[LOOP_HEADER]], label %[[EXIT]], !llvm.loop [[LOOP8:![0-9]+]]
; CHECK: [[EXIT]]:
; CHECK-NEXT: ret void
;
@@ -298,7 +294,7 @@ define void @icmp_only_first_op_truncated(ptr noalias %dst, i32 %x, i64 %N, i64
; CHECK-NEXT: call void @llvm.masked.scatter.nxv2f64.nxv2p0(<vscale x 2 x double> [[WIDE_MASKED_GATHER]], <vscale x 2 x ptr> [[BROADCAST_SPLAT6]], i32 8, <vscale x 2 x i1> [[TMP8]])
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP6]]
; CHECK-NEXT: [[TMP11:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
-; CHECK-NEXT: br i1 [[TMP11]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
+; CHECK-NEXT: br i1 [[TMP11]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP9:![0-9]+]]
; CHECK: [[MIDDLE_BLOCK]]:
; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[TMP0]], [[N_VEC]]
; CHECK-NEXT: br i1 [[CMP_N]], label %[[EXIT:.*]], label %[[SCALAR_PH]]
@@ -319,7 +315,7 @@ define void @icmp_only_first_op_truncated(ptr noalias %dst, i32 %x, i64 %N, i64
; CHECK: [[LOOP_LATCH]]:
; CHECK-NEXT: [[IV_NEXT]] = add i64 [[IV]], 1
; CHECK-NEXT: [[EC:%.*]] = icmp eq i64 [[IV]], [[V]]
-; CHECK-NEXT: br i1 [[EC]], label %[[EXIT]], label %[[LOOP_HEADER]], !llvm.loop [[LOOP9:![0-9]+]]
+; CHECK-NEXT: br i1 [[EC]], label %[[EXIT]], label %[[LOOP_HEADER]], !llvm.loop [[LOOP10:![0-9]+]]
; CHECK: [[EXIT]]:
; CHECK-NEXT: ret void
;
@@ -359,8 +355,9 @@ attributes #1 = { "target-features"="+64bit,+v" }
; CHECK: [[LOOP3]] = distinct !{[[LOOP3]], [[META2]], [[META1]]}
; CHECK: [[LOOP4]] = distinct !{[[LOOP4]], [[META1]], [[META2]]}
; CHECK: [[LOOP5]] = distinct !{[[LOOP5]], [[META2]], [[META1]]}
-; CHECK: [[LOOP6]] = distinct !{[[LOOP6]], [[META1]], [[META2]]}
-; CHECK: [[LOOP7]] = distinct !{[[LOOP7]], [[META2]], [[META1]]}
-; CHECK: [[LOOP8]] = distinct !{[[LOOP8]], [[META1]], [[META2]]}
-; CHECK: [[LOOP9]] = distinct !{[[LOOP9]], [[META2]], [[META1]]}
+; CHECK: [[LOOP6]] = distinct !{[[LOOP6]], [[META1]], [[META7:![0-9]+]], [[META2]]}
+; CHECK: [[META7]] = !{!"llvm.loop.isvectorized.tailfoldingstyle", !"evl"}
+; CHECK: [[LOOP8]] = distinct !{[[LOOP8]], [[META2]], [[META1]]}
+; CHECK: [[LOOP9]] = distinct !{[[LOOP9]], [[META1]], [[META2]]}
+; CHECK: [[LOOP10]] = distinct !{[[LOOP10]], [[META2]], [[META1]]}
;.
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/uniform-load-store.ll b/llvm/test/Transforms/LoopVectorize/RISCV/uniform-load-store.ll
index 8baf9d90c795a..c6955f11d8520 100644
--- a/llvm/test/Transforms/LoopVectorize/RISCV/uniform-load-store.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/uniform-load-store.ll
@@ -2,9 +2,6 @@
; RUN: opt < %s -passes=loop-vectorize -scalable-vectorization=on -riscv-v-vector-bits-min=0 -mtriple riscv64-linux-gnu -mattr=+v,+f -S 2>%t | FileCheck %s -check-prefix=SCALABLE
; RUN: opt < %s -passes=loop-vectorize -scalable-vectorization=off -mtriple riscv64-linux-gnu -mattr=+v,+f -S 2>%t | FileCheck %s -check-prefix=FIXEDLEN
; RUN: opt < %s -passes=loop-vectorize -scalable-vectorization=on -riscv-v-vector-bits-min=0 -prefer-predicate-over-epilogue=predicate-dont-vectorize -mtriple riscv64-linux-gnu -mattr=+v,+f -S 2>%t | FileCheck %s -check-prefix=TF-SCALABLE
-; RUN: opt < %s -passes=loop-vectorize -scalable-vectorization=off -prefer-predicate-over-epilogue=predicate-dont-vectorize -mtriple riscv64-linux-gnu -mattr=+v,+f -S 2>%t | FileCheck %s -check-prefix=TF-FIXEDLEN
-
-
target datalayout = "e-m:e-p:64:64-i64:64-i128:128-n64-S128"
target triple = "riscv64"
@@ -103,15 +100,19 @@ define void @uniform_load(ptr noalias nocapture %a, ptr noalias nocapture %b, i6
; TF-SCALABLE-NEXT: [[TMP4:%.*]] = mul nuw i64 [[TMP3]], 2
; TF-SCALABLE-NEXT: br label %[[VECTOR_BODY:.*]]
; TF-SCALABLE: [[VECTOR_BODY]]:
-; TF-SCALABLE-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
-; TF-SCALABLE-NEXT: [[ACTIVE_LANE_MASK:%.*]] = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 [[INDEX]], i64 1025)
+; TF-SCALABLE-NEXT: [[INDEX1:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; TF-SCALABLE-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_EVL_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; TF-SCALABLE-NEXT: [[AVL:%.*]] = sub i64 1025, [[INDEX]]
+; TF-SCALABLE-NEXT: [[TMP6:%.*]] = call i32 @llvm.experimental.get.vector.length.i64(i64 [[AVL]], i32 2, i1 true)
; TF-SCALABLE-NEXT: [[TMP5:%.*]] = load i64, ptr [[B]], align 8
; TF-SCALABLE-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[TMP5]], i64 0
; TF-SCALABLE-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 2 x i64> [[BROADCAST_SPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
; TF-SCALABLE-NEXT: [[TMP7:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[INDEX]]
; TF-SCALABLE-NEXT: [[TMP8:%.*]] = getelementptr inbounds i64, ptr [[TMP7]], i32 0
-; TF-SCALABLE-NEXT: call void @llvm.masked.store.nxv2i64.p0(<vscale x 2 x i64> [[BROADCAST_SPLAT]], ptr [[TMP8]], i32 8, <vscale x 2 x i1> [[ACTIVE_LANE_MASK]])
-; TF-SCALABLE-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP4]]
+; TF-SCALABLE-NEXT: call void @llvm.vp.store.nxv2i64.p0(<vscale x 2 x i64> [[BROADCAST_SPLAT]], ptr align 8 [[TMP8]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP6]])
+; TF-SCALABLE-NEXT: [[TMP10:%.*]] = zext i32 [[TMP6]] to i64
+; TF-SCALABLE-NEXT: [[INDEX_EVL_NEXT]] = add nuw i64 [[TMP10]], [[INDEX]]
+; TF-SCALABLE-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX1]], [[TMP4]]
; TF-SCALABLE-NEXT: [[TMP9:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; TF-SCALABLE-NEXT: br i1 [[TMP9]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; TF-SCALABLE: [[MIDDLE_BLOCK]]:
@@ -126,44 +127,10 @@ define void @uniform_load(ptr noalias nocapture %a, ptr noalias nocapture %b, i6
; TF-SCALABLE-NEXT: store i64 [[V]], ptr [[ARRAYIDX]], align 8
; TF-SCALABLE-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; TF-SCALABLE-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], 1025
-; TF-SCALABLE-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
+; TF-SCALABLE-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
; TF-SCALABLE: [[FOR_END]]:
; TF-SCALABLE-NEXT: ret void
;
-; TF-FIXEDLEN-LABEL: define void @uniform_load(
-; TF-FIXEDLEN-SAME: ptr noalias captures(none) [[A:%.*]], ptr noalias captures(none) [[B:%.*]], i64 [[N:%.*]]) #[[ATTR0:[0-9]+]] {
-; TF-FIXEDLEN-NEXT: [[ENTRY:.*]]:
-; TF-FIXEDLEN-NEXT: br i1 false, label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
-; TF-FIXEDLEN: [[VECTOR_PH]]:
-; TF-FIXEDLEN-NEXT: br label %[[VECTOR_BODY:.*]]
-; TF-FIXEDLEN: [[VECTOR_BODY]]:
-; TF-FIXEDLEN-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
-; TF-FIXEDLEN-NEXT: [[ACTIVE_LANE_MASK:%.*]] = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64 [[INDEX]], i64 1025)
-; TF-FIXEDLEN-NEXT: [[TMP0:%.*]] = load i64, ptr [[B]], align 8
-; TF-FIXEDLEN-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i64> poison, i64 [[TMP0]], i64 0
-; TF-FIXEDLEN-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> poison, <4 x i32> zeroinitializer
-; TF-FIXEDLEN-NEXT: [[TMP1:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[INDEX]]
-; TF-FIXEDLEN-NEXT: [[TMP2:%.*]] = getelementptr inbounds i64, ptr [[TMP1]], i32 0
-; TF-FIXEDLEN-NEXT: call void @llvm.masked.store.v4i64.p0(<4 x i64> [[BROADCAST_SPLAT]], ptr [[TMP2]], i32 8, <4 x i1> [[ACTIVE_LANE_MASK]])
-; TF-FIXEDLEN-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
-; TF-FIXEDLEN-NEXT: [[TMP3:%.*]] = icmp eq i64 [[INDEX_NEXT]], 1028
-; TF-FIXEDLEN-NEXT: br i1 [[TMP3]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
-; TF-FIXEDLEN: [[MIDDLE_BLOCK]]:
-; TF-FIXEDLEN-NEXT: br label %[[FOR_END:.*]]
-; TF-FIXEDLEN: [[SCALAR_PH]]:
-; TF-FIXEDLEN-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ 0, %[[ENTRY]] ]
-; TF-FIXEDLEN-NEXT: br label %[[FOR_BODY:.*]]
-; TF-FIXEDLEN: [[FOR_BODY]]:
-; TF-FIXEDLEN-NEXT: [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], %[[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], %[[FOR_BODY]] ]
-; TF-FIXEDLEN-NEXT: [[V:%.*]] = load i64, ptr [[B]], align 8
-; TF-FIXEDLEN-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[IV]]
-; TF-FIXEDLEN-NEXT: store i64 [[V]], ptr [[ARRAYIDX]], align 8
-; TF-FIXEDLEN-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
-; TF-FIXEDLEN-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], 1025
-; TF-FIXEDLEN-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
-; TF-FIXEDLEN: [[FOR_END]]:
-; TF-FIXEDLEN-NEXT: ret void
-;
entry:
br label %for.body
@@ -277,22 +244,6 @@ define i64 @uniform_load_outside_use(ptr noalias nocapture %a, ptr noalias nocap
; TF-SCALABLE-NEXT: [[V_LCSSA:%.*]] = phi i64 [ [[V]], %[[FOR_BODY]] ]
; TF-SCALABLE-NEXT: ret i64 [[V_LCSSA]]
;
-; TF-FIXEDLEN-LABEL: define i64 @uniform_load_outside_use(
-; TF-FIXEDLEN-SAME: ptr noalias captures(none) [[A:%.*]], ptr noalias captures(none) [[B:%.*]], i64 [[N:%.*]]) #[[ATTR0]] {
-; TF-FIXEDLEN-NEXT: [[ENTRY:.*]]:
-; TF-FIXEDLEN-NEXT: br label %[[FOR_BODY:.*]]
-; TF-FIXEDLEN: [[FOR_BODY]]:
-; TF-FIXEDLEN-NEXT: [[IV:%.*]] = phi i64 [ 0, %[[ENTRY]] ], [ [[IV_NEXT:%.*]], %[[FOR_BODY]] ]
-; TF-FIXEDLEN-NEXT: [[V:%.*]] = load i64, ptr [[B]], align 8
-; TF-FIXEDLEN-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[IV]]
-; TF-FIXEDLEN-NEXT: store i64 [[V]], ptr [[ARRAYIDX]], align 8
-; TF-FIXEDLEN-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
-; TF-FIXEDLEN-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], 1025
-; TF-FIXEDLEN-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END:.*]], label %[[FOR_BODY]]
-; TF-FIXEDLEN: [[FOR_END]]:
-; TF-FIXEDLEN-NEXT: [[V_LCSSA:%.*]] = phi i64 [ [[V]], %[[FOR_BODY]] ]
-; TF-FIXEDLEN-NEXT: ret i64 [[V_LCSSA]]
-;
entry:
br label %for.body
@@ -437,25 +388,31 @@ define void @conditional_uniform_load(ptr noalias nocapture %a, ptr noalias noca
; TF-SCALABLE-NEXT: [[TMP5:%.*]] = call <vscale x 4 x i64> @llvm.stepvector.nxv4i64()
; TF-SCALABLE-NEXT: [[TMP6:%.*]] = mul <vscale x 4 x i64> [[TMP5]], splat (i64 1)
; TF-SCALABLE-NEXT: [[INDUCTION:%.*]] = add <vscale x 4 x i64> zeroinitializer, [[TMP6]]
-; TF-SCALABLE-NEXT: [[TMP8:%.*]] = mul i64 1, [[TMP4]]
-; TF-SCALABLE-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TMP8]], i64 0
-; TF-SCALABLE-NEXT: [[DOTSPLAT:%.*]] = shufflevector <vscale x 4 x i64> [[DOTSPLATINSERT]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
; TF-SCALABLE-NEXT: br label %[[VECTOR_BODY:.*]]
; TF-SCALABLE: [[VECTOR_BODY]]:
-; TF-SCALABLE-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; TF-SCALABLE-NEXT: [[INDEX1:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; TF-SCALABLE-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_EVL_NEXT:%.*]], %[[VECTOR_BODY]] ]
; TF-SCALABLE-NEXT: [[VEC_IND:%.*]] = phi <vscale x 4 x i64> [ [[INDUCTION]], %[[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], %[[VECTOR_BODY]] ]
-; TF-SCALABLE-NEXT: [[ACTIVE_LANE_MASK:%.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX]], i64 1025)
+; TF-SCALABLE-NEXT: [[AVL:%.*]] = sub i64 1025, [[INDEX]]
+; TF-SCALABLE-NEXT: [[TMP7:%.*]] = call i32 @llvm.experimental.get.vector.length.i64(i64 [[AVL]], i32 4, i1 true)
+; TF-SCALABLE-NEXT: [[TMP11:%.*]] = zext i32 [[TMP7]] to i64
+; TF-SCALABLE-NEXT: [[TMP8:%.*]] = mul i64 1, [[TMP11]]
+; TF-SCALABLE-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TMP8]], i64 0
+; TF-SCALABLE-NEXT: [[DOTSPLAT:%.*]] = shufflevector <vscale x 4 x i64> [[DOTSPLATINSERT]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
+; TF-SCALABLE-NEXT: [[ACTIVE_LANE_MASK:%.*]] = icmp ule <vscale x 4 x i64> [[VEC_IND]], splat (i64 1024)
; TF-SCALABLE-NEXT: [[TMP10:%.*]] = icmp ugt <vscale x 4 x i64> [[VEC_IND]], splat (i64 10)
; TF-SCALABLE-NEXT: [[TMP9:%.*]] = select <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x i1> [[TMP10]], <vscale x 4 x i1> zeroinitializer
-; TF-SCALABLE-NEXT: [[WIDE_MASKED_GATHER:%.*]] = call <vscale x 4 x i64> @llvm.masked.gather.nxv4i64.nxv4p0(<vscale x 4 x ptr> [[BROADCAST_SPLAT]], i32 8, <vscale x 4 x i1> [[TMP9]], <vscale x 4 x i64> poison)
+; TF-SCALABLE-NEXT: [[WIDE_MASKED_GATHER:%.*]] = call <vscale x 4 x i64> @llvm.vp.gather.nxv4i64.nxv4p0(<vscale x 4 x ptr> align 8 [[BROADCAST_SPLAT]], <vscale x 4 x i1> [[TMP10]], i32 [[TMP7]])
; TF-SCALABLE-NEXT: [[PREDPHI:%.*]] = select <vscale x 4 x i1> [[TMP9]], <vscale x 4 x i64> [[WIDE_MASKED_GATHER]], <vscale x 4 x i64> zeroinitializer
; TF-SCALABLE-NEXT: [[TMP12:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[INDEX]]
; TF-SCALABLE-NEXT: [[TMP13:%.*]] = getelementptr inbounds i64, ptr [[TMP12]], i32 0
-; TF-SCALABLE-NEXT: call void @llvm.masked.store.nxv4i64.p0(<vscale x 4 x i64> [[PREDPHI]], ptr [[TMP13]], i32 8, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]])
-; TF-SCALABLE-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP4]]
+; TF-SCALABLE-NEXT: call void @llvm.vp.store.nxv4i64.p0(<vscale x 4 x i64> [[PREDPHI]], ptr align 8 [[TMP13]], <vscale x 4 x i1> splat (i1 true), i32 [[TMP7]])
+; TF-SCALABLE-NEXT: [[TMP15:%.*]] = zext i32 [[TMP7]] to i64
+; TF-SCALABLE-NEXT: [[INDEX_EVL_NEXT]] = add nuw i64 [[TMP15]], [[INDEX]]
+; TF-SCALABLE-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX1]], [[TMP4]]
; TF-SCALABLE-NEXT: [[VEC_IND_NEXT]] = add <vscale x 4 x i64> [[VEC_IND]], [[DOTSPLAT]]
; TF-SCALABLE-NEXT: [[TMP14:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
-; TF-SCALABLE-NEXT: br i1 [[TMP14]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
+; TF-SCALABLE-NEXT: br i1 [[TMP14]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
; TF-SCALABLE: [[MIDDLE_BLOCK]]:
; TF-SCALABLE-NEXT: br label %[[FOR_END:.*]]
; TF-SCALABLE: [[SCALAR_PH]]:
@@ -474,55 +431,10 @@ define void @conditional_uniform_load(ptr noalias nocapture %a, ptr noalias noca
; TF-SCALABLE-NEXT: store i64 [[PHI]], ptr [[ARRAYIDX]], align 8
; TF-SCALABLE-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; TF-SCALABLE-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], 1025
-; TF-SCALABLE-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
+; TF-SCALABLE-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
; TF-SCALABLE: [[FOR_END]]:
; TF-SCALABLE-NEXT: ret void
;
-; TF-FIXEDLEN-LABEL: define void @conditional_uniform_load(
-; TF-FIXEDLEN-SAME: ptr noalias captures(none) [[A:%.*]], ptr noalias captures(none) [[B:%.*]], i64 [[N:%.*]]) #[[ATTR0]] {
-; TF-FIXEDLEN-NEXT: [[ENTRY:.*]]:
-; TF-FIXEDLEN-NEXT: br i1 false, label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
-; TF-FIXEDLEN: [[VECTOR_PH]]:
-; TF-FIXEDLEN-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x ptr> poison, ptr [[B]], i64 0
-; TF-FIXEDLEN-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x ptr> [[BROADCAST_SPLATINSERT]], <4 x ptr> poison, <4 x i32> zeroinitializer
-; TF-FIXEDLEN-NEXT: br label %[[VECTOR_BODY:.*]]
-; TF-FIXEDLEN: [[VECTOR_BODY]]:
-; TF-FIXEDLEN-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
-; TF-FIXEDLEN-NEXT: [[VEC_IND:%.*]] = phi <4 x i64> [ <i64 0, i64 1, i64 2, i64 3>, %[[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], %[[VECTOR_BODY]] ]
-; TF-FIXEDLEN-NEXT: [[ACTIVE_LANE_MASK:%.*]] = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64 [[INDEX]], i64 1025)
-; TF-FIXEDLEN-NEXT: [[TMP1:%.*]] = icmp ugt <4 x i64> [[VEC_IND]], splat (i64 10)
-; TF-FIXEDLEN-NEXT: [[TMP2:%.*]] = select <4 x i1> [[ACTIVE_LANE_MASK]], <4 x i1> [[TMP1]], <4 x i1> zeroinitializer
-; TF-FIXEDLEN-NEXT: [[WIDE_MASKED_GATHER:%.*]] = call <4 x i64> @llvm.masked.gather.v4i64.v4p0(<4 x ptr> [[BROADCAST_SPLAT]], i32 8, <4 x i1> [[TMP2]], <4 x i64> poison)
-; TF-FIXEDLEN-NEXT: [[PREDPHI:%.*]] = select <4 x i1> [[TMP2]], <4 x i64> [[WIDE_MASKED_GATHER]], <4 x i64> zeroinitializer
-; TF-FIXEDLEN-NEXT: [[TMP3:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[INDEX]]
-; TF-FIXEDLEN-NEXT: [[TMP4:%.*]] = getelementptr inbounds i64, ptr [[TMP3]], i32 0
-; TF-FIXEDLEN-NEXT: call void @llvm.masked.store.v4i64.p0(<4 x i64> [[PREDPHI]], ptr [[TMP4]], i32 8, <4 x i1> [[ACTIVE_LANE_MASK]])
-; TF-FIXEDLEN-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
-; TF-FIXEDLEN-NEXT: [[VEC_IND_NEXT]] = add <4 x i64> [[VEC_IND]], splat (i64 4)
-; TF-FIXEDLEN-NEXT: [[TMP5:%.*]] = icmp eq i64 [[INDEX_NEXT]], 1028
-; TF-FIXEDLEN-NEXT: br i1 [[TMP5]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
-; TF-FIXEDLEN: [[MIDDLE_BLOCK]]:
-; TF-FIXEDLEN-NEXT: br label %[[FOR_END:.*]]
-; TF-FIXEDLEN: [[SCALAR_PH]]:
-; TF-FIXEDLEN-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ 0, %[[ENTRY]] ]
-; TF-FIXEDLEN-NEXT: br label %[[FOR_BODY:.*]]
-; TF-FIXEDLEN: [[FOR_BODY]]:
-; TF-FIXEDLEN-NEXT: [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], %[[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], %[[LATCH:.*]] ]
-; TF-FIXEDLEN-NEXT: [[CMP:%.*]] = icmp ugt i64 [[IV]], 10
-; TF-FIXEDLEN-NEXT: br i1 [[CMP]], label %[[DO_LOAD:.*]], label %[[LATCH]]
-; TF-FIXEDLEN: [[DO_LOAD]]:
-; TF-FIXEDLEN-NEXT: [[V:%.*]] = load i64, ptr [[B]], align 8
-; TF-FIXEDLEN-NEXT: br label %[[LATCH]]
-; TF-FIXEDLEN: [[LATCH]]:
-; TF-FIXEDLEN-NEXT: [[PHI:%.*]] = phi i64 [ 0, %[[FOR_BODY]] ], [ [[V]], %[[DO_LOAD]] ]
-; TF-FIXEDLEN-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[IV]]
-; TF-FIXEDLEN-NEXT: store i64 [[PHI]], ptr [[ARRAYIDX]], align 8
-; TF-FIXEDLEN-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
-; TF-FIXEDLEN-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], 1025
-; TF-FIXEDLEN-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
-; TF-FIXEDLEN: [[FOR_END]]:
-; TF-FIXEDLEN-NEXT: ret void
-;
entry:
br label %for.body
@@ -640,17 +552,21 @@ define void @uniform_load_unaligned(ptr noalias nocapture %a, ptr noalias nocapt
; TF-SCALABLE-NEXT: [[TMP4:%.*]] = mul nuw i64 [[TMP3]], 2
; TF-SCALABLE-NEXT: br label %[[VECTOR_BODY:.*]]
; TF-SCALABLE: [[VECTOR_BODY]]:
-; TF-SCALABLE-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
-; TF-SCALABLE-NEXT: [[ACTIVE_LANE_MASK:%.*]] = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 [[INDEX]], i64 1025)
+; TF-SCALABLE-NEXT: [[INDEX1:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; TF-SCALABLE-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_EVL_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; TF-SCALABLE-NEXT: [[AVL:%.*]] = sub i64 1025, [[INDEX]]
+; TF-SCALABLE-NEXT: [[TMP6:%.*]] = call i32 @llvm.experimental.get.vector.length.i64(i64 [[AVL]], i32 2, i1 true)
; TF-SCALABLE-NEXT: [[TMP5:%.*]] = load i64, ptr [[B]], align 1
; TF-SCALABLE-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[TMP5]], i64 0
; TF-SCALABLE-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 2 x i64> [[BROADCAST_SPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
; TF-SCALABLE-NEXT: [[TMP7:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[INDEX]]
; TF-SCALABLE-NEXT: [[TMP8:%.*]] = getelementptr inbounds i64, ptr [[TMP7]], i32 0
-; TF-SCALABLE-NEXT: call void @llvm.masked.store.nxv2i64.p0(<vscale x 2 x i64> [[BROADCAST_SPLAT]], ptr [[TMP8]], i32 8, <vscale x 2 x i1> [[ACTIVE_LANE_MASK]])
-; TF-SCALABLE-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP4]]
+; TF-SCALABLE-NEXT: call void @llvm.vp.store.nxv2i64.p0(<vscale x 2 x i64> [[BROADCAST_SPLAT]], ptr align 8 [[TMP8]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP6]])
+; TF-SCALABLE-NEXT: [[TMP10:%.*]] = zext i32 [[TMP6]] to i64
+; TF-SCALABLE-NEXT: [[INDEX_EVL_NEXT]] = add nuw i64 [[TMP10]], [[INDEX]]
+; TF-SCALABLE-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX1]], [[TMP4]]
; TF-SCALABLE-NEXT: [[TMP9:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
-; TF-SCALABLE-NEXT: br i1 [[TMP9]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
+; TF-SCALABLE-NEXT: br i1 [[TMP9]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP7:![0-9]+]]
; TF-SCALABLE: [[MIDDLE_BLOCK]]:
; TF-SCALABLE-NEXT: br label %[[FOR_END:.*]]
; TF-SCALABLE: [[SCALAR_PH]]:
@@ -663,44 +579,10 @@ define void @uniform_load_unaligned(ptr noalias nocapture %a, ptr noalias nocapt
; TF-SCALABLE-NEXT: store i64 [[V]], ptr [[ARRAYIDX]], align 8
; TF-SCALABLE-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; TF-SCALABLE-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], 1025
-; TF-SCALABLE-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP7:![0-9]+]]
+; TF-SCALABLE-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
; TF-SCALABLE: [[FOR_END]]:
; TF-SCALABLE-NEXT: ret void
;
-; TF-FIXEDLEN-LABEL: define void @uniform_load_unaligned(
-; TF-FIXEDLEN-SAME: ptr noalias captures(none) [[A:%.*]], ptr noalias captures(none) [[B:%.*]], i64 [[N:%.*]]) #[[ATTR0]] {
-; TF-FIXEDLEN-NEXT: [[ENTRY:.*]]:
-; TF-FIXEDLEN-NEXT: br i1 false, label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
-; TF-FIXEDLEN: [[VECTOR_PH]]:
-; TF-FIXEDLEN-NEXT: br label %[[VECTOR_BODY:.*]]
-; TF-FIXEDLEN: [[VECTOR_BODY]]:
-; TF-FIXEDLEN-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
-; TF-FIXEDLEN-NEXT: [[ACTIVE_LANE_MASK:%.*]] = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64 [[INDEX]], i64 1025)
-; TF-FIXEDLEN-NEXT: [[TMP0:%.*]] = load i64, ptr [[B]], align 1
-; TF-FIXEDLEN-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i64> poison, i64 [[TMP0]], i64 0
-; TF-FIXEDLEN-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> poison, <4 x i32> zeroinitializer
-; TF-FIXEDLEN-NEXT: [[TMP1:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[INDEX]]
-; TF-FIXEDLEN-NEXT: [[TMP2:%.*]] = getelementptr inbounds i64, ptr [[TMP1]], i32 0
-; TF-FIXEDLEN-NEXT: call void @llvm.masked.store.v4i64.p0(<4 x i64> [[BROADCAST_SPLAT]], ptr [[TMP2]], i32 8, <4 x i1> [[ACTIVE_LANE_MASK]])
-; TF-FIXEDLEN-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
-; TF-FIXEDLEN-NEXT: [[TMP3:%.*]] = icmp eq i64 [[INDEX_NEXT]], 1028
-; TF-FIXEDLEN-NEXT: br i1 [[TMP3]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
-; TF-FIXEDLEN: [[MIDDLE_BLOCK]]:
-; TF-FIXEDLEN-NEXT: br label %[[FOR_END:.*]]
-; TF-FIXEDLEN: [[SCALAR_PH]]:
-; TF-FIXEDLEN-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ 0, %[[ENTRY]] ]
-; TF-FIXEDLEN-NEXT: br label %[[FOR_BODY:.*]]
-; TF-FIXEDLEN: [[FOR_BODY]]:
-; TF-FIXEDLEN-NEXT: [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], %[[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], %[[FOR_BODY]] ]
-; TF-FIXEDLEN-NEXT: [[V:%.*]] = load i64, ptr [[B]], align 1
-; TF-FIXEDLEN-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[IV]]
-; TF-FIXEDLEN-NEXT: store i64 [[V]], ptr [[ARRAYIDX]], align 8
-; TF-FIXEDLEN-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
-; TF-FIXEDLEN-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], 1025
-; TF-FIXEDLEN-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP7:![0-9]+]]
-; TF-FIXEDLEN: [[FOR_END]]:
-; TF-FIXEDLEN-NEXT: ret void
-;
entry:
br label %for.body
@@ -813,15 +695,19 @@ define void @uniform_store(ptr noalias nocapture %a, ptr noalias nocapture %b, i
; TF-SCALABLE-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 2 x i64> [[BROADCAST_SPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
; TF-SCALABLE-NEXT: br label %[[VECTOR_BODY:.*]]
; TF-SCALABLE: [[VECTOR_BODY]]:
-; TF-SCALABLE-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
-; TF-SCALABLE-NEXT: [[ACTIVE_LANE_MASK:%.*]] = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 [[INDEX]], i64 1025)
+; TF-SCALABLE-NEXT: [[INDEX1:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; TF-SCALABLE-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_EVL_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; TF-SCALABLE-NEXT: [[AVL:%.*]] = sub i64 1025, [[INDEX]]
+; TF-SCALABLE-NEXT: [[TMP5:%.*]] = call i32 @llvm.experimental.get.vector.length.i64(i64 [[AVL]], i32 2, i1 true)
; TF-SCALABLE-NEXT: store i64 [[V]], ptr [[B]], align 8
; TF-SCALABLE-NEXT: [[TMP6:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[INDEX]]
; TF-SCALABLE-NEXT: [[TMP7:%.*]] = getelementptr inbounds i64, ptr [[TMP6]], i32 0
-; TF-SCALABLE-NEXT: call void @llvm.masked.store.nxv2i64.p0(<vscale x 2 x i64> [[BROADCAST_SPLAT]], ptr [[TMP7]], i32 8, <vscale x 2 x i1> [[ACTIVE_LANE_MASK]])
-; TF-SCALABLE-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP4]]
+; TF-SCALABLE-NEXT: call void @llvm.vp.store.nxv2i64.p0(<vscale x 2 x i64> [[BROADCAST_SPLAT]], ptr align 8 [[TMP7]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP5]])
+; TF-SCALABLE-NEXT: [[TMP9:%.*]] = zext i32 [[TMP5]] to i64
+; TF-SCALABLE-NEXT: [[INDEX_EVL_NEXT]] = add nuw i64 [[TMP9]], [[INDEX]]
+; TF-SCALABLE-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX1]], [[TMP4]]
; TF-SCALABLE-NEXT: [[TMP8:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
-; TF-SCALABLE-NEXT: br i1 [[TMP8]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
+; TF-SCALABLE-NEXT: br i1 [[TMP8]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP9:![0-9]+]]
; TF-SCALABLE: [[MIDDLE_BLOCK]]:
; TF-SCALABLE-NEXT: br label %[[FOR_END:.*]]
; TF-SCALABLE: [[SCALAR_PH]]:
@@ -834,44 +720,10 @@ define void @uniform_store(ptr noalias nocapture %a, ptr noalias nocapture %b, i
; TF-SCALABLE-NEXT: store i64 [[V]], ptr [[ARRAYIDX]], align 8
; TF-SCALABLE-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; TF-SCALABLE-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], 1025
-; TF-SCALABLE-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP9:![0-9]+]]
+; TF-SCALABLE-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP10:![0-9]+]]
; TF-SCALABLE: [[FOR_END]]:
; TF-SCALABLE-NEXT: ret void
;
-; TF-FIXEDLEN-LABEL: define void @uniform_store(
-; TF-FIXEDLEN-SAME: ptr noalias captures(none) [[A:%.*]], ptr noalias captures(none) [[B:%.*]], i64 [[V:%.*]], i64 [[N:%.*]]) #[[ATTR0]] {
-; TF-FIXEDLEN-NEXT: [[ENTRY:.*]]:
-; TF-FIXEDLEN-NEXT: br i1 false, label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
-; TF-FIXEDLEN: [[VECTOR_PH]]:
-; TF-FIXEDLEN-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i64> poison, i64 [[V]], i64 0
-; TF-FIXEDLEN-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> poison, <4 x i32> zeroinitializer
-; TF-FIXEDLEN-NEXT: br label %[[VECTOR_BODY:.*]]
-; TF-FIXEDLEN: [[VECTOR_BODY]]:
-; TF-FIXEDLEN-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
-; TF-FIXEDLEN-NEXT: [[ACTIVE_LANE_MASK:%.*]] = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64 [[INDEX]], i64 1025)
-; TF-FIXEDLEN-NEXT: store i64 [[V]], ptr [[B]], align 8
-; TF-FIXEDLEN-NEXT: [[TMP1:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[INDEX]]
-; TF-FIXEDLEN-NEXT: [[TMP2:%.*]] = getelementptr inbounds i64, ptr [[TMP1]], i32 0
-; TF-FIXEDLEN-NEXT: call void @llvm.masked.store.v4i64.p0(<4 x i64> [[BROADCAST_SPLAT]], ptr [[TMP2]], i32 8, <4 x i1> [[ACTIVE_LANE_MASK]])
-; TF-FIXEDLEN-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
-; TF-FIXEDLEN-NEXT: [[TMP3:%.*]] = icmp eq i64 [[INDEX_NEXT]], 1028
-; TF-FIXEDLEN-NEXT: br i1 [[TMP3]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
-; TF-FIXEDLEN: [[MIDDLE_BLOCK]]:
-; TF-FIXEDLEN-NEXT: br label %[[FOR_END:.*]]
-; TF-FIXEDLEN: [[SCALAR_PH]]:
-; TF-FIXEDLEN-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ 0, %[[ENTRY]] ]
-; TF-FIXEDLEN-NEXT: br label %[[FOR_BODY:.*]]
-; TF-FIXEDLEN: [[FOR_BODY]]:
-; TF-FIXEDLEN-NEXT: [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], %[[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], %[[FOR_BODY]] ]
-; TF-FIXEDLEN-NEXT: store i64 [[V]], ptr [[B]], align 8
-; TF-FIXEDLEN-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[IV]]
-; TF-FIXEDLEN-NEXT: store i64 [[V]], ptr [[ARRAYIDX]], align 8
-; TF-FIXEDLEN-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
-; TF-FIXEDLEN-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], 1025
-; TF-FIXEDLEN-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP9:![0-9]+]]
-; TF-FIXEDLEN: [[FOR_END]]:
-; TF-FIXEDLEN-NEXT: ret void
-;
entry:
br label %for.body
@@ -1003,22 +855,27 @@ define void @uniform_store_of_loop_varying(ptr noalias nocapture %a, ptr noalias
; TF-SCALABLE-NEXT: [[TMP5:%.*]] = call <vscale x 2 x i64> @llvm.stepvector.nxv2i64()
; TF-SCALABLE-NEXT: [[TMP7:%.*]] = mul <vscale x 2 x i64> [[TMP5]], splat (i64 1)
; TF-SCALABLE-NEXT: [[INDUCTION:%.*]] = add <vscale x 2 x i64> zeroinitializer, [[TMP7]]
-; TF-SCALABLE-NEXT: [[TMP8:%.*]] = mul i64 1, [[TMP4]]
-; TF-SCALABLE-NEXT: [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[TMP8]], i64 0
-; TF-SCALABLE-NEXT: [[BROADCAST_SPLAT2:%.*]] = shufflevector <vscale x 2 x i64> [[BROADCAST_SPLATINSERT1]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
; TF-SCALABLE-NEXT: br label %[[VECTOR_BODY:.*]]
; TF-SCALABLE: [[VECTOR_BODY]]:
-; TF-SCALABLE-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; TF-SCALABLE-NEXT: [[INDEX1:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; TF-SCALABLE-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_EVL_NEXT:%.*]], %[[VECTOR_BODY]] ]
; TF-SCALABLE-NEXT: [[VEC_IND:%.*]] = phi <vscale x 2 x i64> [ [[INDUCTION]], %[[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], %[[VECTOR_BODY]] ]
-; TF-SCALABLE-NEXT: [[ACTIVE_LANE_MASK:%.*]] = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 [[INDEX]], i64 1025)
-; TF-SCALABLE-NEXT: call void @llvm.masked.scatter.nxv2i64.nxv2p0(<vscale x 2 x i64> [[VEC_IND]], <vscale x 2 x ptr> [[BROADCAST_SPLAT]], i32 8, <vscale x 2 x i1> [[ACTIVE_LANE_MASK]])
+; TF-SCALABLE-NEXT: [[AVL:%.*]] = sub i64 1025, [[INDEX]]
+; TF-SCALABLE-NEXT: [[TMP9:%.*]] = call i32 @llvm.experimental.get.vector.length.i64(i64 [[AVL]], i32 2, i1 true)
+; TF-SCALABLE-NEXT: [[TMP13:%.*]] = zext i32 [[TMP9]] to i64
+; TF-SCALABLE-NEXT: [[TMP8:%.*]] = mul i64 1, [[TMP13]]
+; TF-SCALABLE-NEXT: [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[TMP8]], i64 0
+; TF-SCALABLE-NEXT: [[BROADCAST_SPLAT2:%.*]] = shufflevector <vscale x 2 x i64> [[BROADCAST_SPLATINSERT1]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
+; TF-SCALABLE-NEXT: call void @llvm.vp.scatter.nxv2i64.nxv2p0(<vscale x 2 x i64> [[VEC_IND]], <vscale x 2 x ptr> align 8 [[BROADCAST_SPLAT]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP9]])
; TF-SCALABLE-NEXT: [[TMP10:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[INDEX]]
; TF-SCALABLE-NEXT: [[TMP11:%.*]] = getelementptr inbounds i64, ptr [[TMP10]], i32 0
-; TF-SCALABLE-NEXT: call void @llvm.masked.store.nxv2i64.p0(<vscale x 2 x i64> [[BROADCAST_SPLAT3]], ptr [[TMP11]], i32 8, <vscale x 2 x i1> [[ACTIVE_LANE_MASK]])
-; TF-SCALABLE-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP4]]
+; TF-SCALABLE-NEXT: call void @llvm.vp.store.nxv2i64.p0(<vscale x 2 x i64> [[BROADCAST_SPLAT3]], ptr align 8 [[TMP11]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP9]])
+; TF-SCALABLE-NEXT: [[TMP14:%.*]] = zext i32 [[TMP9]] to i64
+; TF-SCALABLE-NEXT: [[INDEX_EVL_NEXT]] = add nuw i64 [[TMP14]], [[INDEX]]
+; TF-SCALABLE-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX1]], [[TMP4]]
; TF-SCALABLE-NEXT: [[VEC_IND_NEXT]] = add <vscale x 2 x i64> [[VEC_IND]], [[BROADCAST_SPLAT2]]
; TF-SCALABLE-NEXT: [[TMP12:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
-; TF-SCALABLE-NEXT: br i1 [[TMP12]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP10:![0-9]+]]
+; TF-SCALABLE-NEXT: br i1 [[TMP12]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP11:![0-9]+]]
; TF-SCALABLE: [[MIDDLE_BLOCK]]:
; TF-SCALABLE-NEXT: br label %[[FOR_END:.*]]
; TF-SCALABLE: [[SCALAR_PH]]:
@@ -1031,71 +888,10 @@ define void @uniform_store_of_loop_varying(ptr noalias nocapture %a, ptr noalias
; TF-SCALABLE-NEXT: store i64 [[V]], ptr [[ARRAYIDX]], align 8
; TF-SCALABLE-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; TF-SCALABLE-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], 1025
-; TF-SCALABLE-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP11:![0-9]+]]
+; TF-SCALABLE-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP12:![0-9]+]]
; TF-SCALABLE: [[FOR_END]]:
; TF-SCALABLE-NEXT: ret void
;
-; TF-FIXEDLEN-LABEL: define void @uniform_store_of_loop_varying(
-; TF-FIXEDLEN-SAME: ptr noalias captures(none) [[A:%.*]], ptr noalias captures(none) [[B:%.*]], i64 [[V:%.*]], i64 [[N:%.*]]) #[[ATTR0]] {
-; TF-FIXEDLEN-NEXT: [[ENTRY:.*]]:
-; TF-FIXEDLEN-NEXT: br i1 false, label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
-; TF-FIXEDLEN: [[VECTOR_PH]]:
-; TF-FIXEDLEN-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i64> poison, i64 [[V]], i64 0
-; TF-FIXEDLEN-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> poison, <4 x i32> zeroinitializer
-; TF-FIXEDLEN-NEXT: br label %[[VECTOR_BODY:.*]]
-; TF-FIXEDLEN: [[VECTOR_BODY]]:
-; TF-FIXEDLEN-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[PRED_STORE_CONTINUE6:.*]] ]
-; TF-FIXEDLEN-NEXT: [[ACTIVE_LANE_MASK:%.*]] = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64 [[INDEX]], i64 1025)
-; TF-FIXEDLEN-NEXT: [[TMP0:%.*]] = extractelement <4 x i1> [[ACTIVE_LANE_MASK]], i32 0
-; TF-FIXEDLEN-NEXT: br i1 [[TMP0]], label %[[PRED_STORE_IF:.*]], label %[[PRED_STORE_CONTINUE:.*]]
-; TF-FIXEDLEN: [[PRED_STORE_IF]]:
-; TF-FIXEDLEN-NEXT: [[TMP1:%.*]] = add i64 [[INDEX]], 0
-; TF-FIXEDLEN-NEXT: store i64 [[TMP1]], ptr [[B]], align 8
-; TF-FIXEDLEN-NEXT: br label %[[PRED_STORE_CONTINUE]]
-; TF-FIXEDLEN: [[PRED_STORE_CONTINUE]]:
-; TF-FIXEDLEN-NEXT: [[TMP2:%.*]] = extractelement <4 x i1> [[ACTIVE_LANE_MASK]], i32 1
-; TF-FIXEDLEN-NEXT: br i1 [[TMP2]], label %[[PRED_STORE_IF1:.*]], label %[[PRED_STORE_CONTINUE2:.*]]
-; TF-FIXEDLEN: [[PRED_STORE_IF1]]:
-; TF-FIXEDLEN-NEXT: [[TMP3:%.*]] = add i64 [[INDEX]], 1
-; TF-FIXEDLEN-NEXT: store i64 [[TMP3]], ptr [[B]], align 8
-; TF-FIXEDLEN-NEXT: br label %[[PRED_STORE_CONTINUE2]]
-; TF-FIXEDLEN: [[PRED_STORE_CONTINUE2]]:
-; TF-FIXEDLEN-NEXT: [[TMP4:%.*]] = extractelement <4 x i1> [[ACTIVE_LANE_MASK]], i32 2
-; TF-FIXEDLEN-NEXT: br i1 [[TMP4]], label %[[PRED_STORE_IF3:.*]], label %[[PRED_STORE_CONTINUE4:.*]]
-; TF-FIXEDLEN: [[PRED_STORE_IF3]]:
-; TF-FIXEDLEN-NEXT: [[TMP5:%.*]] = add i64 [[INDEX]], 2
-; TF-FIXEDLEN-NEXT: store i64 [[TMP5]], ptr [[B]], align 8
-; TF-FIXEDLEN-NEXT: br label %[[PRED_STORE_CONTINUE4]]
-; TF-FIXEDLEN: [[PRED_STORE_CONTINUE4]]:
-; TF-FIXEDLEN-NEXT: [[TMP6:%.*]] = extractelement <4 x i1> [[ACTIVE_LANE_MASK]], i32 3
-; TF-FIXEDLEN-NEXT: br i1 [[TMP6]], label %[[PRED_STORE_IF5:.*]], label %[[PRED_STORE_CONTINUE6]]
-; TF-FIXEDLEN: [[PRED_STORE_IF5]]:
-; TF-FIXEDLEN-NEXT: [[TMP7:%.*]] = add i64 [[INDEX]], 3
-; TF-FIXEDLEN-NEXT: store i64 [[TMP7]], ptr [[B]], align 8
-; TF-FIXEDLEN-NEXT: br label %[[PRED_STORE_CONTINUE6]]
-; TF-FIXEDLEN: [[PRED_STORE_CONTINUE6]]:
-; TF-FIXEDLEN-NEXT: [[TMP8:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[INDEX]]
-; TF-FIXEDLEN-NEXT: [[TMP9:%.*]] = getelementptr inbounds i64, ptr [[TMP8]], i32 0
-; TF-FIXEDLEN-NEXT: call void @llvm.masked.store.v4i64.p0(<4 x i64> [[BROADCAST_SPLAT]], ptr [[TMP9]], i32 8, <4 x i1> [[ACTIVE_LANE_MASK]])
-; TF-FIXEDLEN-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
-; TF-FIXEDLEN-NEXT: [[TMP10:%.*]] = icmp eq i64 [[INDEX_NEXT]], 1028
-; TF-FIXEDLEN-NEXT: br i1 [[TMP10]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP10:![0-9]+]]
-; TF-FIXEDLEN: [[MIDDLE_BLOCK]]:
-; TF-FIXEDLEN-NEXT: br label %[[FOR_END:.*]]
-; TF-FIXEDLEN: [[SCALAR_PH]]:
-; TF-FIXEDLEN-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ 0, %[[ENTRY]] ]
-; TF-FIXEDLEN-NEXT: br label %[[FOR_BODY:.*]]
-; TF-FIXEDLEN: [[FOR_BODY]]:
-; TF-FIXEDLEN-NEXT: [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], %[[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], %[[FOR_BODY]] ]
-; TF-FIXEDLEN-NEXT: store i64 [[IV]], ptr [[B]], align 8
-; TF-FIXEDLEN-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[IV]]
-; TF-FIXEDLEN-NEXT: store i64 [[V]], ptr [[ARRAYIDX]], align 8
-; TF-FIXEDLEN-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
-; TF-FIXEDLEN-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], 1025
-; TF-FIXEDLEN-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP11:![0-9]+]]
-; TF-FIXEDLEN: [[FOR_END]]:
-; TF-FIXEDLEN-NEXT: ret void
-;
entry:
br label %for.body
@@ -1240,24 +1036,28 @@ define void @conditional_uniform_store(ptr noalias nocapture %a, ptr noalias noc
; TF-SCALABLE-NEXT: [[TMP5:%.*]] = call <vscale x 2 x i64> @llvm.stepvector.nxv2i64()
; TF-SCALABLE-NEXT: [[TMP7:%.*]] = mul <vscale x 2 x i64> [[TMP5]], splat (i64 1)
; TF-SCALABLE-NEXT: [[INDUCTION:%.*]] = add <vscale x 2 x i64> zeroinitializer, [[TMP7]]
-; TF-SCALABLE-NEXT: [[TMP8:%.*]] = mul i64 1, [[TMP4]]
-; TF-SCALABLE-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[TMP8]], i64 0
-; TF-SCALABLE-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 2 x i64> [[BROADCAST_SPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
; TF-SCALABLE-NEXT: br label %[[VECTOR_BODY:.*]]
; TF-SCALABLE: [[VECTOR_BODY]]:
-; TF-SCALABLE-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; TF-SCALABLE-NEXT: [[INDEX1:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; TF-SCALABLE-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_EVL_NEXT:%.*]], %[[VECTOR_BODY]] ]
; TF-SCALABLE-NEXT: [[VEC_IND:%.*]] = phi <vscale x 2 x i64> [ [[INDUCTION]], %[[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], %[[VECTOR_BODY]] ]
-; TF-SCALABLE-NEXT: [[ACTIVE_LANE_MASK:%.*]] = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 [[INDEX]], i64 1025)
+; TF-SCALABLE-NEXT: [[AVL:%.*]] = sub i64 1025, [[INDEX]]
+; TF-SCALABLE-NEXT: [[TMP9:%.*]] = call i32 @llvm.experimental.get.vector.length.i64(i64 [[AVL]], i32 2, i1 true)
+; TF-SCALABLE-NEXT: [[TMP11:%.*]] = zext i32 [[TMP9]] to i64
+; TF-SCALABLE-NEXT: [[TMP8:%.*]] = mul i64 1, [[TMP11]]
+; TF-SCALABLE-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[TMP8]], i64 0
+; TF-SCALABLE-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 2 x i64> [[BROADCAST_SPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
; TF-SCALABLE-NEXT: [[TMP10:%.*]] = icmp ugt <vscale x 2 x i64> [[VEC_IND]], splat (i64 10)
-; TF-SCALABLE-NEXT: [[TMP9:%.*]] = select <vscale x 2 x i1> [[ACTIVE_LANE_MASK]], <vscale x 2 x i1> [[TMP10]], <vscale x 2 x i1> zeroinitializer
-; TF-SCALABLE-NEXT: call void @llvm.masked.scatter.nxv2i64.nxv2p0(<vscale x 2 x i64> [[BROADCAST_SPLAT1]], <vscale x 2 x ptr> [[BROADCAST_SPLAT2]], i32 8, <vscale x 2 x i1> [[TMP9]])
+; TF-SCALABLE-NEXT: call void @llvm.vp.scatter.nxv2i64.nxv2p0(<vscale x 2 x i64> [[BROADCAST_SPLAT1]], <vscale x 2 x ptr> align 8 [[BROADCAST_SPLAT2]], <vscale x 2 x i1> [[TMP10]], i32 [[TMP9]])
; TF-SCALABLE-NEXT: [[TMP12:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[INDEX]]
; TF-SCALABLE-NEXT: [[TMP13:%.*]] = getelementptr inbounds i64, ptr [[TMP12]], i32 0
-; TF-SCALABLE-NEXT: call void @llvm.masked.store.nxv2i64.p0(<vscale x 2 x i64> [[BROADCAST_SPLAT1]], ptr [[TMP13]], i32 8, <vscale x 2 x i1> [[ACTIVE_LANE_MASK]])
-; TF-SCALABLE-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP4]]
+; TF-SCALABLE-NEXT: call void @llvm.vp.store.nxv2i64.p0(<vscale x 2 x i64> [[BROADCAST_SPLAT1]], ptr align 8 [[TMP13]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP9]])
+; TF-SCALABLE-NEXT: [[TMP15:%.*]] = zext i32 [[TMP9]] to i64
+; TF-SCALABLE-NEXT: [[INDEX_EVL_NEXT]] = add nuw i64 [[TMP15]], [[INDEX]]
+; TF-SCALABLE-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX1]], [[TMP4]]
; TF-SCALABLE-NEXT: [[VEC_IND_NEXT]] = add <vscale x 2 x i64> [[VEC_IND]], [[BROADCAST_SPLAT]]
; TF-SCALABLE-NEXT: [[TMP14:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
-; TF-SCALABLE-NEXT: br i1 [[TMP14]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP12:![0-9]+]]
+; TF-SCALABLE-NEXT: br i1 [[TMP14]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP13:![0-9]+]]
; TF-SCALABLE: [[MIDDLE_BLOCK]]:
; TF-SCALABLE-NEXT: br label %[[FOR_END:.*]]
; TF-SCALABLE: [[SCALAR_PH]]:
@@ -1275,55 +1075,10 @@ define void @conditional_uniform_store(ptr noalias nocapture %a, ptr noalias noc
; TF-SCALABLE-NEXT: store i64 [[V]], ptr [[ARRAYIDX]], align 8
; TF-SCALABLE-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; TF-SCALABLE-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], 1025
-; TF-SCALABLE-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP13:![0-9]+]]
+; TF-SCALABLE-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP14:![0-9]+]]
; TF-SCALABLE: [[FOR_END]]:
; TF-SCALABLE-NEXT: ret void
;
-; TF-FIXEDLEN-LABEL: define void @conditional_uniform_store(
-; TF-FIXEDLEN-SAME: ptr noalias captures(none) [[A:%.*]], ptr noalias captures(none) [[B:%.*]], i64 [[V:%.*]], i64 [[N:%.*]]) #[[ATTR0]] {
-; TF-FIXEDLEN-NEXT: [[ENTRY:.*]]:
-; TF-FIXEDLEN-NEXT: br i1 false, label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
-; TF-FIXEDLEN: [[VECTOR_PH]]:
-; TF-FIXEDLEN-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i64> poison, i64 [[V]], i64 0
-; TF-FIXEDLEN-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> poison, <4 x i32> zeroinitializer
-; TF-FIXEDLEN-NEXT: [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <4 x ptr> poison, ptr [[B]], i64 0
-; TF-FIXEDLEN-NEXT: [[BROADCAST_SPLAT2:%.*]] = shufflevector <4 x ptr> [[BROADCAST_SPLATINSERT1]], <4 x ptr> poison, <4 x i32> zeroinitializer
-; TF-FIXEDLEN-NEXT: br label %[[VECTOR_BODY:.*]]
-; TF-FIXEDLEN: [[VECTOR_BODY]]:
-; TF-FIXEDLEN-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
-; TF-FIXEDLEN-NEXT: [[VEC_IND:%.*]] = phi <4 x i64> [ <i64 0, i64 1, i64 2, i64 3>, %[[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], %[[VECTOR_BODY]] ]
-; TF-FIXEDLEN-NEXT: [[ACTIVE_LANE_MASK:%.*]] = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64 [[INDEX]], i64 1025)
-; TF-FIXEDLEN-NEXT: [[TMP0:%.*]] = icmp ugt <4 x i64> [[VEC_IND]], splat (i64 10)
-; TF-FIXEDLEN-NEXT: [[TMP1:%.*]] = select <4 x i1> [[ACTIVE_LANE_MASK]], <4 x i1> [[TMP0]], <4 x i1> zeroinitializer
-; TF-FIXEDLEN-NEXT: call void @llvm.masked.scatter.v4i64.v4p0(<4 x i64> [[BROADCAST_SPLAT]], <4 x ptr> [[BROADCAST_SPLAT2]], i32 8, <4 x i1> [[TMP1]])
-; TF-FIXEDLEN-NEXT: [[TMP3:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[INDEX]]
-; TF-FIXEDLEN-NEXT: [[TMP4:%.*]] = getelementptr inbounds i64, ptr [[TMP3]], i32 0
-; TF-FIXEDLEN-NEXT: call void @llvm.masked.store.v4i64.p0(<4 x i64> [[BROADCAST_SPLAT]], ptr [[TMP4]], i32 8, <4 x i1> [[ACTIVE_LANE_MASK]])
-; TF-FIXEDLEN-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
-; TF-FIXEDLEN-NEXT: [[VEC_IND_NEXT]] = add <4 x i64> [[VEC_IND]], splat (i64 4)
-; TF-FIXEDLEN-NEXT: [[TMP5:%.*]] = icmp eq i64 [[INDEX_NEXT]], 1028
-; TF-FIXEDLEN-NEXT: br i1 [[TMP5]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP12:![0-9]+]]
-; TF-FIXEDLEN: [[MIDDLE_BLOCK]]:
-; TF-FIXEDLEN-NEXT: br label %[[FOR_END:.*]]
-; TF-FIXEDLEN: [[SCALAR_PH]]:
-; TF-FIXEDLEN-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ 0, %[[ENTRY]] ]
-; TF-FIXEDLEN-NEXT: br label %[[FOR_BODY:.*]]
-; TF-FIXEDLEN: [[FOR_BODY]]:
-; TF-FIXEDLEN-NEXT: [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], %[[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], %[[LATCH:.*]] ]
-; TF-FIXEDLEN-NEXT: [[CMP:%.*]] = icmp ugt i64 [[IV]], 10
-; TF-FIXEDLEN-NEXT: br i1 [[CMP]], label %[[DO_STORE:.*]], label %[[LATCH]]
-; TF-FIXEDLEN: [[DO_STORE]]:
-; TF-FIXEDLEN-NEXT: store i64 [[V]], ptr [[B]], align 8
-; TF-FIXEDLEN-NEXT: br label %[[LATCH]]
-; TF-FIXEDLEN: [[LATCH]]:
-; TF-FIXEDLEN-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[IV]]
-; TF-FIXEDLEN-NEXT: store i64 [[V]], ptr [[ARRAYIDX]], align 8
-; TF-FIXEDLEN-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
-; TF-FIXEDLEN-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], 1025
-; TF-FIXEDLEN-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP13:![0-9]+]]
-; TF-FIXEDLEN: [[FOR_END]]:
-; TF-FIXEDLEN-NEXT: ret void
-;
entry:
br label %for.body
@@ -1442,15 +1197,19 @@ define void @uniform_store_unaligned(ptr noalias nocapture %a, ptr noalias nocap
; TF-SCALABLE-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 2 x i64> [[BROADCAST_SPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
; TF-SCALABLE-NEXT: br label %[[VECTOR_BODY:.*]]
; TF-SCALABLE: [[VECTOR_BODY]]:
-; TF-SCALABLE-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
-; TF-SCALABLE-NEXT: [[ACTIVE_LANE_MASK:%.*]] = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 [[INDEX]], i64 1025)
+; TF-SCALABLE-NEXT: [[INDEX1:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; TF-SCALABLE-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_EVL_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; TF-SCALABLE-NEXT: [[AVL:%.*]] = sub i64 1025, [[INDEX]]
+; TF-SCALABLE-NEXT: [[TMP5:%.*]] = call i32 @llvm.experimental.get.vector.length.i64(i64 [[AVL]], i32 2, i1 true)
; TF-SCALABLE-NEXT: store i64 [[V]], ptr [[B]], align 1
; TF-SCALABLE-NEXT: [[TMP6:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[INDEX]]
; TF-SCALABLE-NEXT: [[TMP7:%.*]] = getelementptr inbounds i64, ptr [[TMP6]], i32 0
-; TF-SCALABLE-NEXT: call void @llvm.masked.store.nxv2i64.p0(<vscale x 2 x i64> [[BROADCAST_SPLAT]], ptr [[TMP7]], i32 8, <vscale x 2 x i1> [[ACTIVE_LANE_MASK]])
-; TF-SCALABLE-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP4]]
+; TF-SCALABLE-NEXT: call void @llvm.vp.store.nxv2i64.p0(<vscale x 2 x i64> [[BROADCAST_SPLAT]], ptr align 8 [[TMP7]], <vscale x 2 x i1> splat (i1 true), i32 [[TMP5]])
+; TF-SCALABLE-NEXT: [[TMP9:%.*]] = zext i32 [[TMP5]] to i64
+; TF-SCALABLE-NEXT: [[INDEX_EVL_NEXT]] = add nuw i64 [[TMP9]], [[INDEX]]
+; TF-SCALABLE-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX1]], [[TMP4]]
; TF-SCALABLE-NEXT: [[TMP8:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
-; TF-SCALABLE-NEXT: br i1 [[TMP8]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP14:![0-9]+]]
+; TF-SCALABLE-NEXT: br i1 [[TMP8]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP15:![0-9]+]]
; TF-SCALABLE: [[MIDDLE_BLOCK]]:
; TF-SCALABLE-NEXT: br label %[[FOR_END:.*]]
; TF-SCALABLE: [[SCALAR_PH]]:
@@ -1463,44 +1222,10 @@ define void @uniform_store_unaligned(ptr noalias nocapture %a, ptr noalias nocap
; TF-SCALABLE-NEXT: store i64 [[V]], ptr [[ARRAYIDX]], align 8
; TF-SCALABLE-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; TF-SCALABLE-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], 1025
-; TF-SCALABLE-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP15:![0-9]+]]
+; TF-SCALABLE-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP16:![0-9]+]]
; TF-SCALABLE: [[FOR_END]]:
; TF-SCALABLE-NEXT: ret void
;
-; TF-FIXEDLEN-LABEL: define void @uniform_store_unaligned(
-; TF-FIXEDLEN-SAME: ptr noalias captures(none) [[A:%.*]], ptr noalias captures(none) [[B:%.*]], i64 [[V:%.*]], i64 [[N:%.*]]) #[[ATTR0]] {
-; TF-FIXEDLEN-NEXT: [[ENTRY:.*]]:
-; TF-FIXEDLEN-NEXT: br i1 false, label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
-; TF-FIXEDLEN: [[VECTOR_PH]]:
-; TF-FIXEDLEN-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i64> poison, i64 [[V]], i64 0
-; TF-FIXEDLEN-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> poison, <4 x i32> zeroinitializer
-; TF-FIXEDLEN-NEXT: br label %[[VECTOR_BODY:.*]]
-; TF-FIXEDLEN: [[VECTOR_BODY]]:
-; TF-FIXEDLEN-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
-; TF-FIXEDLEN-NEXT: [[ACTIVE_LANE_MASK:%.*]] = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64 [[INDEX]], i64 1025)
-; TF-FIXEDLEN-NEXT: store i64 [[V]], ptr [[B]], align 1
-; TF-FIXEDLEN-NEXT: [[TMP1:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[INDEX]]
-; TF-FIXEDLEN-NEXT: [[TMP2:%.*]] = getelementptr inbounds i64, ptr [[TMP1]], i32 0
-; TF-FIXEDLEN-NEXT: call void @llvm.masked.store.v4i64.p0(<4 x i64> [[BROADCAST_SPLAT]], ptr [[TMP2]], i32 8, <4 x i1> [[ACTIVE_LANE_MASK]])
-; TF-FIXEDLEN-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
-; TF-FIXEDLEN-NEXT: [[TMP3:%.*]] = icmp eq i64 [[INDEX_NEXT]], 1028
-; TF-FIXEDLEN-NEXT: br i1 [[TMP3]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP14:![0-9]+]]
-; TF-FIXEDLEN: [[MIDDLE_BLOCK]]:
-; TF-FIXEDLEN-NEXT: br label %[[FOR_END:.*]]
-; TF-FIXEDLEN: [[SCALAR_PH]]:
-; TF-FIXEDLEN-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ 0, %[[ENTRY]] ]
-; TF-FIXEDLEN-NEXT: br label %[[FOR_BODY:.*]]
-; TF-FIXEDLEN: [[FOR_BODY]]:
-; TF-FIXEDLEN-NEXT: [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], %[[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], %[[FOR_BODY]] ]
-; TF-FIXEDLEN-NEXT: store i64 [[V]], ptr [[B]], align 1
-; TF-FIXEDLEN-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[IV]]
-; TF-FIXEDLEN-NEXT: store i64 [[V]], ptr [[ARRAYIDX]], align 8
-; TF-FIXEDLEN-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
-; TF-FIXEDLEN-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], 1025
-; TF-FIXEDLEN-NEXT: br i1 [[EXITCOND_NOT]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP15:![0-9]+]]
-; TF-FIXEDLEN: [[FOR_END]]:
-; TF-FIXEDLEN-NEXT: ret void
-;
entry:
br label %for.body
More information about the llvm-commits
mailing list