[llvm] [LV][AArch64] Prefer epilogue with fixed-width over scalable VF in case of equal costs. (PR #155546)

Hassnaa Hamdi via llvm-commits llvm-commits at lists.llvm.org
Tue Sep 2 07:04:15 PDT 2025


https://github.com/hassnaaHamdi updated https://github.com/llvm/llvm-project/pull/155546

>From 3af468fe6a15f348b56bcc3711dfa80fdf47b492 Mon Sep 17 00:00:00 2001
From: Hassnaa Hamdi <hassnaa.hamdi at arm.com>
Date: Wed, 27 Aug 2025 03:36:58 +0000
Subject: [PATCH 1/2] [LV][AArch64] Prefer epilogue with fixed-width over
 scalable VF in case of equal costs.

For cases like post-LTO vectorization, epilogue with fixed-width VF
can be removed when we eventually know that the trip count is less than
the epilogue iterations.
---
 .../llvm/Analysis/TargetTransformInfo.h       |   2 +-
 .../llvm/Analysis/TargetTransformInfoImpl.h   |   4 +-
 llvm/lib/Analysis/TargetTransformInfo.cpp     |   5 +-
 .../AArch64/AArch64TargetTransformInfo.cpp    |   8 +-
 .../AArch64/AArch64TargetTransformInfo.h      |   2 +-
 .../Vectorize/LoopVectorizationPlanner.h      |   6 +-
 .../Transforms/Vectorize/LoopVectorize.cpp    |  15 +-
 .../AArch64/low_trip_count_predicates.ll      |  52 +++----
 .../LoopVectorize/AArch64/store-costs-sve.ll  |  26 ++--
 .../AArch64/sve-epilog-vect-vscale-tune.ll    |   2 +-
 .../LoopVectorize/AArch64/sve-epilog-vect.ll  | 129 +++++++-----------
 11 files changed, 104 insertions(+), 147 deletions(-)

diff --git a/llvm/include/llvm/Analysis/TargetTransformInfo.h b/llvm/include/llvm/Analysis/TargetTransformInfo.h
index c4ba8e9857dc4..b38e5e28363db 100644
--- a/llvm/include/llvm/Analysis/TargetTransformInfo.h
+++ b/llvm/include/llvm/Analysis/TargetTransformInfo.h
@@ -1815,7 +1815,7 @@ class TargetTransformInfo {
   /// \returns True if the targets prefers fixed width vectorization if the
   /// loop vectorizer's cost-model assigns an equal cost to the fixed and
   /// scalable version of the vectorized loop.
-  LLVM_ABI bool preferFixedOverScalableIfEqualCost() const;
+  LLVM_ABI bool preferFixedOverScalableIfEqualCost(bool IsEpilogue) const;
 
   /// \returns True if target prefers SLP vectorizer with altermate opcode
   /// vectorization, false - otherwise.
diff --git a/llvm/include/llvm/Analysis/TargetTransformInfoImpl.h b/llvm/include/llvm/Analysis/TargetTransformInfoImpl.h
index 43813d2f3acb5..d5589113a14c9 100644
--- a/llvm/include/llvm/Analysis/TargetTransformInfoImpl.h
+++ b/llvm/include/llvm/Analysis/TargetTransformInfoImpl.h
@@ -1092,7 +1092,9 @@ class TargetTransformInfoImplBase {
     return VF;
   }
 
-  virtual bool preferFixedOverScalableIfEqualCost() const { return false; }
+  virtual bool preferFixedOverScalableIfEqualCost(bool IsEpilogue) const {
+    return false;
+  }
 
   virtual bool preferInLoopReduction(RecurKind Kind, Type *Ty) const {
     return false;
diff --git a/llvm/lib/Analysis/TargetTransformInfo.cpp b/llvm/lib/Analysis/TargetTransformInfo.cpp
index 4ac8f03e6dbf5..35e69857d8987 100644
--- a/llvm/lib/Analysis/TargetTransformInfo.cpp
+++ b/llvm/lib/Analysis/TargetTransformInfo.cpp
@@ -1402,8 +1402,9 @@ unsigned TargetTransformInfo::getStoreVectorFactor(unsigned VF,
   return TTIImpl->getStoreVectorFactor(VF, StoreSize, ChainSizeInBytes, VecTy);
 }
 
-bool TargetTransformInfo::preferFixedOverScalableIfEqualCost() const {
-  return TTIImpl->preferFixedOverScalableIfEqualCost();
+bool TargetTransformInfo::preferFixedOverScalableIfEqualCost(
+    bool IsEpilogue) const {
+  return TTIImpl->preferFixedOverScalableIfEqualCost(IsEpilogue);
 }
 
 bool TargetTransformInfo::preferInLoopReduction(RecurKind Kind,
diff --git a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
index 490f6391c15a0..22b2323d639be 100644
--- a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -6017,9 +6017,15 @@ static bool containsDecreasingPointers(Loop *TheLoop,
   return false;
 }
 
-bool AArch64TTIImpl::preferFixedOverScalableIfEqualCost() const {
+bool AArch64TTIImpl::preferFixedOverScalableIfEqualCost(bool IsEpilogue) const {
   if (SVEPreferFixedOverScalableIfEqualCost.getNumOccurrences())
     return SVEPreferFixedOverScalableIfEqualCost;
+  // For cases like post-LTO vectorization, when we eventually know the trip
+  // count, epilogue with fixed-width vectorization can be deleted if the trip
+  // count is less than the epilogue iterations. That's why we prefer
+  // fixed-width vectorization in epilogue in case of equal costs.
+  if (IsEpilogue)
+    return true;
   return ST->useFixedOverScalableIfEqualCost();
 }
 
diff --git a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.h b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.h
index 42ae962b3b426..8ca263ec1cb65 100644
--- a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.h
+++ b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.h
@@ -424,7 +424,7 @@ class AArch64TTIImpl final : public BasicTTIImplBase<AArch64TTIImpl> {
     return TailFoldingStyle::DataWithoutLaneMask;
   }
 
-  bool preferFixedOverScalableIfEqualCost() const override;
+  bool preferFixedOverScalableIfEqualCost(bool IsEpilogue) const override;
 
   unsigned getEpilogueVectorizationMinVF() const override;
 
diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorizationPlanner.h b/llvm/lib/Transforms/Vectorize/LoopVectorizationPlanner.h
index 11bb34e5ba702..0392e004c68f0 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorizationPlanner.h
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorizationPlanner.h
@@ -622,13 +622,15 @@ class LoopVectorizationPlanner {
   /// Returns true if the per-lane cost of VectorizationFactor A is lower than
   /// that of B.
   bool isMoreProfitable(const VectorizationFactor &A,
-                        const VectorizationFactor &B, bool HasTail) const;
+                        const VectorizationFactor &B, bool HasTail,
+                        bool IsEpilogue = false) const;
 
   /// Returns true if the per-lane cost of VectorizationFactor A is lower than
   /// that of B in the context of vectorizing a loop with known \p MaxTripCount.
   bool isMoreProfitable(const VectorizationFactor &A,
                         const VectorizationFactor &B,
-                        const unsigned MaxTripCount, bool HasTail) const;
+                        const unsigned MaxTripCount, bool HasTail,
+                        bool IsEpilogue = false) const;
 
   /// Determines if we have the infrastructure to vectorize the loop and its
   /// epilogue, assuming the main loop is vectorized by \p VF.
diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
index 6317bc3c20e25..0c767ce61d152 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -3850,7 +3850,8 @@ ElementCount LoopVectorizationCostModel::getMaximizedVFForTarget(
 bool LoopVectorizationPlanner::isMoreProfitable(const VectorizationFactor &A,
                                                 const VectorizationFactor &B,
                                                 const unsigned MaxTripCount,
-                                                bool HasTail) const {
+                                                bool HasTail,
+                                                bool IsEpilogue) const {
   InstructionCost CostA = A.Cost;
   InstructionCost CostB = B.Cost;
 
@@ -3874,7 +3875,7 @@ bool LoopVectorizationPlanner::isMoreProfitable(const VectorizationFactor &A,
   // Assume vscale may be larger than 1 (or the value being tuned for),
   // so that scalable vectorization is slightly favorable over fixed-width
   // vectorization.
-  bool PreferScalable = !TTI.preferFixedOverScalableIfEqualCost() &&
+  bool PreferScalable = !TTI.preferFixedOverScalableIfEqualCost(IsEpilogue) &&
                         A.Width.isScalable() && !B.Width.isScalable();
 
   auto CmpFn = [PreferScalable](const InstructionCost &LHS,
@@ -3912,10 +3913,11 @@ bool LoopVectorizationPlanner::isMoreProfitable(const VectorizationFactor &A,
 
 bool LoopVectorizationPlanner::isMoreProfitable(const VectorizationFactor &A,
                                                 const VectorizationFactor &B,
-                                                bool HasTail) const {
+                                                bool HasTail,
+                                                bool IsEpilogue) const {
   const unsigned MaxTripCount = PSE.getSmallConstantMaxTripCount();
-  return LoopVectorizationPlanner::isMoreProfitable(A, B, MaxTripCount,
-                                                    HasTail);
+  return LoopVectorizationPlanner::isMoreProfitable(A, B, MaxTripCount, HasTail,
+                                                    IsEpilogue);
 }
 
 void LoopVectorizationPlanner::emitInvalidCostRemarks(
@@ -4441,7 +4443,8 @@ VectorizationFactor LoopVectorizationPlanner::selectEpilogueVectorizationFactor(
     }
 
     if (Result.Width.isScalar() ||
-        isMoreProfitable(NextVF, Result, MaxTripCount, !CM.foldTailByMasking()))
+        isMoreProfitable(NextVF, Result, MaxTripCount, !CM.foldTailByMasking(),
+                         /*IsEpilogue*/ true))
       Result = NextVF;
   }
 
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/low_trip_count_predicates.ll b/llvm/test/Transforms/LoopVectorize/AArch64/low_trip_count_predicates.ll
index 1f486fba069c9..d61c3cf6e2bea 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/low_trip_count_predicates.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/low_trip_count_predicates.ll
@@ -12,9 +12,9 @@ target triple = "aarch64-unknown-linux-gnu"
 ; DEBUG: LV: Found maximum trip count: 19
 ; DEBUG: LV: IC is 1
 ; DEBUG-VS1: LV: VF is vscale x 16
-; DEBUG-VS1: Main Loop VF:vscale x 16, Main Loop UF:1, Epilogue Loop VF:vscale x 8, Epilogue Loop UF:1
+; DEBUG-VS1: Main Loop VF:vscale x 16, Main Loop UF:1, Epilogue Loop VF:8, Epilogue Loop UF:1
 ; DEBUG-VS2: LV: VF is vscale x 8
-; DEBUG-VS2: Main Loop VF:vscale x 8, Main Loop UF:1, Epilogue Loop VF:vscale x 4, Epilogue Loop UF:1
+; DEBUG-VS2: Main Loop VF:vscale x 8, Main Loop UF:1, Epilogue Loop VF:8, Epilogue Loop UF:1
 
 ; DEBUG-LABEL: LV: Checking a loop in 'trip_count_too_small'
 ; DEBUG: LV: Found a loop with a very small trip count. This loop is worth vectorizing only if no scalar iteration overheads are incurred.
@@ -48,9 +48,7 @@ define void @low_vf_ic_is_better(ptr nocapture noundef %p, i32 %tc, i16 noundef
 ; CHECK-VS1-NEXT:    [[TMP1:%.*]] = add i32 [[TC]], 1
 ; CHECK-VS1-NEXT:    [[TMP2:%.*]] = zext i32 [[TMP1]] to i64
 ; CHECK-VS1-NEXT:    [[TMP3:%.*]] = sub i64 20, [[TMP2]]
-; CHECK-VS1-NEXT:    [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-VS1-NEXT:    [[TMP5:%.*]] = shl nuw i64 [[TMP4]], 3
-; CHECK-VS1-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP3]], [[TMP5]]
+; CHECK-VS1-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP3]], 8
 ; CHECK-VS1-NEXT:    br i1 [[MIN_ITERS_CHECK]], label %[[VEC_EPILOG_SCALAR_PH:.*]], label %[[VECTOR_SCEVCHECK:.*]]
 ; CHECK-VS1:       [[VECTOR_SCEVCHECK]]:
 ; CHECK-VS1-NEXT:    [[TMP6:%.*]] = add i32 [[TC]], 1
@@ -91,28 +89,24 @@ define void @low_vf_ic_is_better(ptr nocapture noundef %p, i32 %tc, i16 noundef
 ; CHECK-VS1:       [[VEC_EPILOG_ITER_CHECK]]:
 ; CHECK-VS1-NEXT:    [[IND_END4:%.*]] = add i64 [[TMP0]], [[N_VEC]]
 ; CHECK-VS1-NEXT:    [[N_VEC_REMAINING:%.*]] = sub i64 [[TMP3]], [[N_VEC]]
-; CHECK-VS1-NEXT:    [[TMP26:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-VS1-NEXT:    [[TMP27:%.*]] = shl nuw i64 [[TMP26]], 3
-; CHECK-VS1-NEXT:    [[MIN_EPILOG_ITERS_CHECK:%.*]] = icmp ult i64 [[N_VEC_REMAINING]], [[TMP27]]
+; CHECK-VS1-NEXT:    [[MIN_EPILOG_ITERS_CHECK:%.*]] = icmp ult i64 [[N_VEC_REMAINING]], 8
 ; CHECK-VS1-NEXT:    br i1 [[MIN_EPILOG_ITERS_CHECK]], label %[[VEC_EPILOG_SCALAR_PH]], label %[[VEC_EPILOG_PH]]
 ; CHECK-VS1:       [[VEC_EPILOG_PH]]:
 ; CHECK-VS1-NEXT:    [[VEC_EPILOG_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], %[[VEC_EPILOG_ITER_CHECK]] ], [ 0, %[[VECTOR_MAIN_LOOP_ITER_CHECK]] ]
-; CHECK-VS1-NEXT:    [[TMP28:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-VS1-NEXT:    [[TMP29:%.*]] = mul nuw i64 [[TMP28]], 8
-; CHECK-VS1-NEXT:    [[N_MOD_VF2:%.*]] = urem i64 [[TMP3]], [[TMP29]]
+; CHECK-VS1-NEXT:    [[N_MOD_VF2:%.*]] = urem i64 [[TMP3]], 8
 ; CHECK-VS1-NEXT:    [[N_VEC3:%.*]] = sub i64 [[TMP3]], [[N_MOD_VF2]]
 ; CHECK-VS1-NEXT:    [[TMP39:%.*]] = add i64 [[TMP0]], [[N_VEC3]]
-; CHECK-VS1-NEXT:    [[BROADCAST_SPLATINSERT7:%.*]] = insertelement <vscale x 8 x i8> poison, i8 [[CONV]], i64 0
-; CHECK-VS1-NEXT:    [[BROADCAST_SPLAT8:%.*]] = shufflevector <vscale x 8 x i8> [[BROADCAST_SPLATINSERT7]], <vscale x 8 x i8> poison, <vscale x 8 x i32> zeroinitializer
+; CHECK-VS1-NEXT:    [[BROADCAST_SPLATINSERT4:%.*]] = insertelement <8 x i8> poison, i8 [[CONV]], i64 0
+; CHECK-VS1-NEXT:    [[BROADCAST_SPLAT5:%.*]] = shufflevector <8 x i8> [[BROADCAST_SPLATINSERT4]], <8 x i8> poison, <8 x i32> zeroinitializer
 ; CHECK-VS1-NEXT:    br label %[[VEC_EPILOG_VECTOR_BODY:.*]]
 ; CHECK-VS1:       [[VEC_EPILOG_VECTOR_BODY]]:
 ; CHECK-VS1-NEXT:    [[INDEX5:%.*]] = phi i64 [ [[VEC_EPILOG_RESUME_VAL]], %[[VEC_EPILOG_PH]] ], [ [[INDEX_NEXT9:%.*]], %[[VEC_EPILOG_VECTOR_BODY]] ]
 ; CHECK-VS1-NEXT:    [[OFFSET_IDX:%.*]] = add i64 [[TMP0]], [[INDEX5]]
 ; CHECK-VS1-NEXT:    [[TMP33:%.*]] = getelementptr inbounds nuw i8, ptr [[V]], i64 [[OFFSET_IDX]]
-; CHECK-VS1-NEXT:    [[WIDE_LOAD6:%.*]] = load <vscale x 8 x i8>, ptr [[TMP33]], align 1
-; CHECK-VS1-NEXT:    [[TMP35:%.*]] = add <vscale x 8 x i8> [[WIDE_LOAD6]], [[BROADCAST_SPLAT8]]
-; CHECK-VS1-NEXT:    store <vscale x 8 x i8> [[TMP35]], ptr [[TMP33]], align 1
-; CHECK-VS1-NEXT:    [[INDEX_NEXT9]] = add nuw i64 [[INDEX5]], [[TMP29]]
+; CHECK-VS1-NEXT:    [[WIDE_LOAD7:%.*]] = load <8 x i8>, ptr [[TMP33]], align 1
+; CHECK-VS1-NEXT:    [[TMP23:%.*]] = add <8 x i8> [[WIDE_LOAD7]], [[BROADCAST_SPLAT5]]
+; CHECK-VS1-NEXT:    store <8 x i8> [[TMP23]], ptr [[TMP33]], align 1
+; CHECK-VS1-NEXT:    [[INDEX_NEXT9]] = add nuw i64 [[INDEX5]], 8
 ; CHECK-VS1-NEXT:    [[TMP36:%.*]] = icmp eq i64 [[INDEX_NEXT9]], [[N_VEC3]]
 ; CHECK-VS1-NEXT:    br i1 [[TMP36]], label %[[VEC_EPILOG_MIDDLE_BLOCK:.*]], label %[[VEC_EPILOG_VECTOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
 ; CHECK-VS1:       [[VEC_EPILOG_MIDDLE_BLOCK]]:
@@ -148,9 +142,7 @@ define void @low_vf_ic_is_better(ptr nocapture noundef %p, i32 %tc, i16 noundef
 ; CHECK-VS2-NEXT:    [[TMP1:%.*]] = add i32 [[TC]], 1
 ; CHECK-VS2-NEXT:    [[TMP2:%.*]] = zext i32 [[TMP1]] to i64
 ; CHECK-VS2-NEXT:    [[TMP3:%.*]] = sub i64 20, [[TMP2]]
-; CHECK-VS2-NEXT:    [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-VS2-NEXT:    [[TMP5:%.*]] = shl nuw i64 [[TMP4]], 2
-; CHECK-VS2-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP3]], [[TMP5]]
+; CHECK-VS2-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP3]], 8
 ; CHECK-VS2-NEXT:    br i1 [[MIN_ITERS_CHECK]], label %[[VEC_EPILOG_SCALAR_PH:.*]], label %[[VECTOR_SCEVCHECK:.*]]
 ; CHECK-VS2:       [[VECTOR_SCEVCHECK]]:
 ; CHECK-VS2-NEXT:    [[TMP6:%.*]] = add i32 [[TC]], 1
@@ -191,28 +183,24 @@ define void @low_vf_ic_is_better(ptr nocapture noundef %p, i32 %tc, i16 noundef
 ; CHECK-VS2:       [[VEC_EPILOG_ITER_CHECK]]:
 ; CHECK-VS2-NEXT:    [[IND_END4:%.*]] = add i64 [[TMP0]], [[N_VEC]]
 ; CHECK-VS2-NEXT:    [[N_VEC_REMAINING:%.*]] = sub i64 [[TMP3]], [[N_VEC]]
-; CHECK-VS2-NEXT:    [[TMP26:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-VS2-NEXT:    [[TMP27:%.*]] = shl nuw i64 [[TMP26]], 2
-; CHECK-VS2-NEXT:    [[MIN_EPILOG_ITERS_CHECK:%.*]] = icmp ult i64 [[N_VEC_REMAINING]], [[TMP27]]
+; CHECK-VS2-NEXT:    [[MIN_EPILOG_ITERS_CHECK:%.*]] = icmp ult i64 [[N_VEC_REMAINING]], 8
 ; CHECK-VS2-NEXT:    br i1 [[MIN_EPILOG_ITERS_CHECK]], label %[[VEC_EPILOG_SCALAR_PH]], label %[[VEC_EPILOG_PH]]
 ; CHECK-VS2:       [[VEC_EPILOG_PH]]:
 ; CHECK-VS2-NEXT:    [[VEC_EPILOG_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], %[[VEC_EPILOG_ITER_CHECK]] ], [ 0, %[[VECTOR_MAIN_LOOP_ITER_CHECK]] ]
-; CHECK-VS2-NEXT:    [[TMP28:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-VS2-NEXT:    [[TMP29:%.*]] = mul nuw i64 [[TMP28]], 4
-; CHECK-VS2-NEXT:    [[N_MOD_VF2:%.*]] = urem i64 [[TMP3]], [[TMP29]]
+; CHECK-VS2-NEXT:    [[N_MOD_VF2:%.*]] = urem i64 [[TMP3]], 8
 ; CHECK-VS2-NEXT:    [[N_VEC3:%.*]] = sub i64 [[TMP3]], [[N_MOD_VF2]]
 ; CHECK-VS2-NEXT:    [[TMP39:%.*]] = add i64 [[TMP0]], [[N_VEC3]]
-; CHECK-VS2-NEXT:    [[BROADCAST_SPLATINSERT7:%.*]] = insertelement <vscale x 4 x i8> poison, i8 [[CONV]], i64 0
-; CHECK-VS2-NEXT:    [[BROADCAST_SPLAT8:%.*]] = shufflevector <vscale x 4 x i8> [[BROADCAST_SPLATINSERT7]], <vscale x 4 x i8> poison, <vscale x 4 x i32> zeroinitializer
+; CHECK-VS2-NEXT:    [[BROADCAST_SPLATINSERT4:%.*]] = insertelement <8 x i8> poison, i8 [[CONV]], i64 0
+; CHECK-VS2-NEXT:    [[BROADCAST_SPLAT5:%.*]] = shufflevector <8 x i8> [[BROADCAST_SPLATINSERT4]], <8 x i8> poison, <8 x i32> zeroinitializer
 ; CHECK-VS2-NEXT:    br label %[[VEC_EPILOG_VECTOR_BODY:.*]]
 ; CHECK-VS2:       [[VEC_EPILOG_VECTOR_BODY]]:
 ; CHECK-VS2-NEXT:    [[INDEX5:%.*]] = phi i64 [ [[VEC_EPILOG_RESUME_VAL]], %[[VEC_EPILOG_PH]] ], [ [[INDEX_NEXT9:%.*]], %[[VEC_EPILOG_VECTOR_BODY]] ]
 ; CHECK-VS2-NEXT:    [[OFFSET_IDX:%.*]] = add i64 [[TMP0]], [[INDEX5]]
 ; CHECK-VS2-NEXT:    [[TMP33:%.*]] = getelementptr inbounds nuw i8, ptr [[V]], i64 [[OFFSET_IDX]]
-; CHECK-VS2-NEXT:    [[WIDE_LOAD6:%.*]] = load <vscale x 4 x i8>, ptr [[TMP33]], align 1
-; CHECK-VS2-NEXT:    [[TMP35:%.*]] = add <vscale x 4 x i8> [[WIDE_LOAD6]], [[BROADCAST_SPLAT8]]
-; CHECK-VS2-NEXT:    store <vscale x 4 x i8> [[TMP35]], ptr [[TMP33]], align 1
-; CHECK-VS2-NEXT:    [[INDEX_NEXT9]] = add nuw i64 [[INDEX5]], [[TMP29]]
+; CHECK-VS2-NEXT:    [[WIDE_LOAD7:%.*]] = load <8 x i8>, ptr [[TMP33]], align 1
+; CHECK-VS2-NEXT:    [[TMP23:%.*]] = add <8 x i8> [[WIDE_LOAD7]], [[BROADCAST_SPLAT5]]
+; CHECK-VS2-NEXT:    store <8 x i8> [[TMP23]], ptr [[TMP33]], align 1
+; CHECK-VS2-NEXT:    [[INDEX_NEXT9]] = add nuw i64 [[INDEX5]], 8
 ; CHECK-VS2-NEXT:    [[TMP36:%.*]] = icmp eq i64 [[INDEX_NEXT9]], [[N_VEC3]]
 ; CHECK-VS2-NEXT:    br i1 [[TMP36]], label %[[VEC_EPILOG_MIDDLE_BLOCK:.*]], label %[[VEC_EPILOG_VECTOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
 ; CHECK-VS2:       [[VEC_EPILOG_MIDDLE_BLOCK]]:
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/store-costs-sve.ll b/llvm/test/Transforms/LoopVectorize/AArch64/store-costs-sve.ll
index f6de370874d12..dc537b1700162 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/store-costs-sve.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/store-costs-sve.ll
@@ -9,10 +9,7 @@ define void @cost_store_i8(ptr %dst) #0 {
 ; DEFAULT-LABEL: define void @cost_store_i8(
 ; DEFAULT-SAME: ptr [[DST:%.*]]) #[[ATTR0:[0-9]+]] {
 ; DEFAULT-NEXT:  iter.check:
-; DEFAULT-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
-; DEFAULT-NEXT:    [[TMP1:%.*]] = shl nuw i64 [[TMP0]], 3
-; DEFAULT-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 101, [[TMP1]]
-; DEFAULT-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[VEC_EPILOG_SCALAR_PH:%.*]], label [[VECTOR_MAIN_LOOP_ITER_CHECK:%.*]]
+; DEFAULT-NEXT:    br i1 false, label [[VEC_EPILOG_SCALAR_PH:%.*]], label [[VECTOR_MAIN_LOOP_ITER_CHECK:%.*]]
 ; DEFAULT:       vector.main.loop.iter.check:
 ; DEFAULT-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
 ; DEFAULT-NEXT:    [[TMP3:%.*]] = shl nuw i64 [[TMP2]], 5
@@ -40,29 +37,22 @@ define void @cost_store_i8(ptr %dst) #0 {
 ; DEFAULT-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[VEC_EPILOG_ITER_CHECK:%.*]]
 ; DEFAULT:       vec.epilog.iter.check:
 ; DEFAULT-NEXT:    [[N_VEC_REMAINING:%.*]] = sub i64 101, [[N_VEC]]
-; DEFAULT-NEXT:    [[TMP12:%.*]] = call i64 @llvm.vscale.i64()
-; DEFAULT-NEXT:    [[TMP13:%.*]] = shl nuw i64 [[TMP12]], 3
-; DEFAULT-NEXT:    [[MIN_EPILOG_ITERS_CHECK:%.*]] = icmp ult i64 [[N_VEC_REMAINING]], [[TMP13]]
+; DEFAULT-NEXT:    [[MIN_EPILOG_ITERS_CHECK:%.*]] = icmp ult i64 [[N_VEC_REMAINING]], 8
 ; DEFAULT-NEXT:    br i1 [[MIN_EPILOG_ITERS_CHECK]], label [[VEC_EPILOG_SCALAR_PH]], label [[VEC_EPILOG_PH]]
 ; DEFAULT:       vec.epilog.ph:
 ; DEFAULT-NEXT:    [[VEC_EPILOG_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[VEC_EPILOG_ITER_CHECK]] ], [ 0, [[VECTOR_MAIN_LOOP_ITER_CHECK]] ]
-; DEFAULT-NEXT:    [[TMP14:%.*]] = call i64 @llvm.vscale.i64()
-; DEFAULT-NEXT:    [[TMP15:%.*]] = mul nuw i64 [[TMP14]], 8
-; DEFAULT-NEXT:    [[N_MOD_VF2:%.*]] = urem i64 101, [[TMP15]]
-; DEFAULT-NEXT:    [[N_VEC3:%.*]] = sub i64 101, [[N_MOD_VF2]]
 ; DEFAULT-NEXT:    br label [[VEC_EPILOG_VECTOR_BODY:%.*]]
 ; DEFAULT:       vec.epilog.vector.body:
 ; DEFAULT-NEXT:    [[INDEX5:%.*]] = phi i64 [ [[VEC_EPILOG_RESUME_VAL]], [[VEC_EPILOG_PH]] ], [ [[INDEX_NEXT6:%.*]], [[VEC_EPILOG_VECTOR_BODY]] ]
 ; DEFAULT-NEXT:    [[TMP19:%.*]] = getelementptr i8, ptr [[DST]], i64 [[INDEX5]]
-; DEFAULT-NEXT:    store <vscale x 8 x i8> zeroinitializer, ptr [[TMP19]], align 1
-; DEFAULT-NEXT:    [[INDEX_NEXT6]] = add nuw i64 [[INDEX5]], [[TMP15]]
-; DEFAULT-NEXT:    [[TMP21:%.*]] = icmp eq i64 [[INDEX_NEXT6]], [[N_VEC3]]
-; DEFAULT-NEXT:    br i1 [[TMP21]], label [[VEC_EPILOG_MIDDLE_BLOCK:%.*]], label [[VEC_EPILOG_VECTOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
+; DEFAULT-NEXT:    store <8 x i8> zeroinitializer, ptr [[TMP19]], align 1
+; DEFAULT-NEXT:    [[INDEX_NEXT6]] = add nuw i64 [[INDEX5]], 8
+; DEFAULT-NEXT:    [[TMP10:%.*]] = icmp eq i64 [[INDEX_NEXT6]], 96
+; DEFAULT-NEXT:    br i1 [[TMP10]], label [[VEC_EPILOG_MIDDLE_BLOCK:%.*]], label [[VEC_EPILOG_VECTOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
 ; DEFAULT:       vec.epilog.middle.block:
-; DEFAULT-NEXT:    [[CMP_N4:%.*]] = icmp eq i64 101, [[N_VEC3]]
-; DEFAULT-NEXT:    br i1 [[CMP_N4]], label [[EXIT]], label [[VEC_EPILOG_SCALAR_PH]]
+; DEFAULT-NEXT:    br i1 false, label [[EXIT]], label [[VEC_EPILOG_SCALAR_PH]]
 ; DEFAULT:       vec.epilog.scalar.ph:
-; DEFAULT-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC3]], [[VEC_EPILOG_MIDDLE_BLOCK]] ], [ [[N_VEC]], [[VEC_EPILOG_ITER_CHECK]] ], [ 0, [[ITER_CHECK:%.*]] ]
+; DEFAULT-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ 96, [[VEC_EPILOG_MIDDLE_BLOCK]] ], [ [[N_VEC]], [[VEC_EPILOG_ITER_CHECK]] ], [ 0, [[ITER_CHECK:%.*]] ]
 ; DEFAULT-NEXT:    br label [[LOOP:%.*]]
 ; DEFAULT:       loop:
 ; DEFAULT-NEXT:    [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[VEC_EPILOG_SCALAR_PH]] ], [ [[IV_NEXT:%.*]], [[LOOP]] ]
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-epilog-vect-vscale-tune.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-epilog-vect-vscale-tune.ll
index 52d343e4105c7..eaa48eafafea7 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-epilog-vect-vscale-tune.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-epilog-vect-vscale-tune.ll
@@ -10,7 +10,7 @@ target triple = "aarch64-unknown-linux-gnu"
 define void @foo(ptr noalias nocapture readonly %p, ptr noalias nocapture %q, i64 %len) #0 {
 ; CHECK-EPILOG:      vec.epilog.ph:
 ; CHECK-EPILOG:      vec.epilog.vector.body:
-; CHECK-EPILOG:        load <vscale x 4 x i16>
+; CHECK-EPILOG:        load <8 x i16>
 
 ; The epilogue loop gets vectorised vscale x 2 x i16 wide.
 ; CHECK-EPILOG-V2:      vec.epilog.ph:
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-epilog-vect.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-epilog-vect.ll
index 6b0da1bb2ed82..b43208810daf0 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-epilog-vect.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-epilog-vect.ll
@@ -11,7 +11,7 @@ target triple = "aarch64-linux-gnu"
 
 ; DEBUG: LV: Checking a loop in 'main_vf_vscale_x_16'
 ; DEBUG: Create Skeleton for epilogue vectorized loop (first pass)
-; DEBUG: Main Loop VF:vscale x 16, Main Loop UF:2, Epilogue Loop VF:vscale x 8, Epilogue Loop UF:1
+; DEBUG: Main Loop VF:vscale x 16, Main Loop UF:2, Epilogue Loop VF:8, Epilogue Loop UF:1
 
 ; DEBUG-FORCED: LV: Checking a loop in 'main_vf_vscale_x_16'
 ; DEBUG-FORCED: LEV: Epilogue vectorization factor is forced.
@@ -21,10 +21,7 @@ target triple = "aarch64-linux-gnu"
 define void @main_vf_vscale_x_16(ptr %A) #0 {
 ; CHECK-LABEL: @main_vf_vscale_x_16(
 ; CHECK-NEXT:  iter.check:
-; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP1:%.*]] = shl nuw i64 [[TMP0]], 3
-; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1024, [[TMP1]]
-; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[VEC_EPILOG_SCALAR_PH:%.*]], label [[VECTOR_MAIN_LOOP_ITER_CHECK:%.*]]
+; CHECK-NEXT:    br i1 false, label [[VEC_EPILOG_SCALAR_PH:%.*]], label [[VECTOR_MAIN_LOOP_ITER_CHECK:%.*]]
 ; CHECK:       vector.main.loop.iter.check:
 ; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP3:%.*]] = shl nuw i64 [[TMP2]], 5
@@ -52,29 +49,22 @@ define void @main_vf_vscale_x_16(ptr %A) #0 {
 ; CHECK-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[VEC_EPILOG_ITER_CHECK:%.*]]
 ; CHECK:       vec.epilog.iter.check:
 ; CHECK-NEXT:    [[N_VEC_REMAINING:%.*]] = sub i64 1024, [[N_VEC]]
-; CHECK-NEXT:    [[TMP21:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP22:%.*]] = shl nuw i64 [[TMP21]], 3
-; CHECK-NEXT:    [[MIN_EPILOG_ITERS_CHECK:%.*]] = icmp ult i64 [[N_VEC_REMAINING]], [[TMP22]]
+; CHECK-NEXT:    [[MIN_EPILOG_ITERS_CHECK:%.*]] = icmp ult i64 [[N_VEC_REMAINING]], 8
 ; CHECK-NEXT:    br i1 [[MIN_EPILOG_ITERS_CHECK]], label [[VEC_EPILOG_SCALAR_PH]], label [[VEC_EPILOG_PH]]
 ; CHECK:       vec.epilog.ph:
 ; CHECK-NEXT:    [[VEC_EPILOG_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[VEC_EPILOG_ITER_CHECK]] ], [ 0, [[VECTOR_MAIN_LOOP_ITER_CHECK]] ]
-; CHECK-NEXT:    [[TMP23:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP24:%.*]] = mul nuw i64 [[TMP23]], 8
-; CHECK-NEXT:    [[N_MOD_VF2:%.*]] = urem i64 1024, [[TMP24]]
-; CHECK-NEXT:    [[N_VEC3:%.*]] = sub i64 1024, [[N_MOD_VF2]]
 ; CHECK-NEXT:    br label [[VEC_EPILOG_VECTOR_BODY:%.*]]
 ; CHECK:       vec.epilog.vector.body:
 ; CHECK-NEXT:    [[INDEX5:%.*]] = phi i64 [ [[VEC_EPILOG_RESUME_VAL]], [[VEC_EPILOG_PH]] ], [ [[INDEX_NEXT6:%.*]], [[VEC_EPILOG_VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[TMP28:%.*]] = getelementptr inbounds i8, ptr [[A]], i64 [[INDEX5]]
-; CHECK-NEXT:    store <vscale x 8 x i8> splat (i8 1), ptr [[TMP28]], align 1
-; CHECK-NEXT:    [[INDEX_NEXT6]] = add nuw i64 [[INDEX5]], [[TMP24]]
-; CHECK-NEXT:    [[TMP30:%.*]] = icmp eq i64 [[INDEX_NEXT6]], [[N_VEC3]]
-; CHECK-NEXT:    br i1 [[TMP30]], label [[VEC_EPILOG_MIDDLE_BLOCK:%.*]], label [[VEC_EPILOG_VECTOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
+; CHECK-NEXT:    store <8 x i8> splat (i8 1), ptr [[TMP28]], align 1
+; CHECK-NEXT:    [[INDEX_NEXT6]] = add nuw i64 [[INDEX5]], 8
+; CHECK-NEXT:    [[TMP10:%.*]] = icmp eq i64 [[INDEX_NEXT6]], 1024
+; CHECK-NEXT:    br i1 [[TMP10]], label [[VEC_EPILOG_MIDDLE_BLOCK:%.*]], label [[VEC_EPILOG_VECTOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
 ; CHECK:       vec.epilog.middle.block:
-; CHECK-NEXT:    [[CMP_N4:%.*]] = icmp eq i64 1024, [[N_VEC3]]
-; CHECK-NEXT:    br i1 [[CMP_N4]], label [[EXIT]], label [[VEC_EPILOG_SCALAR_PH]]
+; CHECK-NEXT:    br i1 true, label [[EXIT]], label [[VEC_EPILOG_SCALAR_PH]]
 ; CHECK:       vec.epilog.scalar.ph:
-; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC3]], [[VEC_EPILOG_MIDDLE_BLOCK]] ], [ [[N_VEC]], [[VEC_EPILOG_ITER_CHECK]] ], [ 0, [[ITER_CHECK:%.*]] ]
+; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ 1024, [[VEC_EPILOG_MIDDLE_BLOCK]] ], [ [[N_VEC]], [[VEC_EPILOG_ITER_CHECK]] ], [ 0, [[ITER_CHECK:%.*]] ]
 ; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
 ; CHECK:       for.body:
 ;
@@ -147,22 +137,22 @@ define void @main_vf_vscale_x_2_no_epi_iteration(ptr %A) #0 vscale_range(8, 8) {
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
 ; CHECK:       vector.ph:
-; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP3:%.*]] = mul nuw i64 [[TMP2]], 4
-; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP3]]
+; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP1:%.*]] = mul nuw i64 [[TMP0]], 4
+; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP1]]
 ; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 1024, [[N_MOD_VF]]
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT:    [[TMP6:%.*]] = getelementptr inbounds i64, ptr [[A:%.*]], i64 [[INDEX]]
-; CHECK-NEXT:    [[TMP7:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP8:%.*]] = shl nuw i64 [[TMP7]], 1
-; CHECK-NEXT:    [[TMP9:%.*]] = getelementptr inbounds i64, ptr [[TMP6]], i64 [[TMP8]]
-; CHECK-NEXT:    store <vscale x 2 x i64> splat (i64 1), ptr [[TMP6]], align 1
-; CHECK-NEXT:    store <vscale x 2 x i64> splat (i64 1), ptr [[TMP9]], align 1
-; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP3]]
-; CHECK-NEXT:    [[TMP11:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
-; CHECK-NEXT:    br i1 [[TMP11]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
+; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i64, ptr [[A:%.*]], i64 [[INDEX]]
+; CHECK-NEXT:    [[TMP3:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP4:%.*]] = shl nuw i64 [[TMP3]], 1
+; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i64, ptr [[TMP2]], i64 [[TMP4]]
+; CHECK-NEXT:    store <vscale x 2 x i64> splat (i64 1), ptr [[TMP2]], align 1
+; CHECK-NEXT:    store <vscale x 2 x i64> splat (i64 1), ptr [[TMP5]], align 1
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP1]]
+; CHECK-NEXT:    [[TMP6:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT:    br i1 [[TMP6]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
 ; CHECK:       middle.block:
 ; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 1024, [[N_VEC]]
 ; CHECK-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
@@ -376,10 +366,7 @@ exit:
 define void @test_pr57912_pointer_induction(ptr %start) #0 {
 ; CHECK-LABEL: @test_pr57912_pointer_induction(
 ; CHECK-NEXT:  iter.check:
-; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP1:%.*]] = shl nuw i64 [[TMP0]], 3
-; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 10000, [[TMP1]]
-; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[VEC_EPILOG_SCALAR_PH:%.*]], label [[VECTOR_MAIN_LOOP_ITER_CHECK:%.*]]
+; CHECK-NEXT:    br i1 false, label [[VEC_EPILOG_SCALAR_PH:%.*]], label [[VECTOR_MAIN_LOOP_ITER_CHECK:%.*]]
 ; CHECK:       vector.main.loop.iter.check:
 ; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP3:%.*]] = shl nuw i64 [[TMP2]], 5
@@ -408,30 +395,23 @@ define void @test_pr57912_pointer_induction(ptr %start) #0 {
 ; CHECK:       vec.epilog.iter.check:
 ; CHECK-NEXT:    [[IND_END4:%.*]] = getelementptr i8, ptr [[START]], i64 [[N_VEC]]
 ; CHECK-NEXT:    [[N_VEC_REMAINING:%.*]] = sub i64 10000, [[N_VEC]]
-; CHECK-NEXT:    [[TMP21:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP22:%.*]] = shl nuw i64 [[TMP21]], 3
-; CHECK-NEXT:    [[MIN_EPILOG_ITERS_CHECK:%.*]] = icmp ult i64 [[N_VEC_REMAINING]], [[TMP22]]
+; CHECK-NEXT:    [[MIN_EPILOG_ITERS_CHECK:%.*]] = icmp ult i64 [[N_VEC_REMAINING]], 8
 ; CHECK-NEXT:    br i1 [[MIN_EPILOG_ITERS_CHECK]], label [[VEC_EPILOG_SCALAR_PH]], label [[VEC_EPILOG_PH]]
 ; CHECK:       vec.epilog.ph:
 ; CHECK-NEXT:    [[VEC_EPILOG_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[VEC_EPILOG_ITER_CHECK]] ], [ 0, [[VECTOR_MAIN_LOOP_ITER_CHECK]] ]
-; CHECK-NEXT:    [[TMP23:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP24:%.*]] = mul nuw i64 [[TMP23]], 8
-; CHECK-NEXT:    [[N_MOD_VF2:%.*]] = urem i64 10000, [[TMP24]]
-; CHECK-NEXT:    [[N_VEC3:%.*]] = sub i64 10000, [[N_MOD_VF2]]
-; CHECK-NEXT:    [[IND_END:%.*]] = getelementptr i8, ptr [[START]], i64 [[N_VEC3]]
+; CHECK-NEXT:    [[IND_END:%.*]] = getelementptr i8, ptr [[START]], i64 10000
 ; CHECK-NEXT:    br label [[VEC_EPILOG_VECTOR_BODY:%.*]]
 ; CHECK:       vec.epilog.vector.body:
 ; CHECK-NEXT:    [[INDEX7:%.*]] = phi i64 [ [[VEC_EPILOG_RESUME_VAL]], [[VEC_EPILOG_PH]] ], [ [[INDEX_NEXT8:%.*]], [[VEC_EPILOG_VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[TMP28:%.*]] = getelementptr i8, ptr [[START]], i64 [[INDEX7]]
-; CHECK-NEXT:    store <vscale x 8 x i8> zeroinitializer, ptr [[TMP28]], align 1
-; CHECK-NEXT:    [[INDEX_NEXT8]] = add nuw i64 [[INDEX7]], [[TMP24]]
-; CHECK-NEXT:    [[TMP30:%.*]] = icmp eq i64 [[INDEX_NEXT8]], [[N_VEC3]]
-; CHECK-NEXT:    br i1 [[TMP30]], label [[VEC_EPILOG_MIDDLE_BLOCK:%.*]], label [[VEC_EPILOG_VECTOR_BODY]], !llvm.loop [[LOOP11:![0-9]+]]
+; CHECK-NEXT:    store <8 x i8> zeroinitializer, ptr [[TMP28]], align 1
+; CHECK-NEXT:    [[INDEX_NEXT8]] = add nuw i64 [[INDEX7]], 8
+; CHECK-NEXT:    [[TMP9:%.*]] = icmp eq i64 [[INDEX_NEXT8]], 10000
+; CHECK-NEXT:    br i1 [[TMP9]], label [[VEC_EPILOG_MIDDLE_BLOCK:%.*]], label [[VEC_EPILOG_VECTOR_BODY]], !llvm.loop [[LOOP11:![0-9]+]]
 ; CHECK:       vec.epilog.middle.block:
-; CHECK-NEXT:    [[CMP_N6:%.*]] = icmp eq i64 10000, [[N_VEC3]]
-; CHECK-NEXT:    br i1 [[CMP_N6]], label [[EXIT]], label [[VEC_EPILOG_SCALAR_PH]]
+; CHECK-NEXT:    br i1 true, label [[EXIT]], label [[VEC_EPILOG_SCALAR_PH]]
 ; CHECK:       vec.epilog.scalar.ph:
-; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC3]], [[VEC_EPILOG_MIDDLE_BLOCK]] ], [ [[N_VEC]], [[VEC_EPILOG_ITER_CHECK]] ], [ 0, [[ITER_CHECK:%.*]] ]
+; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ 10000, [[VEC_EPILOG_MIDDLE_BLOCK]] ], [ [[N_VEC]], [[VEC_EPILOG_ITER_CHECK]] ], [ 0, [[ITER_CHECK:%.*]] ]
 ; CHECK-NEXT:    [[BC_RESUME_VAL5:%.*]] = phi ptr [ [[IND_END]], [[VEC_EPILOG_MIDDLE_BLOCK]] ], [ [[IND_END4]], [[VEC_EPILOG_ITER_CHECK]] ], [ [[START]], [[ITER_CHECK]] ]
 ; CHECK-NEXT:    br label [[LOOP:%.*]]
 ; CHECK:       loop:
@@ -510,8 +490,6 @@ define void @trip_count_vscale(ptr noalias %a, ptr noalias %b) vscale_range(1, 1
 ; CHECK-NEXT:  iter.check:
 ; CHECK-NEXT:    [[V:%.*]] = tail call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[N:%.*]] = mul nuw nsw i64 [[V]], 1033
-; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP1:%.*]] = shl nuw i64 [[TMP0]], 1
 ; CHECK-NEXT:    br i1 false, label [[VEC_EPILOG_SCALAR_PH:%.*]], label [[VECTOR_MAIN_LOOP_ITER_CHECK:%.*]]
 ; CHECK:       vector.main.loop.iter.check:
 ; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
@@ -553,26 +531,22 @@ define void @trip_count_vscale(ptr noalias %a, ptr noalias %b) vscale_range(1, 1
 ; CHECK-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[VEC_EPILOG_ITER_CHECK:%.*]]
 ; CHECK:       vec.epilog.iter.check:
 ; CHECK-NEXT:    [[N_VEC_REMAINING:%.*]] = sub i64 [[N]], [[N_VEC]]
-; CHECK-NEXT:    [[TMP24:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP25:%.*]] = shl nuw i64 [[TMP24]], 1
-; CHECK-NEXT:    [[MIN_EPILOG_ITERS_CHECK:%.*]] = icmp ult i64 [[N_VEC_REMAINING]], [[TMP25]]
+; CHECK-NEXT:    [[MIN_EPILOG_ITERS_CHECK:%.*]] = icmp ult i64 [[N_VEC_REMAINING]], 2
 ; CHECK-NEXT:    br i1 [[MIN_EPILOG_ITERS_CHECK]], label [[VEC_EPILOG_SCALAR_PH]], label [[VEC_EPILOG_PH]]
 ; CHECK:       vec.epilog.ph:
 ; CHECK-NEXT:    [[VEC_EPILOG_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[VEC_EPILOG_ITER_CHECK]] ], [ 0, [[VECTOR_MAIN_LOOP_ITER_CHECK]] ]
-; CHECK-NEXT:    [[TMP26:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP27:%.*]] = mul nuw i64 [[TMP26]], 2
-; CHECK-NEXT:    [[N_MOD_VF5:%.*]] = urem i64 [[N]], [[TMP27]]
+; CHECK-NEXT:    [[N_MOD_VF5:%.*]] = urem i64 [[N]], 2
 ; CHECK-NEXT:    [[N_VEC6:%.*]] = sub i64 [[N]], [[N_MOD_VF5]]
 ; CHECK-NEXT:    br label [[VEC_EPILOG_VECTOR_BODY:%.*]]
 ; CHECK:       vec.epilog.vector.body:
 ; CHECK-NEXT:    [[INDEX7:%.*]] = phi i64 [ [[VEC_EPILOG_RESUME_VAL]], [[VEC_EPILOG_PH]] ], [ [[INDEX_NEXT10:%.*]], [[VEC_EPILOG_VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[TMP30:%.*]] = getelementptr inbounds nuw float, ptr [[A]], i64 [[INDEX7]]
-; CHECK-NEXT:    [[WIDE_LOAD8:%.*]] = load <vscale x 2 x float>, ptr [[TMP30]], align 4
+; CHECK-NEXT:    [[WIDE_LOAD7:%.*]] = load <2 x float>, ptr [[TMP30]], align 4
 ; CHECK-NEXT:    [[TMP32:%.*]] = getelementptr inbounds nuw float, ptr [[B]], i64 [[INDEX7]]
-; CHECK-NEXT:    [[WIDE_LOAD9:%.*]] = load <vscale x 2 x float>, ptr [[TMP32]], align 4
-; CHECK-NEXT:    [[TMP34:%.*]] = fmul <vscale x 2 x float> [[WIDE_LOAD8]], [[WIDE_LOAD9]]
-; CHECK-NEXT:    store <vscale x 2 x float> [[TMP34]], ptr [[TMP32]], align 4
-; CHECK-NEXT:    [[INDEX_NEXT10]] = add nuw i64 [[INDEX7]], [[TMP27]]
+; CHECK-NEXT:    [[WIDE_LOAD8:%.*]] = load <2 x float>, ptr [[TMP32]], align 4
+; CHECK-NEXT:    [[TMP24:%.*]] = fmul <2 x float> [[WIDE_LOAD7]], [[WIDE_LOAD8]]
+; CHECK-NEXT:    store <2 x float> [[TMP24]], ptr [[TMP32]], align 4
+; CHECK-NEXT:    [[INDEX_NEXT10]] = add nuw i64 [[INDEX7]], 2
 ; CHECK-NEXT:    [[TMP35:%.*]] = icmp eq i64 [[INDEX_NEXT10]], [[N_VEC6]]
 ; CHECK-NEXT:    br i1 [[TMP35]], label [[VEC_EPILOG_MIDDLE_BLOCK:%.*]], label [[VEC_EPILOG_VECTOR_BODY]], !llvm.loop [[LOOP14:![0-9]+]]
 ; CHECK:       vec.epilog.middle.block:
@@ -654,8 +628,6 @@ define void @trip_count_vscale_no_epilogue_iterations(ptr noalias %a, ptr noalia
 ; CHECK-NEXT:  iter.check:
 ; CHECK-NEXT:    [[V:%.*]] = tail call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[N:%.*]] = mul nuw nsw i64 [[V]], 1024
-; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP1:%.*]] = shl nuw i64 [[TMP0]], 1
 ; CHECK-NEXT:    br i1 false, label [[VEC_EPILOG_SCALAR_PH:%.*]], label [[VECTOR_MAIN_LOOP_ITER_CHECK:%.*]]
 ; CHECK:       vector.main.loop.iter.check:
 ; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
@@ -697,33 +669,26 @@ define void @trip_count_vscale_no_epilogue_iterations(ptr noalias %a, ptr noalia
 ; CHECK-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[VEC_EPILOG_ITER_CHECK:%.*]]
 ; CHECK:       vec.epilog.iter.check:
 ; CHECK-NEXT:    [[N_VEC_REMAINING:%.*]] = sub i64 [[N]], [[N_VEC]]
-; CHECK-NEXT:    [[TMP24:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP25:%.*]] = shl nuw i64 [[TMP24]], 1
-; CHECK-NEXT:    [[MIN_EPILOG_ITERS_CHECK:%.*]] = icmp ult i64 [[N_VEC_REMAINING]], [[TMP25]]
+; CHECK-NEXT:    [[MIN_EPILOG_ITERS_CHECK:%.*]] = icmp ult i64 [[N_VEC_REMAINING]], 2
 ; CHECK-NEXT:    br i1 [[MIN_EPILOG_ITERS_CHECK]], label [[VEC_EPILOG_SCALAR_PH]], label [[VEC_EPILOG_PH]]
 ; CHECK:       vec.epilog.ph:
 ; CHECK-NEXT:    [[VEC_EPILOG_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[VEC_EPILOG_ITER_CHECK]] ], [ 0, [[VECTOR_MAIN_LOOP_ITER_CHECK]] ]
-; CHECK-NEXT:    [[TMP26:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP27:%.*]] = mul nuw i64 [[TMP26]], 2
-; CHECK-NEXT:    [[N_MOD_VF5:%.*]] = urem i64 [[N]], [[TMP27]]
-; CHECK-NEXT:    [[N_VEC6:%.*]] = sub i64 [[N]], [[N_MOD_VF5]]
 ; CHECK-NEXT:    br label [[VEC_EPILOG_VECTOR_BODY:%.*]]
 ; CHECK:       vec.epilog.vector.body:
 ; CHECK-NEXT:    [[INDEX7:%.*]] = phi i64 [ [[VEC_EPILOG_RESUME_VAL]], [[VEC_EPILOG_PH]] ], [ [[INDEX_NEXT10:%.*]], [[VEC_EPILOG_VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[TMP30:%.*]] = getelementptr inbounds nuw float, ptr [[A]], i64 [[INDEX7]]
-; CHECK-NEXT:    [[WIDE_LOAD8:%.*]] = load <vscale x 2 x float>, ptr [[TMP30]], align 4
+; CHECK-NEXT:    [[WIDE_LOAD5:%.*]] = load <2 x float>, ptr [[TMP30]], align 4
 ; CHECK-NEXT:    [[TMP32:%.*]] = getelementptr inbounds nuw float, ptr [[B]], i64 [[INDEX7]]
-; CHECK-NEXT:    [[WIDE_LOAD9:%.*]] = load <vscale x 2 x float>, ptr [[TMP32]], align 4
-; CHECK-NEXT:    [[TMP34:%.*]] = fmul <vscale x 2 x float> [[WIDE_LOAD8]], [[WIDE_LOAD9]]
-; CHECK-NEXT:    store <vscale x 2 x float> [[TMP34]], ptr [[TMP32]], align 4
-; CHECK-NEXT:    [[INDEX_NEXT10]] = add nuw i64 [[INDEX7]], [[TMP27]]
-; CHECK-NEXT:    [[TMP35:%.*]] = icmp eq i64 [[INDEX_NEXT10]], [[N_VEC6]]
-; CHECK-NEXT:    br i1 [[TMP35]], label [[VEC_EPILOG_MIDDLE_BLOCK:%.*]], label [[VEC_EPILOG_VECTOR_BODY]], !llvm.loop [[LOOP17:![0-9]+]]
+; CHECK-NEXT:    [[WIDE_LOAD6:%.*]] = load <2 x float>, ptr [[TMP32]], align 4
+; CHECK-NEXT:    [[TMP24:%.*]] = fmul <2 x float> [[WIDE_LOAD5]], [[WIDE_LOAD6]]
+; CHECK-NEXT:    store <2 x float> [[TMP24]], ptr [[TMP32]], align 4
+; CHECK-NEXT:    [[INDEX_NEXT10]] = add nuw i64 [[INDEX7]], 2
+; CHECK-NEXT:    [[TMP25:%.*]] = icmp eq i64 [[INDEX_NEXT10]], [[N]]
+; CHECK-NEXT:    br i1 [[TMP25]], label [[VEC_EPILOG_MIDDLE_BLOCK:%.*]], label [[VEC_EPILOG_VECTOR_BODY]], !llvm.loop [[LOOP17:![0-9]+]]
 ; CHECK:       vec.epilog.middle.block:
-; CHECK-NEXT:    [[CMP_N11:%.*]] = icmp eq i64 [[N]], [[N_VEC6]]
-; CHECK-NEXT:    br i1 [[CMP_N11]], label [[EXIT]], label [[VEC_EPILOG_SCALAR_PH]]
+; CHECK-NEXT:    br i1 true, label [[EXIT]], label [[VEC_EPILOG_SCALAR_PH]]
 ; CHECK:       vec.epilog.scalar.ph:
-; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC6]], [[VEC_EPILOG_MIDDLE_BLOCK]] ], [ [[N_VEC]], [[VEC_EPILOG_ITER_CHECK]] ], [ 0, [[ITER_CHECK:%.*]] ]
+; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N]], [[VEC_EPILOG_MIDDLE_BLOCK]] ], [ [[N_VEC]], [[VEC_EPILOG_ITER_CHECK]] ], [ 0, [[ITER_CHECK:%.*]] ]
 ; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
 ; CHECK:       for.body:
 ;

>From 1fe2d5df863bf81a8e344cda68d56ef1380fd398 Mon Sep 17 00:00:00 2001
From: Hassnaa Hamdi <hassnaa.hamdi at arm.com>
Date: Tue, 2 Sep 2025 14:00:19 +0000
Subject: [PATCH 2/2] Resolve review comments

---
 .../llvm/Analysis/TargetTransformInfo.h       |   3 +-
 .../AArch64/sve-epilog-vect-vscale-tune.ll    |   7 +
 .../LoopVectorize/AArch64/sve-epilog-vect.ll  | 363 ++++++++++++++++++
 3 files changed, 372 insertions(+), 1 deletion(-)

diff --git a/llvm/include/llvm/Analysis/TargetTransformInfo.h b/llvm/include/llvm/Analysis/TargetTransformInfo.h
index b38e5e28363db..75abf74bb97d0 100644
--- a/llvm/include/llvm/Analysis/TargetTransformInfo.h
+++ b/llvm/include/llvm/Analysis/TargetTransformInfo.h
@@ -1812,9 +1812,10 @@ class TargetTransformInfo {
                                          unsigned ChainSizeInBytes,
                                          VectorType *VecTy) const;
 
-  /// \returns True if the targets prefers fixed width vectorization if the
+  /// \returns True if the target prefers fixed width vectorization if the
   /// loop vectorizer's cost-model assigns an equal cost to the fixed and
   /// scalable version of the vectorized loop.
+  /// \p IsEpilogue is true if the decision is for the epilogue loop.
   LLVM_ABI bool preferFixedOverScalableIfEqualCost(bool IsEpilogue) const;
 
   /// \returns True if target prefers SLP vectorizer with altermate opcode
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-epilog-vect-vscale-tune.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-epilog-vect-vscale-tune.ll
index eaa48eafafea7..a158a25513ae5 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-epilog-vect-vscale-tune.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-epilog-vect-vscale-tune.ll
@@ -1,6 +1,9 @@
 ; RUN: opt -S -passes=loop-vectorize,instsimplify -force-vector-interleave=1 \
 ; RUN:   -mcpu=neoverse-v1 -sve-tail-folding=disabled < %s | FileCheck %s --check-prefix=CHECK-EPILOG
 ; RUN: opt -S -passes=loop-vectorize,instsimplify -force-vector-interleave=1 \
+; RUN:   -mcpu=neoverse-v1 -sve-tail-folding=disabled -sve-prefer-fixed-over-scalable-if-equal=false \
+; RUN:   < %s | FileCheck %s --check-prefix=CHECK-EPILOG-PREFER-SCALABLE
+; RUN: opt -S -passes=loop-vectorize,instsimplify -force-vector-interleave=1 \
 ; RUN:   -mcpu=neoverse-v2 < %s | FileCheck %s --check-prefix=CHECK-EPILOG-V2
 ; RUN: opt -S -passes=loop-vectorize,instsimplify -force-vector-interleave=1 \
 ; RUN:   -mcpu=cortex-x2 < %s | FileCheck %s --check-prefix=CHECK-NO-EPILOG
@@ -12,6 +15,10 @@ define void @foo(ptr noalias nocapture readonly %p, ptr noalias nocapture %q, i6
 ; CHECK-EPILOG:      vec.epilog.vector.body:
 ; CHECK-EPILOG:        load <8 x i16>
 
+; CHECK-EPILOG-PREFER-SCALABLE:      vec.epilog.ph:
+; CHECK-EPILOG-PREFER-SCALABLE:      vec.epilog.vector.body:
+; CHECK-EPILOG-PREFER-SCALABLE:        load <vscale x 4 x i16>
+
 ; The epilogue loop gets vectorised vscale x 2 x i16 wide.
 ; CHECK-EPILOG-V2:      vec.epilog.ph:
 ; CHECK-EPILOG-V2:      vec.epilog.vector.body:
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-epilog-vect.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-epilog-vect.ll
index b43208810daf0..707df785b2c76 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-epilog-vect.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-epilog-vect.ll
@@ -3,6 +3,9 @@
 ; RUN: opt < %s -passes=loop-vectorize -force-vector-interleave=2 -epilogue-vectorization-minimum-VF=0 -prefer-predicate-over-epilogue=scalar-epilogue \
 ; RUN:   -debug-only=loop-vectorize -force-target-instruction-cost=1 -S 2>%t | FileCheck %s --check-prefix=CHECK
 ; RUN: cat %t | FileCheck %s --check-prefix=DEBUG
+; RUN: opt < %s -passes=loop-vectorize -force-vector-interleave=2 -epilogue-vectorization-minimum-VF=0 -prefer-predicate-over-epilogue=scalar-epilogue \
+; RUN:   -debug-only=loop-vectorize -force-target-instruction-cost=1  -sve-prefer-fixed-over-scalable-if-equal=false -S 2>%t | FileCheck %s --check-prefix=CHECK-EPILOG-PREFER-SCALABLE
+; RUN: cat %t | FileCheck %s --check-prefix=DEBUG-EPILOG-PREFER-SCALABLE
 ; RUN: opt < %s -passes=loop-vectorize -force-vector-interleave=2 -epilogue-vectorization-force-VF=8 \
 ; RUN:   -debug-only=loop-vectorize -S 2>%t | FileCheck %s --check-prefix=CHECK-VF8
 ; RUN: cat %t | FileCheck %s --check-prefix=DEBUG-FORCED
@@ -13,6 +16,10 @@ target triple = "aarch64-linux-gnu"
 ; DEBUG: Create Skeleton for epilogue vectorized loop (first pass)
 ; DEBUG: Main Loop VF:vscale x 16, Main Loop UF:2, Epilogue Loop VF:8, Epilogue Loop UF:1
 
+; DEBUG-EPILOG-PREFER-SCALABLE: LV: Checking a loop in 'main_vf_vscale_x_16'
+; DEBUG-EPILOG-PREFER-SCALABLE: Create Skeleton for epilogue vectorized loop (first pass)
+; DEBUG-EPILOG-PREFER-SCALABLE: Main Loop VF:vscale x 16, Main Loop UF:2, Epilogue Loop VF:vscale x 8, Epilogue Loop UF:1
+
 ; DEBUG-FORCED: LV: Checking a loop in 'main_vf_vscale_x_16'
 ; DEBUG-FORCED: LEV: Epilogue vectorization factor is forced.
 ; DEBUG-FORCED: Create Skeleton for epilogue vectorized loop (first pass)
@@ -68,6 +75,65 @@ define void @main_vf_vscale_x_16(ptr %A) #0 {
 ; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
 ; CHECK:       for.body:
 ;
+; CHECK-EPILOG-PREFER-SCALABLE-LABEL: @main_vf_vscale_x_16(
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:  iter.check:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP1:%.*]] = shl nuw i64 [[TMP0]], 3
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1024, [[TMP1]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[VEC_EPILOG_SCALAR_PH:%.*]], label [[VECTOR_MAIN_LOOP_ITER_CHECK:%.*]]
+; CHECK-EPILOG-PREFER-SCALABLE:       vector.main.loop.iter.check:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP3:%.*]] = shl nuw i64 [[TMP2]], 5
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[MIN_ITERS_CHECK1:%.*]] = icmp ult i64 1024, [[TMP3]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br i1 [[MIN_ITERS_CHECK1]], label [[VEC_EPILOG_PH:%.*]], label [[VECTOR_PH:%.*]]
+; CHECK-EPILOG-PREFER-SCALABLE:       vector.ph:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP5:%.*]] = mul nuw i64 [[TMP4]], 32
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP5]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[N_VEC:%.*]] = sub i64 1024, [[N_MOD_VF]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br label [[VECTOR_BODY:%.*]]
+; CHECK-EPILOG-PREFER-SCALABLE:       vector.body:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP6:%.*]] = getelementptr inbounds i8, ptr [[A:%.*]], i64 [[INDEX]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP7:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP8:%.*]] = shl nuw i64 [[TMP7]], 4
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP9:%.*]] = getelementptr inbounds i8, ptr [[TMP6]], i64 [[TMP8]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    store <vscale x 16 x i8> splat (i8 1), ptr [[TMP6]], align 1
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    store <vscale x 16 x i8> splat (i8 1), ptr [[TMP9]], align 1
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP5]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP10:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br i1 [[TMP10]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
+; CHECK-EPILOG-PREFER-SCALABLE:       middle.block:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[CMP_N:%.*]] = icmp eq i64 1024, [[N_VEC]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[VEC_EPILOG_ITER_CHECK:%.*]]
+; CHECK-EPILOG-PREFER-SCALABLE:       vec.epilog.iter.check:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[N_VEC_REMAINING:%.*]] = sub i64 1024, [[N_VEC]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP11:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP12:%.*]] = shl nuw i64 [[TMP11]], 3
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[MIN_EPILOG_ITERS_CHECK:%.*]] = icmp ult i64 [[N_VEC_REMAINING]], [[TMP12]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br i1 [[MIN_EPILOG_ITERS_CHECK]], label [[VEC_EPILOG_SCALAR_PH]], label [[VEC_EPILOG_PH]]
+; CHECK-EPILOG-PREFER-SCALABLE:       vec.epilog.ph:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[VEC_EPILOG_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[VEC_EPILOG_ITER_CHECK]] ], [ 0, [[VECTOR_MAIN_LOOP_ITER_CHECK]] ]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP13:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP14:%.*]] = mul nuw i64 [[TMP13]], 8
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[N_MOD_VF2:%.*]] = urem i64 1024, [[TMP14]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[N_VEC3:%.*]] = sub i64 1024, [[N_MOD_VF2]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br label [[VEC_EPILOG_VECTOR_BODY:%.*]]
+; CHECK-EPILOG-PREFER-SCALABLE:       vec.epilog.vector.body:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[INDEX4:%.*]] = phi i64 [ [[VEC_EPILOG_RESUME_VAL]], [[VEC_EPILOG_PH]] ], [ [[INDEX_NEXT5:%.*]], [[VEC_EPILOG_VECTOR_BODY]] ]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP15:%.*]] = getelementptr inbounds i8, ptr [[A]], i64 [[INDEX4]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    store <vscale x 8 x i8> splat (i8 1), ptr [[TMP15]], align 1
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[INDEX_NEXT5]] = add nuw i64 [[INDEX4]], [[TMP14]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP16:%.*]] = icmp eq i64 [[INDEX_NEXT5]], [[N_VEC3]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br i1 [[TMP16]], label [[VEC_EPILOG_MIDDLE_BLOCK:%.*]], label [[VEC_EPILOG_VECTOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
+; CHECK-EPILOG-PREFER-SCALABLE:       vec.epilog.middle.block:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[CMP_N6:%.*]] = icmp eq i64 1024, [[N_VEC3]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br i1 [[CMP_N6]], label [[EXIT]], label [[VEC_EPILOG_SCALAR_PH]]
+; CHECK-EPILOG-PREFER-SCALABLE:       vec.epilog.scalar.ph:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC3]], [[VEC_EPILOG_MIDDLE_BLOCK]] ], [ [[N_VEC]], [[VEC_EPILOG_ITER_CHECK]] ], [ 0, [[ITER_CHECK:%.*]] ]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br label [[FOR_BODY:%.*]]
+; CHECK-EPILOG-PREFER-SCALABLE:       for.body:
+;
 ; CHECK-VF8-LABEL: @main_vf_vscale_x_16(
 ; CHECK-VF8-NEXT:  iter.check:
 ; CHECK-VF8-NEXT:    br i1 false, label [[VEC_EPILOG_SCALAR_PH:%.*]], label [[VECTOR_MAIN_LOOP_ITER_CHECK:%.*]]
@@ -161,6 +227,34 @@ define void @main_vf_vscale_x_2_no_epi_iteration(ptr %A) #0 vscale_range(8, 8) {
 ; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
 ; CHECK:       for.body:
 ;
+; CHECK-EPILOG-PREFER-SCALABLE-LABEL: @main_vf_vscale_x_2_no_epi_iteration(
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:  entry:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; CHECK-EPILOG-PREFER-SCALABLE:       vector.ph:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP1:%.*]] = mul nuw i64 [[TMP0]], 4
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP1]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[N_VEC:%.*]] = sub i64 1024, [[N_MOD_VF]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br label [[VECTOR_BODY:%.*]]
+; CHECK-EPILOG-PREFER-SCALABLE:       vector.body:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i64, ptr [[A:%.*]], i64 [[INDEX]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP3:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP4:%.*]] = shl nuw i64 [[TMP3]], 1
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i64, ptr [[TMP2]], i64 [[TMP4]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    store <vscale x 2 x i64> splat (i64 1), ptr [[TMP2]], align 1
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    store <vscale x 2 x i64> splat (i64 1), ptr [[TMP5]], align 1
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP1]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP6:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br i1 [[TMP6]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
+; CHECK-EPILOG-PREFER-SCALABLE:       middle.block:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[CMP_N:%.*]] = icmp eq i64 1024, [[N_VEC]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
+; CHECK-EPILOG-PREFER-SCALABLE:       scalar.ph:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br label [[FOR_BODY:%.*]]
+; CHECK-EPILOG-PREFER-SCALABLE:       for.body:
+;
 ; CHECK-VF8-LABEL: @main_vf_vscale_x_2_no_epi_iteration(
 ; CHECK-VF8-NEXT:  iter.check:
 ; CHECK-VF8-NEXT:    br i1 false, label [[VEC_EPILOG_SCALAR_PH:%.*]], label [[VECTOR_MAIN_LOOP_ITER_CHECK:%.*]]
@@ -293,6 +387,59 @@ define void @main_vf_vscale_x_2(ptr %A, i64 %n) #0 vscale_range(8, 8) {
 ; CHECK-NEXT:    br label [[FOR_BODY1:%.*]]
 ; CHECK:       for.body:
 ;
+; CHECK-EPILOG-PREFER-SCALABLE-LABEL: @main_vf_vscale_x_2(
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:  iter.check:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[N:%.*]], 8
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[VEC_EPILOG_SCALAR_PH:%.*]], label [[VECTOR_MAIN_LOOP_ITER_CHECK:%.*]]
+; CHECK-EPILOG-PREFER-SCALABLE:       vector.main.loop.iter.check:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP1:%.*]] = shl nuw i64 [[TMP0]], 2
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[MIN_ITERS_CHECK1:%.*]] = icmp ult i64 [[N]], [[TMP1]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br i1 [[MIN_ITERS_CHECK1]], label [[VEC_EPILOG_PH:%.*]], label [[VECTOR_PH:%.*]]
+; CHECK-EPILOG-PREFER-SCALABLE:       vector.ph:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP3:%.*]] = mul nuw i64 [[TMP2]], 4
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N]], [[TMP3]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[N_VEC:%.*]] = sub i64 [[N]], [[N_MOD_VF]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br label [[VECTOR_BODY:%.*]]
+; CHECK-EPILOG-PREFER-SCALABLE:       vector.body:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP4:%.*]] = getelementptr inbounds i64, ptr [[A:%.*]], i64 [[INDEX]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP5:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP6:%.*]] = shl nuw i64 [[TMP5]], 1
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP7:%.*]] = getelementptr inbounds i64, ptr [[TMP4]], i64 [[TMP6]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    store <vscale x 2 x i64> splat (i64 1), ptr [[TMP4]], align 1
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    store <vscale x 2 x i64> splat (i64 1), ptr [[TMP7]], align 1
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP3]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP8:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br i1 [[TMP8]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP7:![0-9]+]]
+; CHECK-EPILOG-PREFER-SCALABLE:       middle.block:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[CMP_N:%.*]] = icmp eq i64 [[N]], [[N_VEC]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[VEC_EPILOG_ITER_CHECK:%.*]]
+; CHECK-EPILOG-PREFER-SCALABLE:       vec.epilog.iter.check:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[N_VEC_REMAINING:%.*]] = sub i64 [[N]], [[N_VEC]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[MIN_EPILOG_ITERS_CHECK:%.*]] = icmp ult i64 [[N_VEC_REMAINING]], 8
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br i1 [[MIN_EPILOG_ITERS_CHECK]], label [[VEC_EPILOG_SCALAR_PH]], label [[VEC_EPILOG_PH]]
+; CHECK-EPILOG-PREFER-SCALABLE:       vec.epilog.ph:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[VEC_EPILOG_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[VEC_EPILOG_ITER_CHECK]] ], [ 0, [[VECTOR_MAIN_LOOP_ITER_CHECK]] ]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[N_MOD_VF2:%.*]] = urem i64 [[N]], 8
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[N_VEC3:%.*]] = sub i64 [[N]], [[N_MOD_VF2]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br label [[VEC_EPILOG_VECTOR_BODY:%.*]]
+; CHECK-EPILOG-PREFER-SCALABLE:       vec.epilog.vector.body:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[INDEX4:%.*]] = phi i64 [ [[VEC_EPILOG_RESUME_VAL]], [[VEC_EPILOG_PH]] ], [ [[INDEX_NEXT5:%.*]], [[VEC_EPILOG_VECTOR_BODY]] ]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP9:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[INDEX4]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    store <8 x i64> splat (i64 1), ptr [[TMP9]], align 1
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[INDEX_NEXT5]] = add nuw i64 [[INDEX4]], 8
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP10:%.*]] = icmp eq i64 [[INDEX_NEXT5]], [[N_VEC3]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br i1 [[TMP10]], label [[VEC_EPILOG_MIDDLE_BLOCK:%.*]], label [[VEC_EPILOG_VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
+; CHECK-EPILOG-PREFER-SCALABLE:       vec.epilog.middle.block:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[CMP_N6:%.*]] = icmp eq i64 [[N]], [[N_VEC3]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br i1 [[CMP_N6]], label [[EXIT]], label [[VEC_EPILOG_SCALAR_PH]]
+; CHECK-EPILOG-PREFER-SCALABLE:       vec.epilog.scalar.ph:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC3]], [[VEC_EPILOG_MIDDLE_BLOCK]] ], [ [[N_VEC]], [[VEC_EPILOG_ITER_CHECK]] ], [ 0, [[ITER_CHECK:%.*]] ]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br label [[FOR_BODY:%.*]]
+; CHECK-EPILOG-PREFER-SCALABLE:       for.body:
+;
 ; CHECK-VF8-LABEL: @main_vf_vscale_x_2(
 ; CHECK-VF8-NEXT:  iter.check:
 ; CHECK-VF8-NEXT:    [[MIN_ITERS_CHECK1:%.*]] = icmp ult i64 [[N:%.*]], 8
@@ -416,6 +563,68 @@ define void @test_pr57912_pointer_induction(ptr %start) #0 {
 ; CHECK-NEXT:    br label [[LOOP:%.*]]
 ; CHECK:       loop:
 ;
+; CHECK-EPILOG-PREFER-SCALABLE-LABEL: @test_pr57912_pointer_induction(
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:  iter.check:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP1:%.*]] = shl nuw i64 [[TMP0]], 3
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 10000, [[TMP1]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[VEC_EPILOG_SCALAR_PH:%.*]], label [[VECTOR_MAIN_LOOP_ITER_CHECK:%.*]]
+; CHECK-EPILOG-PREFER-SCALABLE:       vector.main.loop.iter.check:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP3:%.*]] = shl nuw i64 [[TMP2]], 5
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[MIN_ITERS_CHECK1:%.*]] = icmp ult i64 10000, [[TMP3]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br i1 [[MIN_ITERS_CHECK1]], label [[VEC_EPILOG_PH:%.*]], label [[VECTOR_PH:%.*]]
+; CHECK-EPILOG-PREFER-SCALABLE:       vector.ph:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP5:%.*]] = mul nuw i64 [[TMP4]], 32
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[N_MOD_VF:%.*]] = urem i64 10000, [[TMP5]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[N_VEC:%.*]] = sub i64 10000, [[N_MOD_VF]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br label [[VECTOR_BODY:%.*]]
+; CHECK-EPILOG-PREFER-SCALABLE:       vector.body:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[NEXT_GEP:%.*]] = getelementptr i8, ptr [[START:%.*]], i64 [[INDEX]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP6:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP7:%.*]] = shl nuw i64 [[TMP6]], 4
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP8:%.*]] = getelementptr i8, ptr [[NEXT_GEP]], i64 [[TMP7]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    store <vscale x 16 x i8> zeroinitializer, ptr [[NEXT_GEP]], align 1
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    store <vscale x 16 x i8> zeroinitializer, ptr [[TMP8]], align 1
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP5]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP9:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br i1 [[TMP9]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP10:![0-9]+]]
+; CHECK-EPILOG-PREFER-SCALABLE:       middle.block:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[CMP_N:%.*]] = icmp eq i64 10000, [[N_VEC]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[VEC_EPILOG_ITER_CHECK:%.*]]
+; CHECK-EPILOG-PREFER-SCALABLE:       vec.epilog.iter.check:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[IND_END:%.*]] = getelementptr i8, ptr [[START]], i64 [[N_VEC]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[N_VEC_REMAINING:%.*]] = sub i64 10000, [[N_VEC]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP10:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP11:%.*]] = shl nuw i64 [[TMP10]], 3
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[MIN_EPILOG_ITERS_CHECK:%.*]] = icmp ult i64 [[N_VEC_REMAINING]], [[TMP11]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br i1 [[MIN_EPILOG_ITERS_CHECK]], label [[VEC_EPILOG_SCALAR_PH]], label [[VEC_EPILOG_PH]]
+; CHECK-EPILOG-PREFER-SCALABLE:       vec.epilog.ph:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[VEC_EPILOG_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[VEC_EPILOG_ITER_CHECK]] ], [ 0, [[VECTOR_MAIN_LOOP_ITER_CHECK]] ]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP12:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP13:%.*]] = mul nuw i64 [[TMP12]], 8
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[N_MOD_VF2:%.*]] = urem i64 10000, [[TMP13]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[N_VEC3:%.*]] = sub i64 10000, [[N_MOD_VF2]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP14:%.*]] = getelementptr i8, ptr [[START]], i64 [[N_VEC3]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br label [[VEC_EPILOG_VECTOR_BODY:%.*]]
+; CHECK-EPILOG-PREFER-SCALABLE:       vec.epilog.vector.body:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[INDEX4:%.*]] = phi i64 [ [[VEC_EPILOG_RESUME_VAL]], [[VEC_EPILOG_PH]] ], [ [[INDEX_NEXT6:%.*]], [[VEC_EPILOG_VECTOR_BODY]] ]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[NEXT_GEP5:%.*]] = getelementptr i8, ptr [[START]], i64 [[INDEX4]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    store <vscale x 8 x i8> zeroinitializer, ptr [[NEXT_GEP5]], align 1
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[INDEX_NEXT6]] = add nuw i64 [[INDEX4]], [[TMP13]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP15:%.*]] = icmp eq i64 [[INDEX_NEXT6]], [[N_VEC3]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br i1 [[TMP15]], label [[VEC_EPILOG_MIDDLE_BLOCK:%.*]], label [[VEC_EPILOG_VECTOR_BODY]], !llvm.loop [[LOOP11:![0-9]+]]
+; CHECK-EPILOG-PREFER-SCALABLE:       vec.epilog.middle.block:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[CMP_N7:%.*]] = icmp eq i64 10000, [[N_VEC3]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br i1 [[CMP_N7]], label [[EXIT]], label [[VEC_EPILOG_SCALAR_PH]]
+; CHECK-EPILOG-PREFER-SCALABLE:       vec.epilog.scalar.ph:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC3]], [[VEC_EPILOG_MIDDLE_BLOCK]] ], [ [[N_VEC]], [[VEC_EPILOG_ITER_CHECK]] ], [ 0, [[ITER_CHECK:%.*]] ]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[BC_RESUME_VAL8:%.*]] = phi ptr [ [[TMP14]], [[VEC_EPILOG_MIDDLE_BLOCK]] ], [ [[IND_END]], [[VEC_EPILOG_ITER_CHECK]] ], [ [[START]], [[ITER_CHECK]] ]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br label [[LOOP:%.*]]
+; CHECK-EPILOG-PREFER-SCALABLE:       loop:
+;
 ; CHECK-VF8-LABEL: @test_pr57912_pointer_induction(
 ; CHECK-VF8-NEXT:  iter.check:
 ; CHECK-VF8-NEXT:    br i1 false, label [[VEC_EPILOG_SCALAR_PH:%.*]], label [[VECTOR_MAIN_LOOP_ITER_CHECK:%.*]]
@@ -557,6 +766,83 @@ define void @trip_count_vscale(ptr noalias %a, ptr noalias %b) vscale_range(1, 1
 ; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
 ; CHECK:       for.body:
 ;
+; CHECK-EPILOG-PREFER-SCALABLE-LABEL: @trip_count_vscale(
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:  iter.check:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[V:%.*]] = tail call i64 @llvm.vscale.i64()
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[N:%.*]] = mul nuw nsw i64 [[V]], 1033
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP1:%.*]] = shl nuw i64 [[TMP0]], 1
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br i1 false, label [[VEC_EPILOG_SCALAR_PH:%.*]], label [[VECTOR_MAIN_LOOP_ITER_CHECK:%.*]]
+; CHECK-EPILOG-PREFER-SCALABLE:       vector.main.loop.iter.check:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP3:%.*]] = shl nuw i64 [[TMP2]], 3
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[N]], [[TMP3]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[VEC_EPILOG_PH:%.*]], label [[VECTOR_PH:%.*]]
+; CHECK-EPILOG-PREFER-SCALABLE:       vector.ph:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP5:%.*]] = mul nuw i64 [[TMP4]], 8
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N]], [[TMP5]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[N_VEC:%.*]] = sub i64 [[N]], [[N_MOD_VF]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br label [[VECTOR_BODY:%.*]]
+; CHECK-EPILOG-PREFER-SCALABLE:       vector.body:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP6:%.*]] = getelementptr inbounds nuw float, ptr [[A:%.*]], i64 [[INDEX]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP7:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP8:%.*]] = shl nuw i64 [[TMP7]], 2
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP9:%.*]] = getelementptr inbounds nuw float, ptr [[TMP6]], i64 [[TMP8]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[WIDE_LOAD:%.*]] = load <vscale x 4 x float>, ptr [[TMP6]], align 4
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[WIDE_LOAD1:%.*]] = load <vscale x 4 x float>, ptr [[TMP9]], align 4
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP10:%.*]] = getelementptr inbounds nuw float, ptr [[B:%.*]], i64 [[INDEX]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP11:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP12:%.*]] = shl nuw i64 [[TMP11]], 2
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP13:%.*]] = getelementptr inbounds nuw float, ptr [[TMP10]], i64 [[TMP12]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[WIDE_LOAD2:%.*]] = load <vscale x 4 x float>, ptr [[TMP10]], align 4
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[WIDE_LOAD3:%.*]] = load <vscale x 4 x float>, ptr [[TMP13]], align 4
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP14:%.*]] = fmul <vscale x 4 x float> [[WIDE_LOAD]], [[WIDE_LOAD2]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP15:%.*]] = fmul <vscale x 4 x float> [[WIDE_LOAD1]], [[WIDE_LOAD3]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP16:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP17:%.*]] = shl nuw i64 [[TMP16]], 2
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP18:%.*]] = getelementptr inbounds nuw float, ptr [[TMP10]], i64 [[TMP17]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    store <vscale x 4 x float> [[TMP14]], ptr [[TMP10]], align 4
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    store <vscale x 4 x float> [[TMP15]], ptr [[TMP18]], align 4
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP5]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP19:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br i1 [[TMP19]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP13:![0-9]+]]
+; CHECK-EPILOG-PREFER-SCALABLE:       middle.block:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[CMP_N:%.*]] = icmp eq i64 [[N]], [[N_VEC]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[VEC_EPILOG_ITER_CHECK:%.*]]
+; CHECK-EPILOG-PREFER-SCALABLE:       vec.epilog.iter.check:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[N_VEC_REMAINING:%.*]] = sub i64 [[N]], [[N_VEC]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP20:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP21:%.*]] = shl nuw i64 [[TMP20]], 1
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[MIN_EPILOG_ITERS_CHECK:%.*]] = icmp ult i64 [[N_VEC_REMAINING]], [[TMP21]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br i1 [[MIN_EPILOG_ITERS_CHECK]], label [[VEC_EPILOG_SCALAR_PH]], label [[VEC_EPILOG_PH]]
+; CHECK-EPILOG-PREFER-SCALABLE:       vec.epilog.ph:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[VEC_EPILOG_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[VEC_EPILOG_ITER_CHECK]] ], [ 0, [[VECTOR_MAIN_LOOP_ITER_CHECK]] ]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP22:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP23:%.*]] = mul nuw i64 [[TMP22]], 2
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[N_MOD_VF4:%.*]] = urem i64 [[N]], [[TMP23]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[N_VEC5:%.*]] = sub i64 [[N]], [[N_MOD_VF4]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br label [[VEC_EPILOG_VECTOR_BODY:%.*]]
+; CHECK-EPILOG-PREFER-SCALABLE:       vec.epilog.vector.body:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[INDEX6:%.*]] = phi i64 [ [[VEC_EPILOG_RESUME_VAL]], [[VEC_EPILOG_PH]] ], [ [[INDEX_NEXT9:%.*]], [[VEC_EPILOG_VECTOR_BODY]] ]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP24:%.*]] = getelementptr inbounds nuw float, ptr [[A]], i64 [[INDEX6]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[WIDE_LOAD7:%.*]] = load <vscale x 2 x float>, ptr [[TMP24]], align 4
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP25:%.*]] = getelementptr inbounds nuw float, ptr [[B]], i64 [[INDEX6]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[WIDE_LOAD8:%.*]] = load <vscale x 2 x float>, ptr [[TMP25]], align 4
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP26:%.*]] = fmul <vscale x 2 x float> [[WIDE_LOAD7]], [[WIDE_LOAD8]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    store <vscale x 2 x float> [[TMP26]], ptr [[TMP25]], align 4
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[INDEX_NEXT9]] = add nuw i64 [[INDEX6]], [[TMP23]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP27:%.*]] = icmp eq i64 [[INDEX_NEXT9]], [[N_VEC5]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br i1 [[TMP27]], label [[VEC_EPILOG_MIDDLE_BLOCK:%.*]], label [[VEC_EPILOG_VECTOR_BODY]], !llvm.loop [[LOOP14:![0-9]+]]
+; CHECK-EPILOG-PREFER-SCALABLE:       vec.epilog.middle.block:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[CMP_N10:%.*]] = icmp eq i64 [[N]], [[N_VEC5]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br i1 [[CMP_N10]], label [[EXIT]], label [[VEC_EPILOG_SCALAR_PH]]
+; CHECK-EPILOG-PREFER-SCALABLE:       vec.epilog.scalar.ph:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC5]], [[VEC_EPILOG_MIDDLE_BLOCK]] ], [ [[N_VEC]], [[VEC_EPILOG_ITER_CHECK]] ], [ 0, [[ITER_CHECK:%.*]] ]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br label [[FOR_BODY:%.*]]
+; CHECK-EPILOG-PREFER-SCALABLE:       for.body:
+;
 ; CHECK-VF8-LABEL: @trip_count_vscale(
 ; CHECK-VF8-NEXT:  entry:
 ; CHECK-VF8-NEXT:    [[V:%.*]] = tail call i64 @llvm.vscale.i64()
@@ -692,6 +978,83 @@ define void @trip_count_vscale_no_epilogue_iterations(ptr noalias %a, ptr noalia
 ; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
 ; CHECK:       for.body:
 ;
+; CHECK-EPILOG-PREFER-SCALABLE-LABEL: @trip_count_vscale_no_epilogue_iterations(
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:  iter.check:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[V:%.*]] = tail call i64 @llvm.vscale.i64()
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[N:%.*]] = mul nuw nsw i64 [[V]], 1024
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP1:%.*]] = shl nuw i64 [[TMP0]], 1
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br i1 false, label [[VEC_EPILOG_SCALAR_PH:%.*]], label [[VECTOR_MAIN_LOOP_ITER_CHECK:%.*]]
+; CHECK-EPILOG-PREFER-SCALABLE:       vector.main.loop.iter.check:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP3:%.*]] = shl nuw i64 [[TMP2]], 3
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[N]], [[TMP3]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[VEC_EPILOG_PH:%.*]], label [[VECTOR_PH:%.*]]
+; CHECK-EPILOG-PREFER-SCALABLE:       vector.ph:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP5:%.*]] = mul nuw i64 [[TMP4]], 8
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N]], [[TMP5]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[N_VEC:%.*]] = sub i64 [[N]], [[N_MOD_VF]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br label [[VECTOR_BODY:%.*]]
+; CHECK-EPILOG-PREFER-SCALABLE:       vector.body:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP6:%.*]] = getelementptr inbounds nuw float, ptr [[A:%.*]], i64 [[INDEX]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP7:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP8:%.*]] = shl nuw i64 [[TMP7]], 2
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP9:%.*]] = getelementptr inbounds nuw float, ptr [[TMP6]], i64 [[TMP8]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[WIDE_LOAD:%.*]] = load <vscale x 4 x float>, ptr [[TMP6]], align 4
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[WIDE_LOAD1:%.*]] = load <vscale x 4 x float>, ptr [[TMP9]], align 4
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP10:%.*]] = getelementptr inbounds nuw float, ptr [[B:%.*]], i64 [[INDEX]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP11:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP12:%.*]] = shl nuw i64 [[TMP11]], 2
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP13:%.*]] = getelementptr inbounds nuw float, ptr [[TMP10]], i64 [[TMP12]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[WIDE_LOAD2:%.*]] = load <vscale x 4 x float>, ptr [[TMP10]], align 4
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[WIDE_LOAD3:%.*]] = load <vscale x 4 x float>, ptr [[TMP13]], align 4
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP14:%.*]] = fmul <vscale x 4 x float> [[WIDE_LOAD]], [[WIDE_LOAD2]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP15:%.*]] = fmul <vscale x 4 x float> [[WIDE_LOAD1]], [[WIDE_LOAD3]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP16:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP17:%.*]] = shl nuw i64 [[TMP16]], 2
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP18:%.*]] = getelementptr inbounds nuw float, ptr [[TMP10]], i64 [[TMP17]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    store <vscale x 4 x float> [[TMP14]], ptr [[TMP10]], align 4
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    store <vscale x 4 x float> [[TMP15]], ptr [[TMP18]], align 4
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP5]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP19:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br i1 [[TMP19]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP16:![0-9]+]]
+; CHECK-EPILOG-PREFER-SCALABLE:       middle.block:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[CMP_N:%.*]] = icmp eq i64 [[N]], [[N_VEC]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[VEC_EPILOG_ITER_CHECK:%.*]]
+; CHECK-EPILOG-PREFER-SCALABLE:       vec.epilog.iter.check:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[N_VEC_REMAINING:%.*]] = sub i64 [[N]], [[N_VEC]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP20:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP21:%.*]] = shl nuw i64 [[TMP20]], 1
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[MIN_EPILOG_ITERS_CHECK:%.*]] = icmp ult i64 [[N_VEC_REMAINING]], [[TMP21]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br i1 [[MIN_EPILOG_ITERS_CHECK]], label [[VEC_EPILOG_SCALAR_PH]], label [[VEC_EPILOG_PH]]
+; CHECK-EPILOG-PREFER-SCALABLE:       vec.epilog.ph:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[VEC_EPILOG_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[VEC_EPILOG_ITER_CHECK]] ], [ 0, [[VECTOR_MAIN_LOOP_ITER_CHECK]] ]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP22:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP23:%.*]] = mul nuw i64 [[TMP22]], 2
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[N_MOD_VF4:%.*]] = urem i64 [[N]], [[TMP23]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[N_VEC5:%.*]] = sub i64 [[N]], [[N_MOD_VF4]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br label [[VEC_EPILOG_VECTOR_BODY:%.*]]
+; CHECK-EPILOG-PREFER-SCALABLE:       vec.epilog.vector.body:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[INDEX6:%.*]] = phi i64 [ [[VEC_EPILOG_RESUME_VAL]], [[VEC_EPILOG_PH]] ], [ [[INDEX_NEXT9:%.*]], [[VEC_EPILOG_VECTOR_BODY]] ]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP24:%.*]] = getelementptr inbounds nuw float, ptr [[A]], i64 [[INDEX6]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[WIDE_LOAD7:%.*]] = load <vscale x 2 x float>, ptr [[TMP24]], align 4
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP25:%.*]] = getelementptr inbounds nuw float, ptr [[B]], i64 [[INDEX6]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[WIDE_LOAD8:%.*]] = load <vscale x 2 x float>, ptr [[TMP25]], align 4
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP26:%.*]] = fmul <vscale x 2 x float> [[WIDE_LOAD7]], [[WIDE_LOAD8]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    store <vscale x 2 x float> [[TMP26]], ptr [[TMP25]], align 4
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[INDEX_NEXT9]] = add nuw i64 [[INDEX6]], [[TMP23]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[TMP27:%.*]] = icmp eq i64 [[INDEX_NEXT9]], [[N_VEC5]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br i1 [[TMP27]], label [[VEC_EPILOG_MIDDLE_BLOCK:%.*]], label [[VEC_EPILOG_VECTOR_BODY]], !llvm.loop [[LOOP17:![0-9]+]]
+; CHECK-EPILOG-PREFER-SCALABLE:       vec.epilog.middle.block:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[CMP_N10:%.*]] = icmp eq i64 [[N]], [[N_VEC5]]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br i1 [[CMP_N10]], label [[EXIT]], label [[VEC_EPILOG_SCALAR_PH]]
+; CHECK-EPILOG-PREFER-SCALABLE:       vec.epilog.scalar.ph:
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC5]], [[VEC_EPILOG_MIDDLE_BLOCK]] ], [ [[N_VEC]], [[VEC_EPILOG_ITER_CHECK]] ], [ 0, [[ITER_CHECK:%.*]] ]
+; CHECK-EPILOG-PREFER-SCALABLE-NEXT:    br label [[FOR_BODY:%.*]]
+; CHECK-EPILOG-PREFER-SCALABLE:       for.body:
+;
 ; CHECK-VF8-LABEL: @trip_count_vscale_no_epilogue_iterations(
 ; CHECK-VF8-NEXT:  entry:
 ; CHECK-VF8-NEXT:    [[V:%.*]] = tail call i64 @llvm.vscale.i64()



More information about the llvm-commits mailing list