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

via llvm-commits llvm-commits at lists.llvm.org
Wed Aug 27 00:00:33 PDT 2025


llvmbot wrote:


<!--LLVM PR SUMMARY COMMENT-->

@llvm/pr-subscribers-backend-aarch64

Author: Hassnaa Hamdi (hassnaaHamdi)

<details>
<summary>Changes</summary>

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.


---

Patch is 127.67 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/155546.diff


14 Files Affected:

- (modified) llvm/include/llvm/Analysis/TargetTransformInfo.h (+1-1) 
- (modified) llvm/include/llvm/Analysis/TargetTransformInfoImpl.h (+3-1) 
- (modified) llvm/lib/Analysis/TargetTransformInfo.cpp (+3-2) 
- (modified) llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp (+7-1) 
- (modified) llvm/lib/Target/AArch64/AArch64TargetTransformInfo.h (+1-1) 
- (modified) llvm/lib/Transforms/Vectorize/LoopVectorizationPlanner.h (+4-2) 
- (modified) llvm/lib/Transforms/Vectorize/LoopVectorize.cpp (+10-13) 
- (modified) llvm/test/Transforms/LoopVectorize/AArch64/induction-costs-sve.ll (+63-24) 
- (modified) llvm/test/Transforms/LoopVectorize/AArch64/interleaving-reduction.ll (+103-76) 
- (modified) llvm/test/Transforms/LoopVectorize/AArch64/low_trip_count_predicates.ll (+20-32) 
- (modified) llvm/test/Transforms/LoopVectorize/AArch64/reduction-recurrence-costs-sve.ll (+51-15) 
- (modified) llvm/test/Transforms/LoopVectorize/AArch64/store-costs-sve.ll (+8-18) 
- (modified) llvm/test/Transforms/LoopVectorize/AArch64/sve-epilog-vect-vscale-tune.ll (+1-1) 
- (modified) llvm/test/Transforms/LoopVectorize/AArch64/sve-epilog-vect.ll (+268-303) 


``````````diff
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..f073e2c259632 100644
--- a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -6017,7 +6017,13 @@ static bool containsDecreasingPointers(Loop *TheLoop,
   return false;
 }
 
-bool AArch64TTIImpl::preferFixedOverScalableIfEqualCost() const {
+bool AArch64TTIImpl::preferFixedOverScalableIfEqualCost(bool IsEpilogue) const {
+  // 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;
   if (SVEPreferFixedOverScalableIfEqualCost.getNumOccurrences())
     return SVEPreferFixedOverScalableIfEqualCost;
   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 838476dcae661..0f6f991e866a3 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorizationPlanner.h
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorizationPlanner.h
@@ -613,13 +613,15 @@ 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 7fc87a0b49f70..677e1b4096645 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -3939,7 +3939,8 @@ 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;
 
@@ -3963,7 +3964,7 @@ 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,
@@ -4001,10 +4002,11 @@ 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(
@@ -4398,16 +4400,10 @@ bool LoopVectorizationCostModel::isEpilogueVectorizationProfitable(
   if (TTI.getMaxInterleaveFactor(VF) <= 1)
     return false;
 
-  // TODO: PR #108190 introduced a discrepancy between fixed-width and scalable
-  // VFs when deciding profitability.
-  // See related "TODO: extend to support scalable VFs." in
-  // selectEpilogueVectorizationFactor.
-  unsigned Multiplier = VF.isFixed() ? IC : 1;
   unsigned MinVFThreshold = EpilogueVectorizationMinVF.getNumOccurrences() > 0
                                 ? EpilogueVectorizationMinVF
                                 : TTI.getEpilogueVectorizationMinVF();
-  return estimateElementCount(VF * Multiplier, VScaleForTuning) >=
-         MinVFThreshold;
+  return estimateElementCount(VF * IC, VScaleForTuning) >= MinVFThreshold;
 }
 
 VectorizationFactor LoopVectorizationPlanner::selectEpilogueVectorizationFactor(
@@ -4511,7 +4507,8 @@ 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/induction-costs-sve.ll b/llvm/test/Transforms/LoopVectorize/AArch64/induction-costs-sve.ll
index 137e07336fd50..80130305aaf04 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/induction-costs-sve.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/induction-costs-sve.ll
@@ -8,24 +8,29 @@ target triple = "arm64-apple-macosx14.0.0"
 define void @iv_casts(ptr %dst, ptr %src, i32 %x, i64 %N) #0 {
 ; DEFAULT-LABEL: define void @iv_casts(
 ; DEFAULT-SAME: ptr [[DST:%.*]], ptr [[SRC:%.*]], i32 [[X:%.*]], i64 [[N:%.*]]) #[[ATTR0:[0-9]+]] {
-; DEFAULT-NEXT:  [[ENTRY:.*]]:
+; DEFAULT-NEXT:  [[ITER_CHECK:.*]]:
 ; DEFAULT-NEXT:    [[SRC2:%.*]] = ptrtoint ptr [[SRC]] to i64
 ; DEFAULT-NEXT:    [[DST1:%.*]] = ptrtoint ptr [[DST]] to i64
 ; DEFAULT-NEXT:    [[TMP0:%.*]] = add i64 [[N]], 1
 ; DEFAULT-NEXT:    [[TMP1:%.*]] = call i64 @llvm.vscale.i64()
-; DEFAULT-NEXT:    [[TMP2:%.*]] = shl nuw i64 [[TMP1]], 4
+; DEFAULT-NEXT:    [[TMP2:%.*]] = shl nuw i64 [[TMP1]], 2
 ; DEFAULT-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP0]], [[TMP2]]
-; DEFAULT-NEXT:    br i1 [[MIN_ITERS_CHECK]], label %[[SCALAR_PH:.*]], label %[[VECTOR_MEMCHECK:.*]]
+; DEFAULT-NEXT:    br i1 [[MIN_ITERS_CHECK]], label %[[VEC_EPILOG_SCALAR_PH:.*]], label %[[VECTOR_MEMCHECK:.*]]
 ; DEFAULT:       [[VECTOR_MEMCHECK]]:
 ; DEFAULT-NEXT:    [[TMP3:%.*]] = call i64 @llvm.vscale.i64()
 ; DEFAULT-NEXT:    [[TMP4:%.*]] = mul nuw i64 [[TMP3]], 8
 ; DEFAULT-NEXT:    [[TMP5:%.*]] = mul i64 [[TMP4]], 2
 ; DEFAULT-NEXT:    [[TMP6:%.*]] = sub i64 [[DST1]], [[SRC2]]
 ; DEFAULT-NEXT:    [[DIFF_CHECK:%.*]] = icmp ult i64 [[TMP6]], [[TMP5]]
-; DEFAULT-NEXT:    br i1 [[DIFF_CHECK]], label %[[SCALAR_PH]], label %[[VECTOR_PH:.*]]
-; DEFAULT:       [[VECTOR_PH]]:
+; DEFAULT-NEXT:    br i1 [[DIFF_CHECK]], label %[[VEC_EPILOG_SCALAR_PH]], label %[[VECTOR_MAIN_LOOP_ITER_CHECK:.*]]
+; DEFAULT:       [[VECTOR_MAIN_LOOP_ITER_CHECK]]:
 ; DEFAULT-NEXT:    [[TMP9:%.*]] = call i64 @llvm.vscale.i64()
-; DEFAULT-NEXT:    [[TMP10:%.*]] = mul nuw i64 [[TMP9]], 16
+; DEFAULT-NEXT:    [[TMP8:%.*]] = shl nuw i64 [[TMP9]], 4
+; DEFAULT-NEXT:    [[MIN_ITERS_CHECK3:%.*]] = icmp ult i64 [[TMP0]], [[TMP8]]
+; DEFAULT-NEXT:    br i1 [[MIN_ITERS_CHECK3]], label %[[VEC_EPILOG_PH:.*]], label %[[VECTOR_PH:.*]]
+; DEFAULT:       [[VECTOR_PH]]:
+; DEFAULT-NEXT:    [[TMP11:%.*]] = call i64 @llvm.vscale.i64()
+; DEFAULT-NEXT:    [[TMP10:%.*]] = mul nuw i64 [[TMP11]], 16
 ; DEFAULT-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[TMP0]], [[TMP10]]
 ; DEFAULT-NEXT:    [[N_VEC:%.*]] = sub i64 [[TMP0]], [[N_MOD_VF]]
 ; DEFAULT-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 8 x i32> poison, i32 [[X]], i64 0
@@ -63,25 +68,59 @@ define void @iv_casts(ptr %dst, ptr %src, i32 %x, i64 %N) #0 {
 ; DEFAULT-NEXT:    br i1 [[TMP44]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
 ; DEFAULT:       [[MIDDLE_BLOCK]]:
 ; DEFAULT-NEXT:    [[CMP_N:%.*]] = icmp eq i64 [[TMP0]], [[N_VEC]]
-; DEFAULT-NEXT:    br i1 [[CMP_N]], label %[[EXIT:.*]], label %[[SCALAR_PH]]
-; DEFAULT:       [[SCALAR_PH]]:
-; DEFAULT-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], %[[MIDDLE_BLOCK]] ], [ 0, %[[ENTRY]] ], [ 0, %[[VECTOR_MEMCHECK]] ]
+; 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 [[TMP0]], [[N_VEC]]
+; DEFAULT-NEXT:    [[TMP47:%.*]] = call i64 @llvm.vscale.i64()
+; DEFAULT-NEXT:    [[TMP48:%.*]] = shl nuw i64 [[TMP47]], 2
+; DEFAULT-NEXT:    [[MIN_EPILOG_ITERS_CHECK:%.*]] = icmp ult i64 [[N_VEC_REMAINING]], [[TMP48]]
+; 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:    [[TMP49:%.*]] = call i64 @llvm.vscale.i64()
+; DEFAULT-NEXT:    [[TMP50:%.*]] = mul nuw i64 [[TMP49]], 4
+; DEFAULT-NEXT:    [[N_MOD_VF5:%.*]] = urem i64 [[TMP0]], [[TMP50]]
+; DEFAULT-NEXT:    [[N_VEC6:%.*]] = sub i64 [[TMP0]], [[N_MOD_VF5]]
+; DEFAULT-NEXT:    [[BROADCAST_SPLATINSERT7:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[X]], i64 0
+; DEFAULT-NEXT:    [[BROADCAST_SPLAT8:%.*]] = shufflevector <vscale x 4 x i32> [[BROADCAST_SPLATINSERT7]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
+; DEFAULT-NEXT:    [[TMP51:%.*]] = trunc <vscale x 4 x i32> [[BROADCAST_SPLAT8]] to <vscale x 4 x i16>
+; DEFAULT-NEXT:    br label %[[VEC_EPILOG_VECTOR_BODY:.*]]
+; DEFAULT:       [[VEC_EPILOG_VECTOR_BODY]]:
+; DEFAULT-NEXT:    [[IV:%.*]] = phi i64 [ [[VEC_EPILOG_RESUME_VAL]], %[[VEC_EPILOG_PH]] ], [ [[INDEX_NEXT11:%.*]], %[[VEC_EPILOG_VECTOR_BODY]] ]
+; DEFAULT-NEXT:    [[GEP_SRC:%.*]] = getelementptr i8, ptr [[SRC]], i64 [[IV]]
+; DEFAULT-NEXT:    [[WIDE_LOAD10:%.*]] = load <vscale x 4 x i8>, ptr [[GEP_SRC]], align 1
+; DEFAULT-NEXT:    [[TMP39:%.*]] = zext <vscale x 4 x i8> [[WIDE_LOAD10]] to <vscale x 4 x i16>
+; DEFAULT-NEXT:    [[TMP40:%.*]] = mul <vscale x 4 x i16> [[TMP39]], [[TMP51]]
+; DEFAULT-NEXT:    [[TMP52:%.*]] = zext <vscale x 4 x i8> [[WIDE_LOAD10]] to <vscale x 4 x i16>
+; DEFAULT-NEXT:    [[TMP53:%.*]] = or <vscale x 4 x i16> [[TMP40]], [[TMP52]]
+; DEFAULT-NEXT:    [[TMP54:%.*]] = lshr <vscale x 4 x i16> [[TMP53]], splat (i16 1)
+; DEFAULT-NEXT:    [[TMP55:%.*]] = trunc <vscale x 4 x i16> [[TMP54]] to <vscale x 4 x i8>
+; DEFAULT-NEXT:    [[TMP45:%.*]] = getelementptr i8, ptr [[DST]], i64 [[IV]]
+; DEFAULT-NEXT:    store <vscale x 4 x i8> [[TMP55]], ptr [[TMP45]], align 1
+; DEFAULT-NEXT:    [[INDEX_NEXT11]] = add nuw i64 [[IV]], [[TMP50]]
+; DEFAULT-NEXT:    [[TMP46:%.*]] = icmp eq i64 [[INDEX_NEXT11]], [[N_VEC6]]
+; DEFAULT-NEXT:    br i1 [[TMP46]], label %[[VEC_EPILOG_MIDDLE_BLOCK:.*]], label %[[VEC_EPILOG_VECTOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
+; DEFAULT:       [[VEC_EPILOG_MIDDLE_BLOCK]]:
+; DEFAULT-NEXT:    [[CMP_N12:%.*]] = icmp eq i64 [[TMP0]], [[N_VEC6]]
+; DEFAULT-NEXT:    br i1 [[CMP_N12]], label %[[EXIT]], label %[[VEC_EPILOG_SCALAR_PH]]
+; DEFAULT:       [[VEC_EPILOG_SCALAR_PH]]:
+; DEFAULT-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC6]], %[[VEC_EPILOG_MIDDLE_BLOCK]] ], [ [[N_VEC]], %[[VEC_EPILOG_ITER_CHECK]] ], [ 0, %[[VECTOR_MEMCHECK]] ], [ 0, %[[ITER_CHECK]] ]
 ; DEFAULT-NEXT:    br label %[[LOOP:.*]]
 ; DEFAULT:       [[LOOP]]:
-; DEFAULT-NEXT:    [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], %[[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], %[[LOOP]] ]
-; DEFAULT-NEXT:    [[GEP_SRC:%.*]] = getelementptr i8, ptr [[SRC]], i64 [[IV]]
-; DEFAULT-NEXT:    [[L:%.*]] = load i8, ptr [[GEP_SRC]], align 1
+; DEFAULT-NEXT:    [[IV1:%.*]] = phi i64 [ [[BC_RESUME_VAL]], %[[VEC_EPILOG_SCALAR_PH]] ], [ [[IV_NEXT:%.*]], %[[LOOP]] ]
+; DEFAULT-NEXT:    [[GEP_SRC1:%.*]] = getelementptr i8, ptr [[SRC]], i64 [[IV1]]
+; DEFAULT-NEXT:    [[L:%.*]] = load i8, ptr [[GEP_SRC1]], align 1
 ; DEFAULT-NEXT:    [[L_EXT:%.*]] = zext i8 [[L]] to i32
 ; DEFAULT-NEXT:    [[MUL16_US:%.*]] = mul i32 [[L_EXT]], [[X]]
-; DEFAULT-NEXT:    [[IV_NEXT]] = add i64 [[IV]], 1
+; DEFAULT-NEXT:    [[IV_NEXT]] = add i64 [[IV1]], 1
 ; DEFAULT-NEXT:    [[CONV25_US:%.*]] = zext i8 [[L]] to i32
 ; DEFAULT-NEXT:    [[ADD34_US:%.*]] = or i32 [[MUL16_US]], [[CONV25_US]]
 ; DEFAULT-NEXT:    [[SHR35_US:%.*]] = lshr i32 [[ADD34_US]], 1
 ; DEFAULT-NEXT:    [[CONV36_US:%.*]] = trunc i32 [[SHR35_US]] to i8
-; DEFAULT-NEXT:    [[GEP_DST:%.*]] = getelementptr i8, ptr [[DST]], i64 [[IV]]
+; DEFAULT-NEXT:    [[GEP_DST:%.*]] = getelementptr i8, ptr [[DST]], i64 [[IV1]]
 ; DEFAULT-NEXT:    store i8 [[CONV36_US]], ptr [[GEP_DST]], align 1
-; DEFAULT-NEXT:    [[EC:%.*]] = icmp eq i64 [[IV]], [[N]]
-; DEFAULT-NEXT:    br i1 [[EC]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP3:![0-9]+]]
+; DEFAULT-NEXT:    [[EC:%.*]] = icmp eq i64 [[IV1]], [[N]]
+; DEFAULT-NEXT:    br i1 [[EC]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP4:![0-9]+]]
 ; DEFAULT:       [[EXIT]]:
 ; DEFAULT-NEXT:    ret void
 ;
@@ -218,7 +257,7 @@ define void @iv_trunc(i32 %x, ptr %dst, i64 %N) #0 {
 ; DEFAULT-NEXT:    store i32 1, ptr [[TMP21]], align 4
 ; DEFAULT-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 2
 ; DEFAULT-NEXT:    [[TMP22:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
-; DEFAULT-NEXT:    br i1 [[TMP22]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
+; DEFAULT-NEXT:    br i1 [[TMP22]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
 ; DEFAULT:       [[MIDDLE_BLOCK]]:
 ; DEFAULT-NEXT:    [[CMP_N:%.*]] = icmp eq i64 [[TMP0]], [[N_VEC]]
 ; DEFAULT-NEXT:    br i1 [[CMP_N]], label %[[EXIT:.*]], label %[[SCALAR_PH]]
@@ -234,7 +273,7 @@ define void @iv_trunc(i32 %x, ptr %dst, i64 %N) #0 {
 ; DEFAULT-NEXT:    store i32 1, ptr [[GEP]], align 4
 ; DEFAULT-NEXT:    [[IV_NEXT]] = add i64 [[IV]], 1
 ; DEFAULT-NEXT:    [[EC:%.*]] = icmp eq i64 [[IV]], [[N]]
-; DEFAULT-NEXT:    br i1 [[EC]], label %[[EXIT]], label %[[FOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
+; DEFAULT-NEXT:    br i1 [[EC]], label %[[EXIT]], label %[[FOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
 ; DEFAULT:       [[EXIT]]:
 ; DEFAULT-NEXT:    ret void
 ;
@@ -382,7 +421,7 @@ define void @trunc_ivs_and_store(i32 %x, ptr %dst, i64 %N) #0 {
 ; DEFAULT-NEXT:    store i32 [[TMP15]], ptr [[TMP24]], align 4
 ; DEFAULT-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 2
 ; DEFAULT-NEXT:    [[TMP25:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
-; DEFAULT-NEXT:    br i1 [[TMP25]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
+; DEFAULT-NEXT:    br i1 [[TMP25]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP7:![0-9]+]]
 ; DEFAULT:       [[MIDDLE_BLOCK]]:
 ; DEFAULT-NEXT:    [[CMP_N:%.*]] = icmp eq i64 [[TMP0]], [[N_VEC]]
 ; DEFAULT-NEXT:    br i1 [[CMP_N]], label %[[EXIT:.*]], label %[[SCALAR_PH]]
@@ -401,7 +440,7 @@ define void @trunc_ivs_and_store(i32 %x, ptr %dst, i64 %N) #0 {
 ; DEFAULT-NEXT:    store i32 [[IV_2]], ptr [[GEP]], align 4
 ; DEFAULT-NEXT:    [[IV_1_NEXT]] = add i64 [[IV_1]], 1
 ; DEFAULT-NEXT:    [[EXITCOND_3_NOT:%.*]] = icmp eq i64 [[IV_1]], [[N]]
-; DEFAULT-NEXT:    br i1 [[EXITCOND_3_NOT]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP7:![0-9]+]]
+; DEFAULT-NEXT:    br i1 [[EXITCOND_3_NOT]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP8:![0-9]+]]
 ; DEFAULT:       [[EXIT]]:
 ; DEFAULT-NEXT:    ret void
 ;
@@ -574,7 +613,7 @@ define void @ivs_trunc_and_ext(i32 %x, ptr %dst, i64 %N) #0 {
 ; DEFAULT-NEXT:    store i32 [[TMP14]], ptr [[TMP23]], align 4
 ; DEFAULT-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 2
 ; DEFAULT-NEXT:    [[TMP24:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
-; DEFAULT-NEXT:    br i1 [[TMP24]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
+; DEFAULT-NEXT:    br i1 [[TMP24]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP9:![0-9]+]]
 ; DEFAULT:       [[MIDDLE_BLOCK]]:
 ; DEFAULT-NEXT:    [[CMP_N:%.*]] = icmp eq i64 [[TMP0]], [[N_VEC]]
 ; DEFAULT-NEXT:    br i1 [[CMP_N]], label %[[EXIT:.*]], label %[[SCALAR_PH]]
@@ -593,7 +632,7 @@ define void @ivs_trunc_and_ext(i32 %x, ptr %dst, i64 %N) #0 {
 ; DEFAULT-NEXT:    store i32 [[IV_2]], ptr [[GEP]], align 4
 ; DEFAULT-NEXT:    [[IV_1_NEXT]] = add i64 [[IV_1]], 1
 ; DEFAULT-NEXT:    [[EC:%.*]] = icmp eq i64 [[IV_1]], [[N]]
-; DEFAULT-NEXT:    br i1 [[EC]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP9:![0-9]+]]
+; DEFAULT-NEXT:    br i1 [[EC]], label %[[EX...
[truncated]

``````````

</details>


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


More information about the llvm-commits mailing list