[llvm] LAA: strip unit-stride check in getPtrStride (PR #122879)

via llvm-commits llvm-commits at lists.llvm.org
Tue Jan 14 01:59:21 PST 2025


llvmbot wrote:


<!--LLVM PR SUMMARY COMMENT-->

@llvm/pr-subscribers-llvm-analysis

Author: Ramkumar Ramachandra (artagnon)

<details>
<summary>Changes</summary>

Strip an unnecessary unit-stride check in getPtrStride, when checking whether null pointer dereference is undefined. This patch is similar in spirit to a353e25 (Don't require Stride == 1/-1 for inbounds pointer AddRecs nowrap.), and has the effect of removing redundant SCEV checks.

-- 8< --
Requires rebase after #<!-- -->122876 is landed.

---

Patch is 64.81 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/122879.diff


7 Files Affected:

- (modified) llvm/lib/Analysis/LoopAccessAnalysis.cpp (+4-5) 
- (modified) llvm/test/Analysis/LoopAccessAnalysis/nusw-predicates.ll (-3) 
- (modified) llvm/test/Analysis/LoopAccessAnalysis/wrapping-pointer-versioning.ll (-4) 
- (modified) llvm/test/Transforms/LoopVectorize/AArch64/conditional-branches-cost.ll (+37-91) 
- (modified) llvm/test/Transforms/LoopVectorize/X86/interleave-cost.ll (+24-208) 
- (modified) llvm/test/Transforms/LoopVersioning/incorrect-phi.ll (+40-8) 
- (modified) llvm/test/Transforms/LoopVersioning/wrapping-pointer-versioning.ll (+12-51) 


``````````diff
diff --git a/llvm/lib/Analysis/LoopAccessAnalysis.cpp b/llvm/lib/Analysis/LoopAccessAnalysis.cpp
index 2a68979add666d..4122afcc1db3c8 100644
--- a/llvm/lib/Analysis/LoopAccessAnalysis.cpp
+++ b/llvm/lib/Analysis/LoopAccessAnalysis.cpp
@@ -1520,12 +1520,11 @@ llvm::getPtrStride(PredicatedScalarEvolution &PSE, Type *AccessTy, Value *Ptr,
       GEP && GEP->hasNoUnsignedSignedWrap())
     return Stride;
 
-  // If the null pointer is undefined, then a access sequence which would
-  // otherwise access it can be assumed not to unsigned wrap.  Note that this
-  // assumes the object in memory is aligned to the natural alignment.
+  // If the null pointer dereference is undefined, then a access sequence which
+  // would otherwise access it can be assumed not to unsigned wrap. Note that
+  // this assumes the object in memory is aligned to the natural alignment.
   unsigned AddrSpace = Ty->getPointerAddressSpace();
-  if (!NullPointerIsDefined(Lp->getHeader()->getParent(), AddrSpace) &&
-      (Stride == 1 || Stride == -1))
+  if (!NullPointerIsDefined(Lp->getHeader()->getParent(), AddrSpace))
     return Stride;
 
   if (Assume) {
diff --git a/llvm/test/Analysis/LoopAccessAnalysis/nusw-predicates.ll b/llvm/test/Analysis/LoopAccessAnalysis/nusw-predicates.ll
index 5234d8f107271a..f2c1fb3e22b071 100644
--- a/llvm/test/Analysis/LoopAccessAnalysis/nusw-predicates.ll
+++ b/llvm/test/Analysis/LoopAccessAnalysis/nusw-predicates.ll
@@ -19,7 +19,6 @@ define void @int_and_pointer_predicate(ptr %v, i32 %N) {
 ; CHECK-NEXT:      Non vectorizable stores to invariant address were not found in loop.
 ; CHECK-NEXT:      SCEV assumptions:
 ; CHECK-NEXT:      {0,+,1}<%loop> Added Flags: <nusw>
-; CHECK-NEXT:      {%v,+,4}<%loop> Added Flags: <nusw>
 ; CHECK-EMPTY:
 ; CHECK-NEXT:      Expressions re-written:
 ;
@@ -93,8 +92,6 @@ define void @int_and_multiple_pointer_predicates(ptr %v, ptr %w, i32 %N) {
 ; CHECK-NEXT:      Non vectorizable stores to invariant address were not found in loop.
 ; CHECK-NEXT:      SCEV assumptions:
 ; CHECK-NEXT:      {0,+,1}<%loop> Added Flags: <nusw>
-; CHECK-NEXT:      {%v,+,4}<%loop> Added Flags: <nusw>
-; CHECK-NEXT:      {%w,+,4}<%loop> Added Flags: <nusw>
 ; CHECK-EMPTY:
 ; CHECK-NEXT:      Expressions re-written:
 ;
diff --git a/llvm/test/Analysis/LoopAccessAnalysis/wrapping-pointer-versioning.ll b/llvm/test/Analysis/LoopAccessAnalysis/wrapping-pointer-versioning.ll
index 71c20bc2b2a824..457c85d2d7f916 100644
--- a/llvm/test/Analysis/LoopAccessAnalysis/wrapping-pointer-versioning.ll
+++ b/llvm/test/Analysis/LoopAccessAnalysis/wrapping-pointer-versioning.ll
@@ -39,7 +39,6 @@ define void @f1(ptr noalias %a, ptr noalias %b, i64 %N) {
 ; CHECK-NEXT:      Non vectorizable stores to invariant address were not found in loop.
 ; CHECK-NEXT:      SCEV assumptions:
 ; CHECK-NEXT:      {0,+,2}<%for.body> Added Flags: <nusw>
-; CHECK-NEXT:      {%a,+,4}<%for.body> Added Flags: <nusw>
 ; CHECK-EMPTY:
 ; CHECK-NEXT:      Expressions re-written:
 ; CHECK-NEXT:      [PSE] %arrayidxA = getelementptr i16, ptr %a, i64 %mul_ext:
@@ -115,7 +114,6 @@ define void @f2(ptr noalias %a, ptr noalias %b, i64 %N) {
 ; CHECK-NEXT:      Non vectorizable stores to invariant address were not found in loop.
 ; CHECK-NEXT:      SCEV assumptions:
 ; CHECK-NEXT:      {(2 * (trunc i64 %N to i32)),+,-2}<%for.body> Added Flags: <nusw>
-; CHECK-NEXT:      {((4 * (zext i31 (trunc i64 %N to i31) to i64))<nuw><nsw> + %a),+,-4}<%for.body> Added Flags: <nusw>
 ; CHECK-EMPTY:
 ; CHECK-NEXT:      Expressions re-written:
 ; CHECK-NEXT:      [PSE] %arrayidxA = getelementptr i16, ptr %a, i64 %mul_ext:
@@ -176,7 +174,6 @@ define void @f3(ptr noalias %a, ptr noalias %b, i64 %N) {
 ; CHECK-NEXT:      Non vectorizable stores to invariant address were not found in loop.
 ; CHECK-NEXT:      SCEV assumptions:
 ; CHECK-NEXT:      {0,+,2}<%for.body> Added Flags: <nssw>
-; CHECK-NEXT:      {%a,+,4}<%for.body> Added Flags: <nusw>
 ; CHECK-EMPTY:
 ; CHECK-NEXT:      Expressions re-written:
 ; CHECK-NEXT:      [PSE] %arrayidxA = getelementptr i16, ptr %a, i64 %mul_ext:
@@ -233,7 +230,6 @@ define void @f4(ptr noalias %a, ptr noalias %b, i64 %N) {
 ; CHECK-NEXT:      Non vectorizable stores to invariant address were not found in loop.
 ; CHECK-NEXT:      SCEV assumptions:
 ; CHECK-NEXT:      {(2 * (trunc i64 %N to i32)),+,-2}<%for.body> Added Flags: <nssw>
-; CHECK-NEXT:      {((2 * (sext i32 (2 * (trunc i64 %N to i32)) to i64))<nsw> + %a),+,-4}<%for.body> Added Flags: <nusw>
 ; CHECK-EMPTY:
 ; CHECK-NEXT:      Expressions re-written:
 ; CHECK-NEXT:      [PSE] %arrayidxA = getelementptr i16, ptr %a, i64 %mul_ext:
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/conditional-branches-cost.ll b/llvm/test/Transforms/LoopVectorize/AArch64/conditional-branches-cost.ll
index caa98d766a8c34..e6f1099f12b39b 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/conditional-branches-cost.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/conditional-branches-cost.ll
@@ -1120,35 +1120,8 @@ define void @test_conditional_interleave_group (ptr noalias %src.1, ptr noalias
 ; DEFAULT-SAME: ptr noalias [[SRC_1:%.*]], ptr noalias [[SRC_2:%.*]], ptr noalias [[SRC_3:%.*]], ptr noalias [[SRC_4:%.*]], ptr noalias [[DST:%.*]], i64 [[N:%.*]]) #[[ATTR3:[0-9]+]] {
 ; DEFAULT-NEXT:  entry:
 ; DEFAULT-NEXT:    [[TMP0:%.*]] = add i64 [[N]], 1
-; DEFAULT-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP0]], 32
-; DEFAULT-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_SCEVCHECK:%.*]]
-; DEFAULT:       vector.scevcheck:
-; DEFAULT-NEXT:    [[SCEVGEP:%.*]] = getelementptr i8, ptr [[DST]], i64 4
-; DEFAULT-NEXT:    [[MUL:%.*]] = call { i64, i1 } @llvm.umul.with.overflow.i64(i64 16, i64 [[N]])
-; DEFAULT-NEXT:    [[MUL_RESULT:%.*]] = extractvalue { i64, i1 } [[MUL]], 0
-; DEFAULT-NEXT:    [[MUL_OVERFLOW:%.*]] = extractvalue { i64, i1 } [[MUL]], 1
-; DEFAULT-NEXT:    [[TMP1:%.*]] = sub i64 0, [[MUL_RESULT]]
-; DEFAULT-NEXT:    [[TMP2:%.*]] = getelementptr i8, ptr [[SCEVGEP]], i64 [[MUL_RESULT]]
-; DEFAULT-NEXT:    [[TMP3:%.*]] = icmp ult ptr [[TMP2]], [[SCEVGEP]]
-; DEFAULT-NEXT:    [[TMP4:%.*]] = or i1 [[TMP3]], [[MUL_OVERFLOW]]
-; DEFAULT-NEXT:    [[SCEVGEP1:%.*]] = getelementptr i8, ptr [[DST]], i64 8
-; DEFAULT-NEXT:    [[MUL2:%.*]] = call { i64, i1 } @llvm.umul.with.overflow.i64(i64 16, i64 [[N]])
-; DEFAULT-NEXT:    [[MUL_RESULT3:%.*]] = extractvalue { i64, i1 } [[MUL2]], 0
-; DEFAULT-NEXT:    [[MUL_OVERFLOW4:%.*]] = extractvalue { i64, i1 } [[MUL2]], 1
-; DEFAULT-NEXT:    [[TMP5:%.*]] = sub i64 0, [[MUL_RESULT3]]
-; DEFAULT-NEXT:    [[TMP6:%.*]] = getelementptr i8, ptr [[SCEVGEP1]], i64 [[MUL_RESULT3]]
-; DEFAULT-NEXT:    [[TMP7:%.*]] = icmp ult ptr [[TMP6]], [[SCEVGEP1]]
-; DEFAULT-NEXT:    [[TMP8:%.*]] = or i1 [[TMP7]], [[MUL_OVERFLOW4]]
-; DEFAULT-NEXT:    [[MUL5:%.*]] = call { i64, i1 } @llvm.umul.with.overflow.i64(i64 16, i64 [[N]])
-; DEFAULT-NEXT:    [[MUL_RESULT6:%.*]] = extractvalue { i64, i1 } [[MUL5]], 0
-; DEFAULT-NEXT:    [[MUL_OVERFLOW7:%.*]] = extractvalue { i64, i1 } [[MUL5]], 1
-; DEFAULT-NEXT:    [[TMP9:%.*]] = sub i64 0, [[MUL_RESULT6]]
-; DEFAULT-NEXT:    [[TMP10:%.*]] = getelementptr i8, ptr [[DST]], i64 [[MUL_RESULT6]]
-; DEFAULT-NEXT:    [[TMP11:%.*]] = icmp ult ptr [[TMP10]], [[DST]]
-; DEFAULT-NEXT:    [[TMP12:%.*]] = or i1 [[TMP11]], [[MUL_OVERFLOW7]]
-; DEFAULT-NEXT:    [[TMP13:%.*]] = or i1 [[TMP4]], [[TMP8]]
-; DEFAULT-NEXT:    [[TMP14:%.*]] = or i1 [[TMP13]], [[TMP12]]
-; DEFAULT-NEXT:    br i1 [[TMP14]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
+; DEFAULT-NEXT:    [[TMP14:%.*]] = icmp ult i64 [[TMP0]], 8
+; DEFAULT-NEXT:    br i1 [[TMP14]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
 ; DEFAULT:       vector.ph:
 ; DEFAULT-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[TMP0]], 8
 ; DEFAULT-NEXT:    [[N_VEC:%.*]] = sub i64 [[TMP0]], [[N_MOD_VF]]
@@ -1190,7 +1163,7 @@ define void @test_conditional_interleave_group (ptr noalias %src.1, ptr noalias
 ; DEFAULT:       pred.store.continue:
 ; DEFAULT-NEXT:    [[TMP31:%.*]] = extractelement <8 x i1> [[TMP22]], i32 1
 ; DEFAULT-NEXT:    br i1 [[TMP31]], label [[PRED_STORE_IF14:%.*]], label [[PRED_STORE_CONTINUE15:%.*]]
-; DEFAULT:       pred.store.if14:
+; DEFAULT:       pred.store.if7:
 ; DEFAULT-NEXT:    [[TMP32:%.*]] = extractelement <8 x ptr> [[TMP23]], i32 1
 ; DEFAULT-NEXT:    store float 0.000000e+00, ptr [[TMP32]], align 4
 ; DEFAULT-NEXT:    [[TMP33:%.*]] = extractelement <8 x ptr> [[TMP23]], i32 1
@@ -1202,10 +1175,10 @@ define void @test_conditional_interleave_group (ptr noalias %src.1, ptr noalias
 ; DEFAULT-NEXT:    [[TMP37:%.*]] = extractelement <8 x ptr> [[TMP23]], i32 1
 ; DEFAULT-NEXT:    store float 0.000000e+00, ptr [[TMP37]], align 4
 ; DEFAULT-NEXT:    br label [[PRED_STORE_CONTINUE15]]
-; DEFAULT:       pred.store.continue15:
+; DEFAULT:       pred.store.continue8:
 ; DEFAULT-NEXT:    [[TMP38:%.*]] = extractelement <8 x i1> [[TMP22]], i32 2
 ; DEFAULT-NEXT:    br i1 [[TMP38]], label [[PRED_STORE_IF16:%.*]], label [[PRED_STORE_CONTINUE17:%.*]]
-; DEFAULT:       pred.store.if16:
+; DEFAULT:       pred.store.if9:
 ; DEFAULT-NEXT:    [[TMP39:%.*]] = extractelement <8 x ptr> [[TMP23]], i32 2
 ; DEFAULT-NEXT:    store float 0.000000e+00, ptr [[TMP39]], align 4
 ; DEFAULT-NEXT:    [[TMP40:%.*]] = extractelement <8 x ptr> [[TMP23]], i32 2
@@ -1217,10 +1190,10 @@ define void @test_conditional_interleave_group (ptr noalias %src.1, ptr noalias
 ; DEFAULT-NEXT:    [[TMP44:%.*]] = extractelement <8 x ptr> [[TMP23]], i32 2
 ; DEFAULT-NEXT:    store float 0.000000e+00, ptr [[TMP44]], align 4
 ; DEFAULT-NEXT:    br label [[PRED_STORE_CONTINUE17]]
-; DEFAULT:       pred.store.continue17:
+; DEFAULT:       pred.store.continue10:
 ; DEFAULT-NEXT:    [[TMP45:%.*]] = extractelement <8 x i1> [[TMP22]], i32 3
 ; DEFAULT-NEXT:    br i1 [[TMP45]], label [[PRED_STORE_IF18:%.*]], label [[PRED_STORE_CONTINUE19:%.*]]
-; DEFAULT:       pred.store.if18:
+; DEFAULT:       pred.store.if11:
 ; DEFAULT-NEXT:    [[TMP46:%.*]] = extractelement <8 x ptr> [[TMP23]], i32 3
 ; DEFAULT-NEXT:    store float 0.000000e+00, ptr [[TMP46]], align 4
 ; DEFAULT-NEXT:    [[TMP47:%.*]] = extractelement <8 x ptr> [[TMP23]], i32 3
@@ -1232,10 +1205,10 @@ define void @test_conditional_interleave_group (ptr noalias %src.1, ptr noalias
 ; DEFAULT-NEXT:    [[TMP51:%.*]] = extractelement <8 x ptr> [[TMP23]], i32 3
 ; DEFAULT-NEXT:    store float 0.000000e+00, ptr [[TMP51]], align 4
 ; DEFAULT-NEXT:    br label [[PRED_STORE_CONTINUE19]]
-; DEFAULT:       pred.store.continue19:
+; DEFAULT:       pred.store.continue12:
 ; DEFAULT-NEXT:    [[TMP52:%.*]] = extractelement <8 x i1> [[TMP22]], i32 4
 ; DEFAULT-NEXT:    br i1 [[TMP52]], label [[PRED_STORE_IF20:%.*]], label [[PRED_STORE_CONTINUE21:%.*]]
-; DEFAULT:       pred.store.if20:
+; DEFAULT:       pred.store.if13:
 ; DEFAULT-NEXT:    [[TMP53:%.*]] = extractelement <8 x ptr> [[TMP23]], i32 4
 ; DEFAULT-NEXT:    store float 0.000000e+00, ptr [[TMP53]], align 4
 ; DEFAULT-NEXT:    [[TMP54:%.*]] = extractelement <8 x ptr> [[TMP23]], i32 4
@@ -1247,10 +1220,10 @@ define void @test_conditional_interleave_group (ptr noalias %src.1, ptr noalias
 ; DEFAULT-NEXT:    [[TMP58:%.*]] = extractelement <8 x ptr> [[TMP23]], i32 4
 ; DEFAULT-NEXT:    store float 0.000000e+00, ptr [[TMP58]], align 4
 ; DEFAULT-NEXT:    br label [[PRED_STORE_CONTINUE21]]
-; DEFAULT:       pred.store.continue21:
+; DEFAULT:       pred.store.continue14:
 ; DEFAULT-NEXT:    [[TMP59:%.*]] = extractelement <8 x i1> [[TMP22]], i32 5
 ; DEFAULT-NEXT:    br i1 [[TMP59]], label [[PRED_STORE_IF22:%.*]], label [[PRED_STORE_CONTINUE23:%.*]]
-; DEFAULT:       pred.store.if22:
+; DEFAULT:       pred.store.if15:
 ; DEFAULT-NEXT:    [[TMP60:%.*]] = extractelement <8 x ptr> [[TMP23]], i32 5
 ; DEFAULT-NEXT:    store float 0.000000e+00, ptr [[TMP60]], align 4
 ; DEFAULT-NEXT:    [[TMP61:%.*]] = extractelement <8 x ptr> [[TMP23]], i32 5
@@ -1262,10 +1235,10 @@ define void @test_conditional_interleave_group (ptr noalias %src.1, ptr noalias
 ; DEFAULT-NEXT:    [[TMP65:%.*]] = extractelement <8 x ptr> [[TMP23]], i32 5
 ; DEFAULT-NEXT:    store float 0.000000e+00, ptr [[TMP65]], align 4
 ; DEFAULT-NEXT:    br label [[PRED_STORE_CONTINUE23]]
-; DEFAULT:       pred.store.continue23:
+; DEFAULT:       pred.store.continue16:
 ; DEFAULT-NEXT:    [[TMP66:%.*]] = extractelement <8 x i1> [[TMP22]], i32 6
 ; DEFAULT-NEXT:    br i1 [[TMP66]], label [[PRED_STORE_IF24:%.*]], label [[PRED_STORE_CONTINUE25:%.*]]
-; DEFAULT:       pred.store.if24:
+; DEFAULT:       pred.store.if17:
 ; DEFAULT-NEXT:    [[TMP67:%.*]] = extractelement <8 x ptr> [[TMP23]], i32 6
 ; DEFAULT-NEXT:    store float 0.000000e+00, ptr [[TMP67]], align 4
 ; DEFAULT-NEXT:    [[TMP68:%.*]] = extractelement <8 x ptr> [[TMP23]], i32 6
@@ -1277,10 +1250,10 @@ define void @test_conditional_interleave_group (ptr noalias %src.1, ptr noalias
 ; DEFAULT-NEXT:    [[TMP72:%.*]] = extractelement <8 x ptr> [[TMP23]], i32 6
 ; DEFAULT-NEXT:    store float 0.000000e+00, ptr [[TMP72]], align 4
 ; DEFAULT-NEXT:    br label [[PRED_STORE_CONTINUE25]]
-; DEFAULT:       pred.store.continue25:
+; DEFAULT:       pred.store.continue18:
 ; DEFAULT-NEXT:    [[TMP73:%.*]] = extractelement <8 x i1> [[TMP22]], i32 7
 ; DEFAULT-NEXT:    br i1 [[TMP73]], label [[PRED_STORE_IF26:%.*]], label [[PRED_STORE_CONTINUE27]]
-; DEFAULT:       pred.store.if26:
+; DEFAULT:       pred.store.if19:
 ; DEFAULT-NEXT:    [[TMP74:%.*]] = extractelement <8 x ptr> [[TMP23]], i32 7
 ; DEFAULT-NEXT:    store float 0.000000e+00, ptr [[TMP74]], align 4
 ; DEFAULT-NEXT:    [[TMP75:%.*]] = extractelement <8 x ptr> [[TMP23]], i32 7
@@ -1292,7 +1265,7 @@ define void @test_conditional_interleave_group (ptr noalias %src.1, ptr noalias
 ; DEFAULT-NEXT:    [[TMP79:%.*]] = extractelement <8 x ptr> [[TMP23]], i32 7
 ; DEFAULT-NEXT:    store float 0.000000e+00, ptr [[TMP79]], align 4
 ; DEFAULT-NEXT:    br label [[PRED_STORE_CONTINUE27]]
-; DEFAULT:       pred.store.continue27:
+; DEFAULT:       pred.store.continue20:
 ; DEFAULT-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 8
 ; DEFAULT-NEXT:    [[VEC_IND_NEXT]] = add <8 x i64> [[VEC_IND]], splat (i64 8)
 ; DEFAULT-NEXT:    [[TMP80:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
@@ -1301,7 +1274,7 @@ define void @test_conditional_interleave_group (ptr noalias %src.1, ptr noalias
 ; 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, [[VECTOR_SCEVCHECK]] ], [ 0, [[ENTRY:%.*]] ]
+; DEFAULT-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
 ; DEFAULT-NEXT:    br label [[LOOP_HEADER:%.*]]
 ; DEFAULT:       loop.header:
 ; DEFAULT-NEXT:    [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], [[LOOP_LATCH:%.*]] ]
@@ -1336,33 +1309,6 @@ define void @test_conditional_interleave_group (ptr noalias %src.1, ptr noalias
 ; PRED-NEXT:  entry:
 ; PRED-NEXT:    [[TMP0:%.*]] = add i64 [[N]], 1
 ; PRED-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_SCEVCHECK:%.*]]
-; PRED:       vector.scevcheck:
-; PRED-NEXT:    [[SCEVGEP:%.*]] = getelementptr i8, ptr [[DST]], i64 4
-; PRED-NEXT:    [[MUL:%.*]] = call { i64, i1 } @llvm.umul.with.overflow.i64(i64 16, i64 [[N]])
-; PRED-NEXT:    [[MUL_RESULT:%.*]] = extractvalue { i64, i1 } [[MUL]], 0
-; PRED-NEXT:    [[MUL_OVERFLOW:%.*]] = extractvalue { i64, i1 } [[MUL]], 1
-; PRED-NEXT:    [[TMP1:%.*]] = sub i64 0, [[MUL_RESULT]]
-; PRED-NEXT:    [[TMP2:%.*]] = getelementptr i8, ptr [[SCEVGEP]], i64 [[MUL_RESULT]]
-; PRED-NEXT:    [[TMP3:%.*]] = icmp ult ptr [[TMP2]], [[SCEVGEP]]
-; PRED-NEXT:    [[TMP4:%.*]] = or i1 [[TMP3]], [[MUL_OVERFLOW]]
-; PRED-NEXT:    [[SCEVGEP1:%.*]] = getelementptr i8, ptr [[DST]], i64 8
-; PRED-NEXT:    [[MUL2:%.*]] = call { i64, i1 } @llvm.umul.with.overflow.i64(i64 16, i64 [[N]])
-; PRED-NEXT:    [[MUL_RESULT3:%.*]] = extractvalue { i64, i1 } [[MUL2]], 0
-; PRED-NEXT:    [[MUL_OVERFLOW4:%.*]] = extractvalue { i64, i1 } [[MUL2]], 1
-; PRED-NEXT:    [[TMP5:%.*]] = sub i64 0, [[MUL_RESULT3]]
-; PRED-NEXT:    [[TMP6:%.*]] = getelementptr i8, ptr [[SCEVGEP1]], i64 [[MUL_RESULT3]]
-; PRED-NEXT:    [[TMP7:%.*]] = icmp ult ptr [[TMP6]], [[SCEVGEP1]]
-; PRED-NEXT:    [[TMP8:%.*]] = or i1 [[TMP7]], [[MUL_OVERFLOW4]]
-; PRED-NEXT:    [[MUL5:%.*]] = call { i64, i1 } @llvm.umul.with.overflow.i64(i64 16, i64 [[N]])
-; PRED-NEXT:    [[MUL_RESULT6:%.*]] = extractvalue { i64, i1 } [[MUL5]], 0
-; PRED-NEXT:    [[MUL_OVERFLOW7:%.*]] = extractvalue { i64, i1 } [[MUL5]], 1
-; PRED-NEXT:    [[TMP9:%.*]] = sub i64 0, [[MUL_RESULT6]]
-; PRED-NEXT:    [[TMP10:%.*]] = getelementptr i8, ptr [[DST]], i64 [[MUL_RESULT6]]
-; PRED-NEXT:    [[TMP11:%.*]] = icmp ult ptr [[TMP10]], [[DST]]
-; PRED-NEXT:    [[TMP12:%.*]] = or i1 [[TMP11]], [[MUL_OVERFLOW7]]
-; PRED-NEXT:    [[TMP13:%.*]] = or i1 [[TMP4]], [[TMP8]]
-; PRED-NEXT:    [[TMP14:%.*]] = or i1 [[TMP13]], [[TMP12]]
-; PRED-NEXT:    br i1 [[TMP14]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
 ; PRED:       vector.ph:
 ; PRED-NEXT:    [[N_RND_UP:%.*]] = add i64 [[TMP0]], 7
 ; PRED-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], 8
@@ -1373,9 +1319,9 @@ define void @test_conditional_interleave_group (ptr noalias %src.1, ptr noalias
 ; PRED-NEXT:    [[ACTIVE_LANE_MASK_ENTRY:%.*]] = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i64(i64 0, i64 [[TMP0]])
 ; PRED-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; PRED:       vector.body:
-; PRED-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[PRED_STORE_CONTINUE27:%.*]] ]
-; PRED-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = phi <8 x i1> [ [[ACTIVE_LANE_MASK_ENTRY]], [[VECTOR_PH]] ], [ [[ACTIVE_LANE_MASK_NEXT:%.*]], [[PRED_STORE_CONTINUE27]] ]
-; PRED-NEXT:    [[VEC_IND:%.*]] = phi <8 x i64> [ <i64 0, i64 1, i64 2, i64 3, i64 4, i64 5, i64 6, i64 7>, [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[PRED_STORE_CONTINUE27]] ]
+; PRED-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_SCEVCHECK]] ], [ [[INDEX_NEXT:%.*]], [[PRED_STORE_CONTINUE27:%.*]] ]
+; PRED-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = phi <8 x i1> [ [[ACTIVE_LANE_MASK_ENTRY]], [[VECTOR_SCEVCHECK]] ], [ [[ACTIVE_LANE_MASK_NEXT:%.*]], [[PRED_STORE_CONTINUE27]] ]
+; PRED-NEXT:    [[VEC_IND:%.*]] = phi <8 x i64> [ <i64 0, i64 1, i64 2, i64 3, i64 4, i64 5, i64 6, i64 7>, [[VECTOR_SCEVCHECK]] ], [ [[VEC_IND_NEXT:%.*]], [[PRED_STORE_CONTINUE27]] ]
 ; PRED-NEXT:    [[TMP18:%.*]] = load float, ptr [[SRC_1]], align 4
 ; PRED-NEXT:    [[BROADCAST_SPLATINSERT8:%.*]] = insertelement <8 x float> poison, float [[TMP18]], i64 0
 ; PRED-NEXT:    [[BROADCAST_SPLAT9:%.*]] = shufflevector <8 x float> [[BROADCAST_SPLATINSERT8]], <8 x float> poison, <8 x i32> zeroinitializer
@@ -1411,7 +1357,7 @@ define void @test_conditional_interleave_group (ptr noalias %src.1, ptr noalias
 ; PRED:       pred.store.continue:
 ; PRED-NEXT:    [[TMP35:%.*]] = extractelement <8 x i1> [[TMP26]], i32 1
 ; PRED-NEXT:    br i1 [[TMP35]], label [[PRED_STORE_IF14:%.*]], label [[PRED_STORE_CONTINUE15:%.*]]
-; PRED:       pred.store.if14:
+; PRED:       pred.store.if7:
 ; PRED-NEXT:    [[TMP36:%.*]] = extractelement <8 x ptr> [[TMP27]], i32 1
 ; PRED-NEXT:    store float 0.000000e+00, ptr [[TMP36]], align 4
 ; PRED-NEXT:    [[TMP37:%.*]] = extractelement <8 x ptr> [[TMP27]], i32 1
@@ -1423,10 +1369,10 @@ define void @test_conditional_interleave_group (ptr noalias %src.1, ptr noalias
 ; PRED-NEXT:    [[TMP41:%.*]] = extractelement <8 x ptr> [[TMP27]], i32 1
 ; PRED-NEXT:    store float 0.000000e+00, ptr [[TMP41]], align 4
 ; PRED-NEXT:    br label [[PRED_STORE_CONTINUE15]]
-; PRED:       pred.store.continue15:
+; PRED:       pred.store.continue8:
 ; PRED-NEXT:    [[TMP42:%.*]] = extractelement <8 x i1> [[TMP26]], i32 2
 ; PRED-NEXT:    br i1 [[TMP42]], label [[PRED_STORE_IF16:%.*]], label [[PRED_STORE_CONTINUE17:%.*]]
-; PRED:       pred.store.if16:
+; PRED:       pred.store.if9:
 ; PRED-NEXT:    [[TMP43:%.*]] = extractelement <8 x ptr> [[TMP27]], i32 2
 ; PRED-NEXT:    store float 0.000000e+00, ptr [[TMP43]], align 4
 ; PRED-NEXT:    [[TMP44:%.*]] = extractelement <8 x ptr> [[TMP27]], i32 2
@@ -1438,10 +1384,10 @@ define void @test_conditional_interleave_group (ptr noalias %src.1, ptr noalias
 ; PRED-NEXT:    [[TMP48:%.*]] = extractelem...
[truncated]

``````````

</details>


https://github.com/llvm/llvm-project/pull/122879


More information about the llvm-commits mailing list