[llvm] SCEV: teach isImpliedViaOperations about samesign (PR #124270)
Ramkumar Ramachandra via llvm-commits
llvm-commits at lists.llvm.org
Thu Feb 6 03:58:54 PST 2025
https://github.com/artagnon updated https://github.com/llvm/llvm-project/pull/124270
>From 57e945e8cf88580162ec8d4124b81f17b89f0be1 Mon Sep 17 00:00:00 2001
From: Ramkumar Ramachandra <ramkumar.ramachandra at codasip.com>
Date: Fri, 24 Jan 2025 13:19:29 +0000
Subject: [PATCH 1/2] SCEV: pre-commit implied-via-division tests
---
.../ScalarEvolution/implied-via-division.ll | 164 ++++++++++++++----
1 file changed, 131 insertions(+), 33 deletions(-)
diff --git a/llvm/test/Analysis/ScalarEvolution/implied-via-division.ll b/llvm/test/Analysis/ScalarEvolution/implied-via-division.ll
index a1d30406095ec58..ef23e37972e6103 100644
--- a/llvm/test/Analysis/ScalarEvolution/implied-via-division.ll
+++ b/llvm/test/Analysis/ScalarEvolution/implied-via-division.ll
@@ -2,12 +2,10 @@
; RUN: opt < %s -disable-output -passes="print<scalar-evolution>" \
; RUN: -scalar-evolution-classify-expressions=0 2>&1 | FileCheck %s
-declare void @llvm.experimental.guard(i1, ...)
-
-define void @test_1(i32 %n) nounwind {
-; Prove that (n > 1) ===> (n / 2 > 0).
-; CHECK-LABEL: 'test_1'
-; CHECK-NEXT: Determining loop execution counts for: @test_1
+define void @implied1(i32 %n) {
+; Prove that (n s> 1) ===> (n / 2 s> 0).
+; CHECK-LABEL: 'implied1'
+; CHECK-NEXT: Determining loop execution counts for: @implied1
; CHECK-NEXT: Loop %header: backedge-taken count is (-1 + %n.div.2)<nsw>
; CHECK-NEXT: Loop %header: constant max backedge-taken count is i32 1073741822
; CHECK-NEXT: Loop %header: symbolic max backedge-taken count is (-1 + %n.div.2)<nsw>
@@ -29,10 +27,35 @@ exit:
ret void
}
-define void @test_1neg(i32 %n) nounwind {
-; Prove that (n > 0) =\=> (n / 2 > 0).
-; CHECK-LABEL: 'test_1neg'
-; CHECK-NEXT: Determining loop execution counts for: @test_1neg
+define void @implied1_samesign(i32 %n) {
+; Prove that (n > 1) ===> (n / 2 s> 0).
+; CHECK-LABEL: 'implied1_samesign'
+; CHECK-NEXT: Determining loop execution counts for: @implied1_samesign
+; CHECK-NEXT: Loop %header: backedge-taken count is (-1 + (1 smax %n.div.2))<nsw>
+; CHECK-NEXT: Loop %header: constant max backedge-taken count is i32 1073741822
+; CHECK-NEXT: Loop %header: symbolic max backedge-taken count is (-1 + (1 smax %n.div.2))<nsw>
+; CHECK-NEXT: Loop %header: Trip multiple is 1
+;
+entry:
+ %cmp1 = icmp samesign ugt i32 %n, 1
+ %n.div.2 = sdiv i32 %n, 2
+ call void @llvm.assume(i1 %cmp1)
+ br label %header
+
+header:
+ %indvar = phi i32 [ %indvar.next, %header ], [ 0, %entry ]
+ %indvar.next = add i32 %indvar, 1
+ %exitcond = icmp sgt i32 %n.div.2, %indvar.next
+ br i1 %exitcond, label %header, label %exit
+
+exit:
+ ret void
+}
+
+define void @implied1_neg(i32 %n) {
+; Prove that (n s> 0) =\=> (n / 2 s> 0).
+; CHECK-LABEL: 'implied1_neg'
+; CHECK-NEXT: Determining loop execution counts for: @implied1_neg
; CHECK-NEXT: Loop %header: backedge-taken count is (-1 + (1 smax %n.div.2))<nsw>
; CHECK-NEXT: Loop %header: constant max backedge-taken count is i32 1073741822
; CHECK-NEXT: Loop %header: symbolic max backedge-taken count is (-1 + (1 smax %n.div.2))<nsw>
@@ -54,10 +77,10 @@ exit:
ret void
}
-define void @test_2(i32 %n) nounwind {
-; Prove that (n >= 2) ===> (n / 2 > 0).
-; CHECK-LABEL: 'test_2'
-; CHECK-NEXT: Determining loop execution counts for: @test_2
+define void @implied2(i32 %n) {
+; Prove that (n s>= 2) ===> (n / 2 s> 0).
+; CHECK-LABEL: 'implied2'
+; CHECK-NEXT: Determining loop execution counts for: @implied2
; CHECK-NEXT: Loop %header: backedge-taken count is (-1 + %n.div.2)<nsw>
; CHECK-NEXT: Loop %header: constant max backedge-taken count is i32 1073741822
; CHECK-NEXT: Loop %header: symbolic max backedge-taken count is (-1 + %n.div.2)<nsw>
@@ -79,10 +102,35 @@ exit:
ret void
}
-define void @test_2neg(i32 %n) nounwind {
-; Prove that (n >= 1) =\=> (n / 2 > 0).
-; CHECK-LABEL: 'test_2neg'
-; CHECK-NEXT: Determining loop execution counts for: @test_2neg
+define void @implied2_samesign(i32 %n) {
+; Prove that (n >= 2) ===> (n / 2 s> 0).
+; CHECK-LABEL: 'implied2_samesign'
+; CHECK-NEXT: Determining loop execution counts for: @implied2_samesign
+; CHECK-NEXT: Loop %header: backedge-taken count is (-1 + (1 smax %n.div.2))<nsw>
+; CHECK-NEXT: Loop %header: constant max backedge-taken count is i32 1073741822
+; CHECK-NEXT: Loop %header: symbolic max backedge-taken count is (-1 + (1 smax %n.div.2))<nsw>
+; CHECK-NEXT: Loop %header: Trip multiple is 1
+;
+entry:
+ %cmp1 = icmp samesign uge i32 %n, 2
+ %n.div.2 = sdiv i32 %n, 2
+ call void @llvm.assume(i1 %cmp1)
+ br label %header
+
+header:
+ %indvar = phi i32 [ %indvar.next, %header ], [ 0, %entry ]
+ %indvar.next = add i32 %indvar, 1
+ %exitcond = icmp sgt i32 %n.div.2, %indvar.next
+ br i1 %exitcond, label %header, label %exit
+
+exit:
+ ret void
+}
+
+define void @implied2_neg(i32 %n) {
+; Prove that (n s>= 1) =\=> (n / 2 s> 0).
+; CHECK-LABEL: 'implied2_neg'
+; CHECK-NEXT: Determining loop execution counts for: @implied2_neg
; CHECK-NEXT: Loop %header: backedge-taken count is (-1 + (1 smax %n.div.2))<nsw>
; CHECK-NEXT: Loop %header: constant max backedge-taken count is i32 1073741822
; CHECK-NEXT: Loop %header: symbolic max backedge-taken count is (-1 + (1 smax %n.div.2))<nsw>
@@ -104,10 +152,10 @@ exit:
ret void
}
-define void @test_3(i32 %n) nounwind {
-; Prove that (n > -2) ===> (n / 2 >= 0).
-; CHECK-LABEL: 'test_3'
-; CHECK-NEXT: Determining loop execution counts for: @test_3
+define void @implied3(i32 %n) {
+; Prove that (n s> -2) ===> (n / 2 s>= 0).
+; CHECK-LABEL: 'implied3'
+; CHECK-NEXT: Determining loop execution counts for: @implied3
; CHECK-NEXT: Loop %header: backedge-taken count is (1 + %n.div.2)<nsw>
; CHECK-NEXT: Loop %header: constant max backedge-taken count is i32 1073741824
; CHECK-NEXT: Loop %header: symbolic max backedge-taken count is (1 + %n.div.2)<nsw>
@@ -129,10 +177,35 @@ exit:
ret void
}
-define void @test_3neg(i32 %n) nounwind {
+define void @implied3_samesign(i32 %n) {
+; Prove that (n > -2) ===> (n / 2 s>= 0).
+; CHECK-LABEL: 'implied3_samesign'
+; CHECK-NEXT: Determining loop execution counts for: @implied3_samesign
+; CHECK-NEXT: Loop %header: backedge-taken count is (1 + %n.div.2)<nsw>
+; CHECK-NEXT: Loop %header: constant max backedge-taken count is i32 1
+; CHECK-NEXT: Loop %header: symbolic max backedge-taken count is (1 + %n.div.2)<nsw>
+; CHECK-NEXT: Loop %header: Trip multiple is 1
+;
+entry:
+ %cmp1 = icmp samesign ugt i32 %n, -2
+ %n.div.2 = sdiv i32 %n, 2
+ call void @llvm.assume(i1 %cmp1)
+ br label %header
+
+header:
+ %indvar = phi i32 [ %indvar.next, %header ], [ 0, %entry ]
+ %indvar.next = add i32 %indvar, 1
+ %exitcond = icmp sge i32 %n.div.2, %indvar
+ br i1 %exitcond, label %header, label %exit
+
+exit:
+ ret void
+}
+
+define void @implied3_neg(i32 %n) {
; Prove that (n > -3) =\=> (n / 2 >= 0).
-; CHECK-LABEL: 'test_3neg'
-; CHECK-NEXT: Determining loop execution counts for: @test_3neg
+; CHECK-LABEL: 'implied3_neg'
+; CHECK-NEXT: Determining loop execution counts for: @implied3_neg
; CHECK-NEXT: Loop %header: backedge-taken count is (0 smax (1 + %n.div.2)<nsw>)
; CHECK-NEXT: Loop %header: constant max backedge-taken count is i32 1073741824
; CHECK-NEXT: Loop %header: symbolic max backedge-taken count is (0 smax (1 + %n.div.2)<nsw>)
@@ -154,10 +227,10 @@ exit:
ret void
}
-define void @test_4(i32 %n) nounwind {
-; Prove that (n >= -1) ===> (n / 2 >= 0).
-; CHECK-LABEL: 'test_4'
-; CHECK-NEXT: Determining loop execution counts for: @test_4
+define void @implied4(i32 %n) {
+; Prove that (n s>= -1) ===> (n / 2 s>= 0).
+; CHECK-LABEL: 'implied4'
+; CHECK-NEXT: Determining loop execution counts for: @implied4
; CHECK-NEXT: Loop %header: backedge-taken count is (1 + %n.div.2)<nsw>
; CHECK-NEXT: Loop %header: constant max backedge-taken count is i32 1073741824
; CHECK-NEXT: Loop %header: symbolic max backedge-taken count is (1 + %n.div.2)<nsw>
@@ -179,10 +252,35 @@ exit:
ret void
}
-define void @test_4neg(i32 %n) nounwind {
-; Prove that (n >= -2) =\=> (n / 2 >= 0).
-; CHECK-LABEL: 'test_4neg'
-; CHECK-NEXT: Determining loop execution counts for: @test_4neg
+define void @implied4_samesign(i32 %n) {
+; Prove that (n >= -1) ===> (n / 2 s>= 0).
+; CHECK-LABEL: 'implied4_samesign'
+; CHECK-NEXT: Determining loop execution counts for: @implied4_samesign
+; CHECK-NEXT: Loop %header: backedge-taken count is (1 + %n.div.2)<nsw>
+; CHECK-NEXT: Loop %header: constant max backedge-taken count is i32 1
+; CHECK-NEXT: Loop %header: symbolic max backedge-taken count is (1 + %n.div.2)<nsw>
+; CHECK-NEXT: Loop %header: Trip multiple is 1
+;
+entry:
+ %cmp1 = icmp samesign uge i32 %n, -1
+ %n.div.2 = sdiv i32 %n, 2
+ call void @llvm.assume(i1 %cmp1)
+ br label %header
+
+header:
+ %indvar = phi i32 [ %indvar.next, %header ], [ 0, %entry ]
+ %indvar.next = add i32 %indvar, 1
+ %exitcond = icmp sge i32 %n.div.2, %indvar
+ br i1 %exitcond, label %header, label %exit
+
+exit:
+ ret void
+}
+
+define void @implied4_neg(i32 %n) {
+; Prove that (n s>= -2) =\=> (n / 2 s>= 0).
+; CHECK-LABEL: 'implied4_neg'
+; CHECK-NEXT: Determining loop execution counts for: @implied4_neg
; CHECK-NEXT: Loop %header: backedge-taken count is (0 smax (1 + %n.div.2)<nsw>)
; CHECK-NEXT: Loop %header: constant max backedge-taken count is i32 1073741824
; CHECK-NEXT: Loop %header: symbolic max backedge-taken count is (0 smax (1 + %n.div.2)<nsw>)
>From c485e502cff8ca4a1b027ae5a0051ee306a211be Mon Sep 17 00:00:00 2001
From: Ramkumar Ramachandra <ramkumar.ramachandra at codasip.com>
Date: Fri, 24 Jan 2025 13:29:40 +0000
Subject: [PATCH 2/2] SCEV: teach isImpliedViaOperations about samesign
Use CmpPredicate::getMatching in isImpliedCondBalancedTypes to pass
samesign information to isImpliedViaOperations, and teach it to call
CmpPredicate::getPreferredSignedPredicate, effectively making it
optimize with samesign information.
---
llvm/lib/Analysis/ScalarEvolution.cpp | 33 ++++++++++---------
.../ScalarEvolution/exit-count-samesign.ll | 4 +--
.../ScalarEvolution/implied-via-division.ll | 4 +--
.../IndVarSimplify/iv-ext-samesign.ll | 24 +++++++++-----
4 files changed, 37 insertions(+), 28 deletions(-)
diff --git a/llvm/lib/Analysis/ScalarEvolution.cpp b/llvm/lib/Analysis/ScalarEvolution.cpp
index 0d7bbe3f996408d..f89887118d8d745 100644
--- a/llvm/lib/Analysis/ScalarEvolution.cpp
+++ b/llvm/lib/Analysis/ScalarEvolution.cpp
@@ -11860,15 +11860,13 @@ bool ScalarEvolution::isImpliedCondBalancedTypes(
}
// Check whether the found predicate is the same as the desired predicate.
- // FIXME: use CmpPredicate::getMatching here.
- if (FoundPred == static_cast<CmpInst::Predicate>(Pred))
- return isImpliedCondOperands(Pred, LHS, RHS, FoundLHS, FoundRHS, CtxI);
+ if (auto P = CmpPredicate::getMatching(FoundPred, Pred))
+ return isImpliedCondOperands(*P, LHS, RHS, FoundLHS, FoundRHS, CtxI);
// Check whether swapping the found predicate makes it the same as the
// desired predicate.
- // FIXME: use CmpPredicate::getMatching here.
- if (ICmpInst::getSwappedCmpPredicate(FoundPred) ==
- static_cast<CmpInst::Predicate>(Pred)) {
+ if (auto P = CmpPredicate::getMatching(
+ ICmpInst::getSwappedCmpPredicate(FoundPred), Pred)) {
// We can write the implication
// 0. LHS Pred RHS <- FoundLHS SwapPred FoundRHS
// using one of the following ways:
@@ -11879,22 +11877,23 @@ bool ScalarEvolution::isImpliedCondBalancedTypes(
// Forms 1. and 2. require swapping the operands of one condition. Don't
// do this if it would break canonical constant/addrec ordering.
if (!isa<SCEVConstant>(RHS) && !isa<SCEVAddRecExpr>(LHS))
- return isImpliedCondOperands(FoundPred, RHS, LHS, FoundLHS, FoundRHS,
- CtxI);
+ return isImpliedCondOperands(ICmpInst::getSwappedCmpPredicate(*P), RHS,
+ LHS, FoundLHS, FoundRHS, CtxI);
if (!isa<SCEVConstant>(FoundRHS) && !isa<SCEVAddRecExpr>(FoundLHS))
- return isImpliedCondOperands(Pred, LHS, RHS, FoundRHS, FoundLHS, CtxI);
+ return isImpliedCondOperands(*P, LHS, RHS, FoundRHS, FoundLHS, CtxI);
// There's no clear preference between forms 3. and 4., try both. Avoid
// forming getNotSCEV of pointer values as the resulting subtract is
// not legal.
if (!LHS->getType()->isPointerTy() && !RHS->getType()->isPointerTy() &&
- isImpliedCondOperands(FoundPred, getNotSCEV(LHS), getNotSCEV(RHS),
- FoundLHS, FoundRHS, CtxI))
+ isImpliedCondOperands(ICmpInst::getSwappedCmpPredicate(*P),
+ getNotSCEV(LHS), getNotSCEV(RHS), FoundLHS,
+ FoundRHS, CtxI))
return true;
if (!FoundLHS->getType()->isPointerTy() &&
!FoundRHS->getType()->isPointerTy() &&
- isImpliedCondOperands(Pred, LHS, RHS, getNotSCEV(FoundLHS),
+ isImpliedCondOperands(*P, LHS, RHS, getNotSCEV(FoundLHS),
getNotSCEV(FoundRHS), CtxI))
return true;
@@ -12564,14 +12563,16 @@ bool ScalarEvolution::isImpliedViaOperations(CmpPredicate Pred, const SCEV *LHS,
return false;
// We only want to work with GT comparison so far.
- if (Pred == ICmpInst::ICMP_ULT || Pred == ICmpInst::ICMP_SLT) {
+ if (ICmpInst::isLT(Pred)) {
Pred = ICmpInst::getSwappedCmpPredicate(Pred);
std::swap(LHS, RHS);
std::swap(FoundLHS, FoundRHS);
}
+ CmpInst::Predicate P = Pred.getPreferredSignedPredicate();
+
// For unsigned, try to reduce it to corresponding signed comparison.
- if (Pred == ICmpInst::ICMP_UGT)
+ if (P == ICmpInst::ICMP_UGT)
// We can replace unsigned predicate with its signed counterpart if all
// involved values are non-negative.
// TODO: We could have better support for unsigned.
@@ -12584,10 +12585,10 @@ bool ScalarEvolution::isImpliedViaOperations(CmpPredicate Pred, const SCEV *LHS,
FoundRHS) &&
isImpliedCondOperands(ICmpInst::ICMP_SGT, RHS, MinusOne, FoundLHS,
FoundRHS))
- Pred = ICmpInst::ICMP_SGT;
+ P = ICmpInst::ICMP_SGT;
}
- if (Pred != ICmpInst::ICMP_SGT)
+ if (P != ICmpInst::ICMP_SGT)
return false;
auto GetOpFromSExt = [&](const SCEV *S) {
diff --git a/llvm/test/Analysis/ScalarEvolution/exit-count-samesign.ll b/llvm/test/Analysis/ScalarEvolution/exit-count-samesign.ll
index 93c6bc08af2a095..4d569cc69fa2b11 100644
--- a/llvm/test/Analysis/ScalarEvolution/exit-count-samesign.ll
+++ b/llvm/test/Analysis/ScalarEvolution/exit-count-samesign.ll
@@ -5,9 +5,9 @@
define i32 @exit_count_samesign(i32 %iter.count, ptr %ptr) {
; CHECK-LABEL: 'exit_count_samesign'
; CHECK-NEXT: Determining loop execution counts for: @exit_count_samesign
-; CHECK-NEXT: Loop %inner.loop: backedge-taken count is (-1 + (1 smax {(-1 + %iter.count)<nsw>,+,-1}<nsw><%outer.loop>))<nsw>
+; CHECK-NEXT: Loop %inner.loop: backedge-taken count is {(-2 + %iter.count),+,-1}<nw><%outer.loop>
; CHECK-NEXT: Loop %inner.loop: constant max backedge-taken count is i32 2147483646
-; CHECK-NEXT: Loop %inner.loop: symbolic max backedge-taken count is (-1 + (1 smax {(-1 + %iter.count)<nsw>,+,-1}<nsw><%outer.loop>))<nsw>
+; CHECK-NEXT: Loop %inner.loop: symbolic max backedge-taken count is {(-2 + %iter.count),+,-1}<nw><%outer.loop>
; CHECK-NEXT: Loop %inner.loop: Trip multiple is 1
; CHECK-NEXT: Loop %outer.loop: <multiple exits> Unpredictable backedge-taken count.
; CHECK-NEXT: Loop %outer.loop: Unpredictable constant max backedge-taken count.
diff --git a/llvm/test/Analysis/ScalarEvolution/implied-via-division.ll b/llvm/test/Analysis/ScalarEvolution/implied-via-division.ll
index ef23e37972e6103..d83301243ef30bd 100644
--- a/llvm/test/Analysis/ScalarEvolution/implied-via-division.ll
+++ b/llvm/test/Analysis/ScalarEvolution/implied-via-division.ll
@@ -31,9 +31,9 @@ define void @implied1_samesign(i32 %n) {
; Prove that (n > 1) ===> (n / 2 s> 0).
; CHECK-LABEL: 'implied1_samesign'
; CHECK-NEXT: Determining loop execution counts for: @implied1_samesign
-; CHECK-NEXT: Loop %header: backedge-taken count is (-1 + (1 smax %n.div.2))<nsw>
+; CHECK-NEXT: Loop %header: backedge-taken count is (-1 + %n.div.2)<nsw>
; CHECK-NEXT: Loop %header: constant max backedge-taken count is i32 1073741822
-; CHECK-NEXT: Loop %header: symbolic max backedge-taken count is (-1 + (1 smax %n.div.2))<nsw>
+; CHECK-NEXT: Loop %header: symbolic max backedge-taken count is (-1 + %n.div.2)<nsw>
; CHECK-NEXT: Loop %header: Trip multiple is 1
;
entry:
diff --git a/llvm/test/Transforms/IndVarSimplify/iv-ext-samesign.ll b/llvm/test/Transforms/IndVarSimplify/iv-ext-samesign.ll
index 1207f47c5e3c90c..c4e26c98ed24a6a 100644
--- a/llvm/test/Transforms/IndVarSimplify/iv-ext-samesign.ll
+++ b/llvm/test/Transforms/IndVarSimplify/iv-ext-samesign.ll
@@ -68,28 +68,32 @@ define i32 @iv_zext_zext_gt_slt(i32 %iter.count, ptr %ptr) {
; CHECK-LABEL: define i32 @iv_zext_zext_gt_slt(
; CHECK-SAME: i32 [[ITER_COUNT:%.*]], ptr [[PTR:%.*]]) {
; CHECK-NEXT: [[ENTRY:.*]]:
-; CHECK-NEXT: [[TMP0:%.*]] = sext i32 [[ITER_COUNT]] to i64
+; CHECK-NEXT: [[TMP0:%.*]] = add nsw i32 [[ITER_COUNT]], -1
; CHECK-NEXT: br label %[[OUTER_LOOP:.*]]
; CHECK: [[PH_LOOPEXIT:.*]]:
; CHECK-NEXT: br label %[[PH:.*]]
; CHECK: [[PH]]:
+; CHECK-NEXT: [[INDVARS_IV_NEXT3:%.*]] = add i32 [[INDVARS_IV1:%.*]], -1
; CHECK-NEXT: br label %[[OUTER_LOOP]]
; CHECK: [[OUTER_LOOP]]:
-; CHECK-NEXT: [[INDVARS_IV1:%.*]] = phi i64 [ [[INDVARS_IV_NEXT2:%.*]], %[[PH]] ], [ [[TMP0]], %[[ENTRY]] ]
-; CHECK-NEXT: [[INDVARS_IV_NEXT2]] = add nsw i64 [[INDVARS_IV1]], -1
+; CHECK-NEXT: [[INDVARS_IV1]] = phi i32 [ [[INDVARS_IV_NEXT3]], %[[PH]] ], [ [[TMP0]], %[[ENTRY]] ]
+; CHECK-NEXT: [[IV_OUTER:%.*]] = phi i32 [ [[IV_OUTER_1:%.*]], %[[PH]] ], [ [[ITER_COUNT]], %[[ENTRY]] ]
+; CHECK-NEXT: [[IV_OUTER_1]] = add nsw i32 [[IV_OUTER]], -1
+; CHECK-NEXT: [[INDVARS_IV_NEXT2:%.*]] = zext nneg i32 [[IV_OUTER_1]] to i64
; CHECK-NEXT: [[GEP_OUTER:%.*]] = getelementptr i8, ptr [[PTR]], i64 [[INDVARS_IV_NEXT2]]
; CHECK-NEXT: store i8 0, ptr [[GEP_OUTER]], align 1
-; CHECK-NEXT: [[EXIT_COND_OUTER:%.*]] = icmp samesign ugt i64 [[INDVARS_IV1]], 1
+; CHECK-NEXT: [[EXIT_COND_OUTER:%.*]] = icmp samesign ugt i32 [[IV_OUTER]], 1
; CHECK-NEXT: br i1 [[EXIT_COND_OUTER]], label %[[INNER_LOOP_PREHEADER:.*]], label %[[PH]]
; CHECK: [[INNER_LOOP_PREHEADER]]:
+; CHECK-NEXT: [[WIDE_TRIP_COUNT:%.*]] = zext i32 [[INDVARS_IV1]] to i64
; CHECK-NEXT: br label %[[INNER_LOOP:.*]]
; CHECK: [[INNER_LOOP]]:
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ 0, %[[INNER_LOOP_PREHEADER]] ], [ [[INDVARS_IV_NEXT:%.*]], %[[INNER_LOOP]] ]
; CHECK-NEXT: [[GEP_INNER:%.*]] = getelementptr i8, ptr [[PTR]], i64 [[INDVARS_IV]]
; CHECK-NEXT: store i8 0, ptr [[GEP_INNER]], align 1
; CHECK-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
-; CHECK-NEXT: [[EXIT_COND_INNER:%.*]] = icmp slt i64 [[INDVARS_IV_NEXT]], [[INDVARS_IV_NEXT2]]
-; CHECK-NEXT: br i1 [[EXIT_COND_INNER]], label %[[INNER_LOOP]], label %[[PH_LOOPEXIT]]
+; CHECK-NEXT: [[EXITCOND:%.*]] = icmp ne i64 [[INDVARS_IV_NEXT]], [[WIDE_TRIP_COUNT]]
+; CHECK-NEXT: br i1 [[EXITCOND]], label %[[INNER_LOOP]], label %[[PH_LOOPEXIT]]
; CHECK: [[EXIT:.*:]]
; CHECK-NEXT: ret i32 0
;
@@ -424,28 +428,32 @@ define i32 @iv_sext_sext_gt_slt(i32 %iter.count, ptr %ptr) {
; CHECK-LABEL: define i32 @iv_sext_sext_gt_slt(
; CHECK-SAME: i32 [[ITER_COUNT:%.*]], ptr [[PTR:%.*]]) {
; CHECK-NEXT: [[ENTRY:.*]]:
+; CHECK-NEXT: [[TMP1:%.*]] = add nsw i32 [[ITER_COUNT]], -1
; CHECK-NEXT: [[TMP0:%.*]] = sext i32 [[ITER_COUNT]] to i64
; CHECK-NEXT: br label %[[OUTER_LOOP:.*]]
; CHECK: [[PH_LOOPEXIT:.*]]:
; CHECK-NEXT: br label %[[PH:.*]]
; CHECK: [[PH]]:
+; CHECK-NEXT: [[INDVARS_IV_NEXT3:%.*]] = add i32 [[INDVARS_IV2:%.*]], -1
; CHECK-NEXT: br label %[[OUTER_LOOP]]
; CHECK: [[OUTER_LOOP]]:
; CHECK-NEXT: [[INDVARS_IV1:%.*]] = phi i64 [ [[INDVARS_IV_NEXT2:%.*]], %[[PH]] ], [ [[TMP0]], %[[ENTRY]] ]
+; CHECK-NEXT: [[INDVARS_IV2]] = phi i32 [ [[INDVARS_IV_NEXT3]], %[[PH]] ], [ [[TMP1]], %[[ENTRY]] ]
; CHECK-NEXT: [[INDVARS_IV_NEXT2]] = add nsw i64 [[INDVARS_IV1]], -1
; CHECK-NEXT: [[GEP_OUTER:%.*]] = getelementptr i8, ptr [[PTR]], i64 [[INDVARS_IV_NEXT2]]
; CHECK-NEXT: store i8 0, ptr [[GEP_OUTER]], align 1
; CHECK-NEXT: [[EXIT_COND_OUTER:%.*]] = icmp samesign ugt i64 [[INDVARS_IV1]], 1
; CHECK-NEXT: br i1 [[EXIT_COND_OUTER]], label %[[INNER_LOOP_PREHEADER:.*]], label %[[PH]]
; CHECK: [[INNER_LOOP_PREHEADER]]:
+; CHECK-NEXT: [[WIDE_TRIP_COUNT:%.*]] = zext i32 [[INDVARS_IV2]] to i64
; CHECK-NEXT: br label %[[INNER_LOOP:.*]]
; CHECK: [[INNER_LOOP]]:
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ 0, %[[INNER_LOOP_PREHEADER]] ], [ [[INDVARS_IV_NEXT:%.*]], %[[INNER_LOOP]] ]
; CHECK-NEXT: [[GEP_INNER:%.*]] = getelementptr i8, ptr [[PTR]], i64 [[INDVARS_IV]]
; CHECK-NEXT: store i8 0, ptr [[GEP_INNER]], align 1
; CHECK-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
-; CHECK-NEXT: [[EXIT_COND_INNER:%.*]] = icmp slt i64 [[INDVARS_IV_NEXT]], [[INDVARS_IV_NEXT2]]
-; CHECK-NEXT: br i1 [[EXIT_COND_INNER]], label %[[INNER_LOOP]], label %[[PH_LOOPEXIT]]
+; CHECK-NEXT: [[EXITCOND:%.*]] = icmp ne i64 [[INDVARS_IV_NEXT]], [[WIDE_TRIP_COUNT]]
+; CHECK-NEXT: br i1 [[EXITCOND]], label %[[INNER_LOOP]], label %[[PH_LOOPEXIT]]
; CHECK: [[EXIT:.*:]]
; CHECK-NEXT: ret i32 0
;
More information about the llvm-commits
mailing list