[llvm] [SCEV] Collect guard info for ICMP NE w/o constants. (PR #160500)
Florian Hahn via llvm-commits
llvm-commits at lists.llvm.org
Wed Oct 8 05:29:02 PDT 2025
https://github.com/fhahn updated https://github.com/llvm/llvm-project/pull/160500
>From c80a098ba32cad896d1827cc5fa609b2ba08e09c Mon Sep 17 00:00:00 2001
From: Florian Hahn <flo at fhahn.com>
Date: Tue, 7 Oct 2025 21:45:34 +0100
Subject: [PATCH 1/3] Peel tes
---
.../test/Analysis/ScalarEvolution/ptrtoint.ll | 78 +++++++++++++++++++
1 file changed, 78 insertions(+)
diff --git a/llvm/test/Analysis/ScalarEvolution/ptrtoint.ll b/llvm/test/Analysis/ScalarEvolution/ptrtoint.ll
index e784d25385980..acac2c98ad174 100644
--- a/llvm/test/Analysis/ScalarEvolution/ptrtoint.ll
+++ b/llvm/test/Analysis/ScalarEvolution/ptrtoint.ll
@@ -447,6 +447,84 @@ bb5:
ret void
}
+define void @pr46786_c26_char_cmp_ops_swapped(ptr %arg, ptr %arg1, ptr %arg2) {
+; X64-LABEL: 'pr46786_c26_char_cmp_ops_swapped'
+; X64-NEXT: Classifying expressions for: @pr46786_c26_char_cmp_ops_swapped
+; X64-NEXT: %i4 = ptrtoint ptr %arg to i64
+; X64-NEXT: --> (ptrtoint ptr %arg to i64) U: full-set S: full-set
+; X64-NEXT: %i7 = phi ptr [ %arg, %bb3 ], [ %i14, %bb6 ]
+; X64-NEXT: --> {%arg,+,1}<nuw><%bb6> U: full-set S: full-set Exits: (-1 + (-1 * (ptrtoint ptr %arg to i64)) + (ptrtoint ptr %arg1 to i64) + %arg) LoopDispositions: { %bb6: Computable }
+; X64-NEXT: %i8 = load i8, ptr %i7, align 1
+; X64-NEXT: --> %i8 U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %bb6: Variant }
+; X64-NEXT: %i9 = ptrtoint ptr %i7 to i64
+; X64-NEXT: --> {(ptrtoint ptr %arg to i64),+,1}<nuw><%bb6> U: full-set S: full-set Exits: (-1 + (ptrtoint ptr %arg1 to i64)) LoopDispositions: { %bb6: Computable }
+; X64-NEXT: %i10 = sub i64 %i9, %i4
+; X64-NEXT: --> {0,+,1}<nuw><%bb6> U: full-set S: full-set Exits: (-1 + (-1 * (ptrtoint ptr %arg to i64)) + (ptrtoint ptr %arg1 to i64)) LoopDispositions: { %bb6: Computable }
+; X64-NEXT: %i11 = getelementptr inbounds i8, ptr %arg2, i64 %i10
+; X64-NEXT: --> {%arg2,+,1}<nw><%bb6> U: full-set S: full-set Exits: (-1 + (-1 * (ptrtoint ptr %arg to i64)) + (ptrtoint ptr %arg1 to i64) + %arg2) LoopDispositions: { %bb6: Computable }
+; X64-NEXT: %i12 = load i8, ptr %i11, align 1
+; X64-NEXT: --> %i12 U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %bb6: Variant }
+; X64-NEXT: %i13 = add i8 %i12, %i8
+; X64-NEXT: --> (%i12 + %i8) U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %bb6: Variant }
+; X64-NEXT: %i14 = getelementptr inbounds i8, ptr %i7, i64 1
+; X64-NEXT: --> {(1 + %arg),+,1}<nuw><%bb6> U: full-set S: full-set Exits: ((-1 * (ptrtoint ptr %arg to i64)) + (ptrtoint ptr %arg1 to i64) + %arg) LoopDispositions: { %bb6: Computable }
+; X64-NEXT: Determining loop execution counts for: @pr46786_c26_char_cmp_ops_swapped
+; X64-NEXT: Loop %bb6: backedge-taken count is (-1 + (-1 * (ptrtoint ptr %arg to i64)) + (ptrtoint ptr %arg1 to i64))
+; X64-NEXT: Loop %bb6: constant max backedge-taken count is i64 -1
+; X64-NEXT: Loop %bb6: symbolic max backedge-taken count is (-1 + (-1 * (ptrtoint ptr %arg to i64)) + (ptrtoint ptr %arg1 to i64))
+; X64-NEXT: Loop %bb6: Trip multiple is 1
+;
+; X32-LABEL: 'pr46786_c26_char_cmp_ops_swapped'
+; X32-NEXT: Classifying expressions for: @pr46786_c26_char_cmp_ops_swapped
+; X32-NEXT: %i4 = ptrtoint ptr %arg to i64
+; X32-NEXT: --> (zext i32 (ptrtoint ptr %arg to i32) to i64) U: [0,4294967296) S: [0,4294967296)
+; X32-NEXT: %i7 = phi ptr [ %arg, %bb3 ], [ %i14, %bb6 ]
+; X32-NEXT: --> {%arg,+,1}<nuw><%bb6> U: full-set S: full-set Exits: (-1 + (-1 * (ptrtoint ptr %arg to i32)) + (ptrtoint ptr %arg1 to i32) + %arg) LoopDispositions: { %bb6: Computable }
+; X32-NEXT: %i8 = load i8, ptr %i7, align 1
+; X32-NEXT: --> %i8 U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %bb6: Variant }
+; X32-NEXT: %i9 = ptrtoint ptr %i7 to i64
+; X32-NEXT: --> {(zext i32 (ptrtoint ptr %arg to i32) to i64),+,1}<nuw><%bb6> U: [0,8589934591) S: [0,8589934591) Exits: ((zext i32 (-1 + (-1 * (ptrtoint ptr %arg to i32)) + (ptrtoint ptr %arg1 to i32)) to i64) + (zext i32 (ptrtoint ptr %arg to i32) to i64)) LoopDispositions: { %bb6: Computable }
+; X32-NEXT: %i10 = sub i64 %i9, %i4
+; X32-NEXT: --> {0,+,1}<nuw><%bb6> U: [0,4294967296) S: [0,4294967296) Exits: (zext i32 (-1 + (-1 * (ptrtoint ptr %arg to i32)) + (ptrtoint ptr %arg1 to i32)) to i64) LoopDispositions: { %bb6: Computable }
+; X32-NEXT: %i11 = getelementptr inbounds i8, ptr %arg2, i64 %i10
+; X32-NEXT: --> {%arg2,+,1}<%bb6> U: full-set S: full-set Exits: (-1 + (-1 * (ptrtoint ptr %arg to i32)) + (ptrtoint ptr %arg1 to i32) + %arg2) LoopDispositions: { %bb6: Computable }
+; X32-NEXT: %i12 = load i8, ptr %i11, align 1
+; X32-NEXT: --> %i12 U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %bb6: Variant }
+; X32-NEXT: %i13 = add i8 %i12, %i8
+; X32-NEXT: --> (%i12 + %i8) U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %bb6: Variant }
+; X32-NEXT: %i14 = getelementptr inbounds i8, ptr %i7, i64 1
+; X32-NEXT: --> {(1 + %arg),+,1}<nuw><%bb6> U: full-set S: full-set Exits: ((-1 * (ptrtoint ptr %arg to i32)) + (ptrtoint ptr %arg1 to i32) + %arg) LoopDispositions: { %bb6: Computable }
+; X32-NEXT: Determining loop execution counts for: @pr46786_c26_char_cmp_ops_swapped
+; X32-NEXT: Loop %bb6: backedge-taken count is (-1 + (-1 * (ptrtoint ptr %arg to i32)) + (ptrtoint ptr %arg1 to i32))
+; X32-NEXT: Loop %bb6: constant max backedge-taken count is i32 -1
+; X32-NEXT: Loop %bb6: symbolic max backedge-taken count is (-1 + (-1 * (ptrtoint ptr %arg to i32)) + (ptrtoint ptr %arg1 to i32))
+; X32-NEXT: Loop %bb6: Trip multiple is 1
+;
+ %i = icmp eq ptr %arg1, %arg
+ br i1 %i, label %bb5, label %bb3
+
+bb3:
+ %i4 = ptrtoint ptr %arg to i64
+ br label %bb6
+
+bb6:
+ %i7 = phi ptr [ %arg, %bb3 ], [ %i14, %bb6 ]
+ %i8 = load i8, ptr %i7
+ %i9 = ptrtoint ptr %i7 to i64
+ %i10 = sub i64 %i9, %i4
+ %i11 = getelementptr inbounds i8, ptr %arg2, i64 %i10
+ %i12 = load i8, ptr %i11
+ %i13 = add i8 %i12, %i8
+ store i8 %i13, ptr %i11
+ %i14 = getelementptr inbounds i8, ptr %i7, i64 1
+ %i15 = icmp eq ptr %i14, %arg1
+ br i1 %i15, label %bb5, label %bb6
+
+bb5:
+ ret void
+}
+
+
; void pr46786_c26_int(int* start, int *end, int *other) {
; for (int* cur = start; cur != end; ++cur)
; other[cur - start] += *cur;
>From dabb6a4b9dea40237a4cf5f83841250925a10b25 Mon Sep 17 00:00:00 2001
From: Florian Hahn <flo at fhahn.com>
Date: Mon, 22 Sep 2025 11:46:30 +0100
Subject: [PATCH 2/3] [SCEV] Collect guard info for ICMP NE w/o constants.
When collecting information from loop guards, use UMax(1, %b - %a) for
ICMP NE %a, %b, if neither are constant.
This improves results in some cases, and will be even more useful
together with
* https://github.com/llvm/llvm-project/pull/160012
* https://github.com/llvm/llvm-project/pull/159942
https://alive2.llvm.org/ce/z/YyBvoT
---
llvm/lib/Analysis/ScalarEvolution.cpp | 10 ++++++++++
llvm/test/Analysis/ScalarEvolution/ptrtoint.ll | 10 +++++-----
.../Transforms/IndVarSimplify/pointer-loop-guards.ll | 2 +-
llvm/test/Transforms/LoopUnroll/scevunroll.ll | 3 +--
4 files changed, 17 insertions(+), 8 deletions(-)
diff --git a/llvm/lib/Analysis/ScalarEvolution.cpp b/llvm/lib/Analysis/ScalarEvolution.cpp
index 6f6776c827729..b2dc422e490fc 100644
--- a/llvm/lib/Analysis/ScalarEvolution.cpp
+++ b/llvm/lib/Analysis/ScalarEvolution.cpp
@@ -15885,6 +15885,16 @@ void ScalarEvolution::LoopGuards::collectFromBlock(
const SCEV *OneAlignedUp =
DividesBy ? GetNextSCEVDividesByDivisor(One, DividesBy) : One;
To = SE.getUMaxExpr(FromRewritten, OneAlignedUp);
+ } else {
+ if (LHS->getType()->isPointerTy()) {
+ LHS = SE.getLosslessPtrToIntExpr(LHS);
+ RHS = SE.getLosslessPtrToIntExpr(RHS);
+ if (isa<SCEVCouldNotCompute>(LHS) || isa<SCEVCouldNotCompute>(RHS))
+ break;
+ }
+ From = SE.getMinusSCEV(RHS, LHS);
+ FromRewritten = From;
+ To = SE.getUMaxExpr(FromRewritten, SE.getOne(From->getType()));
}
break;
default:
diff --git a/llvm/test/Analysis/ScalarEvolution/ptrtoint.ll b/llvm/test/Analysis/ScalarEvolution/ptrtoint.ll
index acac2c98ad174..0dda7bf1d1ba9 100644
--- a/llvm/test/Analysis/ScalarEvolution/ptrtoint.ll
+++ b/llvm/test/Analysis/ScalarEvolution/ptrtoint.ll
@@ -382,7 +382,7 @@ define void @pr46786_c26_char(ptr %arg, ptr %arg1, ptr %arg2) {
; X64-NEXT: %i9 = ptrtoint ptr %i7 to i64
; X64-NEXT: --> {(ptrtoint ptr %arg to i64),+,1}<nuw><%bb6> U: full-set S: full-set Exits: (-1 + (ptrtoint ptr %arg1 to i64)) LoopDispositions: { %bb6: Computable }
; X64-NEXT: %i10 = sub i64 %i9, %i4
-; X64-NEXT: --> {0,+,1}<nuw><%bb6> U: full-set S: full-set Exits: (-1 + (-1 * (ptrtoint ptr %arg to i64)) + (ptrtoint ptr %arg1 to i64)) LoopDispositions: { %bb6: Computable }
+; X64-NEXT: --> {0,+,1}<nuw><%bb6> U: [0,-1) S: [0,-1) Exits: (-1 + (-1 * (ptrtoint ptr %arg to i64)) + (ptrtoint ptr %arg1 to i64)) LoopDispositions: { %bb6: Computable }
; X64-NEXT: %i11 = getelementptr inbounds i8, ptr %arg2, i64 %i10
; X64-NEXT: --> {%arg2,+,1}<nw><%bb6> U: full-set S: full-set Exits: (-1 + (-1 * (ptrtoint ptr %arg to i64)) + (ptrtoint ptr %arg1 to i64) + %arg2) LoopDispositions: { %bb6: Computable }
; X64-NEXT: %i12 = load i8, ptr %i11, align 1
@@ -393,7 +393,7 @@ define void @pr46786_c26_char(ptr %arg, ptr %arg1, ptr %arg2) {
; X64-NEXT: --> {(1 + %arg),+,1}<nuw><%bb6> U: full-set S: full-set Exits: ((-1 * (ptrtoint ptr %arg to i64)) + (ptrtoint ptr %arg1 to i64) + %arg) LoopDispositions: { %bb6: Computable }
; X64-NEXT: Determining loop execution counts for: @pr46786_c26_char
; X64-NEXT: Loop %bb6: backedge-taken count is (-1 + (-1 * (ptrtoint ptr %arg to i64)) + (ptrtoint ptr %arg1 to i64))
-; X64-NEXT: Loop %bb6: constant max backedge-taken count is i64 -1
+; X64-NEXT: Loop %bb6: constant max backedge-taken count is i64 -2
; X64-NEXT: Loop %bb6: symbolic max backedge-taken count is (-1 + (-1 * (ptrtoint ptr %arg to i64)) + (ptrtoint ptr %arg1 to i64))
; X64-NEXT: Loop %bb6: Trip multiple is 1
;
@@ -406,9 +406,9 @@ define void @pr46786_c26_char(ptr %arg, ptr %arg1, ptr %arg2) {
; X32-NEXT: %i8 = load i8, ptr %i7, align 1
; X32-NEXT: --> %i8 U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %bb6: Variant }
; X32-NEXT: %i9 = ptrtoint ptr %i7 to i64
-; X32-NEXT: --> {(zext i32 (ptrtoint ptr %arg to i32) to i64),+,1}<nuw><%bb6> U: [0,8589934591) S: [0,8589934591) Exits: ((zext i32 (-1 + (-1 * (ptrtoint ptr %arg to i32)) + (ptrtoint ptr %arg1 to i32)) to i64) + (zext i32 (ptrtoint ptr %arg to i32) to i64)) LoopDispositions: { %bb6: Computable }
+; X32-NEXT: --> {(zext i32 (ptrtoint ptr %arg to i32) to i64),+,1}<nuw><%bb6> U: [0,8589934590) S: [0,8589934590) Exits: ((zext i32 (-1 + (-1 * (ptrtoint ptr %arg to i32)) + (ptrtoint ptr %arg1 to i32)) to i64) + (zext i32 (ptrtoint ptr %arg to i32) to i64)) LoopDispositions: { %bb6: Computable }
; X32-NEXT: %i10 = sub i64 %i9, %i4
-; X32-NEXT: --> {0,+,1}<nuw><%bb6> U: [0,4294967296) S: [0,4294967296) Exits: (zext i32 (-1 + (-1 * (ptrtoint ptr %arg to i32)) + (ptrtoint ptr %arg1 to i32)) to i64) LoopDispositions: { %bb6: Computable }
+; X32-NEXT: --> {0,+,1}<nuw><%bb6> U: [0,4294967295) S: [0,4294967295) Exits: (zext i32 (-1 + (-1 * (ptrtoint ptr %arg to i32)) + (ptrtoint ptr %arg1 to i32)) to i64) LoopDispositions: { %bb6: Computable }
; X32-NEXT: %i11 = getelementptr inbounds i8, ptr %arg2, i64 %i10
; X32-NEXT: --> {%arg2,+,1}<%bb6> U: full-set S: full-set Exits: (-1 + (-1 * (ptrtoint ptr %arg to i32)) + (ptrtoint ptr %arg1 to i32) + %arg2) LoopDispositions: { %bb6: Computable }
; X32-NEXT: %i12 = load i8, ptr %i11, align 1
@@ -419,7 +419,7 @@ define void @pr46786_c26_char(ptr %arg, ptr %arg1, ptr %arg2) {
; X32-NEXT: --> {(1 + %arg),+,1}<nuw><%bb6> U: full-set S: full-set Exits: ((-1 * (ptrtoint ptr %arg to i32)) + (ptrtoint ptr %arg1 to i32) + %arg) LoopDispositions: { %bb6: Computable }
; X32-NEXT: Determining loop execution counts for: @pr46786_c26_char
; X32-NEXT: Loop %bb6: backedge-taken count is (-1 + (-1 * (ptrtoint ptr %arg to i32)) + (ptrtoint ptr %arg1 to i32))
-; X32-NEXT: Loop %bb6: constant max backedge-taken count is i32 -1
+; X32-NEXT: Loop %bb6: constant max backedge-taken count is i32 -2
; X32-NEXT: Loop %bb6: symbolic max backedge-taken count is (-1 + (-1 * (ptrtoint ptr %arg to i32)) + (ptrtoint ptr %arg1 to i32))
; X32-NEXT: Loop %bb6: Trip multiple is 1
;
diff --git a/llvm/test/Transforms/IndVarSimplify/pointer-loop-guards.ll b/llvm/test/Transforms/IndVarSimplify/pointer-loop-guards.ll
index 89b132e981899..9371fe24be05d 100644
--- a/llvm/test/Transforms/IndVarSimplify/pointer-loop-guards.ll
+++ b/llvm/test/Transforms/IndVarSimplify/pointer-loop-guards.ll
@@ -18,7 +18,7 @@ define i64 @test_ptr_compare_guard(ptr %start, ptr %end) {
; CHECK-NEXT: br i1 [[C_1]], label %[[LOOP_LATCH]], label %[[EXIT_LOOPEXIT:.*]]
; CHECK: [[LOOP_LATCH]]:
; CHECK-NEXT: [[PTR_IV_NEXT]] = getelementptr i8, ptr [[PTR_IV]], i64 1
-; CHECK-NEXT: [[I64_IV_NEXT]] = add i64 [[I64_IV]], 1
+; CHECK-NEXT: [[I64_IV_NEXT]] = add nuw i64 [[I64_IV]], 1
; CHECK-NEXT: [[C_2:%.*]] = icmp eq ptr [[PTR_IV_NEXT]], [[END]]
; CHECK-NEXT: br i1 [[C_2]], label %[[EXIT_LOOPEXIT]], label %[[LOOP_HEADER]]
; CHECK: [[EXIT_LOOPEXIT]]:
diff --git a/llvm/test/Transforms/LoopUnroll/scevunroll.ll b/llvm/test/Transforms/LoopUnroll/scevunroll.ll
index fa55eab062198..bc63f79296a30 100644
--- a/llvm/test/Transforms/LoopUnroll/scevunroll.ll
+++ b/llvm/test/Transforms/LoopUnroll/scevunroll.ll
@@ -465,8 +465,7 @@ define void @peel_int_eq_condition(i32 %start) {
; CHECK-NEXT: br label [[LOOP:%.*]]
; CHECK: loop:
; CHECK-NEXT: [[IV:%.*]] = phi i32 [ [[IV_NEXT_PEEL]], [[ENTRY_PEEL_NEWPH]] ], [ [[IV_NEXT:%.*]], [[LOOP_LATCH:%.*]] ]
-; CHECK-NEXT: [[C_0:%.*]] = icmp eq i32 [[IV]], [[START]]
-; CHECK-NEXT: br i1 [[C_0]], label [[IF_THEN:%.*]], label [[LOOP_LATCH]]
+; CHECK-NEXT: br i1 false, label [[IF_THEN:%.*]], label [[LOOP_LATCH]]
; CHECK: if.then:
; CHECK-NEXT: call void @fn(i32 [[IV]])
; CHECK-NEXT: br label [[LOOP_LATCH]]
>From 9947da661a7c0b58ad1abde9642f884dbf611d37 Mon Sep 17 00:00:00 2001
From: Florian Hahn <flo at fhahn.com>
Date: Tue, 7 Oct 2025 21:50:38 +0100
Subject: [PATCH 3/3] !fixup add both
---
llvm/lib/Analysis/ScalarEvolution.cpp | 11 ++++++++---
llvm/test/Analysis/ScalarEvolution/ptrtoint.ll | 10 +++++-----
2 files changed, 13 insertions(+), 8 deletions(-)
diff --git a/llvm/lib/Analysis/ScalarEvolution.cpp b/llvm/lib/Analysis/ScalarEvolution.cpp
index b2dc422e490fc..0855c1e2de0e1 100644
--- a/llvm/lib/Analysis/ScalarEvolution.cpp
+++ b/llvm/lib/Analysis/ScalarEvolution.cpp
@@ -15892,9 +15892,14 @@ void ScalarEvolution::LoopGuards::collectFromBlock(
if (isa<SCEVCouldNotCompute>(LHS) || isa<SCEVCouldNotCompute>(RHS))
break;
}
- From = SE.getMinusSCEV(RHS, LHS);
- FromRewritten = From;
- To = SE.getUMaxExpr(FromRewritten, SE.getOne(From->getType()));
+ auto AddSubRewrite = [&](const SCEV *A, const SCEV *B) {
+ const SCEV *Sub = SE.getMinusSCEV(A, B);
+ AddRewrite(Sub, Sub,
+ SE.getUMaxExpr(Sub, SE.getOne(From->getType())));
+ };
+ AddSubRewrite(LHS, RHS);
+ AddSubRewrite(RHS, LHS);
+ continue;
}
break;
default:
diff --git a/llvm/test/Analysis/ScalarEvolution/ptrtoint.ll b/llvm/test/Analysis/ScalarEvolution/ptrtoint.ll
index 0dda7bf1d1ba9..0c1f37bf58601 100644
--- a/llvm/test/Analysis/ScalarEvolution/ptrtoint.ll
+++ b/llvm/test/Analysis/ScalarEvolution/ptrtoint.ll
@@ -459,7 +459,7 @@ define void @pr46786_c26_char_cmp_ops_swapped(ptr %arg, ptr %arg1, ptr %arg2) {
; X64-NEXT: %i9 = ptrtoint ptr %i7 to i64
; X64-NEXT: --> {(ptrtoint ptr %arg to i64),+,1}<nuw><%bb6> U: full-set S: full-set Exits: (-1 + (ptrtoint ptr %arg1 to i64)) LoopDispositions: { %bb6: Computable }
; X64-NEXT: %i10 = sub i64 %i9, %i4
-; X64-NEXT: --> {0,+,1}<nuw><%bb6> U: full-set S: full-set Exits: (-1 + (-1 * (ptrtoint ptr %arg to i64)) + (ptrtoint ptr %arg1 to i64)) LoopDispositions: { %bb6: Computable }
+; X64-NEXT: --> {0,+,1}<nuw><%bb6> U: [0,-1) S: [0,-1) Exits: (-1 + (-1 * (ptrtoint ptr %arg to i64)) + (ptrtoint ptr %arg1 to i64)) LoopDispositions: { %bb6: Computable }
; X64-NEXT: %i11 = getelementptr inbounds i8, ptr %arg2, i64 %i10
; X64-NEXT: --> {%arg2,+,1}<nw><%bb6> U: full-set S: full-set Exits: (-1 + (-1 * (ptrtoint ptr %arg to i64)) + (ptrtoint ptr %arg1 to i64) + %arg2) LoopDispositions: { %bb6: Computable }
; X64-NEXT: %i12 = load i8, ptr %i11, align 1
@@ -470,7 +470,7 @@ define void @pr46786_c26_char_cmp_ops_swapped(ptr %arg, ptr %arg1, ptr %arg2) {
; X64-NEXT: --> {(1 + %arg),+,1}<nuw><%bb6> U: full-set S: full-set Exits: ((-1 * (ptrtoint ptr %arg to i64)) + (ptrtoint ptr %arg1 to i64) + %arg) LoopDispositions: { %bb6: Computable }
; X64-NEXT: Determining loop execution counts for: @pr46786_c26_char_cmp_ops_swapped
; X64-NEXT: Loop %bb6: backedge-taken count is (-1 + (-1 * (ptrtoint ptr %arg to i64)) + (ptrtoint ptr %arg1 to i64))
-; X64-NEXT: Loop %bb6: constant max backedge-taken count is i64 -1
+; X64-NEXT: Loop %bb6: constant max backedge-taken count is i64 -2
; X64-NEXT: Loop %bb6: symbolic max backedge-taken count is (-1 + (-1 * (ptrtoint ptr %arg to i64)) + (ptrtoint ptr %arg1 to i64))
; X64-NEXT: Loop %bb6: Trip multiple is 1
;
@@ -483,9 +483,9 @@ define void @pr46786_c26_char_cmp_ops_swapped(ptr %arg, ptr %arg1, ptr %arg2) {
; X32-NEXT: %i8 = load i8, ptr %i7, align 1
; X32-NEXT: --> %i8 U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %bb6: Variant }
; X32-NEXT: %i9 = ptrtoint ptr %i7 to i64
-; X32-NEXT: --> {(zext i32 (ptrtoint ptr %arg to i32) to i64),+,1}<nuw><%bb6> U: [0,8589934591) S: [0,8589934591) Exits: ((zext i32 (-1 + (-1 * (ptrtoint ptr %arg to i32)) + (ptrtoint ptr %arg1 to i32)) to i64) + (zext i32 (ptrtoint ptr %arg to i32) to i64)) LoopDispositions: { %bb6: Computable }
+; X32-NEXT: --> {(zext i32 (ptrtoint ptr %arg to i32) to i64),+,1}<nuw><%bb6> U: [0,8589934590) S: [0,8589934590) Exits: ((zext i32 (-1 + (-1 * (ptrtoint ptr %arg to i32)) + (ptrtoint ptr %arg1 to i32)) to i64) + (zext i32 (ptrtoint ptr %arg to i32) to i64)) LoopDispositions: { %bb6: Computable }
; X32-NEXT: %i10 = sub i64 %i9, %i4
-; X32-NEXT: --> {0,+,1}<nuw><%bb6> U: [0,4294967296) S: [0,4294967296) Exits: (zext i32 (-1 + (-1 * (ptrtoint ptr %arg to i32)) + (ptrtoint ptr %arg1 to i32)) to i64) LoopDispositions: { %bb6: Computable }
+; X32-NEXT: --> {0,+,1}<nuw><%bb6> U: [0,4294967295) S: [0,4294967295) Exits: (zext i32 (-1 + (-1 * (ptrtoint ptr %arg to i32)) + (ptrtoint ptr %arg1 to i32)) to i64) LoopDispositions: { %bb6: Computable }
; X32-NEXT: %i11 = getelementptr inbounds i8, ptr %arg2, i64 %i10
; X32-NEXT: --> {%arg2,+,1}<%bb6> U: full-set S: full-set Exits: (-1 + (-1 * (ptrtoint ptr %arg to i32)) + (ptrtoint ptr %arg1 to i32) + %arg2) LoopDispositions: { %bb6: Computable }
; X32-NEXT: %i12 = load i8, ptr %i11, align 1
@@ -496,7 +496,7 @@ define void @pr46786_c26_char_cmp_ops_swapped(ptr %arg, ptr %arg1, ptr %arg2) {
; X32-NEXT: --> {(1 + %arg),+,1}<nuw><%bb6> U: full-set S: full-set Exits: ((-1 * (ptrtoint ptr %arg to i32)) + (ptrtoint ptr %arg1 to i32) + %arg) LoopDispositions: { %bb6: Computable }
; X32-NEXT: Determining loop execution counts for: @pr46786_c26_char_cmp_ops_swapped
; X32-NEXT: Loop %bb6: backedge-taken count is (-1 + (-1 * (ptrtoint ptr %arg to i32)) + (ptrtoint ptr %arg1 to i32))
-; X32-NEXT: Loop %bb6: constant max backedge-taken count is i32 -1
+; X32-NEXT: Loop %bb6: constant max backedge-taken count is i32 -2
; X32-NEXT: Loop %bb6: symbolic max backedge-taken count is (-1 + (-1 * (ptrtoint ptr %arg to i32)) + (ptrtoint ptr %arg1 to i32))
; X32-NEXT: Loop %bb6: Trip multiple is 1
;
More information about the llvm-commits
mailing list