[llvm] ec8d87e - [SCEV] Infer nuw from nw for addrecs
Philip Reames via llvm-commits
llvm-commits at lists.llvm.org
Tue Aug 24 14:24:13 PDT 2021
Author: Philip Reames
Date: 2021-08-24T14:24:05-07:00
New Revision: ec8d87e9f56203df851e2d20750224d4a04803be
URL: https://github.com/llvm/llvm-project/commit/ec8d87e9f56203df851e2d20750224d4a04803be
DIFF: https://github.com/llvm/llvm-project/commit/ec8d87e9f56203df851e2d20750224d4a04803be.diff
LOG: [SCEV] Infer nuw from nw for addrecs
This was previously committed in 914836b, and reverted due to confusion on the status of the review.
Differential Revision: https://reviews.llvm.org/D108601
Added:
Modified:
llvm/lib/Analysis/ScalarEvolution.cpp
llvm/test/Analysis/ScalarEvolution/ptrtoint.ll
Removed:
################################################################################
diff --git a/llvm/lib/Analysis/ScalarEvolution.cpp b/llvm/lib/Analysis/ScalarEvolution.cpp
index b43e69fb4ed25..cc966497bb729 100644
--- a/llvm/lib/Analysis/ScalarEvolution.cpp
+++ b/llvm/lib/Analysis/ScalarEvolution.cpp
@@ -2390,6 +2390,13 @@ StrengthenNoWrapFlags(ScalarEvolution *SE, SCEVTypes Type,
}
}
+ // <0,+,nonnegative><nw> is also nuw
+ // TODO: Add corresponding nsw case
+ if (Type == scAddRecExpr && ScalarEvolution::hasFlags(Flags, SCEV::FlagNW) &&
+ !ScalarEvolution::hasFlags(Flags, SCEV::FlagNUW) && Ops.size() == 2 &&
+ Ops[0]->isZero() && IsKnownNonNegative(Ops[1]))
+ Flags = ScalarEvolution::setFlags(Flags, SCEV::FlagNUW);
+
return Flags;
}
diff --git a/llvm/test/Analysis/ScalarEvolution/ptrtoint.ll b/llvm/test/Analysis/ScalarEvolution/ptrtoint.ll
index f4e716409ea8f..f09588bbd04d6 100644
--- a/llvm/test/Analysis/ScalarEvolution/ptrtoint.ll
+++ b/llvm/test/Analysis/ScalarEvolution/ptrtoint.ll
@@ -386,7 +386,7 @@ define void @pr46786_c26_char(i8* %arg, i8* %arg1, i8* %arg2) {
; X64-NEXT: %i9 = ptrtoint i8* %i7 to i64
; X64-NEXT: --> {(ptrtoint i8* %arg to i64),+,1}<nuw><%bb6> U: full-set S: full-set Exits: (-1 + (ptrtoint i8* %arg1 to i64)) LoopDispositions: { %bb6: Computable }
; X64-NEXT: %i10 = sub i64 %i9, %i4
-; X64-NEXT: --> {0,+,1}<nw><%bb6> U: full-set S: full-set Exits: (-1 + (-1 * (ptrtoint i8* %arg to i64)) + (ptrtoint i8* %arg1 to i64)) LoopDispositions: { %bb6: Computable }
+; X64-NEXT: --> {0,+,1}<nuw><%bb6> U: full-set S: full-set Exits: (-1 + (-1 * (ptrtoint i8* %arg to i64)) + (ptrtoint i8* %arg1 to i64)) LoopDispositions: { %bb6: Computable }
; X64-NEXT: %i11 = getelementptr inbounds i8, i8* %arg2, i64 %i10
; X64-NEXT: --> {%arg2,+,1}<nw><%bb6> U: full-set S: full-set Exits: (-1 + (-1 * (ptrtoint i8* %arg to i64)) + (ptrtoint i8* %arg1 to i64) + %arg2) LoopDispositions: { %bb6: Computable }
; X64-NEXT: %i12 = load i8, i8* %i11, align 1
@@ -413,7 +413,7 @@ define void @pr46786_c26_char(i8* %arg, i8* %arg1, i8* %arg2) {
; X32-NEXT: %i9 = ptrtoint i8* %i7 to i64
; X32-NEXT: --> {(zext i32 (ptrtoint i8* %arg to i32) to i64),+,1}<nuw><%bb6> U: [0,8589934591) S: [0,8589934591) Exits: ((zext i32 (-1 + (-1 * (ptrtoint i8* %arg to i32)) + (ptrtoint i8* %arg1 to i32)) to i64) + (zext i32 (ptrtoint i8* %arg to i32) to i64)) LoopDispositions: { %bb6: Computable }
; X32-NEXT: %i10 = sub i64 %i9, %i4
-; X32-NEXT: --> {0,+,1}<nw><%bb6> U: [0,4294967296) S: [0,4294967296) Exits: (zext i32 (-1 + (-1 * (ptrtoint i8* %arg to i32)) + (ptrtoint i8* %arg1 to i32)) to i64) LoopDispositions: { %bb6: Computable }
+; X32-NEXT: --> {0,+,1}<nuw><%bb6> U: [0,4294967296) S: [0,4294967296) Exits: (zext i32 (-1 + (-1 * (ptrtoint i8* %arg to i32)) + (ptrtoint i8* %arg1 to i32)) to i64) LoopDispositions: { %bb6: Computable }
; X32-NEXT: %i11 = getelementptr inbounds i8, i8* %arg2, i64 %i10
; X32-NEXT: --> {%arg2,+,1}<%bb6> U: full-set S: full-set Exits: (-1 + (-1 * (ptrtoint i8* %arg to i32)) + (ptrtoint i8* %arg1 to i32) + %arg2) LoopDispositions: { %bb6: Computable }
; X32-NEXT: %i12 = load i8, i8* %i11, align 1
@@ -471,7 +471,7 @@ define void @pr46786_c26_int(i32* %arg, i32* %arg1, i32* %arg2) {
; X64-NEXT: %i9 = ptrtoint i32* %i7 to i64
; X64-NEXT: --> {(ptrtoint i32* %arg to i64),+,4}<nuw><%bb6> U: full-set S: full-set Exits: ((4 * ((-4 + (-1 * (ptrtoint i32* %arg to i64)) + (ptrtoint i32* %arg1 to i64)) /u 4))<nuw> + (ptrtoint i32* %arg to i64)) LoopDispositions: { %bb6: Computable }
; X64-NEXT: %i10 = sub i64 %i9, %i4
-; X64-NEXT: --> {0,+,4}<nw><%bb6> U: [0,-3) S: [-9223372036854775808,9223372036854775805) Exits: (4 * ((-4 + (-1 * (ptrtoint i32* %arg to i64)) + (ptrtoint i32* %arg1 to i64)) /u 4))<nuw> LoopDispositions: { %bb6: Computable }
+; X64-NEXT: --> {0,+,4}<nuw><%bb6> U: [0,-3) S: [-9223372036854775808,9223372036854775805) Exits: (4 * ((-4 + (-1 * (ptrtoint i32* %arg to i64)) + (ptrtoint i32* %arg1 to i64)) /u 4))<nuw> LoopDispositions: { %bb6: Computable }
; X64-NEXT: %i11 = ashr exact i64 %i10, 2
; X64-NEXT: --> %i11 U: [-2305843009213693952,2305843009213693952) S: [-2305843009213693952,2305843009213693952) Exits: <<Unknown>> LoopDispositions: { %bb6: Variant }
; X64-NEXT: %i12 = getelementptr inbounds i32, i32* %arg2, i64 %i11
@@ -500,7 +500,7 @@ define void @pr46786_c26_int(i32* %arg, i32* %arg1, i32* %arg2) {
; X32-NEXT: %i9 = ptrtoint i32* %i7 to i64
; X32-NEXT: --> {(zext i32 (ptrtoint i32* %arg to i32) to i64),+,4}<nuw><%bb6> U: [0,8589934588) S: [0,8589934588) Exits: ((zext i32 (ptrtoint i32* %arg to i32) to i64) + (4 * ((zext i32 (-4 + (-1 * (ptrtoint i32* %arg to i32)) + (ptrtoint i32* %arg1 to i32)) to i64) /u 4))<nuw><nsw>) LoopDispositions: { %bb6: Computable }
; X32-NEXT: %i10 = sub i64 %i9, %i4
-; X32-NEXT: --> {0,+,4}<nw><%bb6> U: [0,4294967293) S: [0,4294967293) Exits: (4 * ((zext i32 (-4 + (-1 * (ptrtoint i32* %arg to i32)) + (ptrtoint i32* %arg1 to i32)) to i64) /u 4))<nuw><nsw> LoopDispositions: { %bb6: Computable }
+; X32-NEXT: --> {0,+,4}<nuw><%bb6> U: [0,4294967293) S: [0,4294967293) Exits: (4 * ((zext i32 (-4 + (-1 * (ptrtoint i32* %arg to i32)) + (ptrtoint i32* %arg1 to i32)) to i64) /u 4))<nuw><nsw> LoopDispositions: { %bb6: Computable }
; X32-NEXT: %i11 = ashr exact i64 %i10, 2
; X32-NEXT: --> %i11 U: [-2147483648,2147483648) S: [-2147483648,2147483648) Exits: <<Unknown>> LoopDispositions: { %bb6: Variant }
; X32-NEXT: %i12 = getelementptr inbounds i32, i32* %arg2, i64 %i11
More information about the llvm-commits
mailing list