forked from OSchip/llvm-project
[ScalarEvolution] createSCEV(): recognize `udiv`/`urem` disguised as an `sdiv`/`srem`
Summary: While InstCombine trivially converts that `srem` into a `urem`, it might happen later than wanted, in particular i'd like for that to happen on https://godbolt.org/z/bwuEmJ test case early in pipeline, before first instcombine run, just before `-mem2reg`. SCEV should recognize this case natively. Reviewers: mkazantsev, efriedma, nikic, reames Reviewed By: efriedma Subscribers: clementval, hiraditya, javed.absar, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D82721
This commit is contained in:
parent
68498ce8af
commit
2c16100e6f
|
@ -6303,6 +6303,20 @@ const SCEV *ScalarEvolution::createSCEV(Value *V) {
|
|||
return getSCEV(U->getOperand(0));
|
||||
break;
|
||||
|
||||
case Instruction::SDiv:
|
||||
// If both operands are non-negative, this is just an udiv.
|
||||
if (isKnownNonNegative(getSCEV(U->getOperand(0))) &&
|
||||
isKnownNonNegative(getSCEV(U->getOperand(1))))
|
||||
return getUDivExpr(getSCEV(U->getOperand(0)), getSCEV(U->getOperand(1)));
|
||||
break;
|
||||
|
||||
case Instruction::SRem:
|
||||
// If both operands are non-negative, this is just an urem.
|
||||
if (isKnownNonNegative(getSCEV(U->getOperand(0))) &&
|
||||
isKnownNonNegative(getSCEV(U->getOperand(1))))
|
||||
return getURemExpr(getSCEV(U->getOperand(0)), getSCEV(U->getOperand(1)));
|
||||
break;
|
||||
|
||||
// It's tempting to handle inttoptr and ptrtoint as no-ops, however this can
|
||||
// lead to pointer expressions which cannot safely be expanded to GEPs,
|
||||
// because ScalarEvolution doesn't respect the GEP aliasing rules when
|
||||
|
|
|
@ -14,11 +14,11 @@ define dso_local void @_Z4loopi(i32 %width) local_unnamed_addr #0 {
|
|||
; CHECK-NEXT: %i.0 = phi i32 [ 0, %entry ], [ %inc, %for.body ]
|
||||
; CHECK-NEXT: --> {0,+,1}<nuw><nsw><%for.cond> U: [0,-2147483648) S: [0,-2147483648) Exits: %width LoopDispositions: { %for.cond: Computable }
|
||||
; CHECK-NEXT: %rem = sdiv i32 %i.0, 2
|
||||
; CHECK-NEXT: --> %rem U: full-set S: [-1073741824,1073741824) Exits: <<Unknown>> LoopDispositions: { %for.cond: Variant }
|
||||
; CHECK-NEXT: --> ({0,+,1}<nuw><nsw><%for.cond> /u 2) U: [0,1073741824) S: [0,1073741824) Exits: (%width /u 2) LoopDispositions: { %for.cond: Computable }
|
||||
; CHECK-NEXT: %idxprom = sext i32 %rem to i64
|
||||
; CHECK-NEXT: --> (sext i32 %rem to i64) U: [-2147483648,2147483648) S: [-1073741824,1073741824) Exits: <<Unknown>> LoopDispositions: { %for.cond: Variant }
|
||||
; CHECK-NEXT: --> ({0,+,1}<nuw><nsw><%for.cond> /u 2) U: [0,2147483648) S: [0,2147483648) Exits: ((zext i32 %width to i64) /u 2) LoopDispositions: { %for.cond: Computable }
|
||||
; CHECK-NEXT: %arrayidx = getelementptr inbounds [2 x i32], [2 x i32]* %storage, i64 0, i64 %idxprom
|
||||
; CHECK-NEXT: --> ((4 * (sext i32 %rem to i64))<nsw> + %storage)<nsw> U: [0,-3) S: [-9223372036854775808,9223372036854775805) Exits: <<Unknown>> LoopDispositions: { %for.cond: Variant }
|
||||
; CHECK-NEXT: --> ((4 * ({0,+,1}<nuw><nsw><%for.cond> /u 2))<nuw><nsw> + %storage)<nsw> U: [0,-3) S: [-9223372036854775808,9223372036854775805) Exits: ((4 * ((zext i32 %width to i64) /u 2))<nuw><nsw> + %storage)<nsw> LoopDispositions: { %for.cond: Computable }
|
||||
; CHECK-NEXT: %1 = load i32, i32* %arrayidx, align 4
|
||||
; CHECK-NEXT: --> %1 U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %for.cond: Variant }
|
||||
; CHECK-NEXT: %call = call i32 @_Z3adji(i32 %1)
|
||||
|
|
|
@ -14,11 +14,11 @@ define dso_local void @_Z4loopi(i32 %width) local_unnamed_addr #0 {
|
|||
; CHECK-NEXT: %i.0 = phi i32 [ 0, %entry ], [ %inc, %for.body ]
|
||||
; CHECK-NEXT: --> {0,+,1}<nuw><nsw><%for.cond> U: [0,-2147483648) S: [0,-2147483648) Exits: %width LoopDispositions: { %for.cond: Computable }
|
||||
; CHECK-NEXT: %rem = srem i32 %i.0, 2
|
||||
; CHECK-NEXT: --> %rem U: [0,2) S: [-2,2) Exits: <<Unknown>> LoopDispositions: { %for.cond: Variant }
|
||||
; CHECK-NEXT: --> (zext i1 {false,+,true}<%for.cond> to i32) U: [0,2) S: [0,2) Exits: (zext i1 (trunc i32 %width to i1) to i32) LoopDispositions: { %for.cond: Computable }
|
||||
; CHECK-NEXT: %idxprom = sext i32 %rem to i64
|
||||
; CHECK-NEXT: --> (sext i32 %rem to i64) U: [0,2) S: [-2,2) Exits: <<Unknown>> LoopDispositions: { %for.cond: Variant }
|
||||
; CHECK-NEXT: --> (zext i1 {false,+,true}<%for.cond> to i64) U: [0,2) S: [0,2) Exits: (zext i1 (trunc i32 %width to i1) to i64) LoopDispositions: { %for.cond: Computable }
|
||||
; CHECK-NEXT: %arrayidx = getelementptr inbounds [2 x i32], [2 x i32]* %storage, i64 0, i64 %idxprom
|
||||
; CHECK-NEXT: --> ((4 * (sext i32 %rem to i64))<nuw><nsw> + %storage)<nsw> U: [0,-3) S: [-9223372036854775808,9223372036854775805) Exits: <<Unknown>> LoopDispositions: { %for.cond: Variant }
|
||||
; CHECK-NEXT: --> ((4 * (zext i1 {false,+,true}<%for.cond> to i64))<nuw><nsw> + %storage)<nsw> U: [0,-3) S: [-9223372036854775808,9223372036854775805) Exits: ((4 * (zext i1 (trunc i32 %width to i1) to i64))<nuw><nsw> + %storage)<nsw> LoopDispositions: { %for.cond: Computable }
|
||||
; CHECK-NEXT: %1 = load i32, i32* %arrayidx, align 4
|
||||
; CHECK-NEXT: --> %1 U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %for.cond: Variant }
|
||||
; CHECK-NEXT: %call = call i32 @_Z3adji(i32 %1)
|
||||
|
|
Loading…
Reference in New Issue