forked from OSchip/llvm-project
[IndVars] Use more precise context when eliminating narrowing
When deciding to widen narrow use, we may need to prove some facts about it. For proof, the context is used. Currently we take the instruction being widened as the context. However, we may be more precise here if we take as context the point that dominates all users of instruction being widened. Differential Revision: https://reviews.llvm.org/D90456 Reviewed By: skatkov
This commit is contained in:
parent
8e6d92026c
commit
28d7ba1543
|
@ -1561,6 +1561,21 @@ bool WidenIV::widenWithVariantUse(WidenIV::NarrowIVDefUse DU) {
|
|||
return true;
|
||||
}
|
||||
|
||||
// We'll prove some facts that should be true in the context of ext users. If
|
||||
// there is no users, we are done now. If there are some, pick their common
|
||||
// dominator as context.
|
||||
Instruction *Context = nullptr;
|
||||
for (auto *Ext : ExtUsers) {
|
||||
if (!Context || DT->dominates(Ext, Context))
|
||||
Context = Ext;
|
||||
else if (!DT->dominates(Context, Ext))
|
||||
// For users that don't have dominance relation, use common dominator.
|
||||
Context =
|
||||
DT->findNearestCommonDominator(Context->getParent(), Ext->getParent())
|
||||
->getTerminator();
|
||||
}
|
||||
assert(Context && "Context not found?");
|
||||
|
||||
if (!CanSignExtend && !CanZeroExtend) {
|
||||
// Because InstCombine turns 'sub nuw' to 'add' losing the no-wrap flag, we
|
||||
// will most likely not see it. Let's try to prove it.
|
||||
|
@ -1573,7 +1588,7 @@ bool WidenIV::widenWithVariantUse(WidenIV::NarrowIVDefUse DU) {
|
|||
if (!SE->isKnownNegative(RHS))
|
||||
return false;
|
||||
bool ProvedSubNUW = SE->isKnownPredicateAt(
|
||||
ICmpInst::ICMP_UGE, LHS, SE->getNegativeSCEV(RHS), NarrowUse);
|
||||
ICmpInst::ICMP_UGE, LHS, SE->getNegativeSCEV(RHS), Context);
|
||||
if (!ProvedSubNUW)
|
||||
return false;
|
||||
// In fact, our 'add' is 'sub nuw'. We will need to widen the 2nd operand as
|
||||
|
|
|
@ -554,16 +554,13 @@ define i32 @test11(i32 %start, i32* %p, i32* %q) {
|
|||
; CHECK-NEXT: br label [[LOOP:%.*]]
|
||||
; CHECK: loop:
|
||||
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[BACKEDGE:%.*]] ], [ [[TMP0]], [[ENTRY:%.*]] ]
|
||||
; CHECK-NEXT: [[TMP1:%.*]] = trunc i64 [[INDVARS_IV]] to i32
|
||||
; CHECK-NEXT: [[IV_NEXT:%.*]] = add i32 [[TMP1]], -1
|
||||
; CHECK-NEXT: [[TMP1:%.*]] = add nsw i64 [[INDVARS_IV]], -1
|
||||
; CHECK-NEXT: [[COND:%.*]] = icmp eq i64 [[INDVARS_IV]], 0
|
||||
; CHECK-NEXT: br i1 [[COND]], label [[EXIT:%.*]], label [[BACKEDGE]]
|
||||
; CHECK: backedge:
|
||||
; CHECK-NEXT: [[INDEX:%.*]] = zext i32 [[IV_NEXT]] to i64
|
||||
; CHECK-NEXT: [[STORE_ADDR:%.*]] = getelementptr i32, i32* [[P:%.*]], i64 [[INDEX]]
|
||||
; CHECK-NEXT: [[STORE_ADDR:%.*]] = getelementptr i32, i32* [[P:%.*]], i64 [[TMP1]]
|
||||
; CHECK-NEXT: store i32 1, i32* [[STORE_ADDR]], align 4
|
||||
; CHECK-NEXT: [[LOAD_ADDR:%.*]] = getelementptr i32, i32* [[Q:%.*]], i64 [[INDEX]]
|
||||
; CHECK-NEXT: [[STOP:%.*]] = load i32, i32* [[Q]], align 4
|
||||
; CHECK-NEXT: [[STOP:%.*]] = load i32, i32* [[Q:%.*]], align 4
|
||||
; CHECK-NEXT: [[LOOP_COND:%.*]] = icmp eq i32 [[STOP]], 0
|
||||
; CHECK-NEXT: [[INDVARS_IV_NEXT]] = add nsw i64 [[INDVARS_IV]], -1
|
||||
; CHECK-NEXT: br i1 [[LOOP_COND]], label [[LOOP]], label [[FAILURE:%.*]]
|
||||
|
|
Loading…
Reference in New Issue