[DA] Refactor with a better API

Refactor from iteratively using BitCastInst::getOperand()
to using stripPointerCasts() instead. This is an improvement
since now we are able to analyze more cases, please refer
to test cases added in this patch.

Reviewed By: Meinersbur, #loopoptwg

Differential Revision: https://reviews.llvm.org/D123559
This commit is contained in:
Congzhe Cao 2022-04-13 14:45:48 -04:00 committed by CongzheUalberta
parent 04641b2121
commit 557b131c88
2 changed files with 45 additions and 10 deletions

View File

@ -3349,12 +3349,8 @@ bool DependenceInfo::tryDelinearizeFixedSize(
return false;
}
Value *SrcBasePtr = SrcGEP->getOperand(0);
Value *DstBasePtr = DstGEP->getOperand(0);
while (auto *PCast = dyn_cast<BitCastInst>(SrcBasePtr))
SrcBasePtr = PCast->getOperand(0);
while (auto *PCast = dyn_cast<BitCastInst>(DstBasePtr))
DstBasePtr = PCast->getOperand(0);
Value *SrcBasePtr = SrcGEP->getOperand(0)->stripPointerCasts();
Value *DstBasePtr = DstGEP->getOperand(0)->stripPointerCasts();
// Check that for identical base pointers we do not miss index offsets
// that have been added before this GEP is applied.

View File

@ -15,7 +15,8 @@
;; for (int j = 2; j < M; ++j)
;; a[i][j] = a[i+1][j-2];
;; }
;;
;; Note that there is a getelementptr with index 0, make sure we can analyze this case.
define void @t1([2048 x i32]* %a) {
entry:
br label %for.body
@ -30,7 +31,8 @@ for.body4: ; preds = %for.body, %for.body
%1 = add nsw i64 %indvars.iv, -2
%arrayidx6 = getelementptr inbounds [2048 x i32], [2048 x i32]* %a, i64 %0, i64 %1
%2 = load i32, i32* %arrayidx6, align 4
%arrayidx10 = getelementptr inbounds [2048 x i32], [2048 x i32]* %a, i64 %indvars.iv4, i64 %indvars.iv
%a_gep = getelementptr inbounds [2048 x i32], [2048 x i32]* %a, i64 0
%arrayidx10 = getelementptr inbounds [2048 x i32], [2048 x i32]* %a_gep, i64 %indvars.iv4, i64 %indvars.iv
store i32 %2, i32* %arrayidx10, align 4
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond = icmp ne i64 %indvars.iv.next, 2048
@ -45,8 +47,45 @@ for.end13: ; preds = %for.inc11
ret void
}
; CHECK-LABEL: t2
; CHECK: da analyze - consistent anti [1 -2]!
;; Similar to @t1 but includes a call with a "returned" arg, make sure we can analyze
;; this case.
define void @t2([2048 x i32]* %a) {
entry:
br label %for.body
for.body: ; preds = %entry, %for.inc11
%indvars.iv4 = phi i64 [ 0, %entry ], [ %indvars.iv.next5, %for.inc11 ]
br label %for.body4
for.body4: ; preds = %for.body, %for.body4
%indvars.iv = phi i64 [ 2, %for.body ], [ %indvars.iv.next, %for.body4 ]
%0 = add nuw nsw i64 %indvars.iv4, 1
%1 = add nsw i64 %indvars.iv, -2
%arrayidx6 = getelementptr inbounds [2048 x i32], [2048 x i32]* %a, i64 %0, i64 %1
%2 = load i32, i32* %arrayidx6, align 4
%call = call [2048 x i32]* @func_with_returned_arg([2048 x i32]* returned %a)
%arrayidx10 = getelementptr inbounds [2048 x i32], [2048 x i32]* %call, i64 %indvars.iv4, i64 %indvars.iv
store i32 %2, i32* %arrayidx10, align 4
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond = icmp ne i64 %indvars.iv.next, 2048
br i1 %exitcond, label %for.body4, label %for.inc11
for.inc11: ; preds = %for.body4
%indvars.iv.next5 = add nuw nsw i64 %indvars.iv4, 1
%exitcond7 = icmp ne i64 %indvars.iv.next5, 1023
br i1 %exitcond7, label %for.body, label %for.end13
for.end13: ; preds = %for.inc11
ret void
}
declare [2048 x i32]* @func_with_returned_arg([2048 x i32]* returned %arg)
; CHECK-LABEL: t3
; CHECK: da analyze - none!
; CHECK: da analyze - consistent anti [1 -2 0 -3 2]!
; CHECK: da analyze - none!
@ -62,7 +101,7 @@ for.end13: ; preds = %for.inc11
;; a[i1][i2][i3][i4][i5] = a[i1+1][i2-2][i3][i4-3][i5+2];
;; }
define void @t2([1024 x [1024 x [1024 x [2048 x i32]]]]* %a) {
define void @t3([1024 x [1024 x [1024 x [2048 x i32]]]]* %a) {
entry:
br label %for.body