forked from OSchip/llvm-project
[LoopInterchange] Fix legality for triangular loops
This is a bug fix in legality check.
When we encounter triangular loops such as the following form:
for (int i = 0; i < m; i++)
for (int j = 0; j < i; j++), or
for (int i = 0; i < m; i++)
for (int j = 0; j*i < n; j++),
we should not perform interchange since the number of executions of the loop body
will be different before and after interchange, resulting in incorrect results.
Reviewed By: bmahjour
Differential Revision: https://reviews.llvm.org/D101305
This commit is contained in:
Congzhe Cao
CongzheUalberta
parent
c58912eca7
commit
29342291d2
|
|
@ -656,6 +656,65 @@ bool LoopInterchangeLegality::isLoopStructureUnderstood(
|
|||
return false;
|
||||
}
|
||||
}
|
||||
|
||||
// TODO: Handle triangular loops of another form.
|
||||
// e.g. for(int i=0;i<N;i++)
|
||||
// for(int j=0;j<i;j++)
|
||||
// or,
|
||||
// for(int i=0;i<N;i++)
|
||||
// for(int j=0;j*i<N;j++)
|
||||
BasicBlock *InnerLoopLatch = InnerLoop->getLoopLatch();
|
||||
BranchInst *InnerLoopLatchBI =
|
||||
dyn_cast<BranchInst>(InnerLoopLatch->getTerminator());
|
||||
if (!InnerLoopLatchBI->isConditional())
|
||||
return false;
|
||||
if (CmpInst *InnerLoopCmp =
|
||||
dyn_cast<CmpInst>(InnerLoopLatchBI->getCondition())) {
|
||||
Value *Op0 = InnerLoopCmp->getOperand(0);
|
||||
Value *Op1 = InnerLoopCmp->getOperand(1);
|
||||
|
||||
// LHS and RHS of the inner loop exit condition, e.g.,
|
||||
// in "for(int j=0;j<i;j++)", LHS is j and RHS is i.
|
||||
Value *Left = nullptr;
|
||||
Value *Right = nullptr;
|
||||
|
||||
// Check if V only involves inner loop induction variable.
|
||||
// Return true if V is InnerInduction, or a cast from
|
||||
// InnerInduction, or a binary operator that involves
|
||||
// InnerInduction and a constant.
|
||||
std::function<bool(Value *)> IsPathToIndVar;
|
||||
IsPathToIndVar = [&InnerInduction, &IsPathToIndVar](Value *V) -> bool {
|
||||
if (V == InnerInduction)
|
||||
return true;
|
||||
if (isa<Constant>(V))
|
||||
return true;
|
||||
Instruction *I = dyn_cast<Instruction>(V);
|
||||
if (!I)
|
||||
return false;
|
||||
if (isa<CastInst>(I))
|
||||
return IsPathToIndVar(I->getOperand(0));
|
||||
if (isa<BinaryOperator>(I))
|
||||
return IsPathToIndVar(I->getOperand(0)) &&
|
||||
IsPathToIndVar(I->getOperand(1));
|
||||
return false;
|
||||
};
|
||||
|
||||
if (IsPathToIndVar(Op0) && !isa<Constant>(Op0)) {
|
||||
Left = Op0;
|
||||
Right = Op1;
|
||||
} else if (IsPathToIndVar(Op1) && !isa<Constant>(Op1)) {
|
||||
Left = Op1;
|
||||
Right = Op0;
|
||||
}
|
||||
|
||||
if (Left == nullptr)
|
||||
return false;
|
||||
|
||||
const SCEV *S = SE->getSCEV(Right);
|
||||
if (!SE->isLoopInvariant(S, OuterLoop))
|
||||
return false;
|
||||
}
|
||||
|
||||
return true;
|
||||
}
|
||||
|
||||
|
|
|
|||
|
|
@ -0,0 +1,152 @@
|
|||
; RUN: opt < %s -basic-aa -loop-interchange -verify-dom-info -verify-loop-info \
|
||||
; RUN: -S -debug 2>&1 | FileCheck %s
|
||||
|
||||
@A = common global [100 x [100 x i64]] zeroinitializer
|
||||
@N = dso_local local_unnamed_addr global i64 100, align 8
|
||||
|
||||
|
||||
;; for(int i=0;i<100;i++)
|
||||
;; for(int j=0;j<i;j++)
|
||||
;; A[j][i] = A[j][i]+k;
|
||||
|
||||
;; Inner loop induction variable exit condition depends on the
|
||||
;; outer loop induction variable, i.e., triangular loops.
|
||||
; CHECK: Loop structure not understood by pass
|
||||
; CHECK: Not interchanging loops. Cannot prove legality.
|
||||
|
||||
define void @interchange_01(i64 %k) {
|
||||
entry:
|
||||
br label %for1.header
|
||||
|
||||
for1.header:
|
||||
%i = phi i64 [ 0, %entry ], [ %i.next, %for1.inc10 ]
|
||||
br label %for2
|
||||
|
||||
for2:
|
||||
%j = phi i64 [ %j.next, %for2 ], [ 0, %for1.header ]
|
||||
%arrayidx5 = getelementptr inbounds [100 x [100 x i64]], [100 x [100 x i64]]* @A, i64 0, i64 %j, i64 %i
|
||||
%lv = load i64, i64* %arrayidx5
|
||||
%add = add nsw i64 %lv, %k
|
||||
store i64 %add, i64* %arrayidx5
|
||||
%j.next = add nuw nsw i64 %j, 1
|
||||
%exitcond = icmp eq i64 %j, %i
|
||||
br i1 %exitcond, label %for1.inc10, label %for2
|
||||
|
||||
for1.inc10:
|
||||
%i.next = add nuw nsw i64 %i, 1
|
||||
%exitcond26 = icmp eq i64 %i, 99
|
||||
br i1 %exitcond26, label %for.end12, label %for1.header
|
||||
|
||||
for.end12:
|
||||
ret void
|
||||
}
|
||||
|
||||
|
||||
;; for(int i=0;i<100;i++)
|
||||
;; for(int j=0;j+i<100;j++)
|
||||
;; A[j][i] = A[j][i]+k;
|
||||
|
||||
;; Inner loop induction variable exit condition depends on the
|
||||
;; outer loop induction variable, i.e., triangular loops.
|
||||
; CHECK: Loop structure not understood by pass
|
||||
; CHECK: Not interchanging loops. Cannot prove legality.
|
||||
|
||||
define void @interchange_02(i64 %k) {
|
||||
entry:
|
||||
br label %for1.header
|
||||
|
||||
for1.header:
|
||||
%i = phi i64 [ 0, %entry ], [ %i.next, %for1.inc10 ]
|
||||
br label %for2
|
||||
|
||||
for2:
|
||||
%j = phi i64 [ %j.next, %for2 ], [ 0, %for1.header ]
|
||||
%arrayidx5 = getelementptr inbounds [100 x [100 x i64]], [100 x [100 x i64]]* @A, i64 0, i64 %j, i64 %i
|
||||
%lv = load i64, i64* %arrayidx5
|
||||
%add = add nsw i64 %lv, %k
|
||||
store i64 %add, i64* %arrayidx5
|
||||
%0 = add nuw nsw i64 %j, %i
|
||||
%j.next = add nuw nsw i64 %j, 1
|
||||
%exitcond = icmp eq i64 %0, 100
|
||||
br i1 %exitcond, label %for1.inc10, label %for2
|
||||
|
||||
for1.inc10:
|
||||
%i.next = add nuw nsw i64 %i, 1
|
||||
%exitcond26 = icmp eq i64 %i, 99
|
||||
br i1 %exitcond26, label %for.end12, label %for1.header
|
||||
|
||||
for.end12:
|
||||
ret void
|
||||
}
|
||||
|
||||
;; for(int i=0;i<100;i++)
|
||||
;; for(int j=0;i>j;j++)
|
||||
;; A[j][i] = A[j][i]+k;
|
||||
|
||||
;; Inner loop induction variable exit condition depends on the
|
||||
;; outer loop induction variable, i.e., triangular loops.
|
||||
; CHECK: Loop structure not understood by pass
|
||||
; CHECK: Not interchanging loops. Cannot prove legality.
|
||||
|
||||
define void @interchange_03(i64 %k) {
|
||||
entry:
|
||||
br label %for1.header
|
||||
|
||||
for1.header:
|
||||
%i = phi i64 [ 0, %entry ], [ %i.next, %for1.inc10 ]
|
||||
br label %for2
|
||||
|
||||
for2:
|
||||
%j = phi i64 [ %j.next, %for2 ], [ 0, %for1.header ]
|
||||
%arrayidx5 = getelementptr inbounds [100 x [100 x i64]], [100 x [100 x i64]]* @A, i64 0, i64 %j, i64 %i
|
||||
%lv = load i64, i64* %arrayidx5
|
||||
%add = add nsw i64 %lv, %k
|
||||
store i64 %add, i64* %arrayidx5
|
||||
%j.next = add nuw nsw i64 %j, 1
|
||||
%exitcond = icmp ne i64 %i, %j
|
||||
br i1 %exitcond, label %for2, label %for1.inc10
|
||||
|
||||
for1.inc10:
|
||||
%i.next = add nuw nsw i64 %i, 1
|
||||
%exitcond26 = icmp eq i64 %i, 99
|
||||
br i1 %exitcond26, label %for.end12, label %for1.header
|
||||
|
||||
for.end12:
|
||||
ret void
|
||||
}
|
||||
|
||||
;; for(int i=0;i<100;i++)
|
||||
;; for(int j=0;N>j;j++)
|
||||
;; A[j][i] = A[j][i]+k;
|
||||
|
||||
;; Inner loop induction variable exit condition depends on
|
||||
;; an outer loop invariant, can do interchange.
|
||||
; CHECK: Loops interchanged
|
||||
|
||||
define void @interchange_04(i64 %k) {
|
||||
entry:
|
||||
%0 = load i64, i64* @N, align 4
|
||||
br label %for1.header
|
||||
|
||||
for1.header:
|
||||
%i = phi i64 [ 0, %entry ], [ %i.next, %for1.inc10 ]
|
||||
br label %for2
|
||||
|
||||
for2:
|
||||
%j = phi i64 [ %j.next, %for2 ], [ 0, %for1.header ]
|
||||
%arrayidx5 = getelementptr inbounds [100 x [100 x i64]], [100 x [100 x i64]]* @A, i64 0, i64 %j, i64 %i
|
||||
%lv = load i64, i64* %arrayidx5
|
||||
%add = add nsw i64 %lv, %k
|
||||
store i64 %add, i64* %arrayidx5
|
||||
%j.next = add nuw nsw i64 %j, 1
|
||||
%exitcond = icmp ne i64 %0, %j
|
||||
br i1 %exitcond, label %for2, label %for1.inc10
|
||||
|
||||
for1.inc10:
|
||||
%i.next = add nuw nsw i64 %i, 1
|
||||
%exitcond26 = icmp eq i64 %i, 99
|
||||
br i1 %exitcond26, label %for.end12, label %for1.header
|
||||
|
||||
for.end12:
|
||||
ret void
|
||||
}
|
||||
Loading…
Reference in New Issue