maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[IndVars] Change the order to compute WidenAddRec in widenIVUse. 

When both WidenIV::getWideRecurrence and WidenIV::getExtendedOperandRecurrence
return non-null but different WideAddRec, if getWideRecurrence is called
before getExtendedOperandRecurrence, we won't bother to call
getExtendedOperandRecurrence again. But As we know it is possible that after
SCEV folding, we cannot prove the legality using the SCEVAddRecExpr returned
by getWideRecurrence. Meanwhile if getExtendedOperandRecurrence returns non-null
WideAddRec, we know for sure that it is legal to do widening for current instruction.
So it is better to put getExtendedOperandRecurrence before getWideRecurrence, which
will increase the chance of successful widening.

Differential Revision: https://reviews.llvm.org/D26059

llvm-svn: 286987
This commit is contained in:
Wei Mi 2016-11-15 17:34:52 +00:00
parent 6d279e8e98
commit d2948cef70
3 changed files with 65 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
llvm/lib/Transforms/Scalar/IndVarSimplify.cpp
View File

@ -1412,9 +1412,9 @@ Instruction *WidenIV::widenIVUse(NarrowIVDefUse DU, SCEVExpander &Rewriter) {
}
// Does this user itself evaluate to a recurrence after widening?
WidenedRecTy WideAddRec = getWideRecurrence(DU);
WidenedRecTy WideAddRec = getExtendedOperandRecurrence(DU);
if (!WideAddRec.first)
WideAddRec = getExtendedOperandRecurrence(DU);
WideAddRec = getWideRecurrence(DU);
assert((WideAddRec.first == nullptr) == (WideAddRec.second == Unknown));
if (!WideAddRec.first) {

9
llvm/test/Transforms/IndVarSimplify/iv-widen-elim-ext.ll
View File

@ -21,8 +21,11 @@ define void @foo(i32* %A, i32* %B, i32* %C, i32 %N) {
; CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds i32, i32* %C, i64 [[TMP1]]
; CHECK-NEXT: [[TMP2:%.*]] = load i32, i32* [[ARRAYIDX2]], align 4
; CHECK-NEXT: [[ADD3:%.*]] = add nsw i32 [[TMP0]], [[TMP2]]
; CHECK-NEXT: [[TRUNC0:%.*]] = trunc i64 [[TMP1]] to i32
; CHECK-NEXT: [[DIV0:%.*]] = udiv i32 5, [[TRUNC0]]
; CHECK-NEXT: [[ADD4:%.*]] = add nsw i32 [[ADD3]], [[DIV0]]
; CHECK-NEXT: [[ARRAYIDX5:%.*]] = getelementptr inbounds i32, i32* %A, i64 [[INDVARS_IV]]
; CHECK-NEXT: store i32 [[ADD3]], i32* [[ARRAYIDX5]], align 4
; CHECK-NEXT: store i32 [[ADD4]], i32* [[ARRAYIDX5]], align 4
; CHECK-NEXT: br label %for.inc
; CHECK: for.inc:
; CHECK-NEXT: [[INDVARS_IV_NEXT:%.*]] = add nuw nsw i64 [[INDVARS_IV]], 1
@ -51,9 +54,11 @@ for.body: ; preds = %for.body.lr.ph, %fo
%arrayidx2 = getelementptr inbounds i32, i32* %C, i64 %idxprom1
%1 = load i32, i32* %arrayidx2, align 4
%add3 = add nsw i32 %0, %1
%div0 = udiv i32 5, %add
%add4 = add nsw i32 %add3, %div0
%idxprom4 = zext i32 %i.02 to i64
%arrayidx5 = getelementptr inbounds i32, i32* %A, i64 %idxprom4
store i32 %add3, i32* %arrayidx5, align 4
store i32 %add4, i32* %arrayidx5, align 4
br label %for.inc
for.inc: ; preds = %for.body

56
llvm/test/Transforms/IndVarSimplify/iv-widen.ll
View File

@ -69,3 +69,59 @@ define void @loop_1(i32 %lim) {
declare void @dummy(i32)
declare void @dummy.i64(i64)
define void @loop_2(i32 %size, i32 %nsteps, i32 %hsize, i32* %lined, i8 %tmp1) {
; CHECK-LABEL: @loop_2(
entry:
%cmp215 = icmp sgt i32 %size, 1
%tmp0 = bitcast i32* %lined to i8*
br label %for.body
for.body:
%j = phi i32 [ 0, %entry ], [ %inc6, %for.inc ]
%mul = mul nsw i32 %j, %size
%add = add nsw i32 %mul, %hsize
br i1 %cmp215, label %for.body2, label %for.inc
; check that the induction variable of the inner loop has been widened after indvars.
; CHECK: [[INNERLOOPINV:%[^ ]+]] = add nsw i64
; CHECK: for.body2:
; CHECK-NEXT: %indvars.iv = phi i64 [ 1, %for.body2.preheader ], [ %indvars.iv.next, %for.body2 ]
; CHECK-NEXT: [[WIDENED:%[^ ]+]] = add nsw i64 [[INNERLOOPINV]], %indvars.iv
; CHECK-NEXT: %add.ptr = getelementptr inbounds i8, i8* %tmp0, i64 [[WIDENED]]
for.body2:
%k = phi i32 [ %inc, %for.body2 ], [ 1, %for.body ]
%add4 = add nsw i32 %add, %k
%idx.ext = sext i32 %add4 to i64
%add.ptr = getelementptr inbounds i8, i8* %tmp0, i64 %idx.ext
store i8 %tmp1, i8* %add.ptr, align 1
%inc = add nsw i32 %k, 1
%cmp2 = icmp slt i32 %inc, %size
br i1 %cmp2, label %for.body2, label %for.body3
; check that the induction variable of the inner loop has been widened after indvars.
; CHECK: for.body3.preheader:
; CHECK: [[INNERLOOPINV:%[^ ]+]] = zext i32
; CHECK: for.body3:
; CHECK-NEXT: %indvars.iv2 = phi i64 [ 1, %for.body3.preheader ], [ %indvars.iv.next3, %for.body3 ]
; CHECK-NEXT: [[WIDENED:%[^ ]+]] = add nuw nsw i64 [[INNERLOOPINV]], %indvars.iv2
; CHECK-NEXT: %add.ptr2 = getelementptr inbounds i8, i8* %tmp0, i64 [[WIDENED]]
for.body3:
%l = phi i32 [ %inc2, %for.body3 ], [ 1, %for.body2 ]
%add5 = add nuw i32 %add, %l
%idx.ext2 = zext i32 %add5 to i64
%add.ptr2 = getelementptr inbounds i8, i8* %tmp0, i64 %idx.ext2
store i8 %tmp1, i8* %add.ptr2, align 1
%inc2 = add nsw i32 %l, 1
%cmp3 = icmp slt i32 %inc2, %size
br i1 %cmp3, label %for.body3, label %for.inc
for.inc:
%inc6 = add nsw i32 %j, 1
%cmp = icmp slt i32 %inc6, %nsteps
br i1 %cmp, label %for.body, label %for.end.loopexit
for.end.loopexit:
ret void
}