RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-19 11:02:59 +02:00
Code Issues Projects Releases Wiki Activity

[SCEV] Use mustprogress flag on loops (in addition to function attribute)

Browse Source 
This addresses a performance regression reported against 3c6e4191.  That change (correctly) limited a transform based on assumed finiteness to mustprogress loops, but the previous change (38540d7) which introduced the mustprogress check utility only handled function attributes, not the loop metadata form.

It turns out that clang uses the function attribute form for C++, and the loop metadata form for C.  As a result, 3c6e4191 ended up being a large regression in practice for C code as loops weren't being considered mustprogress despite the language semantics.
This commit is contained in:
Philip Reames 2021-06-10 13:16:50 -07:00
parent 52d05589ca
commit d870f55264
2 changed files with 28 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
lib/Analysis/ScalarEvolution.cpp
View File

@ -6579,8 +6579,8 @@ ScalarEvolution::getLoopProperties(const Loop *L) {
}
bool ScalarEvolution::loopIsFiniteByAssumption(const Loop *L) {
// TODO: Use the loop metadata form of mustprogress as well.
if (!L->getHeader()->getParent()->mustProgress())
if (!L->getHeader()->getParent()->mustProgress() &&
!hasMustProgress(L))
return false;
// A loop without side effects must be finite.

26
test/Analysis/ScalarEvolution/trip-count-unknown-stride.ll
View File

@ -82,3 +82,29 @@ for.body: ; preds = %entry, %for.body
for.end: ; preds = %for.body, %entry
ret void
}
; Same as foo2, but with mustprogress on loop, not function
; CHECK: Determining loop execution counts for: @foo4
; CHECK: backedge-taken count is ((-1 + (%n smax %s)) /u %s)
; CHECK: max backedge-taken count is -1
define void @foo4(i32* nocapture %A, i32 %n, i32 %s) {
entry:
br label %for.body
for.body: ; preds = %entry, %for.body
%i.05 = phi i32 [ %add, %for.body ], [ 0, %entry ]
%arrayidx = getelementptr inbounds i32, i32* %A, i32 %i.05
%0 = load i32, i32* %arrayidx, align 4
%inc = add nsw i32 %0, 1
store i32 %inc, i32* %arrayidx, align 4
%add = add nsw i32 %i.05, %s
%cmp = icmp slt i32 %add, %n
br i1 %cmp, label %for.body, label %for.end, !llvm.loop !8
for.end: ; preds = %for.body, %entry
ret void
}
!8 = distinct !{!8, !9}
!9 = !{!"llvm.loop.mustprogress"}