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

[Peeling] Extend the scope of peeling a bit 

Currently we allow peeling of the loops if there is a exiting latch block
and all other exits are blocks ending with deopt.

Actually we want that exit would end up with deopt unconditionally but
it is not required that exit itself ends with deopt.

Reviewers: reames, ashlykov, fhahn, apilipenko, fedor.sergeev
Reviewed By: apilipenko
Subscribers: hiraditya, zzheng, dantrushin, llvm-commits
Differential Revision: https://reviews.llvm.org/D81140
This commit is contained in:
Serguei Katkov 2020-06-03 17:56:08 +07:00
parent fa5d416efd
commit 29b2c1ca72
3 changed files with 49 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
llvm/lib/Transforms/Utils/LoopUnrollPeel.cpp
View File

@ -90,7 +90,7 @@ bool llvm::canPeel(Loop *L) {
const BranchInst *T = dyn_cast<BranchInst>(Latch->getTerminator());
return T && T->isConditional() && L->isLoopExiting(Latch) &&
all_of(Exits, [](const BasicBlock *BB) {
return BB->getTerminatingDeoptimizeCall();
return BB->getPostdominatingDeoptimizeCall();
});
}
}

2
llvm/lib/Transforms/Utils/LoopUtils.cpp
View File

@ -744,7 +744,7 @@ static BranchInst *getExpectedExitLoopLatchBranch(Loop *L) {
SmallVector<BasicBlock *, 4> ExitBlocks;
L->getUniqueNonLatchExitBlocks(ExitBlocks);
if (any_of(ExitBlocks, [](const BasicBlock *EB) {
return !EB->getTerminatingDeoptimizeCall();
return !EB->getPostdominatingDeoptimizeCall();
}))
return nullptr;

47
llvm/test/Transforms/LoopUnroll/peel-loop-pgo-deopt-pd.ll Normal file
View File

@ -0,0 +1,47 @@
; RUN: opt < %s -S -loop-unroll -unroll-runtime -unroll-peel-multi-deopt-exit 2>&1 | FileCheck %s
; Make sure that we can peel even if deopt block is not in immidiate exit.
; CHECK-LABEL: @basic
; CHECK: br i1 %c, label %{{.*}}, label %side_exit
; CHECK: br i1 %{{.*}}, label %[[NEXT0:.*]], label %exit
; CHECK: [[NEXT0]]:
; CHECK: br i1 %c, label %{{.*}}, label %side_exit
; CHECK: br i1 %{{.*}}, label %[[NEXT1:.*]], label %exit
define i32 @basic(i32* %p, i32 %k, i1 %c) #0 !prof !1 {
entry:
%cmp3 = icmp slt i32 0, %k
br i1 %cmp3, label %header, label %deopt
header:
br label %body
body:
%i = phi i32 [ 0, %header ], [ %inc, %backedge ]
%addr = getelementptr inbounds i32, i32* %p, i32 %i
store i32 %i, i32* %addr, align 4
%inc = add nsw i32 %i, 1
%cmp = icmp slt i32 %inc, %k
br i1 %c, label %backedge, label %side_exit, !prof !3
backedge:
br i1 %cmp, label %body, label %exit, !prof !2
exit:
ret i32 %i
side_exit:
br label %deopt
deopt:
%deopt_kind = phi i32 [0, %entry], [1, %side_exit]
%rval = call i32(...) @llvm.experimental.deoptimize.i32() [ "deopt"(i32 %deopt_kind) ]
ret i32 %rval
}
declare i32 @llvm.experimental.deoptimize.i32(...)
!1 = !{!"function_entry_count", i64 1}
!2 = !{!"branch_weights", i32 0, i32 1}
!3 = !{!"branch_weights", i32 1, i32 0}