RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-26 12:43:36 +01:00
Code Issues Projects Releases Wiki Activity

[LoopUnroll] Update branch weight for remainder loop

Browse Source 
Unrolling a loop with compile-time unknown trip count results in a remainder loop. The remainder loop executes the remaining iterations of the original loop when the original trip count is not a multiple of the unroll factor. For better profile counts maintenance throughout the optimization pipeline, I'm assigning an artificial weight to the latch branch of the remainder loop.

A remainder loop runs up to as many times as the unroll factor subtracted by 1. Therefore I'm assigning the maximum possible trip count as the back edge weight. This should be more accurate than the default non-profile weight, which assumes the back edge runs much more frequently than the exit edge.

Differential Revision: https://reviews.llvm.org/D83187
This commit is contained in:
Hongtao Yu 2020-07-04 20:24:11 -07:00
parent 4e76681a5e
commit cc553c933f
2 changed files with 66 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

32
lib/Transforms/Utils/LoopUnrollRuntime.cpp
View File

@ -27,6 +27,7 @@
#include "llvm/Analysis/ScalarEvolution.h"
#include "llvm/IR/BasicBlock.h"
#include "llvm/IR/Dominators.h"
#include "llvm/IR/MDBuilder.h"
#include "llvm/IR/Metadata.h"
#include "llvm/IR/Module.h"
#include "llvm/Support/CommandLine.h"
@ -505,6 +506,32 @@ static bool canProfitablyUnrollMultiExitLoop(
// know of kinds of multiexit loops that would benefit from unrolling.
}
// Assign the maximum possible trip count as the back edge weight for the
// remainder loop if the original loop comes with a branch weight.
static void updateLatchBranchWeightsForRemainderLoop(Loop *OrigLoop,
Loop *RemainderLoop,
uint64_t UnrollFactor) {
uint64_t TrueWeight, FalseWeight;
BranchInst *LatchBR =
cast<BranchInst>(OrigLoop->getLoopLatch()->getTerminator());
if (LatchBR->extractProfMetadata(TrueWeight, FalseWeight)) {
uint64_t ExitWeight = LatchBR->getSuccessor(0) == OrigLoop->getHeader()
? FalseWeight
: TrueWeight;
assert(UnrollFactor > 1);
uint64_t BackEdgeWeight = (UnrollFactor - 1) * ExitWeight;
BasicBlock *Header = RemainderLoop->getHeader();
BasicBlock *Latch = RemainderLoop->getLoopLatch();
auto *RemainderLatchBR = cast<BranchInst>(Latch->getTerminator());
unsigned HeaderIdx = (RemainderLatchBR->getSuccessor(0) == Header ? 0 : 1);
MDBuilder MDB(RemainderLatchBR->getContext());
MDNode *WeightNode =
HeaderIdx ? MDB.createBranchWeights(ExitWeight, BackEdgeWeight)
: MDB.createBranchWeights(BackEdgeWeight, ExitWeight);
RemainderLatchBR->setMetadata(LLVMContext::MD_prof, WeightNode);
}
}
/// Insert code in the prolog/epilog code when unrolling a loop with a
/// run-time trip-count.
///
@ -788,6 +815,11 @@ bool llvm::UnrollRuntimeLoopRemainder(
InsertTop, InsertBot,
NewPreHeader, NewBlocks, LoopBlocks, VMap, DT, LI);
// Assign the maximum possible trip count as the back edge weight for the
// remainder loop if the original loop comes with a branch weight.
if (remainderLoop && !UnrollRemainder)
updateLatchBranchWeightsForRemainderLoop(L, remainderLoop, Count);
// Insert the cloned blocks into the function.
F->getBasicBlockList().splice(InsertBot->getIterator(),
F->getBasicBlockList(),

34
test/Transforms/LoopUnroll/runtime-loop-branchweight.ll Normal file
View File

@ -0,0 +1,34 @@
; RUN: opt < %s -S -loop-unroll -unroll-runtime=true -unroll-count=4 | FileCheck %s
; RUN: opt < %s -S -passes=loop-unroll -unroll-runtime=true -unroll-count=4 | FileCheck %s
;; Check that the remainder loop is properly assigned a branch weight for its latch branch.
; CHECK-LABEL: @test(
; CHECK-LABEL: for.body:
; CHECK: br i1 [[COND1:%.*]], label %for.end.loopexit.unr-lcssa.loopexit, label %for.body, !prof ![[#PROF:]], !llvm.loop ![[#LOOP:]]
; CHECK-LABEL: for.body.epil:
; CHECK: br i1 [[COND2:%.*]], label %for.body.epil, label %for.end.loopexit.epilog-lcssa, !prof ![[#PROF2:]], !llvm.loop ![[#LOOP2:]]
; CHECK: ![[#PROF]] = !{!"branch_weights", i32 1, i32 9999}
; CHECK: ![[#PROF2]] = !{!"branch_weights", i32 3, i32 1}
define i3 @test(i3* %a, i3 %n) {
entry:
%cmp1 = icmp eq i3 %n, 0
br i1 %cmp1, label %for.end, label %for.body
for.body:
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
%sum.02 = phi i3 [ %add, %for.body ], [ 0, %entry ]
%arrayidx = getelementptr inbounds i3, i3* %a, i64 %indvars.iv
%0 = load i3, i3* %arrayidx
%add = add nsw i3 %0, %sum.02
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i3
%exitcond = icmp eq i3 %lftr.wideiv, %n
br i1 %exitcond, label %for.end, label %for.body, !prof !0
for.end:
%sum.0.lcssa = phi i3 [ 0, %entry ], [ %add, %for.body ]
ret i3 %sum.0.lcssa
}
!0 = !{!"branch_weights", i32 1, i32 9999}