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

[AArch64] Use LateSimplifyCFG after expanding atomic operations. 

Summary:
After r308422 we defer optimizations that can destroy loop canonical forms to
LateSimplifyCFG. Running LateSimplifyCFG after expanding atomic operations
can exploit more control-flow opportunities.

Reviewers: mcrosier, t.p.northover, efriedma

Reviewed By: efriedma

Subscribers: aemerson, rengolin, javed.absar, llvm-commits, kristof.beyls

Differential Revision: https://reviews.llvm.org/D38262

llvm-svn: 314857
This commit is contained in:
Balaram Makam 2017-10-03 22:39:24 +00:00
parent 6456455e29
commit e0c43152b5
3 changed files with 64 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
llvm/lib/Target/AArch64/AArch64TargetMachine.cpp
View File

@ -365,7 +365,7 @@ void AArch64PassConfig::addIRPasses() {
// determine whether it succeeded. We can exploit existing control-flow in
// ldrex/strex loops to simplify this, but it needs tidying up.
if (TM->getOptLevel() != CodeGenOpt::None && EnableAtomicTidy)
addPass(createCFGSimplificationPass());
addPass(createLateCFGSimplificationPass());
// Run LoopDataPrefetch
//

6
llvm/test/CodeGen/AArch64/aarch64-loop-gep-opt.ll
View File

@ -19,9 +19,9 @@ entry:
do.body.i:
; CHECK-LABEL: do.body.i:
; CHECK: %uglygep1 = getelementptr i8, i8* %uglygep, i64 %3
; CHECK-NEXT: %4 = bitcast i8* %uglygep1 to i32*
; CHECK-NOT: %uglygep1 = getelementptr i8, i8* %uglygep, i64 1032
; CHECK: %uglygep2 = getelementptr i8, i8* %uglygep, i64 %3
; CHECK-NEXT: %4 = bitcast i8* %uglygep2 to i32*
; CHECK-NOT: %uglygep2 = getelementptr i8, i8* %uglygep, i64 1032
%0 = phi i32 [ 256, %entry ], [ %.be, %do.body.i.backedge ]

60
llvm/test/CodeGen/AArch64/cmpxchg-idioms.ll
View File

@ -91,3 +91,63 @@ end:
declare void @bar()
declare void @baz()
define i1 @test_conditional2(i32 %a, i32 %b, i32* %c) {
; CHECK-LABEL: test_conditional2:
; CHECK: [[LOOP:LBB[0-9]+_[0-9]+]]:
; CHECK: ldaxr [[LOADED:w[0-9]+]], [x19]
; CHECK: cmp [[LOADED]], w21
; CHECK: b.ne [[FAILED:LBB[0-9]+_[0-9]+]]
; CHECK: stlxr [[STATUS:w[0-9]+]], w20, [x19]
; CHECK: cbnz [[STATUS]], [[LOOP]]
; CHECK: orr [[STATUS]], wzr, #0x1
; CHECK: b [[PH:LBB[0-9]+_[0-9]+]]
; CHECK: [[FAILED]]:
; CHECK-NOT: cmp {{w[0-9]+}}, {{w[0-9]+}}
; verify the preheader is simplified by latesimplifycfg.
; CHECK: [[PH]]:
; CHECK: orr w22, wzr, #0x2
; CHECK-NOT: orr w22, wzr, #0x4
; CHECK-NOT: cmn w22, #4
; CHECK: b [[LOOP2:LBB[0-9]+_[0-9]+]]
; CHECK-NOT: b.ne [[LOOP2]]
; CHECK-NOT: b {{LBB[0-9]+_[0-9]+}}
; CHECK: bl _foo
entry:
%pair = cmpxchg i32* %c, i32 %a, i32 %b seq_cst seq_cst
%success = extractvalue { i32, i1 } %pair, 1
br label %for.cond
for.cond: ; preds = %if.end, %entry
%i.0 = phi i32 [ 2, %entry ], [ %dec, %if.end ]
%changed.0.off0 = phi i1 [ %success, %entry ], [ %changed.1.off0, %if.end ]
%dec = add nsw i32 %i.0, -1
%tobool = icmp eq i32 %i.0, 0
br i1 %tobool, label %for.cond.cleanup, label %for.body
for.cond.cleanup: ; preds = %for.cond
%changed.0.off0.lcssa = phi i1 [ %changed.0.off0, %for.cond ]
ret i1 %changed.0.off0.lcssa
for.body: ; preds = %for.cond
%or = or i32 %a, %b
%idxprom = sext i32 %dec to i64
%arrayidx = getelementptr inbounds i32, i32* %c, i64 %idxprom
%0 = load i32, i32* %arrayidx, align 4
%cmp = icmp eq i32 %or, %0
br i1 %cmp, label %if.end, label %if.then
if.then: ; preds = %for.body
store i32 %or, i32* %arrayidx, align 4
tail call void @foo()
br label %if.end
if.end: ; preds = %for.body, %if.then
%changed.1.off0 = phi i1 [ false, %if.then ], [ %changed.0.off0, %for.body ]
br label %for.cond
}
declare void @foo()