Current findBestLoopTop can find and move one kind of block to top, a latch block has one successor. Another common case is:
* a latch block
* it has two successors, one is loop header, another is exit
* it has more than one predecessors
If it is below one of its predecessors P, only P can fall through to it, all other predecessors need a jump to it, and another conditional jump to loop header. If it is moved before loop header, all its predecessors jump to it, then fall through to loop header. So all its predecessors except P can reduce one taken branch.
Differential Revision: https://reviews.llvm.org/D43256
llvm-svn: 363471
47 lines
1.1 KiB
LLVM
47 lines
1.1 KiB
LLVM
; RUN: llc -mtriple=aarch64-linux-gnu -verify-machineinstrs -disable-block-placement -o - %s | FileCheck %s
|
|
; LSR used to pick a sub-optimal solution due to the target responding
|
|
; conservatively to isLegalAddImmediate for negative values.
|
|
|
|
declare void @foo(i32)
|
|
|
|
define void @test(i32 %px) {
|
|
; CHECK_LABEL: test:
|
|
; CHECK_LABEL: %entry
|
|
; CHECK: subs [[REG0:w[0-9]+]],
|
|
; CHECK: csel {{w[0-9]+}}, wzr, [[REG0]]
|
|
entry:
|
|
%sub = add nsw i32 %px, -1
|
|
%cmp = icmp slt i32 %px, 1
|
|
%.sub = select i1 %cmp, i32 0, i32 %sub
|
|
br label %for.body
|
|
|
|
for.body:
|
|
; CHECK_LABEL: %for.body
|
|
; CHECK: cmp
|
|
; CHECK-NEXT: b.eq
|
|
; CHECK-LABEL: %if.then3
|
|
%x.015 = phi i32 [ %inc, %for.inc ], [ %.sub, %entry ]
|
|
%cmp2 = icmp eq i32 %x.015, %px
|
|
br i1 %cmp2, label %for.inc, label %if.then3
|
|
|
|
if.then3:
|
|
tail call void @foo(i32 %x.015)
|
|
br label %for.inc
|
|
|
|
for.inc:
|
|
; CHECK_LABEL: %for.inc
|
|
; CHECK: cmp
|
|
; CHECK-NEXT: add
|
|
; CHECK-NEXT: b.le
|
|
; CHECK_LABEL: %for.cond.cleanup
|
|
%inc = add nsw i32 %x.015, 1
|
|
%cmp1 = icmp sgt i32 %x.015, %px
|
|
br i1 %cmp1, label %for.cond.cleanup.loopexit, label %for.body
|
|
|
|
for.cond.cleanup.loopexit:
|
|
br label %for.cond.cleanup
|
|
|
|
for.cond.cleanup:
|
|
ret void
|
|
}
|