[ARM] add overrides for isCheapToSpeculateCttz() and isCheapToSpeculateCtlz()

ARM V6T2 has instructions for efficient count-leading/trailing-zeros, so this should be
considered a cheap operation (and therefore fair game for speculation) for any ARM V6T2
implementation.

The net result of allowing this speculation for the regression tests in this patch is
that we get this code:

ctlz:               
  clz  r0, r0
  bx  lr
cttz:              
  rbit  r0, r0
  clz  r0, r0
  bx  lr

Instead of:

ctlz:    
  cmp  r0, 
  moveq  r0, 
  clzne  r0, r0
  bx  lr
cttz:     
  cmp   r0, 
  moveq  r0, 
  rbitne  r0, r0
  clzne  r0, r0
  bx  lr

This will help solve a general speculation/despeculation problem noted in PR24818:
https://llvm.org/bugs/show_bug.cgi?id=24818

Differential Revision: http://reviews.llvm.org/D14469

llvm-svn: 252639
This commit is contained in:
Sanjay Patel 2015-11-10 19:24:31 +00:00
parent 8cf44d9684
commit af1b48bfdc
4 changed files with 59 additions and 0 deletions
llvm
lib/Target/ARM
test/Transforms/SimplifyCFG/ARM

View File

@ -11841,6 +11841,14 @@ bool ARMTargetLowering::canCombineStoreAndExtract(Type *VectorTy, Value *Idx,
return false;
}
bool ARMTargetLowering::isCheapToSpeculateCttz() const {
return Subtarget->hasV6T2Ops();
}
bool ARMTargetLowering::isCheapToSpeculateCtlz() const {
return Subtarget->hasV6T2Ops();
}
Value *ARMTargetLowering::emitLoadLinked(IRBuilder<> &Builder, Value *Addr,
AtomicOrdering Ord) const {
Module *M = Builder.GetInsertBlock()->getParent()->getParent();

View File

@ -467,6 +467,9 @@ namespace llvm {
bool canCombineStoreAndExtract(Type *VectorTy, Value *Idx,
unsigned &Cost) const override;
bool isCheapToSpeculateCttz() const override;
bool isCheapToSpeculateCtlz() const override;
protected:
std::pair<const TargetRegisterClass *, uint8_t>
findRepresentativeClass(const TargetRegisterInfo *TRI,

View File

@ -0,0 +1,43 @@
; RUN: opt -S -simplifycfg -mtriple=arm -mattr=+v6t2 < %s | FileCheck %s
define i32 @ctlz(i32 %A) {
; CHECK-LABEL: @ctlz(
; CHECK: [[ICMP:%[A-Za-z0-9]+]] = icmp eq i32 %A, 0
; CHECK-NEXT: [[CTZ:%[A-Za-z0-9]+]] = tail call i32 @llvm.ctlz.i32(i32 %A, i1 true)
; CHECK-NEXT: [[SEL:%[A-Za-z0-9.]+]] = select i1 [[ICMP]], i32 32, i32 [[CTZ]]
; CHECK-NEXT: ret i32 [[SEL]]
entry:
%tobool = icmp eq i32 %A, 0
br i1 %tobool, label %cond.end, label %cond.true
cond.true:
%0 = tail call i32 @llvm.ctlz.i32(i32 %A, i1 true)
br label %cond.end
cond.end:
%cond = phi i32 [ %0, %cond.true ], [ 32, %entry ]
ret i32 %cond
}
define i32 @cttz(i32 %A) {
; CHECK-LABEL: @cttz(
; CHECK: [[ICMP:%[A-Za-z0-9]+]] = icmp eq i32 %A, 0
; CHECK-NEXT: [[CTZ:%[A-Za-z0-9]+]] = tail call i32 @llvm.cttz.i32(i32 %A, i1 true)
; CHECK-NEXT: [[SEL:%[A-Za-z0-9.]+]] = select i1 [[ICMP]], i32 32, i32 [[CTZ]]
; CHECK-NEXT: ret i32 [[SEL]]
entry:
%tobool = icmp eq i32 %A, 0
br i1 %tobool, label %cond.end, label %cond.true
cond.true:
%0 = tail call i32 @llvm.cttz.i32(i32 %A, i1 true)
br label %cond.end
cond.end:
%cond = phi i32 [ %0, %cond.true ], [ 32, %entry ]
ret i32 %cond
}
declare i32 @llvm.ctlz.i32(i32, i1)
declare i32 @llvm.cttz.i32(i32, i1)

View File

@ -0,0 +1,5 @@
config.suffixes = ['.ll']
targets = set(config.root.targets_to_build.split())
if not 'ARM' in targets:
config.unsupported = True