RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-25 20:39:47 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

[AArch64] add overrides for isCheapToSpeculateCttz() and isCheapToSpeculateCtlz()

Browse Source 
AArch64 has instructions for efficient count-leading/trailing-zeros, so this should be
considered a cheap operation (and therefore fair game for speculation) for any AArch64
implementation.

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

ctlz:
  clz  w0, w0
  ret

cttz:
  rbit  w8, w0
  clz  w0, w8
  ret

Instead of:

ctlz:
  cbz  w0, .LBB0_2
  clz  w0, w0
  ret
.LBB0_2:
  orr  w0, wzr, #0x20
  ret

cttz:
  cbz  w0, .LBB1_2
  rbit  w8, w0
  clz  w0, w8
  ret
.LBB1_2:
  orr  w0, wzr, #0x20
  ret

See D14469 for the larger motivation.

Differential Revision: http://reviews.llvm.org/D14505

llvm-svn: 252625
This commit is contained in:
Sanjay Patel 2015-11-10 18:11:37 +00:00
parent 2143e4c7a3
commit d4ce17626c
2 changed files with 51 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
lib/Target/AArch64/AArch64ISelLowering.h
View File

@ -381,6 +381,14 @@ public:
return AArch64::X1;
}
bool isCheapToSpeculateCttz() const override {
return true;
}
bool isCheapToSpeculateCtlz() const override {
return true;
}
private:
bool isExtFreeImpl(const Instruction *Ext) const override;

43
test/Transforms/SimplifyCFG/AArch64/cttz-ctlz.ll Normal file
View File

@ -0,0 +1,43 @@
; RUN: opt -S -simplifycfg -mtriple=aarch64 < %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)