mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-25 14:02:52 +02:00
d4ce17626c
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
44 lines
1.2 KiB
LLVM
44 lines
1.2 KiB
LLVM
; 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)
|
|
|