mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-30 23:42:52 +01:00
aa5932cde5
Instead of having a bunch of separate MOV8r0, MOV16r0, ... pseudo-instructions, it's better to use a single MOV32r0 (which will expand to "xorl %reg, %reg") and obtain other sizes with EXTRACT_SUBREG and SUBREG_TO_REG. The encoding is smaller and partial register updates can sometimes be avoided. Until recently, this sequence was a barrier to rematerialization though. That should now be fixed so it's an appropriate time to make the change. llvm-svn: 182928
43 lines
1.2 KiB
LLVM
43 lines
1.2 KiB
LLVM
; RUN: llc -march=x86-64 -mcpu=generic -mtriple=x86_64-unknown-linux-gnu -relocation-model=static -asm-verbose=false < %s | FileCheck %s
|
|
; RUN: llc -march=x86-64 -mcpu=atom -mtriple=x86_64-unknown-linux-gnu -relocation-model=static -asm-verbose=false < %s | FileCheck -check-prefix=ATOM %s
|
|
|
|
; CHECK: xorl %eax, %eax
|
|
; CHECK: movsd .LCPI0_0(%rip), %xmm0
|
|
; CHECK: align
|
|
; CHECK-NEXT: BB0_2:
|
|
; CHECK-NEXT: movsd A(,%rax,8)
|
|
; CHECK-NEXT: mulsd
|
|
; CHECK-NEXT: movsd
|
|
; CHECK-NEXT: incq %rax
|
|
|
|
|
|
; ATOM: xorl %eax, %eax
|
|
; ATOM: movsd .LCPI0_0(%rip), %xmm0
|
|
; ATOM: align
|
|
; ATOM-NEXT: BB0_2:
|
|
; ATOM-NEXT: movsd A(,%rax,8)
|
|
; ATOM-NEXT: mulsd
|
|
; ATOM-NEXT: movsd
|
|
; ATOM-NEXT: leaq 1(%rax), %rax
|
|
|
|
@A = external global [0 x double]
|
|
|
|
define void @foo(i64 %n) nounwind {
|
|
entry:
|
|
%cmp5 = icmp sgt i64 %n, 0
|
|
br i1 %cmp5, label %for.body, label %for.end
|
|
|
|
for.body:
|
|
%i.06 = phi i64 [ %inc, %for.body ], [ 0, %entry ]
|
|
%arrayidx = getelementptr [0 x double]* @A, i64 0, i64 %i.06
|
|
%tmp3 = load double* %arrayidx, align 8
|
|
%mul = fmul double %tmp3, 2.300000e+00
|
|
store double %mul, double* %arrayidx, align 8
|
|
%inc = add nsw i64 %i.06, 1
|
|
%exitcond = icmp eq i64 %inc, %n
|
|
br i1 %exitcond, label %for.end, label %for.body
|
|
|
|
for.end:
|
|
ret void
|
|
}
|