mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-28 14:32:51 +01:00
e8ffab6ec5
- Factor out code to query and modify the sign bit of a floatingpoint value as an integer. This also works if none of the targets integer types is big enough to hold all bits of the floatingpoint value. - Legalize FABS(x) as FCOPYSIGN(x, 0.0) if FCOPYSIGN is available, otherwise perform bit manipulation on the sign bit. The previous code used "x >u 0 ? x : -x" which is incorrect for x being -0.0! It also takes 34 instructions on ARM Cortex-M4. With this patch we only require 5: vldr d0, LCPI0_0 vmov r2, r3, d0 lsrs r2, r3, #31 bfi r1, r2, #31, #1 bx lr (This could be further improved if the compiler would recognize that r2, r3 is zero). - Only lower FCOPYSIGN(x, y) = sign(x) ? -FABS(x) : FABS(x) if FABS is available otherwise perform bit manipulation on the sign bit. - Perform the sign(x) test by masking out the sign bit and comparing with 0 rather than shifting the sign bit to the highest position and testing for "<s 0". For x86 copysignl (on 80bit values) this gets us: testl $32768, %eax rather than: shlq $48, %rax sets %al testb %al, %al llvm-svn: 242107
22 lines
580 B
LLVM
22 lines
580 B
LLVM
; RUN: llc < %s -march=x86-64 | FileCheck %s
|
|
|
|
; CHECK-LABEL: LCPI0_0:
|
|
; CHECK-NEXT: .long 4286578688
|
|
; CHECK-LABEL: LCPI0_1:
|
|
; CHECK-NEXT: .long 2139095040
|
|
|
|
; CHECK-LABEL: foo:
|
|
; CHECK: movq {{.*}}, %rax
|
|
; CHECK: testl $32768, %eax
|
|
; CHECK: flds LCPI0_0(%rip)
|
|
; CHECK: flds LCPI0_1(%rip)
|
|
; CHECK: fcmovne %st(1), %st(0)
|
|
; CHECK: fstp %st(1)
|
|
; CHECK: retq
|
|
define x86_fp80 @foo(x86_fp80 %a) {
|
|
%1 = tail call x86_fp80 @copysignl(x86_fp80 0xK7FFF8000000000000000, x86_fp80 %a) nounwind readnone
|
|
ret x86_fp80 %1
|
|
}
|
|
|
|
declare x86_fp80 @copysignl(x86_fp80, x86_fp80) nounwind readnone
|