mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2025-01-31 20:51:52 +01:00
a735dedfe5
Exploit native VSX rounding instruction, x(v|s)r(d|s)pic, which does rounding using current rounding mode. According to C standard library, rint may raise INEXACT exception while nearbyint won't. Reviewed By: lkail Differential Revision: https://reviews.llvm.org/D72685
53 lines
1.9 KiB
LLVM
53 lines
1.9 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -verify-machineinstrs -mtriple=powerpc64le-linux-gnu < %s \
|
|
; RUN: | FileCheck --check-prefix=CHECK-LE %s
|
|
; RUN: llc -verify-machineinstrs -mtriple=powerpc64-linux-gnu -mattr=+vsx < %s \
|
|
; RUN: | FileCheck --check-prefix=CHECK-BE %s
|
|
; RUN: llc -verify-machineinstrs -mtriple=powerpc64le-linux-gnu -mcpu=pwr9 < %s \
|
|
; RUN: | FileCheck --check-prefix=CHECK-P9LE %s
|
|
; RUN: llc -verify-machineinstrs -mtriple=powerpc64-linux-gnu -mcpu=pwr9 < %s \
|
|
; RUN: | FileCheck --check-prefix=CHECK-P9BE %s
|
|
|
|
define double @splat_swap(<2 x double> %x, <2 x double> %y) nounwind {
|
|
; CHECK-LE-LABEL: splat_swap:
|
|
; CHECK-LE: # %bb.0:
|
|
; CHECK-LE-NEXT: xvadddp 0, 34, 35
|
|
; CHECK-LE-NEXT: xvrdpic 0, 0
|
|
; CHECK-LE-NEXT: xxswapd 1, 0
|
|
; CHECK-LE-NEXT: xssubdp 1, 1, 0
|
|
; CHECK-LE-NEXT: blr
|
|
;
|
|
; CHECK-BE-LABEL: splat_swap:
|
|
; CHECK-BE: # %bb.0:
|
|
; CHECK-BE-NEXT: xvadddp 0, 34, 35
|
|
; CHECK-BE-NEXT: xvrdpic 0, 0
|
|
; CHECK-BE-NEXT: xxswapd 1, 0
|
|
; CHECK-BE-NEXT: xssubdp 1, 0, 1
|
|
; CHECK-BE-NEXT: blr
|
|
;
|
|
; CHECK-P9LE-LABEL: splat_swap:
|
|
; CHECK-P9LE: # %bb.0:
|
|
; CHECK-P9LE-NEXT: xvadddp 0, 34, 35
|
|
; CHECK-P9LE-NEXT: xvrdpic 0, 0
|
|
; CHECK-P9LE-NEXT: xxswapd 1, 0
|
|
; CHECK-P9LE-NEXT: xssubdp 1, 1, 0
|
|
; CHECK-P9LE-NEXT: blr
|
|
;
|
|
; CHECK-P9BE-LABEL: splat_swap:
|
|
; CHECK-P9BE: # %bb.0:
|
|
; CHECK-P9BE-NEXT: xvadddp 0, 34, 35
|
|
; CHECK-P9BE-NEXT: xvrdpic 0, 0
|
|
; CHECK-P9BE-NEXT: xxswapd 1, 0
|
|
; CHECK-P9BE-NEXT: xssubdp 1, 0, 1
|
|
; CHECK-P9BE-NEXT: blr
|
|
%added = fadd <2 x double> %x, %y
|
|
%call = tail call <2 x double> @llvm.rint.v2f64(<2 x double> %added) nounwind readnone
|
|
%res1 = extractelement <2 x double> %call, i32 0
|
|
%res2 = extractelement <2 x double> %call, i32 1
|
|
%ret = fsub double %res1, %res2
|
|
ret double %ret
|
|
}
|
|
|
|
declare <2 x double> @llvm.rint.v2f64(<2 x double>)
|
|
|