mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-23 19:23:23 +01:00
73b770d782
The z13 vector facility includes some instructions that operate only on the high f64 in a v2f64, effectively extending the FP register set from 16 to 32 registers. It's still better to use the old instructions if the operands happen to fit though, since the older instructions have a shorter encoding. Based on a patch by Richard Sandiford. llvm-svn: 236524
24 lines
617 B
LLVM
24 lines
617 B
LLVM
; Test f64 and v2f64 square root.
|
|
;
|
|
; RUN: llc < %s -mtriple=s390x-linux-gnu -mcpu=z13 | FileCheck %s
|
|
|
|
declare double @llvm.sqrt.f64(double)
|
|
declare <2 x double> @llvm.sqrt.v2f64(<2 x double>)
|
|
|
|
define <2 x double> @f1(<2 x double> %val) {
|
|
; CHECK-LABEL: f1:
|
|
; CHECK: vfsqdb %v24, %v24
|
|
; CHECK: br %r14
|
|
%ret = call <2 x double> @llvm.sqrt.v2f64(<2 x double> %val)
|
|
ret <2 x double> %ret
|
|
}
|
|
|
|
define double @f2(<2 x double> %val) {
|
|
; CHECK-LABEL: f2:
|
|
; CHECK: wfsqdb %f0, %v24
|
|
; CHECK: br %r14
|
|
%scalar = extractelement <2 x double> %val, i32 0
|
|
%ret = call double @llvm.sqrt.f64(double %scalar)
|
|
ret double %ret
|
|
}
|