mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-08-21 18:29:46 +00:00
Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@230794 91177308-0d34-0410-b5e6-96231b3b80d8
48 lines
2.2 KiB
LLVM
48 lines
2.2 KiB
LLVM
; RUN: llc -march=amdgcn -mcpu=SI -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
|
|
; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
|
|
|
|
declare double @llvm.fma.f64(double, double, double) nounwind readnone
|
|
declare <2 x double> @llvm.fma.v2f64(<2 x double>, <2 x double>, <2 x double>) nounwind readnone
|
|
declare <4 x double> @llvm.fma.v4f64(<4 x double>, <4 x double>, <4 x double>) nounwind readnone
|
|
|
|
|
|
; FUNC-LABEL: {{^}}fma_f64:
|
|
; SI: v_fma_f64 {{v\[[0-9]+:[0-9]+\], v\[[0-9]+:[0-9]+\], v\[[0-9]+:[0-9]+\], v\[[0-9]+:[0-9]+\]}}
|
|
define void @fma_f64(double addrspace(1)* %out, double addrspace(1)* %in1,
|
|
double addrspace(1)* %in2, double addrspace(1)* %in3) {
|
|
%r0 = load double, double addrspace(1)* %in1
|
|
%r1 = load double, double addrspace(1)* %in2
|
|
%r2 = load double, double addrspace(1)* %in3
|
|
%r3 = tail call double @llvm.fma.f64(double %r0, double %r1, double %r2)
|
|
store double %r3, double addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}fma_v2f64:
|
|
; SI: v_fma_f64
|
|
; SI: v_fma_f64
|
|
define void @fma_v2f64(<2 x double> addrspace(1)* %out, <2 x double> addrspace(1)* %in1,
|
|
<2 x double> addrspace(1)* %in2, <2 x double> addrspace(1)* %in3) {
|
|
%r0 = load <2 x double>, <2 x double> addrspace(1)* %in1
|
|
%r1 = load <2 x double>, <2 x double> addrspace(1)* %in2
|
|
%r2 = load <2 x double>, <2 x double> addrspace(1)* %in3
|
|
%r3 = tail call <2 x double> @llvm.fma.v2f64(<2 x double> %r0, <2 x double> %r1, <2 x double> %r2)
|
|
store <2 x double> %r3, <2 x double> addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}fma_v4f64:
|
|
; SI: v_fma_f64
|
|
; SI: v_fma_f64
|
|
; SI: v_fma_f64
|
|
; SI: v_fma_f64
|
|
define void @fma_v4f64(<4 x double> addrspace(1)* %out, <4 x double> addrspace(1)* %in1,
|
|
<4 x double> addrspace(1)* %in2, <4 x double> addrspace(1)* %in3) {
|
|
%r0 = load <4 x double>, <4 x double> addrspace(1)* %in1
|
|
%r1 = load <4 x double>, <4 x double> addrspace(1)* %in2
|
|
%r2 = load <4 x double>, <4 x double> addrspace(1)* %in3
|
|
%r3 = tail call <4 x double> @llvm.fma.v4f64(<4 x double> %r0, <4 x double> %r1, <4 x double> %r2)
|
|
store <4 x double> %r3, <4 x double> addrspace(1)* %out
|
|
ret void
|
|
}
|