mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-08-26 23:29:22 +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
50 lines
1.2 KiB
LLVM
50 lines
1.2 KiB
LLVM
; RUN: llc -mtriple=arm-eabi -mattr=+neon -pre-RA-sched=source -disable-post-ra %s -o - \
|
|
; RUN: | FileCheck %s
|
|
|
|
define <8 x i8> @sdivi8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
|
|
;CHECK: vrecpe.f32
|
|
;CHECK: vmovn.i32
|
|
;CHECK: vrecpe.f32
|
|
;CHECK: vmovn.i32
|
|
;CHECK: vmovn.i16
|
|
%tmp1 = load <8 x i8>, <8 x i8>* %A
|
|
%tmp2 = load <8 x i8>, <8 x i8>* %B
|
|
%tmp3 = sdiv <8 x i8> %tmp1, %tmp2
|
|
ret <8 x i8> %tmp3
|
|
}
|
|
|
|
define <8 x i8> @udivi8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
|
|
;CHECK: vrecpe.f32
|
|
;CHECK: vrecps.f32
|
|
;CHECK: vmovn.i32
|
|
;CHECK: vrecpe.f32
|
|
;CHECK: vrecps.f32
|
|
;CHECK: vmovn.i32
|
|
;CHECK: vqmovun.s16
|
|
%tmp1 = load <8 x i8>, <8 x i8>* %A
|
|
%tmp2 = load <8 x i8>, <8 x i8>* %B
|
|
%tmp3 = udiv <8 x i8> %tmp1, %tmp2
|
|
ret <8 x i8> %tmp3
|
|
}
|
|
|
|
define <4 x i16> @sdivi16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
|
|
;CHECK: vrecpe.f32
|
|
;CHECK: vrecps.f32
|
|
;CHECK: vmovn.i32
|
|
%tmp1 = load <4 x i16>, <4 x i16>* %A
|
|
%tmp2 = load <4 x i16>, <4 x i16>* %B
|
|
%tmp3 = sdiv <4 x i16> %tmp1, %tmp2
|
|
ret <4 x i16> %tmp3
|
|
}
|
|
|
|
define <4 x i16> @udivi16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
|
|
;CHECK: vrecpe.f32
|
|
;CHECK: vrecps.f32
|
|
;CHECK: vrecps.f32
|
|
;CHECK: vmovn.i32
|
|
%tmp1 = load <4 x i16>, <4 x i16>* %A
|
|
%tmp2 = load <4 x i16>, <4 x i16>* %B
|
|
%tmp3 = udiv <4 x i16> %tmp1, %tmp2
|
|
ret <4 x i16> %tmp3
|
|
}
|