mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-12-15 20:29:48 +00:00
7c9c6ed761
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
52 lines
1.8 KiB
LLVM
52 lines
1.8 KiB
LLVM
; RUN: llc -march=x86 -mcpu=generic -mattr=+sse4.2 < %s | FileCheck %s
|
|
; RUN: llc -march=x86 -mcpu=atom < %s | FileCheck -check-prefix=ATOM %s
|
|
|
|
; CHECK: movl
|
|
; CHECK: paddw
|
|
; CHECK: movlpd
|
|
|
|
; Scheduler causes produce a different instruction order
|
|
; ATOM: movl
|
|
; ATOM: paddw
|
|
; ATOM: movlpd
|
|
|
|
; bitcast a v4i16 to v2i32
|
|
|
|
define void @convert(<2 x i32>* %dst, <4 x i16>* %src) nounwind {
|
|
entry:
|
|
%dst.addr = alloca <2 x i32>* ; <<2 x i32>**> [#uses=2]
|
|
%src.addr = alloca <4 x i16>* ; <<4 x i16>**> [#uses=2]
|
|
%i = alloca i32, align 4 ; <i32*> [#uses=6]
|
|
store <2 x i32>* %dst, <2 x i32>** %dst.addr
|
|
store <4 x i16>* %src, <4 x i16>** %src.addr
|
|
store i32 0, i32* %i
|
|
br label %forcond
|
|
|
|
forcond: ; preds = %forinc, %entry
|
|
%tmp = load i32, i32* %i ; <i32> [#uses=1]
|
|
%cmp = icmp slt i32 %tmp, 4 ; <i1> [#uses=1]
|
|
br i1 %cmp, label %forbody, label %afterfor
|
|
|
|
forbody: ; preds = %forcond
|
|
%tmp1 = load i32, i32* %i ; <i32> [#uses=1]
|
|
%tmp2 = load <2 x i32>*, <2 x i32>** %dst.addr ; <<2 x i32>*> [#uses=1]
|
|
%arrayidx = getelementptr <2 x i32>, <2 x i32>* %tmp2, i32 %tmp1 ; <<2 x i32>*> [#uses=1]
|
|
%tmp3 = load i32, i32* %i ; <i32> [#uses=1]
|
|
%tmp4 = load <4 x i16>*, <4 x i16>** %src.addr ; <<4 x i16>*> [#uses=1]
|
|
%arrayidx5 = getelementptr <4 x i16>, <4 x i16>* %tmp4, i32 %tmp3 ; <<4 x i16>*> [#uses=1]
|
|
%tmp6 = load <4 x i16>, <4 x i16>* %arrayidx5 ; <<4 x i16>> [#uses=1]
|
|
%add = add <4 x i16> %tmp6, < i16 1, i16 1, i16 1, i16 1 > ; <<4 x i16>> [#uses=1]
|
|
%conv = bitcast <4 x i16> %add to <2 x i32> ; <<2 x i32>> [#uses=1]
|
|
store <2 x i32> %conv, <2 x i32>* %arrayidx
|
|
br label %forinc
|
|
|
|
forinc: ; preds = %forbody
|
|
%tmp7 = load i32, i32* %i ; <i32> [#uses=1]
|
|
%inc = add i32 %tmp7, 1 ; <i32> [#uses=1]
|
|
store i32 %inc, i32* %i
|
|
br label %forcond
|
|
|
|
afterfor: ; preds = %forcond
|
|
ret void
|
|
}
|