mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-25 04:02:41 +01:00
ab043ff680
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
llvm-svn: 230794
103 lines
4.3 KiB
LLVM
103 lines
4.3 KiB
LLVM
; RUN: llc -mtriple=arm-eabi -mattr=+neon %s -o - | FileCheck %s
|
|
|
|
define <8 x i8> @vuzpi8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
|
|
;CHECK-LABEL: vuzpi8:
|
|
;CHECK: vuzp.8
|
|
;CHECK-NEXT: vadd.i8
|
|
%tmp1 = load <8 x i8>, <8 x i8>* %A
|
|
%tmp2 = load <8 x i8>, <8 x i8>* %B
|
|
%tmp3 = shufflevector <8 x i8> %tmp1, <8 x i8> %tmp2, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
|
|
%tmp4 = shufflevector <8 x i8> %tmp1, <8 x i8> %tmp2, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
|
|
%tmp5 = add <8 x i8> %tmp3, %tmp4
|
|
ret <8 x i8> %tmp5
|
|
}
|
|
|
|
define <4 x i16> @vuzpi16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
|
|
;CHECK-LABEL: vuzpi16:
|
|
;CHECK: vuzp.16
|
|
;CHECK-NEXT: vadd.i16
|
|
%tmp1 = load <4 x i16>, <4 x i16>* %A
|
|
%tmp2 = load <4 x i16>, <4 x i16>* %B
|
|
%tmp3 = shufflevector <4 x i16> %tmp1, <4 x i16> %tmp2, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
|
|
%tmp4 = shufflevector <4 x i16> %tmp1, <4 x i16> %tmp2, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
|
|
%tmp5 = add <4 x i16> %tmp3, %tmp4
|
|
ret <4 x i16> %tmp5
|
|
}
|
|
|
|
; VUZP.32 is equivalent to VTRN.32 for 64-bit vectors.
|
|
|
|
define <16 x i8> @vuzpQi8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
|
|
;CHECK-LABEL: vuzpQi8:
|
|
;CHECK: vuzp.8
|
|
;CHECK-NEXT: vadd.i8
|
|
%tmp1 = load <16 x i8>, <16 x i8>* %A
|
|
%tmp2 = load <16 x i8>, <16 x i8>* %B
|
|
%tmp3 = shufflevector <16 x i8> %tmp1, <16 x i8> %tmp2, <16 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14, i32 16, i32 18, i32 20, i32 22, i32 24, i32 26, i32 28, i32 30>
|
|
%tmp4 = shufflevector <16 x i8> %tmp1, <16 x i8> %tmp2, <16 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15, i32 17, i32 19, i32 21, i32 23, i32 25, i32 27, i32 29, i32 31>
|
|
%tmp5 = add <16 x i8> %tmp3, %tmp4
|
|
ret <16 x i8> %tmp5
|
|
}
|
|
|
|
define <8 x i16> @vuzpQi16(<8 x i16>* %A, <8 x i16>* %B) nounwind {
|
|
;CHECK-LABEL: vuzpQi16:
|
|
;CHECK: vuzp.16
|
|
;CHECK-NEXT: vadd.i16
|
|
%tmp1 = load <8 x i16>, <8 x i16>* %A
|
|
%tmp2 = load <8 x i16>, <8 x i16>* %B
|
|
%tmp3 = shufflevector <8 x i16> %tmp1, <8 x i16> %tmp2, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
|
|
%tmp4 = shufflevector <8 x i16> %tmp1, <8 x i16> %tmp2, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
|
|
%tmp5 = add <8 x i16> %tmp3, %tmp4
|
|
ret <8 x i16> %tmp5
|
|
}
|
|
|
|
define <4 x i32> @vuzpQi32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
|
|
;CHECK-LABEL: vuzpQi32:
|
|
;CHECK: vuzp.32
|
|
;CHECK-NEXT: vadd.i32
|
|
%tmp1 = load <4 x i32>, <4 x i32>* %A
|
|
%tmp2 = load <4 x i32>, <4 x i32>* %B
|
|
%tmp3 = shufflevector <4 x i32> %tmp1, <4 x i32> %tmp2, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
|
|
%tmp4 = shufflevector <4 x i32> %tmp1, <4 x i32> %tmp2, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
|
|
%tmp5 = add <4 x i32> %tmp3, %tmp4
|
|
ret <4 x i32> %tmp5
|
|
}
|
|
|
|
define <4 x float> @vuzpQf(<4 x float>* %A, <4 x float>* %B) nounwind {
|
|
;CHECK-LABEL: vuzpQf:
|
|
;CHECK: vuzp.32
|
|
;CHECK-NEXT: vadd.f32
|
|
%tmp1 = load <4 x float>, <4 x float>* %A
|
|
%tmp2 = load <4 x float>, <4 x float>* %B
|
|
%tmp3 = shufflevector <4 x float> %tmp1, <4 x float> %tmp2, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
|
|
%tmp4 = shufflevector <4 x float> %tmp1, <4 x float> %tmp2, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
|
|
%tmp5 = fadd <4 x float> %tmp3, %tmp4
|
|
ret <4 x float> %tmp5
|
|
}
|
|
|
|
; Undef shuffle indices should not prevent matching to VUZP:
|
|
|
|
define <8 x i8> @vuzpi8_undef(<8 x i8>* %A, <8 x i8>* %B) nounwind {
|
|
;CHECK-LABEL: vuzpi8_undef:
|
|
;CHECK: vuzp.8
|
|
;CHECK-NEXT: vadd.i8
|
|
%tmp1 = load <8 x i8>, <8 x i8>* %A
|
|
%tmp2 = load <8 x i8>, <8 x i8>* %B
|
|
%tmp3 = shufflevector <8 x i8> %tmp1, <8 x i8> %tmp2, <8 x i32> <i32 0, i32 2, i32 undef, i32 undef, i32 8, i32 10, i32 12, i32 14>
|
|
%tmp4 = shufflevector <8 x i8> %tmp1, <8 x i8> %tmp2, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 undef, i32 undef, i32 13, i32 15>
|
|
%tmp5 = add <8 x i8> %tmp3, %tmp4
|
|
ret <8 x i8> %tmp5
|
|
}
|
|
|
|
define <8 x i16> @vuzpQi16_undef(<8 x i16>* %A, <8 x i16>* %B) nounwind {
|
|
;CHECK-LABEL: vuzpQi16_undef:
|
|
;CHECK: vuzp.16
|
|
;CHECK-NEXT: vadd.i16
|
|
%tmp1 = load <8 x i16>, <8 x i16>* %A
|
|
%tmp2 = load <8 x i16>, <8 x i16>* %B
|
|
%tmp3 = shufflevector <8 x i16> %tmp1, <8 x i16> %tmp2, <8 x i32> <i32 0, i32 undef, i32 4, i32 undef, i32 8, i32 10, i32 12, i32 14>
|
|
%tmp4 = shufflevector <8 x i16> %tmp1, <8 x i16> %tmp2, <8 x i32> <i32 1, i32 3, i32 5, i32 undef, i32 undef, i32 11, i32 13, i32 15>
|
|
%tmp5 = add <8 x i16> %tmp3, %tmp4
|
|
ret <8 x i16> %tmp5
|
|
}
|
|
|