1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-24 03:33:20 +01:00
llvm-mirror/test/CodeGen/AArch64/neon-mla-mls.ll
Tim Northover dbac87d1fc AArch64: add initial NEON support
Patch by Ana Pazos.

- Completed implementation of instruction formats:
AdvSIMD three same
AdvSIMD modified immediate
AdvSIMD scalar pairwise

- Completed implementation of instruction classes
(some of the instructions in these classes
belong to yet unfinished instruction formats):
Vector Arithmetic
Vector Immediate
Vector Pairwise Arithmetic

- Initial implementation of instruction formats:
AdvSIMD scalar two-reg misc
AdvSIMD scalar three same

- Intial implementation of instruction class:
Scalar Arithmetic

- Initial clang changes to support arm v8 intrinsics.
Note: no clang changes for scalar intrinsics function name mangling yet.

- Comprehensive test cases for added instructions
To verify auto codegen, encoding, decoding, diagnosis, intrinsics.

llvm-svn: 187567
2013-08-01 09:20:35 +00:00

89 lines
2.7 KiB
LLVM

; RUN: llc < %s -verify-machineinstrs -mtriple=aarch64-none-linux-gnu -mattr=+neon | FileCheck %s
define <8 x i8> @mla8xi8(<8 x i8> %A, <8 x i8> %B, <8 x i8> %C) {
;CHECK: mla {{v[0-31]+}}.8b, {{v[0-31]+}}.8b, {{v[0-31]+}}.8b
%tmp1 = mul <8 x i8> %A, %B;
%tmp2 = add <8 x i8> %C, %tmp1;
ret <8 x i8> %tmp2
}
define <16 x i8> @mla16xi8(<16 x i8> %A, <16 x i8> %B, <16 x i8> %C) {
;CHECK: mla {{v[0-31]+}}.16b, {{v[0-31]+}}.16b, {{v[0-31]+}}.16b
%tmp1 = mul <16 x i8> %A, %B;
%tmp2 = add <16 x i8> %C, %tmp1;
ret <16 x i8> %tmp2
}
define <4 x i16> @mla4xi16(<4 x i16> %A, <4 x i16> %B, <4 x i16> %C) {
;CHECK: mla {{v[0-31]+}}.4h, {{v[0-31]+}}.4h, {{v[0-31]+}}.4h
%tmp1 = mul <4 x i16> %A, %B;
%tmp2 = add <4 x i16> %C, %tmp1;
ret <4 x i16> %tmp2
}
define <8 x i16> @mla8xi16(<8 x i16> %A, <8 x i16> %B, <8 x i16> %C) {
;CHECK: mla {{v[0-31]+}}.8h, {{v[0-31]+}}.8h, {{v[0-31]+}}.8h
%tmp1 = mul <8 x i16> %A, %B;
%tmp2 = add <8 x i16> %C, %tmp1;
ret <8 x i16> %tmp2
}
define <2 x i32> @mla2xi32(<2 x i32> %A, <2 x i32> %B, <2 x i32> %C) {
;CHECK: mla {{v[0-31]+}}.2s, {{v[0-31]+}}.2s, {{v[0-31]+}}.2s
%tmp1 = mul <2 x i32> %A, %B;
%tmp2 = add <2 x i32> %C, %tmp1;
ret <2 x i32> %tmp2
}
define <4 x i32> @mla4xi32(<4 x i32> %A, <4 x i32> %B, <4 x i32> %C) {
;CHECK: mla {{v[0-31]+}}.4s, {{v[0-31]+}}.4s, {{v[0-31]+}}.4s
%tmp1 = mul <4 x i32> %A, %B;
%tmp2 = add <4 x i32> %C, %tmp1;
ret <4 x i32> %tmp2
}
define <8 x i8> @mls8xi8(<8 x i8> %A, <8 x i8> %B, <8 x i8> %C) {
;CHECK: mls {{v[0-31]+}}.8b, {{v[0-31]+}}.8b, {{v[0-31]+}}.8b
%tmp1 = mul <8 x i8> %A, %B;
%tmp2 = sub <8 x i8> %C, %tmp1;
ret <8 x i8> %tmp2
}
define <16 x i8> @mls16xi8(<16 x i8> %A, <16 x i8> %B, <16 x i8> %C) {
;CHECK: mls {{v[0-31]+}}.16b, {{v[0-31]+}}.16b, {{v[0-31]+}}.16b
%tmp1 = mul <16 x i8> %A, %B;
%tmp2 = sub <16 x i8> %C, %tmp1;
ret <16 x i8> %tmp2
}
define <4 x i16> @mls4xi16(<4 x i16> %A, <4 x i16> %B, <4 x i16> %C) {
;CHECK: mls {{v[0-31]+}}.4h, {{v[0-31]+}}.4h, {{v[0-31]+}}.4h
%tmp1 = mul <4 x i16> %A, %B;
%tmp2 = sub <4 x i16> %C, %tmp1;
ret <4 x i16> %tmp2
}
define <8 x i16> @mls8xi16(<8 x i16> %A, <8 x i16> %B, <8 x i16> %C) {
;CHECK: mls {{v[0-31]+}}.8h, {{v[0-31]+}}.8h, {{v[0-31]+}}.8h
%tmp1 = mul <8 x i16> %A, %B;
%tmp2 = sub <8 x i16> %C, %tmp1;
ret <8 x i16> %tmp2
}
define <2 x i32> @mls2xi32(<2 x i32> %A, <2 x i32> %B, <2 x i32> %C) {
;CHECK: mls {{v[0-31]+}}.2s, {{v[0-31]+}}.2s, {{v[0-31]+}}.2s
%tmp1 = mul <2 x i32> %A, %B;
%tmp2 = sub <2 x i32> %C, %tmp1;
ret <2 x i32> %tmp2
}
define <4 x i32> @mls4xi32(<4 x i32> %A, <4 x i32> %B, <4 x i32> %C) {
;CHECK: mls {{v[0-31]+}}.4s, {{v[0-31]+}}.4s, {{v[0-31]+}}.4s
%tmp1 = mul <4 x i32> %A, %B;
%tmp2 = sub <4 x i32> %C, %tmp1;
ret <4 x i32> %tmp2
}