forked from OSchip/llvm-project
142 lines
5.4 KiB
LLVM
142 lines
5.4 KiB
LLVM
; RUN: llc < %s -march=arm -mattr=+neon > %t
|
|
; RUN: grep {vqrshl\\.s8} %t | count 2
|
|
; RUN: grep {vqrshl\\.s16} %t | count 2
|
|
; RUN: grep {vqrshl\\.s32} %t | count 2
|
|
; RUN: grep {vqrshl\\.s64} %t | count 2
|
|
; RUN: grep {vqrshl\\.u8} %t | count 2
|
|
; RUN: grep {vqrshl\\.u16} %t | count 2
|
|
; RUN: grep {vqrshl\\.u32} %t | count 2
|
|
; RUN: grep {vqrshl\\.u64} %t | count 2
|
|
|
|
define <8 x i8> @vqrshls8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
|
|
%tmp1 = load <8 x i8>* %A
|
|
%tmp2 = load <8 x i8>* %B
|
|
%tmp3 = call <8 x i8> @llvm.arm.neon.vqrshifts.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2)
|
|
ret <8 x i8> %tmp3
|
|
}
|
|
|
|
define <4 x i16> @vqrshls16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
|
|
%tmp1 = load <4 x i16>* %A
|
|
%tmp2 = load <4 x i16>* %B
|
|
%tmp3 = call <4 x i16> @llvm.arm.neon.vqrshifts.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2)
|
|
ret <4 x i16> %tmp3
|
|
}
|
|
|
|
define <2 x i32> @vqrshls32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
|
|
%tmp1 = load <2 x i32>* %A
|
|
%tmp2 = load <2 x i32>* %B
|
|
%tmp3 = call <2 x i32> @llvm.arm.neon.vqrshifts.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2)
|
|
ret <2 x i32> %tmp3
|
|
}
|
|
|
|
define <1 x i64> @vqrshls64(<1 x i64>* %A, <1 x i64>* %B) nounwind {
|
|
%tmp1 = load <1 x i64>* %A
|
|
%tmp2 = load <1 x i64>* %B
|
|
%tmp3 = call <1 x i64> @llvm.arm.neon.vqrshifts.v1i64(<1 x i64> %tmp1, <1 x i64> %tmp2)
|
|
ret <1 x i64> %tmp3
|
|
}
|
|
|
|
define <8 x i8> @vqrshlu8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
|
|
%tmp1 = load <8 x i8>* %A
|
|
%tmp2 = load <8 x i8>* %B
|
|
%tmp3 = call <8 x i8> @llvm.arm.neon.vqrshiftu.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2)
|
|
ret <8 x i8> %tmp3
|
|
}
|
|
|
|
define <4 x i16> @vqrshlu16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
|
|
%tmp1 = load <4 x i16>* %A
|
|
%tmp2 = load <4 x i16>* %B
|
|
%tmp3 = call <4 x i16> @llvm.arm.neon.vqrshiftu.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2)
|
|
ret <4 x i16> %tmp3
|
|
}
|
|
|
|
define <2 x i32> @vqrshlu32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
|
|
%tmp1 = load <2 x i32>* %A
|
|
%tmp2 = load <2 x i32>* %B
|
|
%tmp3 = call <2 x i32> @llvm.arm.neon.vqrshiftu.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2)
|
|
ret <2 x i32> %tmp3
|
|
}
|
|
|
|
define <1 x i64> @vqrshlu64(<1 x i64>* %A, <1 x i64>* %B) nounwind {
|
|
%tmp1 = load <1 x i64>* %A
|
|
%tmp2 = load <1 x i64>* %B
|
|
%tmp3 = call <1 x i64> @llvm.arm.neon.vqrshiftu.v1i64(<1 x i64> %tmp1, <1 x i64> %tmp2)
|
|
ret <1 x i64> %tmp3
|
|
}
|
|
|
|
define <16 x i8> @vqrshlQs8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
|
|
%tmp1 = load <16 x i8>* %A
|
|
%tmp2 = load <16 x i8>* %B
|
|
%tmp3 = call <16 x i8> @llvm.arm.neon.vqrshifts.v16i8(<16 x i8> %tmp1, <16 x i8> %tmp2)
|
|
ret <16 x i8> %tmp3
|
|
}
|
|
|
|
define <8 x i16> @vqrshlQs16(<8 x i16>* %A, <8 x i16>* %B) nounwind {
|
|
%tmp1 = load <8 x i16>* %A
|
|
%tmp2 = load <8 x i16>* %B
|
|
%tmp3 = call <8 x i16> @llvm.arm.neon.vqrshifts.v8i16(<8 x i16> %tmp1, <8 x i16> %tmp2)
|
|
ret <8 x i16> %tmp3
|
|
}
|
|
|
|
define <4 x i32> @vqrshlQs32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
|
|
%tmp1 = load <4 x i32>* %A
|
|
%tmp2 = load <4 x i32>* %B
|
|
%tmp3 = call <4 x i32> @llvm.arm.neon.vqrshifts.v4i32(<4 x i32> %tmp1, <4 x i32> %tmp2)
|
|
ret <4 x i32> %tmp3
|
|
}
|
|
|
|
define <2 x i64> @vqrshlQs64(<2 x i64>* %A, <2 x i64>* %B) nounwind {
|
|
%tmp1 = load <2 x i64>* %A
|
|
%tmp2 = load <2 x i64>* %B
|
|
%tmp3 = call <2 x i64> @llvm.arm.neon.vqrshifts.v2i64(<2 x i64> %tmp1, <2 x i64> %tmp2)
|
|
ret <2 x i64> %tmp3
|
|
}
|
|
|
|
define <16 x i8> @vqrshlQu8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
|
|
%tmp1 = load <16 x i8>* %A
|
|
%tmp2 = load <16 x i8>* %B
|
|
%tmp3 = call <16 x i8> @llvm.arm.neon.vqrshiftu.v16i8(<16 x i8> %tmp1, <16 x i8> %tmp2)
|
|
ret <16 x i8> %tmp3
|
|
}
|
|
|
|
define <8 x i16> @vqrshlQu16(<8 x i16>* %A, <8 x i16>* %B) nounwind {
|
|
%tmp1 = load <8 x i16>* %A
|
|
%tmp2 = load <8 x i16>* %B
|
|
%tmp3 = call <8 x i16> @llvm.arm.neon.vqrshiftu.v8i16(<8 x i16> %tmp1, <8 x i16> %tmp2)
|
|
ret <8 x i16> %tmp3
|
|
}
|
|
|
|
define <4 x i32> @vqrshlQu32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
|
|
%tmp1 = load <4 x i32>* %A
|
|
%tmp2 = load <4 x i32>* %B
|
|
%tmp3 = call <4 x i32> @llvm.arm.neon.vqrshiftu.v4i32(<4 x i32> %tmp1, <4 x i32> %tmp2)
|
|
ret <4 x i32> %tmp3
|
|
}
|
|
|
|
define <2 x i64> @vqrshlQu64(<2 x i64>* %A, <2 x i64>* %B) nounwind {
|
|
%tmp1 = load <2 x i64>* %A
|
|
%tmp2 = load <2 x i64>* %B
|
|
%tmp3 = call <2 x i64> @llvm.arm.neon.vqrshiftu.v2i64(<2 x i64> %tmp1, <2 x i64> %tmp2)
|
|
ret <2 x i64> %tmp3
|
|
}
|
|
|
|
declare <8 x i8> @llvm.arm.neon.vqrshifts.v8i8(<8 x i8>, <8 x i8>) nounwind readnone
|
|
declare <4 x i16> @llvm.arm.neon.vqrshifts.v4i16(<4 x i16>, <4 x i16>) nounwind readnone
|
|
declare <2 x i32> @llvm.arm.neon.vqrshifts.v2i32(<2 x i32>, <2 x i32>) nounwind readnone
|
|
declare <1 x i64> @llvm.arm.neon.vqrshifts.v1i64(<1 x i64>, <1 x i64>) nounwind readnone
|
|
|
|
declare <8 x i8> @llvm.arm.neon.vqrshiftu.v8i8(<8 x i8>, <8 x i8>) nounwind readnone
|
|
declare <4 x i16> @llvm.arm.neon.vqrshiftu.v4i16(<4 x i16>, <4 x i16>) nounwind readnone
|
|
declare <2 x i32> @llvm.arm.neon.vqrshiftu.v2i32(<2 x i32>, <2 x i32>) nounwind readnone
|
|
declare <1 x i64> @llvm.arm.neon.vqrshiftu.v1i64(<1 x i64>, <1 x i64>) nounwind readnone
|
|
|
|
declare <16 x i8> @llvm.arm.neon.vqrshifts.v16i8(<16 x i8>, <16 x i8>) nounwind readnone
|
|
declare <8 x i16> @llvm.arm.neon.vqrshifts.v8i16(<8 x i16>, <8 x i16>) nounwind readnone
|
|
declare <4 x i32> @llvm.arm.neon.vqrshifts.v4i32(<4 x i32>, <4 x i32>) nounwind readnone
|
|
declare <2 x i64> @llvm.arm.neon.vqrshifts.v2i64(<2 x i64>, <2 x i64>) nounwind readnone
|
|
|
|
declare <16 x i8> @llvm.arm.neon.vqrshiftu.v16i8(<16 x i8>, <16 x i8>) nounwind readnone
|
|
declare <8 x i16> @llvm.arm.neon.vqrshiftu.v8i16(<8 x i16>, <8 x i16>) nounwind readnone
|
|
declare <4 x i32> @llvm.arm.neon.vqrshiftu.v4i32(<4 x i32>, <4 x i32>) nounwind readnone
|
|
declare <2 x i64> @llvm.arm.neon.vqrshiftu.v2i64(<2 x i64>, <2 x i64>) nounwind readnone
|