forked from OSchip/llvm-project
148 lines
4.9 KiB
LLVM
148 lines
4.9 KiB
LLVM
; RUN: llc < %s -march=arm -mattr=+neon | FileCheck %s
|
|
|
|
define <8 x i8> @vmaxs8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
|
|
;CHECK: vmaxs8:
|
|
;CHECK: vmax.s8
|
|
%tmp1 = load <8 x i8>* %A
|
|
%tmp2 = load <8 x i8>* %B
|
|
%tmp3 = call <8 x i8> @llvm.arm.neon.vmaxs.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2)
|
|
ret <8 x i8> %tmp3
|
|
}
|
|
|
|
define <4 x i16> @vmaxs16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
|
|
;CHECK: vmaxs16:
|
|
;CHECK: vmax.s16
|
|
%tmp1 = load <4 x i16>* %A
|
|
%tmp2 = load <4 x i16>* %B
|
|
%tmp3 = call <4 x i16> @llvm.arm.neon.vmaxs.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2)
|
|
ret <4 x i16> %tmp3
|
|
}
|
|
|
|
define <2 x i32> @vmaxs32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
|
|
;CHECK: vmaxs32:
|
|
;CHECK: vmax.s32
|
|
%tmp1 = load <2 x i32>* %A
|
|
%tmp2 = load <2 x i32>* %B
|
|
%tmp3 = call <2 x i32> @llvm.arm.neon.vmaxs.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2)
|
|
ret <2 x i32> %tmp3
|
|
}
|
|
|
|
define <8 x i8> @vmaxu8(<8 x i8>* %A, <8 x i8>* %B) nounwind {
|
|
;CHECK: vmaxu8:
|
|
;CHECK: vmax.u8
|
|
%tmp1 = load <8 x i8>* %A
|
|
%tmp2 = load <8 x i8>* %B
|
|
%tmp3 = call <8 x i8> @llvm.arm.neon.vmaxu.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2)
|
|
ret <8 x i8> %tmp3
|
|
}
|
|
|
|
define <4 x i16> @vmaxu16(<4 x i16>* %A, <4 x i16>* %B) nounwind {
|
|
;CHECK: vmaxu16:
|
|
;CHECK: vmax.u16
|
|
%tmp1 = load <4 x i16>* %A
|
|
%tmp2 = load <4 x i16>* %B
|
|
%tmp3 = call <4 x i16> @llvm.arm.neon.vmaxu.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2)
|
|
ret <4 x i16> %tmp3
|
|
}
|
|
|
|
define <2 x i32> @vmaxu32(<2 x i32>* %A, <2 x i32>* %B) nounwind {
|
|
;CHECK: vmaxu32:
|
|
;CHECK: vmax.u32
|
|
%tmp1 = load <2 x i32>* %A
|
|
%tmp2 = load <2 x i32>* %B
|
|
%tmp3 = call <2 x i32> @llvm.arm.neon.vmaxu.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2)
|
|
ret <2 x i32> %tmp3
|
|
}
|
|
|
|
define <2 x float> @vmaxf32(<2 x float>* %A, <2 x float>* %B) nounwind {
|
|
;CHECK: vmaxf32:
|
|
;CHECK: vmax.f32
|
|
%tmp1 = load <2 x float>* %A
|
|
%tmp2 = load <2 x float>* %B
|
|
%tmp3 = call <2 x float> @llvm.arm.neon.vmaxs.v2f32(<2 x float> %tmp1, <2 x float> %tmp2)
|
|
ret <2 x float> %tmp3
|
|
}
|
|
|
|
define <16 x i8> @vmaxQs8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
|
|
;CHECK: vmaxQs8:
|
|
;CHECK: vmax.s8
|
|
%tmp1 = load <16 x i8>* %A
|
|
%tmp2 = load <16 x i8>* %B
|
|
%tmp3 = call <16 x i8> @llvm.arm.neon.vmaxs.v16i8(<16 x i8> %tmp1, <16 x i8> %tmp2)
|
|
ret <16 x i8> %tmp3
|
|
}
|
|
|
|
define <8 x i16> @vmaxQs16(<8 x i16>* %A, <8 x i16>* %B) nounwind {
|
|
;CHECK: vmaxQs16:
|
|
;CHECK: vmax.s16
|
|
%tmp1 = load <8 x i16>* %A
|
|
%tmp2 = load <8 x i16>* %B
|
|
%tmp3 = call <8 x i16> @llvm.arm.neon.vmaxs.v8i16(<8 x i16> %tmp1, <8 x i16> %tmp2)
|
|
ret <8 x i16> %tmp3
|
|
}
|
|
|
|
define <4 x i32> @vmaxQs32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
|
|
;CHECK: vmaxQs32:
|
|
;CHECK: vmax.s32
|
|
%tmp1 = load <4 x i32>* %A
|
|
%tmp2 = load <4 x i32>* %B
|
|
%tmp3 = call <4 x i32> @llvm.arm.neon.vmaxs.v4i32(<4 x i32> %tmp1, <4 x i32> %tmp2)
|
|
ret <4 x i32> %tmp3
|
|
}
|
|
|
|
define <16 x i8> @vmaxQu8(<16 x i8>* %A, <16 x i8>* %B) nounwind {
|
|
;CHECK: vmaxQu8:
|
|
;CHECK: vmax.u8
|
|
%tmp1 = load <16 x i8>* %A
|
|
%tmp2 = load <16 x i8>* %B
|
|
%tmp3 = call <16 x i8> @llvm.arm.neon.vmaxu.v16i8(<16 x i8> %tmp1, <16 x i8> %tmp2)
|
|
ret <16 x i8> %tmp3
|
|
}
|
|
|
|
define <8 x i16> @vmaxQu16(<8 x i16>* %A, <8 x i16>* %B) nounwind {
|
|
;CHECK: vmaxQu16:
|
|
;CHECK: vmax.u16
|
|
%tmp1 = load <8 x i16>* %A
|
|
%tmp2 = load <8 x i16>* %B
|
|
%tmp3 = call <8 x i16> @llvm.arm.neon.vmaxu.v8i16(<8 x i16> %tmp1, <8 x i16> %tmp2)
|
|
ret <8 x i16> %tmp3
|
|
}
|
|
|
|
define <4 x i32> @vmaxQu32(<4 x i32>* %A, <4 x i32>* %B) nounwind {
|
|
;CHECK: vmaxQu32:
|
|
;CHECK: vmax.u32
|
|
%tmp1 = load <4 x i32>* %A
|
|
%tmp2 = load <4 x i32>* %B
|
|
%tmp3 = call <4 x i32> @llvm.arm.neon.vmaxu.v4i32(<4 x i32> %tmp1, <4 x i32> %tmp2)
|
|
ret <4 x i32> %tmp3
|
|
}
|
|
|
|
define <4 x float> @vmaxQf32(<4 x float>* %A, <4 x float>* %B) nounwind {
|
|
;CHECK: vmaxQf32:
|
|
;CHECK: vmax.f32
|
|
%tmp1 = load <4 x float>* %A
|
|
%tmp2 = load <4 x float>* %B
|
|
%tmp3 = call <4 x float> @llvm.arm.neon.vmaxs.v4f32(<4 x float> %tmp1, <4 x float> %tmp2)
|
|
ret <4 x float> %tmp3
|
|
}
|
|
|
|
declare <8 x i8> @llvm.arm.neon.vmaxs.v8i8(<8 x i8>, <8 x i8>) nounwind readnone
|
|
declare <4 x i16> @llvm.arm.neon.vmaxs.v4i16(<4 x i16>, <4 x i16>) nounwind readnone
|
|
declare <2 x i32> @llvm.arm.neon.vmaxs.v2i32(<2 x i32>, <2 x i32>) nounwind readnone
|
|
|
|
declare <8 x i8> @llvm.arm.neon.vmaxu.v8i8(<8 x i8>, <8 x i8>) nounwind readnone
|
|
declare <4 x i16> @llvm.arm.neon.vmaxu.v4i16(<4 x i16>, <4 x i16>) nounwind readnone
|
|
declare <2 x i32> @llvm.arm.neon.vmaxu.v2i32(<2 x i32>, <2 x i32>) nounwind readnone
|
|
|
|
declare <2 x float> @llvm.arm.neon.vmaxs.v2f32(<2 x float>, <2 x float>) nounwind readnone
|
|
|
|
declare <16 x i8> @llvm.arm.neon.vmaxs.v16i8(<16 x i8>, <16 x i8>) nounwind readnone
|
|
declare <8 x i16> @llvm.arm.neon.vmaxs.v8i16(<8 x i16>, <8 x i16>) nounwind readnone
|
|
declare <4 x i32> @llvm.arm.neon.vmaxs.v4i32(<4 x i32>, <4 x i32>) nounwind readnone
|
|
|
|
declare <16 x i8> @llvm.arm.neon.vmaxu.v16i8(<16 x i8>, <16 x i8>) nounwind readnone
|
|
declare <8 x i16> @llvm.arm.neon.vmaxu.v8i16(<8 x i16>, <8 x i16>) nounwind readnone
|
|
declare <4 x i32> @llvm.arm.neon.vmaxu.v4i32(<4 x i32>, <4 x i32>) nounwind readnone
|
|
|
|
declare <4 x float> @llvm.arm.neon.vmaxs.v4f32(<4 x float>, <4 x float>) nounwind readnone
|