mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-30 23:42:52 +01:00
d64e304671
the overloaded vector types allowed floating-point or integer vector elements. Most of these operations actually depend on the element type, so bitcasting was not an option. If you include the vpadd intrinsics that I updated earlier, this gets rid of 20 intrinsics. llvm-svn: 78646
84 lines
2.3 KiB
LLVM
84 lines
2.3 KiB
LLVM
; RUN: llvm-as < %s | llc -march=arm -mattr=+neon | FileCheck %s
|
|
|
|
define <8 x i8> @vld1i8(i8* %A) nounwind {
|
|
;CHECK: vld1i8:
|
|
;CHECK: vld1.8
|
|
%tmp1 = call <8 x i8> @llvm.arm.neon.vld1.v8i8(i8* %A)
|
|
ret <8 x i8> %tmp1
|
|
}
|
|
|
|
define <4 x i16> @vld1i16(i16* %A) nounwind {
|
|
;CHECK: vld1i16:
|
|
;CHECK: vld1.16
|
|
%tmp1 = call <4 x i16> @llvm.arm.neon.vld1.v4i16(i16* %A)
|
|
ret <4 x i16> %tmp1
|
|
}
|
|
|
|
define <2 x i32> @vld1i32(i32* %A) nounwind {
|
|
;CHECK: vld1i32:
|
|
;CHECK: vld1.32
|
|
%tmp1 = call <2 x i32> @llvm.arm.neon.vld1.v2i32(i32* %A)
|
|
ret <2 x i32> %tmp1
|
|
}
|
|
|
|
define <2 x float> @vld1f(float* %A) nounwind {
|
|
;CHECK: vld1f:
|
|
;CHECK: vld1.32
|
|
%tmp1 = call <2 x float> @llvm.arm.neon.vld1.v2f32(float* %A)
|
|
ret <2 x float> %tmp1
|
|
}
|
|
|
|
define <1 x i64> @vld1i64(i64* %A) nounwind {
|
|
;CHECK: vld1i64:
|
|
;CHECK: vld1.64
|
|
%tmp1 = call <1 x i64> @llvm.arm.neon.vld1.v1i64(i64* %A)
|
|
ret <1 x i64> %tmp1
|
|
}
|
|
|
|
define <16 x i8> @vld1Qi8(i8* %A) nounwind {
|
|
;CHECK: vld1Qi8:
|
|
;CHECK: vld1.8
|
|
%tmp1 = call <16 x i8> @llvm.arm.neon.vld1.v16i8(i8* %A)
|
|
ret <16 x i8> %tmp1
|
|
}
|
|
|
|
define <8 x i16> @vld1Qi16(i16* %A) nounwind {
|
|
;CHECK: vld1Qi16:
|
|
;CHECK: vld1.16
|
|
%tmp1 = call <8 x i16> @llvm.arm.neon.vld1.v8i16(i16* %A)
|
|
ret <8 x i16> %tmp1
|
|
}
|
|
|
|
define <4 x i32> @vld1Qi32(i32* %A) nounwind {
|
|
;CHECK: vld1Qi32:
|
|
;CHECK: vld1.32
|
|
%tmp1 = call <4 x i32> @llvm.arm.neon.vld1.v4i32(i32* %A)
|
|
ret <4 x i32> %tmp1
|
|
}
|
|
|
|
define <4 x float> @vld1Qf(float* %A) nounwind {
|
|
;CHECK: vld1Qf:
|
|
;CHECK: vld1.32
|
|
%tmp1 = call <4 x float> @llvm.arm.neon.vld1.v4f32(float* %A)
|
|
ret <4 x float> %tmp1
|
|
}
|
|
|
|
define <2 x i64> @vld1Qi64(i64* %A) nounwind {
|
|
;CHECK: vld1Qi64:
|
|
;CHECK: vld1.64
|
|
%tmp1 = call <2 x i64> @llvm.arm.neon.vld1.v2i64(i64* %A)
|
|
ret <2 x i64> %tmp1
|
|
}
|
|
|
|
declare <8 x i8> @llvm.arm.neon.vld1.v8i8(i8*) nounwind readonly
|
|
declare <4 x i16> @llvm.arm.neon.vld1.v4i16(i8*) nounwind readonly
|
|
declare <2 x i32> @llvm.arm.neon.vld1.v2i32(i8*) nounwind readonly
|
|
declare <2 x float> @llvm.arm.neon.vld1.v2f32(i8*) nounwind readonly
|
|
declare <1 x i64> @llvm.arm.neon.vld1.v1i64(i8*) nounwind readonly
|
|
|
|
declare <16 x i8> @llvm.arm.neon.vld1.v16i8(i8*) nounwind readonly
|
|
declare <8 x i16> @llvm.arm.neon.vld1.v8i16(i8*) nounwind readonly
|
|
declare <4 x i32> @llvm.arm.neon.vld1.v4i32(i8*) nounwind readonly
|
|
declare <4 x float> @llvm.arm.neon.vld1.v4f32(i8*) nounwind readonly
|
|
declare <2 x i64> @llvm.arm.neon.vld1.v2i64(i8*) nounwind readonly
|