mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-07-30 03:29:23 +00:00
02170c0034
the intrinsics. The reason for those i8* types is that the intrinsics are overloaded on the vector type and we don't have a way to declare an intrinsic where one argument is an overloaded vector type and another argument is a pointer to the vector element type. The bitcasts added here will match what the frontend will typically generate when these intrinsics are used. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@101840 91177308-0d34-0410-b5e6-96231b3b80d8
125 lines
4.9 KiB
LLVM
125 lines
4.9 KiB
LLVM
; RUN: llc < %s -march=arm -mattr=+neon | FileCheck %s
|
|
|
|
%struct.__neon_int8x8x4_t = type { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> }
|
|
%struct.__neon_int16x4x4_t = type { <4 x i16>, <4 x i16>, <4 x i16>, <4 x i16> }
|
|
%struct.__neon_int32x2x4_t = type { <2 x i32>, <2 x i32>, <2 x i32>, <2 x i32> }
|
|
%struct.__neon_float32x2x4_t = type { <2 x float>, <2 x float>, <2 x float>, <2 x float> }
|
|
%struct.__neon_int64x1x4_t = type { <1 x i64>, <1 x i64>, <1 x i64>, <1 x i64> }
|
|
|
|
%struct.__neon_int8x16x4_t = type { <16 x i8>, <16 x i8>, <16 x i8>, <16 x i8> }
|
|
%struct.__neon_int16x8x4_t = type { <8 x i16>, <8 x i16>, <8 x i16>, <8 x i16> }
|
|
%struct.__neon_int32x4x4_t = type { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> }
|
|
%struct.__neon_float32x4x4_t = type { <4 x float>, <4 x float>, <4 x float>, <4 x float> }
|
|
|
|
define <8 x i8> @vld4i8(i8* %A) nounwind {
|
|
;CHECK: vld4i8:
|
|
;CHECK: vld4.8
|
|
%tmp1 = call %struct.__neon_int8x8x4_t @llvm.arm.neon.vld4.v8i8(i8* %A)
|
|
%tmp2 = extractvalue %struct.__neon_int8x8x4_t %tmp1, 0
|
|
%tmp3 = extractvalue %struct.__neon_int8x8x4_t %tmp1, 2
|
|
%tmp4 = add <8 x i8> %tmp2, %tmp3
|
|
ret <8 x i8> %tmp4
|
|
}
|
|
|
|
define <4 x i16> @vld4i16(i16* %A) nounwind {
|
|
;CHECK: vld4i16:
|
|
;CHECK: vld4.16
|
|
%tmp0 = bitcast i16* %A to i8*
|
|
%tmp1 = call %struct.__neon_int16x4x4_t @llvm.arm.neon.vld4.v4i16(i8* %tmp0)
|
|
%tmp2 = extractvalue %struct.__neon_int16x4x4_t %tmp1, 0
|
|
%tmp3 = extractvalue %struct.__neon_int16x4x4_t %tmp1, 2
|
|
%tmp4 = add <4 x i16> %tmp2, %tmp3
|
|
ret <4 x i16> %tmp4
|
|
}
|
|
|
|
define <2 x i32> @vld4i32(i32* %A) nounwind {
|
|
;CHECK: vld4i32:
|
|
;CHECK: vld4.32
|
|
%tmp0 = bitcast i32* %A to i8*
|
|
%tmp1 = call %struct.__neon_int32x2x4_t @llvm.arm.neon.vld4.v2i32(i8* %tmp0)
|
|
%tmp2 = extractvalue %struct.__neon_int32x2x4_t %tmp1, 0
|
|
%tmp3 = extractvalue %struct.__neon_int32x2x4_t %tmp1, 2
|
|
%tmp4 = add <2 x i32> %tmp2, %tmp3
|
|
ret <2 x i32> %tmp4
|
|
}
|
|
|
|
define <2 x float> @vld4f(float* %A) nounwind {
|
|
;CHECK: vld4f:
|
|
;CHECK: vld4.32
|
|
%tmp0 = bitcast float* %A to i8*
|
|
%tmp1 = call %struct.__neon_float32x2x4_t @llvm.arm.neon.vld4.v2f32(i8* %tmp0)
|
|
%tmp2 = extractvalue %struct.__neon_float32x2x4_t %tmp1, 0
|
|
%tmp3 = extractvalue %struct.__neon_float32x2x4_t %tmp1, 2
|
|
%tmp4 = add <2 x float> %tmp2, %tmp3
|
|
ret <2 x float> %tmp4
|
|
}
|
|
|
|
define <1 x i64> @vld4i64(i64* %A) nounwind {
|
|
;CHECK: vld4i64:
|
|
;CHECK: vld1.64
|
|
%tmp0 = bitcast i64* %A to i8*
|
|
%tmp1 = call %struct.__neon_int64x1x4_t @llvm.arm.neon.vld4.v1i64(i8* %tmp0)
|
|
%tmp2 = extractvalue %struct.__neon_int64x1x4_t %tmp1, 0
|
|
%tmp3 = extractvalue %struct.__neon_int64x1x4_t %tmp1, 2
|
|
%tmp4 = add <1 x i64> %tmp2, %tmp3
|
|
ret <1 x i64> %tmp4
|
|
}
|
|
|
|
define <16 x i8> @vld4Qi8(i8* %A) nounwind {
|
|
;CHECK: vld4Qi8:
|
|
;CHECK: vld4.8
|
|
;CHECK: vld4.8
|
|
%tmp1 = call %struct.__neon_int8x16x4_t @llvm.arm.neon.vld4.v16i8(i8* %A)
|
|
%tmp2 = extractvalue %struct.__neon_int8x16x4_t %tmp1, 0
|
|
%tmp3 = extractvalue %struct.__neon_int8x16x4_t %tmp1, 2
|
|
%tmp4 = add <16 x i8> %tmp2, %tmp3
|
|
ret <16 x i8> %tmp4
|
|
}
|
|
|
|
define <8 x i16> @vld4Qi16(i16* %A) nounwind {
|
|
;CHECK: vld4Qi16:
|
|
;CHECK: vld4.16
|
|
;CHECK: vld4.16
|
|
%tmp0 = bitcast i16* %A to i8*
|
|
%tmp1 = call %struct.__neon_int16x8x4_t @llvm.arm.neon.vld4.v8i16(i8* %tmp0)
|
|
%tmp2 = extractvalue %struct.__neon_int16x8x4_t %tmp1, 0
|
|
%tmp3 = extractvalue %struct.__neon_int16x8x4_t %tmp1, 2
|
|
%tmp4 = add <8 x i16> %tmp2, %tmp3
|
|
ret <8 x i16> %tmp4
|
|
}
|
|
|
|
define <4 x i32> @vld4Qi32(i32* %A) nounwind {
|
|
;CHECK: vld4Qi32:
|
|
;CHECK: vld4.32
|
|
;CHECK: vld4.32
|
|
%tmp0 = bitcast i32* %A to i8*
|
|
%tmp1 = call %struct.__neon_int32x4x4_t @llvm.arm.neon.vld4.v4i32(i8* %tmp0)
|
|
%tmp2 = extractvalue %struct.__neon_int32x4x4_t %tmp1, 0
|
|
%tmp3 = extractvalue %struct.__neon_int32x4x4_t %tmp1, 2
|
|
%tmp4 = add <4 x i32> %tmp2, %tmp3
|
|
ret <4 x i32> %tmp4
|
|
}
|
|
|
|
define <4 x float> @vld4Qf(float* %A) nounwind {
|
|
;CHECK: vld4Qf:
|
|
;CHECK: vld4.32
|
|
;CHECK: vld4.32
|
|
%tmp0 = bitcast float* %A to i8*
|
|
%tmp1 = call %struct.__neon_float32x4x4_t @llvm.arm.neon.vld4.v4f32(i8* %tmp0)
|
|
%tmp2 = extractvalue %struct.__neon_float32x4x4_t %tmp1, 0
|
|
%tmp3 = extractvalue %struct.__neon_float32x4x4_t %tmp1, 2
|
|
%tmp4 = add <4 x float> %tmp2, %tmp3
|
|
ret <4 x float> %tmp4
|
|
}
|
|
|
|
declare %struct.__neon_int8x8x4_t @llvm.arm.neon.vld4.v8i8(i8*) nounwind readonly
|
|
declare %struct.__neon_int16x4x4_t @llvm.arm.neon.vld4.v4i16(i8*) nounwind readonly
|
|
declare %struct.__neon_int32x2x4_t @llvm.arm.neon.vld4.v2i32(i8*) nounwind readonly
|
|
declare %struct.__neon_float32x2x4_t @llvm.arm.neon.vld4.v2f32(i8*) nounwind readonly
|
|
declare %struct.__neon_int64x1x4_t @llvm.arm.neon.vld4.v1i64(i8*) nounwind readonly
|
|
|
|
declare %struct.__neon_int8x16x4_t @llvm.arm.neon.vld4.v16i8(i8*) nounwind readonly
|
|
declare %struct.__neon_int16x8x4_t @llvm.arm.neon.vld4.v8i16(i8*) nounwind readonly
|
|
declare %struct.__neon_int32x4x4_t @llvm.arm.neon.vld4.v4i32(i8*) nounwind readonly
|
|
declare %struct.__neon_float32x4x4_t @llvm.arm.neon.vld4.v4f32(i8*) nounwind readonly
|