mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-31 07:52:55 +01:00
dbac87d1fc
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
93 lines
3.2 KiB
LLVM
93 lines
3.2 KiB
LLVM
; RUN: llc -mtriple=aarch64-none-linux-gnu -mattr=+neon < %s | FileCheck %s
|
|
|
|
declare <8 x i8> @llvm.arm.neon.vpadd.v8i8(<8 x i8>, <8 x i8>)
|
|
|
|
define <8 x i8> @test_addp_v8i8(<8 x i8> %lhs, <8 x i8> %rhs) {
|
|
; Using registers other than v0, v1 are possible, but would be odd.
|
|
; CHECK: test_addp_v8i8:
|
|
%tmp1 = call <8 x i8> @llvm.arm.neon.vpadd.v8i8(<8 x i8> %lhs, <8 x i8> %rhs)
|
|
; CHECK: addp v0.8b, v0.8b, v1.8b
|
|
ret <8 x i8> %tmp1
|
|
}
|
|
|
|
declare <16 x i8> @llvm.arm.neon.vpadd.v16i8(<16 x i8>, <16 x i8>)
|
|
|
|
define <16 x i8> @test_addp_v16i8(<16 x i8> %lhs, <16 x i8> %rhs) {
|
|
; CHECK: test_addp_v16i8:
|
|
%tmp1 = call <16 x i8> @llvm.arm.neon.vpadd.v16i8(<16 x i8> %lhs, <16 x i8> %rhs)
|
|
; CHECK: addp v0.16b, v0.16b, v1.16b
|
|
ret <16 x i8> %tmp1
|
|
}
|
|
|
|
declare <4 x i16> @llvm.arm.neon.vpadd.v4i16(<4 x i16>, <4 x i16>)
|
|
|
|
define <4 x i16> @test_addp_v4i16(<4 x i16> %lhs, <4 x i16> %rhs) {
|
|
; CHECK: test_addp_v4i16:
|
|
%tmp1 = call <4 x i16> @llvm.arm.neon.vpadd.v4i16(<4 x i16> %lhs, <4 x i16> %rhs)
|
|
; CHECK: addp v0.4h, v0.4h, v1.4h
|
|
ret <4 x i16> %tmp1
|
|
}
|
|
|
|
declare <8 x i16> @llvm.arm.neon.vpadd.v8i16(<8 x i16>, <8 x i16>)
|
|
|
|
define <8 x i16> @test_addp_v8i16(<8 x i16> %lhs, <8 x i16> %rhs) {
|
|
; CHECK: test_addp_v8i16:
|
|
%tmp1 = call <8 x i16> @llvm.arm.neon.vpadd.v8i16(<8 x i16> %lhs, <8 x i16> %rhs)
|
|
; CHECK: addp v0.8h, v0.8h, v1.8h
|
|
ret <8 x i16> %tmp1
|
|
}
|
|
|
|
declare <2 x i32> @llvm.arm.neon.vpadd.v2i32(<2 x i32>, <2 x i32>)
|
|
|
|
define <2 x i32> @test_addp_v2i32(<2 x i32> %lhs, <2 x i32> %rhs) {
|
|
; CHECK: test_addp_v2i32:
|
|
%tmp1 = call <2 x i32> @llvm.arm.neon.vpadd.v2i32(<2 x i32> %lhs, <2 x i32> %rhs)
|
|
; CHECK: addp v0.2s, v0.2s, v1.2s
|
|
ret <2 x i32> %tmp1
|
|
}
|
|
|
|
declare <4 x i32> @llvm.arm.neon.vpadd.v4i32(<4 x i32>, <4 x i32>)
|
|
|
|
define <4 x i32> @test_addp_v4i32(<4 x i32> %lhs, <4 x i32> %rhs) {
|
|
; CHECK: test_addp_v4i32:
|
|
%tmp1 = call <4 x i32> @llvm.arm.neon.vpadd.v4i32(<4 x i32> %lhs, <4 x i32> %rhs)
|
|
; CHECK: addp v0.4s, v0.4s, v1.4s
|
|
ret <4 x i32> %tmp1
|
|
}
|
|
|
|
|
|
declare <2 x i64> @llvm.arm.neon.vpadd.v2i64(<2 x i64>, <2 x i64>)
|
|
|
|
define <2 x i64> @test_addp_v2i64(<2 x i64> %lhs, <2 x i64> %rhs) {
|
|
; CHECK: test_addp_v2i64:
|
|
%val = call <2 x i64> @llvm.arm.neon.vpadd.v2i64(<2 x i64> %lhs, <2 x i64> %rhs)
|
|
; CHECK: addp v0.2d, v0.2d, v1.2d
|
|
ret <2 x i64> %val
|
|
}
|
|
|
|
declare <2 x float> @llvm.arm.neon.vpadd.v2f32(<2 x float>, <2 x float>)
|
|
declare <4 x float> @llvm.arm.neon.vpadd.v4f32(<4 x float>, <4 x float>)
|
|
declare <2 x double> @llvm.arm.neon.vpadd.v2f64(<2 x double>, <2 x double>)
|
|
|
|
define <2 x float> @test_faddp_v2f32(<2 x float> %lhs, <2 x float> %rhs) {
|
|
; CHECK: test_faddp_v2f32:
|
|
%val = call <2 x float> @llvm.arm.neon.vpadd.v2f32(<2 x float> %lhs, <2 x float> %rhs)
|
|
; CHECK: faddp v0.2s, v0.2s, v1.2s
|
|
ret <2 x float> %val
|
|
}
|
|
|
|
define <4 x float> @test_faddp_v4f32(<4 x float> %lhs, <4 x float> %rhs) {
|
|
; CHECK: test_faddp_v4f32:
|
|
%val = call <4 x float> @llvm.arm.neon.vpadd.v4f32(<4 x float> %lhs, <4 x float> %rhs)
|
|
; CHECK: faddp v0.4s, v0.4s, v1.4s
|
|
ret <4 x float> %val
|
|
}
|
|
|
|
define <2 x double> @test_faddp_v2f64(<2 x double> %lhs, <2 x double> %rhs) {
|
|
; CHECK: test_faddp_v2f64:
|
|
%val = call <2 x double> @llvm.arm.neon.vpadd.v2f64(<2 x double> %lhs, <2 x double> %rhs)
|
|
; CHECK: faddp v0.2d, v0.2d, v1.2d
|
|
ret <2 x double> %val
|
|
}
|
|
|