6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2026-04-25 05:22:04 +00:00
Code Issues Projects Releases Wiki Activity

Add codegen support for NEON vst3 intrinsics with 128-bit vectors.

Browse Source 
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@83484 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Bob Wilson
2009-10-07 20:30:08 +00:00
parent b8452b80f4
commit 66a70639da
4 changed files with 129 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/CodeGen/ARM/vst3.ll
+41
View File
@@ -32,7 +32,48 @@ define void @vst3f(float* %A, <2 x float>* %B) nounwind {
ret void
}
define void @vst3Qi8(i8* %A, <16 x i8>* %B) nounwind {
;CHECK: vst3Qi8:
;CHECK: vst3.8
;CHECK: vst3.8
%tmp1 = load <16 x i8>* %B
call void @llvm.arm.neon.vst3.v16i8(i8* %A, <16 x i8> %tmp1, <16 x i8> %tmp1, <16 x i8> %tmp1)
ret void
}
define void @vst3Qi16(i16* %A, <8 x i16>* %B) nounwind {
;CHECK: vst3Qi16:
;CHECK: vst3.16
;CHECK: vst3.16
%tmp1 = load <8 x i16>* %B
call void @llvm.arm.neon.vst3.v8i16(i16* %A, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1)
ret void
}
define void @vst3Qi32(i32* %A, <4 x i32>* %B) nounwind {
;CHECK: vst3Qi32:
;CHECK: vst3.32
;CHECK: vst3.32
%tmp1 = load <4 x i32>* %B
call void @llvm.arm.neon.vst3.v4i32(i32* %A, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1)
ret void
}
define void @vst3Qf(float* %A, <4 x float>* %B) nounwind {
;CHECK: vst3Qf:
;CHECK: vst3.32
;CHECK: vst3.32
%tmp1 = load <4 x float>* %B
call void @llvm.arm.neon.vst3.v4f32(float* %A, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1)
ret void
}
declare void @llvm.arm.neon.vst3.v8i8(i8*, <8 x i8>, <8 x i8>, <8 x i8>) nounwind
declare void @llvm.arm.neon.vst3.v4i16(i8*, <4 x i16>, <4 x i16>, <4 x i16>) nounwind
declare void @llvm.arm.neon.vst3.v2i32(i8*, <2 x i32>, <2 x i32>, <2 x i32>) nounwind
declare void @llvm.arm.neon.vst3.v2f32(i8*, <2 x float>, <2 x float>, <2 x float>) nounwind
declare void @llvm.arm.neon.vst3.v16i8(i8*, <16 x i8>, <16 x i8>, <16 x i8>) nounwind
declare void @llvm.arm.neon.vst3.v8i16(i8*, <8 x i16>, <8 x i16>, <8 x i16>) nounwind
declare void @llvm.arm.neon.vst3.v4i32(i8*, <4 x i32>, <4 x i32>, <4 x i32>) nounwind
declare void @llvm.arm.neon.vst3.v4f32(i8*, <4 x float>, <4 x float>, <4 x float>) nounwind