6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2025-08-05 13:26:55 +00:00
Code Issues Projects Releases Wiki Activity

Set alignment operand for NEON VLD instructions.

Browse Source 
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@114696 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Bob Wilson
2010-09-23 21:43:54 +00:00
parent bcf0116751
commit 40ff01a030
5 changed files with 69 additions and 36 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
test/CodeGen/ARM/vld3.ll
View File

@@ -13,8 +13,9 @@
define <8 x i8> @vld3i8(i8* %A) nounwind {
;CHECK: vld3i8:
;CHECK: vld3.8
%tmp1 = call %struct.__neon_int8x8x3_t @llvm.arm.neon.vld3.v8i8(i8* %A, i32 1)
;Check the alignment value. Max for this instruction is 64 bits:
;CHECK: vld3.8 {d0, d1, d2}, [r0, :64]
%tmp1 = call %struct.__neon_int8x8x3_t @llvm.arm.neon.vld3.v8i8(i8* %A, i32 32)
%tmp2 = extractvalue %struct.__neon_int8x8x3_t %tmp1, 0
%tmp3 = extractvalue %struct.__neon_int8x8x3_t %tmp1, 2
%tmp4 = add <8 x i8> %tmp2, %tmp3
@@ -56,9 +57,10 @@ define <2 x float> @vld3f(float* %A) nounwind {
define <1 x i64> @vld3i64(i64* %A) nounwind {
;CHECK: vld3i64:
;CHECK: vld1.64
;Check the alignment value. Max for this instruction is 64 bits:
;CHECK: vld1.64 {d0, d1, d2}, [r0, :64]
%tmp0 = bitcast i64* %A to i8*
%tmp1 = call %struct.__neon_int64x1x3_t @llvm.arm.neon.vld3.v1i64(i8* %tmp0, i32 1)
%tmp1 = call %struct.__neon_int64x1x3_t @llvm.arm.neon.vld3.v1i64(i8* %tmp0, i32 16)
%tmp2 = extractvalue %struct.__neon_int64x1x3_t %tmp1, 0
%tmp3 = extractvalue %struct.__neon_int64x1x3_t %tmp1, 2
%tmp4 = add <1 x i64> %tmp2, %tmp3
@@ -67,9 +69,10 @@ define <1 x i64> @vld3i64(i64* %A) nounwind {
define <16 x i8> @vld3Qi8(i8* %A) nounwind {
;CHECK: vld3Qi8:
;CHECK: vld3.8
;CHECK: vld3.8
%tmp1 = call %struct.__neon_int8x16x3_t @llvm.arm.neon.vld3.v16i8(i8* %A, i32 1)
;Check the alignment value. Max for this instruction is 64 bits:
;CHECK: vld3.8 {d0, d2, d4}, [r0, :64]!
;CHECK: vld3.8 {d1, d3, d5}, [r0, :64]
%tmp1 = call %struct.__neon_int8x16x3_t @llvm.arm.neon.vld3.v16i8(i8* %A, i32 32)
%tmp2 = extractvalue %struct.__neon_int8x16x3_t %tmp1, 0
%tmp3 = extractvalue %struct.__neon_int8x16x3_t %tmp1, 2
%tmp4 = add <16 x i8> %tmp2, %tmp3