RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2025-01-31 01:03:52 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

R600/SI: Add support for v4i32 and v4f32 kernel args

Browse Source 
Tested-By: Aaron Watry <awatry@gmail.com>
llvm-svn: 184820
This commit is contained in:
Tom Stellard 2013-06-25 02:39:25 +00:00
parent 0300b2cb3a
commit b4ab710b43
2 changed files with 15 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
lib/Target/R600/AMDGPUCallingConv.td
View File

@ -38,10 +38,11 @@ def CC_SI : CallingConv<[
// Calling convention for SI compute kernels
def CC_SI_Kernel : CallingConv<[
CCIfType<[i64], CCAssignToStack <8, 4>>,
CCIfType<[i32, f32], CCAssignToStack <4, 4>>,
CCIfType<[i16], CCAssignToStack <2, 4>>,
CCIfType<[i8], CCAssignToStack <1, 4>>
CCIfType<[v4i32, v4f32], CCAssignToStack <16, 4>>,
CCIfType<[i64], CCAssignToStack < 8, 4>>,
CCIfType<[i32, f32], CCAssignToStack < 4, 4>>,
CCIfType<[i16], CCAssignToStack < 2, 4>>,
CCIfType<[i8], CCAssignToStack < 1, 4>>
]>;
def CC_AMDGPU : CallingConv<[

16
test/CodeGen/R600/128bit-kernel-args.ll
View File

@ -1,16 +1,20 @@
;RUN: llc < %s -march=r600 -mcpu=redwood | FileCheck %s
; CHECK: @v4i32_kernel_arg
; CHECK: VTX_READ_128 T{{[0-9]+}}.XYZW, T{{[0-9]+}}.X, 40
; RUN: llc < %s -march=r600 -mcpu=redwood | FileCheck %s --check-prefix=R600-CHECK
; RUN: llc < %s -march=r600 -mcpu=SI | FileCheck %s --check-prefix=SI-CHECK
; R600-CHECK: @v4i32_kernel_arg
; R600-CHECK: VTX_READ_128 T{{[0-9]+}}.XYZW, T{{[0-9]+}}.X, 40
; SI-CHECK: @v4i32_kernel_arg
; SI-CHECK: BUFFER_STORE_DWORDX4
define void @v4i32_kernel_arg(<4 x i32> addrspace(1)* %out, <4 x i32> %in) {
entry:
store <4 x i32> %in, <4 x i32> addrspace(1)* %out
ret void
}
; CHECK: @v4f32_kernel_arg
; CHECK: VTX_READ_128 T{{[0-9]+}}.XYZW, T{{[0-9]+}}.X, 40
; R600-CHECK: @v4f32_kernel_arg
; R600-CHECK: VTX_READ_128 T{{[0-9]+}}.XYZW, T{{[0-9]+}}.X, 40
; SI-CHECK: @v4f32_kernel_arg
; SI-CHECK: BUFFER_STORE_DWORDX4
define void @v4f32_kernel_args(<4 x float> addrspace(1)* %out, <4 x float> %in) {
entry:
store <4 x float> %in, <4 x float> addrspace(1)* %out