RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-22 12:33:33 +02:00
Code Issues Projects Releases Wiki Activity

AMDGPU: Use stricter regexes for add instructions

Browse Source 
Match the entire _co as one optional piece rather than
a set of characters to match multiple times.

llvm-svn: 319275
This commit is contained in:
Matt Arsenault 2017-11-29 02:25:14 +00:00
parent 6ead7b4924
commit d1baa17c1b
6 changed files with 66 additions and 66 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

104
test/CodeGen/AMDGPU/ds-combine-large-stride.ll
View File

@ -4,12 +4,12 @@
; GCN-LABEL: ds_read32_combine_stride_400:
; GCN: s_load_dword [[ARG:s[0-9]+]], s[4:5], 0x0
; GCN: v_mov_b32_e32 [[BASE:v[0-9]+]], [[ARG]]
; GCN-DAG: v_add_{{[_co]*}}u32_e32 [[B1:v[0-9]+]], vcc, 0x320, [[BASE]]
; GCN-DAG: v_add_{{[_co]*}}u32_e32 [[B2:v[0-9]+]], vcc, 0x640, [[BASE]]
; GCN-DAG: v_add_{{[_co]*}}u32_e32 [[B3:v[0-9]+]], vcc, 0x960, [[BASE]]
; GFX9-DAG: v_add_{{[_co]*}}u32_e32 [[B1:v[0-9]+]], vcc, 0x320, [[BASE]]
; GFX9-DAG: v_add_{{[_co]*}}u32_e32 [[B2:v[0-9]+]], vcc, 0x640, [[BASE]]
; GFX9-DAG: v_add_{{[_co]*}}u32_e32 [[B3:v[0-9]+]], vcc, 0x960, [[BASE]]
; GCN-DAG: v_add{{(_co)?}}_u32_e32 [[B1:v[0-9]+]], vcc, 0x320, [[BASE]]
; GCN-DAG: v_add{{(_co)?}}_u32_e32 [[B2:v[0-9]+]], vcc, 0x640, [[BASE]]
; GCN-DAG: v_add{{(_co)?}}_u32_e32 [[B3:v[0-9]+]], vcc, 0x960, [[BASE]]
; GFX9-DAG: v_add{{(_co)?}}_u32_e32 [[B1:v[0-9]+]], vcc, 0x320, [[BASE]]
; GFX9-DAG: v_add{{(_co)?}}_u32_e32 [[B2:v[0-9]+]], vcc, 0x640, [[BASE]]
; GFX9-DAG: v_add{{(_co)?}}_u32_e32 [[B3:v[0-9]+]], vcc, 0x960, [[BASE]]
; GCN-DAG: ds_read2_b32 v[{{[0-9]+:[0-9]+}}], [[BASE]] offset1:100
; GCN-DAG: ds_read2_b32 v[{{[0-9]+:[0-9]+}}], [[B1]] offset1:100
; GCN-DAG: ds_read2_b32 v[{{[0-9]+:[0-9]+}}], [[B2]] offset1:100
@ -46,12 +46,12 @@ bb:
; GCN-LABEL: ds_read32_combine_stride_400_back:
; GCN: s_load_dword [[ARG:s[0-9]+]], s[4:5], 0x0
; GCN: v_mov_b32_e32 [[BASE:v[0-9]+]], [[ARG]]
; GCN-DAG: v_add_{{[_co]*}}u32_e32 [[B1:v[0-9]+]], vcc, 0x320, [[BASE]]
; GCN-DAG: v_add_{{[_co]*}}u32_e32 [[B2:v[0-9]+]], vcc, 0x640, [[BASE]]
; GCN-DAG: v_add_{{[_co]*}}u32_e32 [[B3:v[0-9]+]], vcc, 0x960, [[BASE]]
; GFX9-DAG: v_add_{{[_co]*}}u32_e32 [[B1:v[0-9]+]], vcc, 0x320, [[BASE]]
; GFX9-DAG: v_add_{{[_co]*}}u32_e32 [[B2:v[0-9]+]], vcc, 0x640, [[BASE]]
; GFX9-DAG: v_add_{{[_co]*}}u32_e32 [[B3:v[0-9]+]], vcc, 0x960, [[BASE]]
; GCN-DAG: v_add{{(_co)?}}_u32_e32 [[B1:v[0-9]+]], vcc, 0x320, [[BASE]]
; GCN-DAG: v_add{{(_co)?}}_u32_e32 [[B2:v[0-9]+]], vcc, 0x640, [[BASE]]
; GCN-DAG: v_add{{(_co)?}}_u32_e32 [[B3:v[0-9]+]], vcc, 0x960, [[BASE]]
; GFX9-DAG: v_add{{(_co)?}}_u32_e32 [[B1:v[0-9]+]], vcc, 0x320, [[BASE]]
; GFX9-DAG: v_add{{(_co)?}}_u32_e32 [[B2:v[0-9]+]], vcc, 0x640, [[BASE]]
; GFX9-DAG: v_add{{(_co)?}}_u32_e32 [[B3:v[0-9]+]], vcc, 0x960, [[BASE]]
; GCN-DAG: ds_read2_b32 v[{{[0-9]+:[0-9]+}}], [[BASE]] offset1:100
; GCN-DAG: ds_read2_b32 v[{{[0-9]+:[0-9]+}}], [[B1]] offset1:100
; GCN-DAG: ds_read2_b32 v[{{[0-9]+:[0-9]+}}], [[B2]] offset1:100
@ -124,12 +124,12 @@ bb:
; GCN-LABEL: ds_read32_combine_stride_8192_shifted:
; GCN: s_load_dword [[ARG:s[0-9]+]], s[4:5], 0x0
; GCN: v_mov_b32_e32 [[BASE:v[0-9]+]], [[ARG]]
; GCN-DAG: v_add_{{[_co]*}}u32_e32 [[B1:v[0-9]+]], vcc, 8, [[BASE]]
; GCN-DAG: v_add_{{[_co]*}}u32_e32 [[B2:v[0-9]+]], vcc, 0x4008, [[BASE]]
; GCN-DAG: v_add_{{[_co]*}}u32_e32 [[B3:v[0-9]+]], vcc, 0x8008, [[BASE]]
; GFX9-DAG: v_add_{{[_co]*}}u32_e32 [[B1:v[0-9]+]], vcc, 8, [[BASE]]
; GFX9-DAG: v_add_{{[_co]*}}u32_e32 [[B2:v[0-9]+]], vcc, 0x4008, [[BASE]]
; GFX9-DAG: v_add_{{[_co]*}}u32_e32 [[B3:v[0-9]+]], vcc, 0x8008, [[BASE]]
; GCN-DAG: v_add{{(_co)?}}_u32_e32 [[B1:v[0-9]+]], vcc, 8, [[BASE]]
; GCN-DAG: v_add{{(_co)?}}_u32_e32 [[B2:v[0-9]+]], vcc, 0x4008, [[BASE]]
; GCN-DAG: v_add{{(_co)?}}_u32_e32 [[B3:v[0-9]+]], vcc, 0x8008, [[BASE]]
; GFX9-DAG: v_add{{(_co)?}}_u32_e32 [[B1:v[0-9]+]], vcc, 8, [[BASE]]
; GFX9-DAG: v_add{{(_co)?}}_u32_e32 [[B2:v[0-9]+]], vcc, 0x4008, [[BASE]]
; GFX9-DAG: v_add{{(_co)?}}_u32_e32 [[B3:v[0-9]+]], vcc, 0x8008, [[BASE]]
; GCN-DAG: ds_read2st64_b32 v[{{[0-9]+:[0-9]+}}], [[B1]] offset1:32
; GCN-DAG: ds_read2st64_b32 v[{{[0-9]+:[0-9]+}}], [[B2]] offset1:32
; GCN-DAG: ds_read2st64_b32 v[{{[0-9]+:[0-9]+}}], [[B3]] offset1:32
@ -160,8 +160,8 @@ bb:
; GCN-LABEL: ds_read64_combine_stride_400:
; GCN: s_load_dword [[ARG:s[0-9]+]], s[4:5], 0x0
; GCN: v_mov_b32_e32 [[BASE:v[0-9]+]], [[ARG]]
; GCN-DAG: v_add_{{[_co]*}}u32_e32 [[B1:v[0-9]+]], vcc, 0x960, [[BASE]]
; GFX9-DAG: v_add_{{[_co]*}}u32_e32 [[B1:v[0-9]+]], vcc, 0x960, [[BASE]]
; GCN-DAG: v_add{{(_co)?}}_u32_e32 [[B1:v[0-9]+]], vcc, 0x960, [[BASE]]
; GFX9-DAG: v_add{{(_co)?}}_u32_e32 [[B1:v[0-9]+]], vcc, 0x960, [[BASE]]
; GCN-DAG: ds_read2_b64 v[{{[0-9]+:[0-9]+}}], [[BASE]] offset1:50
; GCN-DAG: ds_read2_b64 v[{{[0-9]+:[0-9]+}}], [[BASE]] offset0:100 offset1:150
; GCN-DAG: ds_read2_b64 v[{{[0-9]+:[0-9]+}}], [[BASE]] offset0:200 offset1:250
@ -198,12 +198,12 @@ bb:
; GCN-LABEL: ds_read64_combine_stride_8192_shifted:
; GCN: s_load_dword [[ARG:s[0-9]+]], s[4:5], 0x0
; GCN: v_mov_b32_e32 [[BASE:v[0-9]+]], [[ARG]]
; GCN-DAG: v_add_{{[_co]*}}u32_e32 [[B1:v[0-9]+]], vcc, 8, [[BASE]]
; GCN-DAG: v_add_{{[_co]*}}u32_e32 [[B2:v[0-9]+]], vcc, 0x4008, [[BASE]]
; GCN-DAG: v_add_{{[_co]*}}u32_e32 [[B3:v[0-9]+]], vcc, 0x8008, [[BASE]]
; GFX9-DAG: v_add_{{[_co]*}}u32_e32 [[B1:v[0-9]+]], vcc, 8, [[BASE]]
; GFX9-DAG: v_add_{{[_co]*}}u32_e32 [[B2:v[0-9]+]], vcc, 0x4008, [[BASE]]
; GFX9-DAG: v_add_{{[_co]*}}u32_e32 [[B3:v[0-9]+]], vcc, 0x8008, [[BASE]]
; GCN-DAG: v_add{{(_co)?}}_u32_e32 [[B1:v[0-9]+]], vcc, 8, [[BASE]]
; GCN-DAG: v_add{{(_co)?}}_u32_e32 [[B2:v[0-9]+]], vcc, 0x4008, [[BASE]]
; GCN-DAG: v_add{{(_co)?}}_u32_e32 [[B3:v[0-9]+]], vcc, 0x8008, [[BASE]]
; GFX9-DAG: v_add{{(_co)?}}_u32_e32 [[B1:v[0-9]+]], vcc, 8, [[BASE]]
; GFX9-DAG: v_add{{(_co)?}}_u32_e32 [[B2:v[0-9]+]], vcc, 0x4008, [[BASE]]
; GFX9-DAG: v_add{{(_co)?}}_u32_e32 [[B3:v[0-9]+]], vcc, 0x8008, [[BASE]]
; GCN-DAG: ds_read2st64_b64 v[{{[0-9]+:[0-9]+}}], [[B1]] offset1:16
; GCN-DAG: ds_read2st64_b64 v[{{[0-9]+:[0-9]+}}], [[B2]] offset1:16
; GCN-DAG: ds_read2st64_b64 v[{{[0-9]+:[0-9]+}}], [[B3]] offset1:16
@ -234,12 +234,12 @@ bb:
; GCN-LABEL: ds_write32_combine_stride_400:
; GCN: s_load_dword [[ARG:s[0-9]+]], s[4:5], 0x0
; GCN: v_mov_b32_e32 [[BASE:v[0-9]+]], [[ARG]]
; GCN-DAG: v_add_{{[_co]*}}u32_e32 [[B1:v[0-9]+]], vcc, 0x320, [[BASE]]
; GCN-DAG: v_add_{{[_co]*}}u32_e32 [[B2:v[0-9]+]], vcc, 0x640, [[BASE]]
; GCN-DAG: v_add_{{[_co]*}}u32_e32 [[B3:v[0-9]+]], vcc, 0x960, [[BASE]]
; GFX9-DAG: v_add_{{[_co]*}}u32_e32 [[B1:v[0-9]+]], vcc, 0x320, [[BASE]]
; GFX9-DAG: v_add_{{[_co]*}}u32_e32 [[B2:v[0-9]+]], vcc, 0x640, [[BASE]]
; GFX9-DAG: v_add_{{[_co]*}}u32_e32 [[B3:v[0-9]+]], vcc, 0x960, [[BASE]]
; GCN-DAG: v_add{{(_co)?}}_u32_e32 [[B1:v[0-9]+]], vcc, 0x320, [[BASE]]
; GCN-DAG: v_add{{(_co)?}}_u32_e32 [[B2:v[0-9]+]], vcc, 0x640, [[BASE]]
; GCN-DAG: v_add{{(_co)?}}_u32_e32 [[B3:v[0-9]+]], vcc, 0x960, [[BASE]]
; GFX9-DAG: v_add{{(_co)?}}_u32_e32 [[B1:v[0-9]+]], vcc, 0x320, [[BASE]]
; GFX9-DAG: v_add{{(_co)?}}_u32_e32 [[B2:v[0-9]+]], vcc, 0x640, [[BASE]]
; GFX9-DAG: v_add{{(_co)?}}_u32_e32 [[B3:v[0-9]+]], vcc, 0x960, [[BASE]]
; GCN-DAG: ds_write2_b32 [[BASE]], v{{[0-9]+}}, v{{[0-9]+}} offset1:100
; GCN-DAG: ds_write2_b32 [[B1]], v{{[0-9]+}}, v{{[0-9]+}} offset1:100
; GCN-DAG: ds_write2_b32 [[B2]], v{{[0-9]+}}, v{{[0-9]+}} offset1:100
@ -267,12 +267,12 @@ bb:
; GCN-LABEL: ds_write32_combine_stride_400_back:
; GCN: s_load_dword [[ARG:s[0-9]+]], s[4:5], 0x0
; GCN: v_mov_b32_e32 [[BASE:v[0-9]+]], [[ARG]]
; GCN-DAG: v_add_{{[_co]*}}u32_e32 [[B1:v[0-9]+]], vcc, 0x320, [[BASE]]
; GCN-DAG: v_add_{{[_co]*}}u32_e32 [[B2:v[0-9]+]], vcc, 0x640, [[BASE]]
; GCN-DAG: v_add_{{[_co]*}}u32_e32 [[B3:v[0-9]+]], vcc, 0x960, [[BASE]]
; GFX9-DAG: v_add_{{[_co]*}}u32_e32 [[B1:v[0-9]+]], vcc, 0x320, [[BASE]]
; GFX9-DAG: v_add_{{[_co]*}}u32_e32 [[B2:v[0-9]+]], vcc, 0x640, [[BASE]]
; GFX9-DAG: v_add_{{[_co]*}}u32_e32 [[B3:v[0-9]+]], vcc, 0x960, [[BASE]]
; GCN-DAG: v_add{{(_co)?}}_u32_e32 [[B1:v[0-9]+]], vcc, 0x320, [[BASE]]
; GCN-DAG: v_add{{(_co)?}}_u32_e32 [[B2:v[0-9]+]], vcc, 0x640, [[BASE]]
; GCN-DAG: v_add{{(_co)?}}_u32_e32 [[B3:v[0-9]+]], vcc, 0x960, [[BASE]]
; GFX9-DAG: v_add{{(_co)?}}_u32_e32 [[B1:v[0-9]+]], vcc, 0x320, [[BASE]]
; GFX9-DAG: v_add{{(_co)?}}_u32_e32 [[B2:v[0-9]+]], vcc, 0x640, [[BASE]]
; GFX9-DAG: v_add{{(_co)?}}_u32_e32 [[B3:v[0-9]+]], vcc, 0x960, [[BASE]]
; GCN-DAG: ds_write2_b32 [[BASE]], v{{[0-9]+}}, v{{[0-9]+}} offset1:100
; GCN-DAG: ds_write2_b32 [[B1]], v{{[0-9]+}}, v{{[0-9]+}} offset1:100
; GCN-DAG: ds_write2_b32 [[B2]], v{{[0-9]+}}, v{{[0-9]+}} offset1:100
@ -327,12 +327,12 @@ bb:
; GCN-LABEL: ds_write32_combine_stride_8192_shifted:
; GCN: s_load_dword [[ARG:s[0-9]+]], s[4:5], 0x0
; GCN: v_mov_b32_e32 [[BASE:v[0-9]+]], [[ARG]]
; GCN-DAG: v_add_{{[_co]*}}u32_e32 [[B1:v[0-9]+]], vcc, 4, [[BASE]]
; GCN-DAG: v_add_{{[_co]*}}u32_e32 [[B2:v[0-9]+]], vcc, 0x4004, [[BASE]]
; GCN-DAG: v_add_{{[_co]*}}u32_e32 [[B3:v[0-9]+]], vcc, 0x8004, [[BASE]]
; GFX9-DAG: v_add_{{[_co]*}}u32_e32 [[B1:v[0-9]+]], vcc, 4, [[BASE]]
; GFX9-DAG: v_add_{{[_co]*}}u32_e32 [[B2:v[0-9]+]], vcc, 0x4004, [[BASE]]
; GFX9-DAG: v_add_{{[_co]*}}u32_e32 [[B3:v[0-9]+]], vcc, 0x8004, [[BASE]]
; GCN-DAG: v_add{{(_co)?}}_u32_e32 [[B1:v[0-9]+]], vcc, 4, [[BASE]]
; GCN-DAG: v_add{{(_co)?}}_u32_e32 [[B2:v[0-9]+]], vcc, 0x4004, [[BASE]]
; GCN-DAG: v_add{{(_co)?}}_u32_e32 [[B3:v[0-9]+]], vcc, 0x8004, [[BASE]]
; GFX9-DAG: v_add{{(_co)?}}_u32_e32 [[B1:v[0-9]+]], vcc, 4, [[BASE]]
; GFX9-DAG: v_add{{(_co)?}}_u32_e32 [[B2:v[0-9]+]], vcc, 0x4004, [[BASE]]
; GFX9-DAG: v_add{{(_co)?}}_u32_e32 [[B3:v[0-9]+]], vcc, 0x8004, [[BASE]]
; GCN-DAG: ds_write2st64_b32 [[B1]], v{{[0-9]+}}, v{{[0-9]+}} offset1:32
; GCN-DAG: ds_write2st64_b32 [[B2]], v{{[0-9]+}}, v{{[0-9]+}} offset1:32
; GCN-DAG: ds_write2st64_b32 [[B3]], v{{[0-9]+}}, v{{[0-9]+}} offset1:32
@ -356,8 +356,8 @@ bb:
; GCN-LABEL: ds_write64_combine_stride_400:
; GCN: s_load_dword [[ARG:s[0-9]+]], s[4:5], 0x0
; GCN: v_mov_b32_e32 [[BASE:v[0-9]+]], [[ARG]]
; GCN-DAG: v_add_{{[_co]*}}u32_e32 [[B1:v[0-9]+]], vcc, 0x960, [[BASE]]
; GFX9-DAG: v_add_{{[_co]*}}u32_e32 [[B1:v[0-9]+]], vcc, 0x960, [[BASE]]
; GCN-DAG: v_add{{(_co)?}}_u32_e32 [[B1:v[0-9]+]], vcc, 0x960, [[BASE]]
; GFX9-DAG: v_add{{(_co)?}}_u32_e32 [[B1:v[0-9]+]], vcc, 0x960, [[BASE]]
; GCN-DAG: ds_write2_b64 [[BASE]], v[{{[0-9]+:[0-9]+}}], v[{{[0-9]+:[0-9]+}}] offset1:50
; GCN-DAG: ds_write2_b64 [[BASE]], v[{{[0-9]+:[0-9]+}}], v[{{[0-9]+:[0-9]+}}] offset0:100 offset1:150
; GCN-DAG: ds_write2_b64 [[BASE]], v[{{[0-9]+:[0-9]+}}], v[{{[0-9]+:[0-9]+}}] offset0:200 offset1:250
@ -385,12 +385,12 @@ bb:
; GCN-LABEL: ds_write64_combine_stride_8192_shifted:
; GCN: s_load_dword [[ARG:s[0-9]+]], s[4:5], 0x0
; GCN: v_mov_b32_e32 [[BASE:v[0-9]+]], [[ARG]]
; GCN-DAG: v_add_{{[_co]*}}u32_e32 [[B1:v[0-9]+]], vcc, 8, [[BASE]]
; GCN-DAG: v_add_{{[_co]*}}u32_e32 [[B2:v[0-9]+]], vcc, 0x4008, [[BASE]]
; GCN-DAG: v_add_{{[_co]*}}u32_e32 [[B3:v[0-9]+]], vcc, 0x8008, [[BASE]]
; GFX9-DAG: v_add_{{[_co]*}}u32_e32 [[B1:v[0-9]+]], vcc, 8, [[BASE]]
; GFX9-DAG: v_add_{{[_co]*}}u32_e32 [[B2:v[0-9]+]], vcc, 0x4008, [[BASE]]
; GFX9-DAG: v_add_{{[_co]*}}u32_e32 [[B3:v[0-9]+]], vcc, 0x8008, [[BASE]]
; GCN-DAG: v_add{{(_co)?}}_u32_e32 [[B1:v[0-9]+]], vcc, 8, [[BASE]]
; GCN-DAG: v_add{{(_co)?}}_u32_e32 [[B2:v[0-9]+]], vcc, 0x4008, [[BASE]]
; GCN-DAG: v_add{{(_co)?}}_u32_e32 [[B3:v[0-9]+]], vcc, 0x8008, [[BASE]]
; GFX9-DAG: v_add{{(_co)?}}_u32_e32 [[B1:v[0-9]+]], vcc, 8, [[BASE]]
; GFX9-DAG: v_add{{(_co)?}}_u32_e32 [[B2:v[0-9]+]], vcc, 0x4008, [[BASE]]
; GFX9-DAG: v_add{{(_co)?}}_u32_e32 [[B3:v[0-9]+]], vcc, 0x8008, [[BASE]]
; GCN-DAG: ds_write2st64_b64 [[B1]], v[{{[0-9]+:[0-9]+}}], v[{{[0-9]+:[0-9]+}}] offset1:16
; GCN-DAG: ds_write2st64_b64 [[B2]], v[{{[0-9]+:[0-9]+}}], v[{{[0-9]+:[0-9]+}}] offset1:16
; GCN-DAG: ds_write2st64_b64 [[B3]], v[{{[0-9]+:[0-9]+}}], v[{{[0-9]+:[0-9]+}}] offset1:16

10
test/CodeGen/AMDGPU/function-args.ll
View File

@ -24,7 +24,7 @@ define void @void_func_i1_zeroext(i1 zeroext %arg0) #0 {
; GCN-LABEL: {{^}}void_func_i1_signext:
; GCN: s_waitcnt
; GCN-NEXT: v_add_{{[_coiu]*}}32_e32 v0, vcc, 12, v0
; GCN-NEXT: v_add{{(_co)?}}_{{i|u}}32_e32 v0, vcc, 12, v0
; GCN-NOT: v0
; GCN: buffer_store_dword v0, off
define void @void_func_i1_signext(i1 signext %arg0) #0 {
@ -60,7 +60,7 @@ define void @void_func_i8(i8 %arg0) #0 {
; GCN-LABEL: {{^}}void_func_i8_zeroext:
; GCN-NOT: and_b32
; GCN: v_add_{{[_coiu]*}}32_e32 v0, vcc, 12, v0
; GCN: v_add{{(_co)?}}_{{i|u}}32_e32 v0, vcc, 12, v0
define void @void_func_i8_zeroext(i8 zeroext %arg0) #0 {
%ext = zext i8 %arg0 to i32
%add = add i32 %ext, 12
@ -70,7 +70,7 @@ define void @void_func_i8_zeroext(i8 zeroext %arg0) #0 {
; GCN-LABEL: {{^}}void_func_i8_signext:
; GCN-NOT: v_bfe_i32
; GCN: v_add_{{[_coiu]*}}32_e32 v0, vcc, 12, v0
; GCN: v_add{{(_co)?}}_{{i|u}}32_e32 v0, vcc, 12, v0
define void @void_func_i8_signext(i8 signext %arg0) #0 {
%ext = sext i8 %arg0 to i32
%add = add i32 %ext, 12
@ -87,7 +87,7 @@ define void @void_func_i16(i16 %arg0) #0 {
; GCN-LABEL: {{^}}void_func_i16_zeroext:
; GCN-NOT: v0
; GCN: v_add_{{[_coiu]*}}32_e32 v0, vcc, 12, v0
; GCN: v_add{{(_co)?}}_{{i|u}}32_e32 v0, vcc, 12, v0
define void @void_func_i16_zeroext(i16 zeroext %arg0) #0 {
%ext = zext i16 %arg0 to i32
%add = add i32 %ext, 12
@ -97,7 +97,7 @@ define void @void_func_i16_zeroext(i16 zeroext %arg0) #0 {
; GCN-LABEL: {{^}}void_func_i16_signext:
; GCN-NOT: v0
; GCN: v_add_{{[_coiu]*}}32_e32 v0, vcc, 12, v0
; GCN: v_add{{(_co)?}}_{{i|u}}32_e32 v0, vcc, 12, v0
define void @void_func_i16_signext(i16 signext %arg0) #0 {
%ext = sext i16 %arg0 to i32
%add = add i32 %ext, 12

2
test/CodeGen/AMDGPU/pack.v2f16.ll
View File

@ -87,7 +87,7 @@ define amdgpu_kernel void @v_pack_v2f16(i32 addrspace(1)* %in0, i32 addrspace(1)
; GFX9: v_and_b32_e32 [[ELT0:v[0-9]+]], 0xffff, [[VAL0]]
; GFX9: v_lshl_or_b32 [[PACKED:v[0-9]+]], [[VAL1]], 16, [[ELT0]]
; GFX9: v_add_{{[_coiu]*}}32_e32 v{{[0-9]+}}, vcc, 9, [[PACKED]]
; GFX9: v_add{{(_co)?}}_{{i|u}}32_e32 v{{[0-9]+}}, vcc, 9, [[PACKED]]
define amdgpu_kernel void @v_pack_v2f16_user(i32 addrspace(1)* %in0, i32 addrspace(1)* %in1) #0 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
%tid.ext = sext i32 %tid to i64

10
test/CodeGen/AMDGPU/sdwa-peephole.ll
View File

@ -5,9 +5,9 @@
; GCN-LABEL: {{^}}add_shr_i32:
; NOSDWA: v_lshrrev_b32_e32 v[[DST:[0-9]+]], 16, v{{[0-9]+}}
; NOSDWA: v_add_u32_e32 v{{[0-9]+}}, vcc, v{{[0-9]+}}, v[[DST]]
; NOSDWA-NOT: v_add_{{[_cou]*}}32_sdwa
; NOSDWA-NOT: v_add_{{(_co)?}}_u32_sdwa
; SDWA: v_add_{{[_cou]*}}32_sdwa v{{[0-9]+}}, vcc, v{{[0-9]+}}, v{{[0-9]+}} dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:WORD_1
; SDWA: v_add{{(_co)?}}_u32_sdwa v{{[0-9]+}}, vcc, v{{[0-9]+}}, v{{[0-9]+}} dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:WORD_1
define amdgpu_kernel void @add_shr_i32(i32 addrspace(1)* %out, i32 addrspace(1)* %in) {
%a = load i32, i32 addrspace(1)* %in, align 4
@ -20,9 +20,9 @@ define amdgpu_kernel void @add_shr_i32(i32 addrspace(1)* %out, i32 addrspace(1)*
; GCN-LABEL: {{^}}sub_shr_i32:
; NOSDWA: v_lshrrev_b32_e32 v[[DST:[0-9]+]], 16, v{{[0-9]+}}
; NOSDWA: v_subrev_u32_e32 v{{[0-9]+}}, vcc, v{{[0-9]+}}, v[[DST]]
; NOSDWA-NOT: v_subrev_{{[_cou]*}}32_sdwa
; NOSDWA-NOT: v_subrev_{{(_co)?}}_u32_sdwa
; SDWA: v_subrev_{{[_cou]*}}32_sdwa v{{[0-9]+}}, vcc, v{{[0-9]+}}, v{{[0-9]+}} dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:WORD_1
; SDWA: v_subrev{{(_co)?}}_u32_sdwa v{{[0-9]+}}, vcc, v{{[0-9]+}}, v{{[0-9]+}} dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:WORD_1
define amdgpu_kernel void @sub_shr_i32(i32 addrspace(1)* %out, i32 addrspace(1)* %in) {
%a = load i32, i32 addrspace(1)* %in, align 4
@ -426,7 +426,7 @@ entry:
}
; GCN-LABEL: {{^}}add_bb_v2i16:
; NOSDWA-NOT: v_add_{{[_cou]*}}32_sdwa
; NOSDWA-NOT: v_add_{{(_co)?}}_u32_sdwa
; VI: v_add_u32_sdwa v{{[0-9]+}}, vcc, v{{[0-9]+}}, v{{[0-9]+}} dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:WORD_1

2
test/CodeGen/AMDGPU/smrd.ll
View File

@ -204,7 +204,7 @@ main_body:
; GCN-LABEL: {{^}}smrd_vgpr_offset_imm_too_large:
; GCN-NEXT: BB#
; GCN-NEXT: v_add_{{[_coiu]*}}32_e32 v0, vcc, 0x1000, v0
; GCN-NEXT: v_add{{(_co)?}}_{{i|u}}32_e32 v0, vcc, 0x1000, v0
; GCN-NEXT: buffer_load_dword v{{[0-9]}}, v0, s[0:3], 0 offen ;
define amdgpu_ps float @smrd_vgpr_offset_imm_too_large(<4 x i32> inreg %desc, i32 %offset) #0 {
main_body:

4
test/CodeGen/AMDGPU/store-hi16.ll
View File

@ -289,7 +289,7 @@ entry:
; GCN-LABEL: {{^}}store_flat_hi_v2i16_neg_offset:
; GCN: s_waitcnt
; GCN: v_add_{{[_cou]*}}32_e32
; GCN: v_add{{(_co)?}}_{{i|u}}32_e32
; VI: v_addc_u32_e32
; GFX9: v_addc_co_u32_e32
@ -328,7 +328,7 @@ entry:
; GCN-LABEL: {{^}}store_flat_hi_v2i16_i8_neg_offset:
; GCN: s_waitcnt
; GCN-DAG: v_add_{{[_cou]*}}32_e32
; GCN-DAG: v_add{{(_co)?}}_{{i|u}}32_e32
; VI-DAG: v_addc_u32_e32
; GFX9-DAG: v_addc_co_u32_e32