replica
/
hanchenye-llvm-project
2
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

AMDGPU/SI: Add latency for export instructions 

Reviewers: arsenm, nhaehnle

Subscribers: nhaehnle, arsenm, llvm-commits

Differential Revision: http://reviews.llvm.org/D18599

llvm-svn: 265708
This commit is contained in:
Tom Stellard 2016-04-07 18:30:05 +00:00
parent 40ad573d2c
commit 9112758077
2 changed files with 5 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
llvm/lib/Target/AMDGPU/SIInstrInfo.td
View File

@ -796,6 +796,7 @@ class EXPCommon : InstSI<
let EXP_CNT = 1;
let Uses = [EXEC];
let SchedRW = [WriteExport];
}
multiclass EXP_m {

9
llvm/test/CodeGen/AMDGPU/ret.ll
View File

@ -18,13 +18,12 @@ define amdgpu_vs {float, float} @vgpr([9 x <16 x i8>] addrspace(2)* byval, i32 i
}
; GCN-LABEL: {{^}}vgpr_literal:
; GCN: v_mov_b32_e32 v4, v0
; GCN: exp 15, 0, 1, 1, 1, v0, v0, v0, v0
; GCN: s_waitcnt expcnt(0)
; GCN-DAG: v_mov_b32_e32 v0, 1.0
; GCN-DAG: v_mov_b32_e32 v1, 2.0
; GCN-DAG: v_mov_b32_e32 v2, 4.0
; GCN-DAG: v_mov_b32_e32 v3, -1.0
; GCN: exp 15, 0, 1, 1, 1, v4, v4, v4, v4
; GCN: s_waitcnt expcnt(0)
; GCN-NOT: s_endpgm
define amdgpu_vs {float, float, float, float} @vgpr_literal([9 x <16 x i8>] addrspace(2)* byval, i32 inreg, i32 inreg, float) {
call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 1, float %3, float %3, float %3, float %3)
@ -230,13 +229,13 @@ define amdgpu_vs {float, i32, float, i32, i32} @both([9 x <16 x i8>] addrspace(2
; GCN-LABEL: {{^}}structure_literal:
; GCN: v_mov_b32_e32 v3, v0
; GCN: exp 15, 0, 1, 1, 1, v0, v0, v0, v0
; GCN: s_waitcnt expcnt(0)
; GCN-DAG: v_mov_b32_e32 v0, 1.0
; GCN-DAG: s_mov_b32 s0, 2
; GCN-DAG: s_mov_b32 s1, 3
; GCN-DAG: v_mov_b32_e32 v1, 2.0
; GCN-DAG: v_mov_b32_e32 v2, 4.0
; GCN-DAG: exp 15, 0, 1, 1, 1, v3, v3, v3, v3
define amdgpu_vs {{float, i32}, {i32, <2 x float>}} @structure_literal([9 x <16 x i8>] addrspace(2)* byval, i32 inreg, i32 inreg, float) {
call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 1, float %3, float %3, float %3, float %3)
ret {{float, i32}, {i32, <2 x float>}} {{float, i32} {float 1.0, i32 2}, {i32, <2 x float>} {i32 3, <2 x float> <float 2.0, float 4.0>}}