diff options
| author | Stanislav Mekhanoshin <Stanislav.Mekhanoshin@amd.com> | 2017-05-30 16:49:24 +0000 |
|---|---|---|
| committer | Stanislav Mekhanoshin <Stanislav.Mekhanoshin@amd.com> | 2017-05-30 16:49:24 +0000 |
| commit | 56ea488d8b8c897599f13c9f9e8058cb36ff808f (patch) | |
| tree | c6091973507e778cdeebd01dc0a57f517fedd56c /llvm/test/CodeGen/AMDGPU/scratch-simple.ll | |
| parent | 8c099fe06e9c4efdea698ac82df2685792ea0b6e (diff) | |
| download | bcm5719-llvm-56ea488d8b8c897599f13c9f9e8058cb36ff808f.tar.gz bcm5719-llvm-56ea488d8b8c897599f13c9f9e8058cb36ff808f.zip | |
[AMDGPU] Allow SDWA in instructions with immediates and SGPRs
An encoding does not allow to use SDWA in an instruction with
scalar operands, either literals or SGPRs. That is however possible
to copy these operands into a VGPR first.
Several copies of the value are produced if multiple SDWA conversions
were done. To cleanup MachineLICM (to hoist copies out of loops),
MachineCSE (to remove duplicate copies) and SIFoldOperands (to replace
SGPR to VGPR copy with immediate copy right to the VGPR) runs are added
after the SDWA pass.
Differential Revision: https://reviews.llvm.org/D33583
llvm-svn: 304219
Diffstat (limited to 'llvm/test/CodeGen/AMDGPU/scratch-simple.ll')
| -rw-r--r-- | llvm/test/CodeGen/AMDGPU/scratch-simple.ll | 6 |
1 files changed, 2 insertions, 4 deletions
diff --git a/llvm/test/CodeGen/AMDGPU/scratch-simple.ll b/llvm/test/CodeGen/AMDGPU/scratch-simple.ll index 60b9b56a48d..6ed730ad60f 100644 --- a/llvm/test/CodeGen/AMDGPU/scratch-simple.ll +++ b/llvm/test/CodeGen/AMDGPU/scratch-simple.ll @@ -9,13 +9,11 @@ ; GCN-LABEL: {{^}}ps_main: ; GCN-DAG: s_mov_b32 [[SWO:s[0-9]+]], s0 -; GCN-DAG: v_mov_b32_e32 [[K:v[0-9]+]], 0x200 -; GCN-DAG: v_mov_b32_e32 [[ZERO:v[0-9]+]], 0x400{{$}} ; GCN-DAG: v_lshlrev_b32_e32 [[BYTES:v[0-9]+]], 2, v0 ; GCN-DAG: v_and_b32_e32 [[CLAMP_IDX:v[0-9]+]], 0x1fc, [[BYTES]] -; GCN-DAG: v_or_b32_e32 [[LO_OFF:v[0-9]+]], [[CLAMP_IDX]], [[K]] -; GCN-DAG: v_or_b32_e32 [[HI_OFF:v[0-9]+]], [[CLAMP_IDX]], [[ZERO]] +; GCN-DAG: v_or_b32_e32 [[LO_OFF:v[0-9]+]], 0x200, [[CLAMP_IDX]] +; GCN-DAG: v_or_b32_e32 [[HI_OFF:v[0-9]+]], 0x400, [[CLAMP_IDX]] ; GCN: buffer_load_dword {{v[0-9]+}}, [[LO_OFF]], {{s\[[0-9]+:[0-9]+\]}}, [[SWO]] offen ; GCN: buffer_load_dword {{v[0-9]+}}, [[HI_OFF]], {{s\[[0-9]+:[0-9]+\]}}, [[SWO]] offen |
