maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[AMDGPU] Do not combine dpp with physreg def 

We will remove dpp mov along with the physreg def otherwise.

Differential Revision: https://reviews.llvm.org/D69063

llvm-svn: 375030
This commit is contained in:
Stanislav Mekhanoshin 2019-10-16 18:48:54 +00:00
parent 48a50ee034
commit 3d99310c15
2 changed files with 16 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
llvm/lib/Target/AMDGPU/GCNDPPCombine.cpp
View File

@ -353,6 +353,10 @@ bool GCNDPPCombine::combineDPPMov(MachineInstr &MovMI) const {
auto *DstOpnd = TII->getNamedOperand(MovMI, AMDGPU::OpName::vdst);
assert(DstOpnd && DstOpnd->isReg());
auto DPPMovReg = DstOpnd->getReg();
if (DPPMovReg.isPhysical()) {
LLVM_DEBUG(dbgs() << " failed: dpp move writes physreg\n");
return false;
}
if (execMayBeModifiedBeforeAnyUse(*MRI, DPPMovReg, MovMI)) {
LLVM_DEBUG(dbgs() << " failed: EXEC mask should remain the same"
" for all uses\n");

12
llvm/test/CodeGen/AMDGPU/dpp_combine.mir
View File

@ -563,6 +563,18 @@ body: |
%3:vgpr_32 = V_CEIL_F32_e32 %2, implicit $exec
...
# Do not combine a dpp mov which writes a physreg.
# GCN-LABEL: name: phys_dpp_mov_dst
# GCN: $vgpr0 = V_MOV_B32_dpp undef %0:vgpr_32, undef %1:vgpr_32, 1, 15, 15, 1, implicit $exec
# GCN: %2:vgpr_32 = V_CEIL_F32_e32 $vgpr0, implicit $exec
name: phys_dpp_mov_dst
tracksRegLiveness: true
body: |
bb.0:
$vgpr0 = V_MOV_B32_dpp undef %1:vgpr_32, undef %0:vgpr_32, 1, 15, 15, 1, implicit $exec
%2:vgpr_32 = V_CEIL_F32_e32 $vgpr0, implicit $exec
...
# GCN-LABEL: name: dpp_reg_sequence_both_combined
# GCN: %0:vreg_64 = COPY $vgpr0_vgpr1
# GCN: %1:vreg_64 = COPY $vgpr2_vgpr3