RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-22 18:54:02 +01:00
Code Issues Projects Releases Wiki Activity

[AMDGPU] GCNDPPCombine: don't shrink V_ADD_CO_U32 if carry out is used

Browse Source 
Don't shrink VOP3 instructions if there are any uses of a carry-out
operand, because the shrunken form of the instruction would write the
carry-out to vcc instead of to a virtual register.

Differential Revision: https://reviews.llvm.org/D100760
This commit is contained in:
Jay Foad 2021-04-19 14:48:20 +01:00
parent eed19ff5a2
commit c7f91a7bf2
2 changed files with 27 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
lib/Target/AMDGPU/GCNDPPCombine.cpp
View File

@ -123,6 +123,13 @@ bool GCNDPPCombine::isShrinkable(MachineInstr &MI) const {
LLVM_DEBUG(dbgs() << " Inst hasn't e32 equivalent\n"); LLVM_DEBUG(dbgs() << " Inst hasn't e32 equivalent\n");
return false; return false;
} }
if (const auto *SDst = TII->getNamedOperand(MI, AMDGPU::OpName::sdst)) {
// Give up if there are any uses of the carry-out from instructions like
// V_ADD_CO_U32. The shrunken form of the instruction would write it to vcc
// instead of to a virtual register.
if (!MRI->use_nodbg_empty(SDst->getReg()))
return false;
}
// check if other than abs|neg modifiers are set (opsel for example) // check if other than abs|neg modifiers are set (opsel for example)
const int64_t Mask = ~(SISrcMods::ABS | SISrcMods::NEG); const int64_t Mask = ~(SISrcMods::ABS | SISrcMods::NEG);
if (!hasNoImmOrEqual(MI, AMDGPU::OpName::src0_modifiers, 0, Mask) || if (!hasNoImmOrEqual(MI, AMDGPU::OpName::src0_modifiers, 0, Mask) ||

20
test/CodeGen/AMDGPU/dpp_combine.mir
View File

@ -354,6 +354,26 @@ body: |
%6:vgpr_32 = V_ADD_U32_e64 %5, %1, 1, implicit $exec %6:vgpr_32 = V_ADD_U32_e64 %5, %1, 1, implicit $exec
... ...
# GCN-LABEL: name: add_co_u32_e64
# GCN: %4:vgpr_32, %5:sreg_64_xexec = V_ADD_CO_U32_e64 %3, %1, 0, implicit $exec
name: add_co_u32_e64
tracksRegLiveness: true
body: |
bb.0:
liveins: $vgpr0, $vgpr1
%0:vgpr_32 = COPY $vgpr0
%1:vgpr_32 = COPY $vgpr1
%2:vgpr_32 = IMPLICIT_DEF
; this shouldn't be combined as the carry-out is used
%3:vgpr_32 = V_MOV_B32_dpp undef %2, %0, 1, 15, 15, 1, implicit $exec
%4:vgpr_32, %5:sreg_64_xexec = V_ADD_CO_U32_e64 %3, %1, 0, implicit $exec
S_NOP 0, implicit %5
...
# tests on sequences of dpp consumers # tests on sequences of dpp consumers
# GCN-LABEL: name: dpp_seq # GCN-LABEL: name: dpp_seq
# GCN: %4:vgpr_32 = V_ADD_CO_U32_dpp %1, %0, %1, 1, 14, 15, 0, implicit-def $vcc, implicit $exec # GCN: %4:vgpr_32 = V_ADD_CO_U32_dpp %1, %0, %1, 1, 14, 15, 0, implicit-def $vcc, implicit $exec