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

[AMDGPU] Enable constant offset promotion to immediate operand for VMEM stores 

Differential revision: https://reviews.llvm.org/D66958

llvm-svn: 371214
This commit is contained in:
Valery Pykhtin 2019-09-06 15:33:53 +00:00
parent 8f10a5f42d
commit e8ade89bb3
2 changed files with 30 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
llvm/lib/Target/AMDGPU/SILoadStoreOptimizer.cpp
View File

@ -1316,13 +1316,14 @@ bool SILoadStoreOptimizer::promoteConstantOffsetToImm(
MemInfoMap &Visited,
SmallPtrSet<MachineInstr *, 4> &AnchorList) {
// TODO: Support flat and scratch.
if (AMDGPU::getGlobalSaddrOp(MI.getOpcode()) < 0 ||
TII->getNamedOperand(MI, AMDGPU::OpName::vdata) != NULL)
if (!(MI.mayLoad() ^ MI.mayStore()))
return false;
// TODO: Support Store.
if (!MI.mayLoad())
// TODO: Support flat and scratch.
if (AMDGPU::getGlobalSaddrOp(MI.getOpcode()) < 0)
return false;
if (MI.mayLoad() && TII->getNamedOperand(MI, AMDGPU::OpName::vdata) != NULL)
return false;
if (AnchorList.count(&MI))

24
llvm/test/CodeGen/AMDGPU/promote-constOffset-to-imm.mir
View File

@ -188,3 +188,27 @@ body: |
%30:vreg_64 = REG_SEQUENCE %26, %subreg.sub0, %28, %subreg.sub1
%31:vreg_64 = GLOBAL_LOAD_DWORDX2 %30, 0, 0, 0, 0, implicit $exec
...
---
# GFX9-LABEL: name: diffoporder_add_store
# GFX9: GLOBAL_STORE_DWORD %{{[0-9]+}}, %0.sub0, 1000, 0, 0, 0
# GFX9: GLOBAL_STORE_DWORD %{{[0-9]+}}, %0.sub1, 0, 0, 0, 0
name: diffoporder_add_store
body: |
bb.0.entry:
%0:vreg_64 = COPY $vgpr0_vgpr1
%1:sgpr_32 = S_MOV_B32 4000
%2:vgpr_32, %3:sreg_64_xexec = V_ADD_I32_e64 %0.sub0, %1, 0, implicit $exec
%4:vgpr_32, dead %5:sreg_64_xexec = V_ADDC_U32_e64 %0.sub1, 0, %3, 0, implicit $exec
%6:vreg_64 = REG_SEQUENCE %2, %subreg.sub0, %4, %subreg.sub1
GLOBAL_STORE_DWORD %6, %0.sub0, 0, 0, 0, 0, implicit $exec
%8:sgpr_32 = S_MOV_B32 3000
%9:vgpr_32, %10:sreg_64_xexec = V_ADD_I32_e64 %0.sub0, %8, 0, implicit $exec
%11:vgpr_32, dead %12:sreg_64_xexec = V_ADDC_U32_e64 %0.sub1, 0, %10, 0, implicit $exec
%13:vreg_64 = REG_SEQUENCE %9, %subreg.sub0, %11, %subreg.sub1
GLOBAL_STORE_DWORD %13, %0.sub1, 0, 0, 0, 0, implicit $exec
...