[PATCH] D80545: [AMDGPU/MemOpsCluster] Let mem ops clustering logic also consider number of clustered bytes

[Mahesha S via Phabricator via llvm-commits]

hsmhsm created this revision.
hsmhsm added reviewers: foad, rampitec, arsenm, vpykhtin, javedabsar.
Herald added subscribers: llvm-commits, kerbowa, javed.absar, hiraditya, t-tye, tpr, dstuttard, yaxunl, nhaehnle, wdng, jvesely, kzhuravl, MatzeB.
Herald added a project: LLVM.
hsmhsm edited the summary of this revision.
hsmhsm edited the summary of this revision.

While clustering mem ops, AMDGPU target needs to consider number of clustered bytes
to decide on max number of mem ops that can be clustered. This patch adds support to pass
number of clustered bytes to target mem ops clustering logic.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D80545

Files:
  llvm/include/llvm/CodeGen/TargetInstrInfo.h
  llvm/lib/CodeGen/MachineScheduler.cpp
  llvm/lib/Target/AArch64/AArch64InstrInfo.cpp
  llvm/lib/Target/AArch64/AArch64InstrInfo.h
  llvm/lib/Target/AMDGPU/SIInsertHardClauses.cpp
  llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
  llvm/lib/Target/AMDGPU/SIInstrInfo.h

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D80545.266152.patch
Type: text/x-patch
Size: 8038 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20200526/f10c855b/attachment.bin>