[all-commits] [llvm/llvm-project] 722b8e: AMDGPU: Invert ABI attribute handling

[Matt Arsenault via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 722b8e0e5a042cf7db682c2b20c88999daa36f4a
      https://github.com/llvm/llvm-project/commit/722b8e0e5a042cf7db682c2b20c88999daa36f4a
  Author: Matt Arsenault <Matthew.Arsenault at amd.com>
  Date:   2021-09-09 (Thu, 09 Sep 2021)

  Changed paths:
    M llvm/lib/Target/AMDGPU/AMDGPUAnnotateKernelFeatures.cpp
    M llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
    M llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.cpp
    M llvm/test/CodeGen/AMDGPU/addrspacecast-constantexpr.ll
    M llvm/test/CodeGen/AMDGPU/annotate-kernel-features-hsa-call.ll
    M llvm/test/CodeGen/AMDGPU/annotate-kernel-features-hsa.ll
    M llvm/test/CodeGen/AMDGPU/annotate-kernel-features.ll
    M llvm/test/CodeGen/AMDGPU/call-constexpr.ll
    M llvm/test/CodeGen/AMDGPU/call-waitcnt.ll
    M llvm/test/CodeGen/AMDGPU/callee-special-input-sgprs-fixed-abi.ll
    M llvm/test/CodeGen/AMDGPU/callee-special-input-sgprs.ll
    M llvm/test/CodeGen/AMDGPU/cc-update.ll
    M llvm/test/CodeGen/AMDGPU/cross-block-use-is-not-abi-copy.ll
    M llvm/test/CodeGen/AMDGPU/direct-indirect-call.ll
    M llvm/test/CodeGen/AMDGPU/ds_read2.ll
    M llvm/test/CodeGen/AMDGPU/duplicate-attribute-indirect.ll
    M llvm/test/CodeGen/AMDGPU/flat-scratch-init.ll
    M llvm/test/CodeGen/AMDGPU/indirect-call.ll
    M llvm/test/CodeGen/AMDGPU/llc-pipeline.ll
    M llvm/test/CodeGen/AMDGPU/llvm.amdgcn.implicitarg.ptr.ll
    M llvm/test/CodeGen/AMDGPU/simple-indirect-call.ll
    M llvm/test/CodeGen/AMDGPU/stack-pointer-offset-relative-frameindex.ll
    M llvm/test/CodeGen/MIR/AMDGPU/machine-function-info.ll

  Log Message:
  -----------
  AMDGPU: Invert ABI attribute handling

Previously we assumed all callable functions did not need any
implicitly passed inputs, and added attributes to functions to
indicate when they were necessary. Requiring attributes for
correctness is pretty ugly, and it makes supporting indirect and
external calls more complicated.

This inverts the direction of the attributes, so an undecorated
function is assumed to need all implicit imputs. This enables
AMDGPUAttributor by default to mark when functions are proven to not
need a given input. This strips the equivalent functionality from the
legacy AMDGPUAnnotateKernelFeatures pass.

However, AMDGPUAnnotateKernelFeatures is not fully removed at this
point although it should be in the future. It is still necessary for
the two hacky amdgpu-calls and amdgpu-stack-objects attributes, which
would be better served by a trivial analysis on the IR during
selection. Additionally, AMDGPUAnnotateKernelFeatures still
redundantly handles the uniform-work-group-size attribute to be
removed in a future commit.

At this point when not using -amdgpu-fixed-function-abi, we are still
modifying the ABI based on these newly negated attributes. In the
future, this option will be removed and the locations for implicit
inputs will always be fixed. We will then use the new attributes to
avoid passing the values when unnecessary.


  Commit: db4963d080916e8ac431257a2d33887b12f5bb99
      https://github.com/llvm/llvm-project/commit/db4963d080916e8ac431257a2d33887b12f5bb99
  Author: Matt Arsenault <Matthew.Arsenault at amd.com>
  Date:   2021-09-09 (Thu, 09 Sep 2021)

  Changed paths:
    M llvm/lib/Target/AMDGPU/AMDGPUAnnotateKernelFeatures.cpp
    M llvm/test/CodeGen/AMDGPU/annotate-kernel-features-hsa-call.ll
    M llvm/test/CodeGen/AMDGPU/direct-indirect-call.ll
    M llvm/test/CodeGen/AMDGPU/uniform-work-group-attribute-missing.ll
    M llvm/test/CodeGen/AMDGPU/uniform-work-group-multistep.ll
    M llvm/test/CodeGen/AMDGPU/uniform-work-group-nested-function-calls.ll
    M llvm/test/CodeGen/AMDGPU/uniform-work-group-prevent-attribute-propagation.ll
    M llvm/test/CodeGen/AMDGPU/uniform-work-group-propagate-attribute.ll
    M llvm/test/CodeGen/AMDGPU/uniform-work-group-recursion-test.ll
    M llvm/test/CodeGen/AMDGPU/uniform-work-group-test.ll

  Log Message:
  -----------
  AMDGPU: Use attributor to propagate uniform-work-group-size

Drop the legacy version in AMDGPUAnnotateKernelFeatures. This has the
side effect of now respecting the linkage, and not changing externally
visible functions.


  Commit: 0197cd0bd4a4ea3d05ae55f05a6e70202cd6a19b
      https://github.com/llvm/llvm-project/commit/0197cd0bd4a4ea3d05ae55f05a6e70202cd6a19b
  Author: Matt Arsenault <Matthew.Arsenault at amd.com>
  Date:   2021-09-09 (Thu, 09 Sep 2021)

  Changed paths:
    M llvm/lib/Target/AMDGPU/AMDGPUCallLowering.cpp
    M llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp
    M llvm/lib/Target/AMDGPU/SIISelLowering.cpp
    M llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-call-abi-attribute-hints.ll
    M llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-sibling-call.ll
    A llvm/test/CodeGen/AMDGPU/abi-attribute-hints-undefined-behavior.ll
    M llvm/test/CodeGen/AMDGPU/callee-special-input-sgprs-fixed-abi.ll
    M llvm/test/CodeGen/AMDGPU/callee-special-input-vgprs.ll

  Log Message:
  -----------
  AMDGPU: Optimize amdgpu-no-* attributes

This allows clobbering a few extra registers in the fixed ABI, and
avoids some workitem ID packing instructions.


Compare: https://github.com/llvm/llvm-project/compare/bfa2a81e926f...0197cd0bd4a4