[all-commits] [llvm/llvm-project] 56910a: [NVPTX] Improve kernel byval parameter lowering (#...

[Alex MacLean via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 56910a8b1b302ebf37e9d30bd200091fd23dc232
      https://github.com/llvm/llvm-project/commit/56910a8b1b302ebf37e9d30bd200091fd23dc232
  Author: Alex MacLean <amaclean at nvidia.com>
  Date:   2025-04-21 (Mon, 21 Apr 2025)

  Changed paths:
    M llvm/include/llvm/IR/IntrinsicsNVVM.td
    M llvm/lib/Target/NVPTX/NVPTXISelDAGToDAG.cpp
    M llvm/lib/Target/NVPTX/NVPTXISelLowering.cpp
    M llvm/lib/Target/NVPTX/NVPTXIntrinsics.td
    M llvm/lib/Target/NVPTX/NVPTXLowerArgs.cpp
    M llvm/lib/Target/NVPTX/NVPTXUtilities.cpp
    M llvm/lib/Target/NVPTX/NVPTXUtilities.h
    M llvm/test/CodeGen/NVPTX/bug21465.ll
    M llvm/test/CodeGen/NVPTX/forward-ld-param.ll
    M llvm/test/CodeGen/NVPTX/lower-args-gridconstant.ll
    M llvm/test/CodeGen/NVPTX/lower-args.ll
    M llvm/test/CodeGen/NVPTX/lower-byval-args.ll
    M llvm/test/tools/UpdateTestChecks/update_llc_test_checks/Inputs/nvptx-basic.ll.expected

  Log Message:
  -----------
  [NVPTX] Improve kernel byval parameter lowering (#136008)

This change introduces a new pattern for lowering kernel byval
parameters in `NVPTXLowerArgs`. Each byval argument is wrapped in a call
to a new intrinsic, `@llvm.nvvm.internal.addrspace.wrap`. This intrinsic
explicitly equates to no instructions and is removed during operation
legalization in SDAG. However, it allows us to change the addrspace of
the arguments to 101 to reflect the fact that they will occupy this
space when lowered by `LowerFormalArgs` in `NVPTXISelLowering`.
Optionally, if a generic pointer to a param is needed, a standard
`addrspacecast` is used. This approach offers several advantages:

- Exposes addrspace optimizations: By using a standard `addrspacecast`
back to generic space we allow InferAS to optimize this instruction,
potentially sinking it through control flow or in other ways unsupported
by `NVPTXLowerArgs`. This is demonstrated in several existing tests.

- Clearer, more consistent semantics: Previously an `addrspacecast` from
generic to param space was implicitly a no-op. This is problematic
because it's not reciprocal with the inverse cast, violating LLVM
semantics. Further it is very confusing given the existence of
`cvta.to.param`. After this change the cast equates to this instruction.

- Allow for the removal of all nvvm.ptr.* intrinsics: In a follow-up
change the nvvm.ptr.gen.to.param and nvvm.ptr.param.to.gen intrinsics
may be removed.



To unsubscribe from these emails, change your notification settings at https://github.com/llvm/llvm-project/settings/notifications