[all-commits] [llvm/llvm-project] b15fdf: [flang][cuda] Exclude non-variable actuals from un...

[Zhen Wang via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: b15fdf4834cfe79f8a5ac04fabd003f876626187
      https://github.com/llvm/llvm-project/commit/b15fdf4834cfe79f8a5ac04fabd003f876626187
  Author: Zhen Wang <zhenw at nvidia.com>
  Date:   2026-06-26 (Fri, 26 Jun 2026)

  Changed paths:
    M flang/include/flang/Support/Fortran.h
    M flang/lib/Semantics/check-call.cpp
    M flang/lib/Semantics/expression.cpp
    M flang/lib/Support/Fortran.cpp
    A flang/test/Semantics/CUDA/cuf-generic-nonvar-unified.cuf

  Log Message:
  -----------
  [flang][cuda] Exclude non-variable actuals from unified-memory CUDA data attribute relaxation (#206121)

Under -gpu=mem:unified, the CUDA data attribute compatibility check
(AreCompatibleCUDADataAttrs) allows an unattributed actual argument to
bind to a Device/Managed/Unified dummy. This relaxation is correct for
variables whose storage is accessible from device code under unified
memory, but not for non-variable expression results (e.g. intrinsic call
results like RESHAPE(...)), which are host temporaries.

Without this fix, a generic SUM call like sum(reshape(hostArray, ...),
dim=2) could resolve to a device-specific overload instead of the
intrinsic, because the RESHAPE result was incorrectly considered
compatible with a DEVICE-attributed dummy.

This patch:

- Adds an actualIsVariable parameter to AreCompatibleCUDADataAttrs
(defaulting to true for backward compatibility) and gates the
unified-memory relaxation for Device/Managed/Unified dummies on it.
- Passes actualIsVariable from CheckExplicitDataArg in check-call.
- Stops setting actualCanUseImplicitCudaMemoryMode for non-variable
expressions in GetMatchingDistance, so the CUDA matching distance
ranking is also correct.



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