Christopher Bate 708185f03f [mlir][NVGPU] Add support for structured sparsity MMA variants ...

This change adds a new NVGPU operation that targets the PTX `mma.sp.sync`
instruction variants. A lowering to NVVM is provided using inline
assembly.

Reviewed By: ThomasRaoux, manishucsd

Differential Revision: https://reviews.llvm.org/D137202

2022-11-07 09:43:03 -07:00

..

CMakeLists.txt

[mlir] (NFC) Clean up bazel and CMake target names

2022-06-13 16:24:15 +00:00

NVGPUDialect.cpp

[mlir][NVGPU] Add support for structured sparsity MMA variants

2022-11-07 09:43:03 -07:00