Release Notes

This section includes significant changes, new features, performance improvements, and various issues. Unless noted, listed issues should not impact functionality. When functionality is impacted, we offer a work-around to avoid the issue (if available).

0.2.0

The second early access (EA) release of cuBLASDx library brings tensor API, mixed precision, and performance improvements.

New Features

• All Device Extensions libraries are bundled together in a single package named nvidia-mathdx-24.08.0.tar.gz.

• Added new tensor-based execute(…) API:

  • Improved performance and user-friendly interface for matrices thanks to support for CuTe tensor (cute::Tensor).

  • Helper methods for slicing shared memory between matrices.

  • Easy tensor creation thanks to get_layout_*() methods and cublasdx::make_tensor.

  • Suggestions for the best layouts for matrices in shared memory to improve the performance of both matrix multiplication and global-shared memory I/O operations.

  • Updated Introduction and Achieving High Performance.

• cublasdx::copy for copying shared and global memory tensors.

• Added support for mixed precision in Precision, especially long requested:

  • TensorFloat-32: Precision<tfloat32_t, tfloat32_t, float>, and

  • Precision<__half, __half, float>.

• Support for 8-bit floating-point matrices (__nv_fp8_e4m3, and __nv_fp8_e5m2) and GEMM.

• Added Alignment operator to provide alignment information. It’s recommended to use 16-byte (128-bit) alignment for better performance.

• TransposeMode operator is deprecated and replaced with Arrangement operator.

• TransposeMode operator (or replacing it Arrangement) is not longer explicitly needed to define complete BLAS execution.

  • The default arrangement is row-major for A matrix, col-major - B , col-major - C.

  • The default transpose mode is now transposed for A matrix, and non-transposed for B.

Known Issues

• It’s recommended to use the latest CUDA Toolkit and NVCC compiler.

0.1.0

The first early access (EA) release of cuBLASDx library.

New Features

• Support for general matrix multiply.

  • Tensor cores support for fp16, fp64, complex fp64 calculations.

• Support for SM70 - SM90 CUDA architectures.

• Multiple examples included.

Known Issues

• Since CUDA Toolkit 12.2 NVCC compiler in certain situation reports incorrect compilation error when value_type type of GEMM description type is used. The problematic code with possible workarounds are presented below:

  // Any GEMM description type
  using GEMM = decltype(Size<32 /* M */, 32 /* N */, 32 /* K */>()
              + Precision<double>()
              + Type<type::real>()
              + TransposeMode<t_mode /* A */, t_mode /* B */>()
              + Function<function::MM>()
              + SM<700>()
              + Block());
  using type = typename GEMM::value_type; // compilation error
  
  // Workaround #1
  using type = typename decltype(GEMM())::value_type;
  
  // Workaround #2 (used in cuBLASDx examples)
  template <typename T>
  using value_type_t = typename T::value_type;
  
  using type = value_type_t<GEMM>;