fb335f6a5f
CUTLASS 2.0 Substantially refactored for - Better performance, particularly for native Turing Tensor Cores - Robust and durable templates spanning the design space - Encapsulated functionality embodying modern C++11 programming techniques - Optimized containers and data types for efficient, generic, portable device code Updates to: - Quick start guide - Documentation - Utilities - CUTLASS Profiler Native Turing Tensor Cores - Efficient GEMM kernels targeting Turing Tensor Cores - Mixed-precision floating point, 8-bit integer, 4-bit integer, and binarized operands Coverage of existing CUTLASS functionality: - GEMM kernels targeting CUDA and Tensor Cores in NVIDIA GPUs - Volta Tensor Cores through native mma.sync and through WMMA API - Optimizations such as parallel reductions, threadblock rasterization, and intra-threadblock reductions - Batched GEMM operations - Complex-valued GEMMs Note: this commit and all that follow require a host compiler supporting C++11 or greater.
39 lines
975 B
C
39 lines
975 B
C
#include <cstdint>
|
|
#include <string>
|
|
|
|
#define CUTLASS_MAJOR @CUTLASS_VERSION_MAJOR@
|
|
#define CUTLASS_MINOR @CUTLASS_VERSION_MINOR@
|
|
#define CUTLASS_PATCH @CUTLASS_VERSION_PATCH@
|
|
#define CUTLASS_BUILD @CUTLASS_VERSION_BUILD@
|
|
#define CUTLASS_VERSION ((CUTLASS_MAJOR)*100 + (CUTLASS_MINOR)*10 + CUTLASS_PATCH)
|
|
|
|
namespace cutlass {
|
|
|
|
inline uint32_t getVersion() {
|
|
return CUTLASS_VERSION;
|
|
}
|
|
inline uint32_t getVersionMajor() {
|
|
return CUTLASS_MAJOR;
|
|
}
|
|
inline uint32_t getVersionMinor() {
|
|
return CUTLASS_MINOR;
|
|
}
|
|
inline uint32_t getVersionPatch() {
|
|
return CUTLASS_PATCH;
|
|
}
|
|
inline uint32_t getVersionBuild() {
|
|
return CUTLASS_BUILD + 0;
|
|
}
|
|
inline std::string getVersionString() {
|
|
std::string version = "@CUTLASS_VERSION@";
|
|
if (getVersionBuild()) {
|
|
version += "." + std::to_string(getVersionBuild());
|
|
}
|
|
return version;
|
|
}
|
|
inline std::string getGitRevision() {
|
|
return "@CUTLASS_REVISION@";
|
|
}
|
|
|
|
} // namespace cutlass
|