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.
46 lines
717 B
JavaScript
46 lines
717 B
JavaScript
var indexSectionsWithContent =
|
|
{
|
|
0: "_abcdefghiklmnopqrstuvwxy~",
|
|
1: "abcdefghiklmnoprstuvwx",
|
|
2: "c",
|
|
3: "abcdefghiklmnoprstvw",
|
|
4: "_abcdefghiklmnopqrstuvw~",
|
|
5: "abcdefghiklmnoprstuvw",
|
|
6: "abcdefghiklmnoprstuvwy",
|
|
7: "cfgklmnos",
|
|
8: "gikrsuv",
|
|
9: "_cns",
|
|
10: "p"
|
|
};
|
|
|
|
var indexSectionNames =
|
|
{
|
|
0: "all",
|
|
1: "classes",
|
|
2: "namespaces",
|
|
3: "files",
|
|
4: "functions",
|
|
5: "variables",
|
|
6: "typedefs",
|
|
7: "enums",
|
|
8: "enumvalues",
|
|
9: "defines",
|
|
10: "groups"
|
|
};
|
|
|
|
var indexSectionLabels =
|
|
{
|
|
0: "All",
|
|
1: "Classes",
|
|
2: "Namespaces",
|
|
3: "Files",
|
|
4: "Functions",
|
|
5: "Variables",
|
|
6: "Typedefs",
|
|
7: "Enumerations",
|
|
8: "Enumerator",
|
|
9: "Macros",
|
|
10: "Modules"
|
|
};
|
|
|