2022-09-22 03:42:42 +08:00
|
|
|
cff-version: 1.2.0
|
|
|
|
|
title: CUTLASS
|
|
|
|
|
message: >-
|
|
|
|
|
If you use this software, please cite using the
|
|
|
|
|
following metadata.
|
|
|
|
|
type: software
|
|
|
|
|
authors:
|
|
|
|
|
- given-names: Andrew
|
|
|
|
|
email: akerr@nvidia.com
|
|
|
|
|
family-names: Kerr
|
|
|
|
|
affiliation: NVIDIA
|
|
|
|
|
- given-names: Haicheng
|
|
|
|
|
family-names: Wu
|
|
|
|
|
affiliation: NVIDIA
|
|
|
|
|
email: haichengw@nvidia.com
|
|
|
|
|
- given-names: Manish
|
|
|
|
|
family-names: Gupta
|
|
|
|
|
affiliation: Google
|
|
|
|
|
email: manigupta@google.com
|
|
|
|
|
- given-names: Dustyn
|
|
|
|
|
family-names: Blasig
|
|
|
|
|
email: dblasig@nvidia.com
|
|
|
|
|
affiliation: NVIDIA
|
|
|
|
|
- given-names: Pradeep
|
|
|
|
|
family-names: Ramini
|
|
|
|
|
email: prramani@nvidia.com
|
|
|
|
|
affiliation: NVIDIA
|
|
|
|
|
- given-names: Duane
|
|
|
|
|
family-names: Merrill
|
|
|
|
|
email: dumerrill@nvidia.com
|
|
|
|
|
affiliation: NVIDIA
|
|
|
|
|
- given-names: Aniket
|
|
|
|
|
family-names: Shivam
|
|
|
|
|
email: ashivam@nvidia.com
|
|
|
|
|
affiliation: NVIDIA
|
|
|
|
|
- given-names: Piotr
|
|
|
|
|
family-names: Majcher
|
|
|
|
|
email: pmajcher@nvidia.com
|
|
|
|
|
affiliation: NVIDIA
|
|
|
|
|
- given-names: Paul
|
|
|
|
|
family-names: Springer
|
|
|
|
|
email: pspringer@nvidia.com
|
|
|
|
|
affiliation: NVIDIA
|
|
|
|
|
- given-names: Markus
|
|
|
|
|
family-names: Hohnerbach
|
|
|
|
|
affiliation: NVIDIA
|
|
|
|
|
email: mhohnerbach@nvidia.com
|
|
|
|
|
- given-names: Jin
|
|
|
|
|
family-names: Wang
|
|
|
|
|
email: jinw@nvidia.com
|
|
|
|
|
affiliation: NVIDIA
|
|
|
|
|
- given-names: Matt
|
|
|
|
|
family-names: Nicely
|
|
|
|
|
email: mnicely@nvidia.com
|
|
|
|
|
affiliation: NVIDIA
|
|
|
|
|
repository-code: 'https://github.com/NVIDIA/cutlass'
|
|
|
|
|
abstract: >-
|
|
|
|
|
CUTLASS is a collection of CUDA C++ template
|
|
|
|
|
abstractions for implementing high-performance
|
|
|
|
|
matrix-multiplication (GEMM) and related
|
|
|
|
|
computations at all levels and scales within CUDA.
|
|
|
|
|
It incorporates strategies for hierarchical
|
|
|
|
|
decomposition and data movement similar to those
|
|
|
|
|
used to implement cuBLAS and cuDNN. CUTLASS
|
|
|
|
|
decomposes these "moving parts" into reusable,
|
|
|
|
|
modular software components abstracted by C++
|
|
|
|
|
template classes. These thread-wide, warp-wide,
|
|
|
|
|
block-wide, and device-wide primitives can be
|
|
|
|
|
specialized and tuned via custom tiling sizes, data
|
|
|
|
|
types, and other algorithmic policy. The resulting
|
|
|
|
|
flexibility simplifies their use as building blocks
|
|
|
|
|
within custom kernels and applications.
|
|
|
|
|
keywords:
|
|
|
|
|
- 'cutlass, tensor cores, cuda'
|
|
|
|
|
license: BSD-3-Clause
|
2022-11-19 22:02:15 +08:00
|
|
|
license-url: https://github.com/NVIDIA/cutlass/blob/v2.11.0/LICENSE.txt
|
|
|
|
|
version: '2.11.0'
|
|
|
|
|
date-released: '2022-11-19'
|
2022-09-22 03:42:42 +08:00
|
|
|
identifiers:
|
|
|
|
|
- type: url
|
2022-11-19 22:02:15 +08:00
|
|
|
value: "https://github.com/NVIDIA/cutlass/tree/v2.11.0"
|
|
|
|
|
description: The GitHub release URL of tag 2.11.0
|
