NVIDIA/cutlass
1
0
Fork 0
mirror of https://github.com/NVIDIA/cutlass.git synced 2026-05-11 08:50:09 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Duane Merrill
2017-12-05 20:55:54 -05:00
committed by GitHub
parent 9dcb2b4c7d
commit 73211bbb88
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
README.md
View File

@@ -8,9 +8,9 @@ It incorporates the same strategies for data movement and hierarchical decomposi
that are used to implement cuBLAS. CUTLASS decomposes these “moving parts” into that are used to implement cuBLAS. CUTLASS decomposes these “moving parts” into
reusable, modular software components abstracted by C++ template classes. These reusable, modular software components abstracted by C++ template classes. These
thread-wide, warp-wide, block-wide, and device-wide primitives can be specialized 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. and tuned via custom tiling sizes, data types, and other algorithmic policy. The
The resulting flexibility simplifies their use as building blocks within custom resulting flexibility simplifies their use as building blocks within custom kernels
kernels and applications. and applications.
To support a wide variety of applications, CUTLASS provides extensive support for To support a wide variety of applications, CUTLASS provides extensive support for
mixed-precision computations, providing specialized data-movement and mixed-precision computations, providing specialized data-movement and