Awesome Open Source
Awesome Open Source

NOTE: UME::Vector library has been moved to github! Please see: https://github.com/edanor/umevector

Build Status Donate

Current stable release is: v0.8.1
To checkout stable release use:

git clone https://[email protected]/edanor/umesimd.git
git checkout tags/v0.8.1

UME::SIMD is an explicit vectorization library. The library defines homogeneous interface for accessing functionality of SIMD registers of AVX, AVX2, AVX512 and IMCI (KNCNI, k1om) instruction set.

You can find the most recent documentation and tutorials here: UME::SIMD tutorials.
Also a link to older wiki(deprecated): wiki pages.

For quotations please refer to: A high-performance portable abstract interface for explicit SIMD vectorization

This piece of code was developed as part of ICE-DIP project at CERN:

"ICE-DIP is a European Industrial Doctorate project funded by the European Community's 7th Framework programme Marie Curie Actions under grant PITN-GA-2012-316596".

All questions should be submitted using the bug tracking system:

bug tracker

or by sending e-mail to:

[email protected]

RELEASE NOTES for v0.8.1

Interface:
-
Performance tuning:
-
Benchmarks:
- Add VS2015 solution for benchmarks.

Fixes:
- remove unnecessary include in explog.
- fix explog to use more portable reinterpret-cast

Tests:
-

Other:
- Update Readme

Donations

I am not getting paid for developing this software, so any type of help would be appreciated. If you like this project and you would like to support it, please feel free to make a volontary donation. This software will remain free regardless of any donations, but money can help keeping it up to date and bug-free.

paypal


Get A Weekly Email With Trending Projects For These Topics
No Spam. Unsubscribe easily at any time.
c-plus-plus (17,649
cpp (1,249
cpp11 (246
benchmark (229
cpp17 (201
cpp14 (141
code-generation (123
vector (110
simd (90
neon (38
avx2 (37
avx512 (29
avx (27
performance-tuning (24
vectorization (18

Find Open Source By Browsing 7,000 Topics Across 59 Categories