Forum topic

Same instruction on all 8 EU?

To get peak performance, all EU in single sub-slice should issue same instruction or in single EU only we need same instruction?


Thanks and regards,

Biren Doshi


Authored by Biren Doshi Last updated on 12/07/2016 - 23:46

Webinar: Getting Started with Intel® SDK for OpenCL* Applications

Authored by admin Last updated on 05/06/2016 - 16:41

Performance Interactions of OpenCL* Code and Intel® Quick Sync Video on Intel® HD Graphics 4000

Developers of video editing and other applications that generate or process video, and encode them using Intel® Quick Sync Video may find it challenging to gain performance advantages. This paper describes how to gain performance advantages using OpenCL*.
Authored by THOMAS C. (Intel) Last updated on 05/06/2016 - 16:41

Manycore processors: Opportunities and challenges

I have a lecture I give to college classes on parallel programming.

Authored by admin Last updated on 04/26/2016 - 23:58

OpenCL* Device Fission for CPU Performance

Download Article
Authored by TERENCE S. (Intel) Last updated on 05/12/2015 - 12:34

Auto vectorization of OpenCL* code with the Intel® SDK for OpenCL* Applications

The Intel® SDK for OpenCL* Applications features an implicit vectorization module which boosts application performance. The implicit vectorization module uses state-of-the-art vectorization algorithms based on up-to-date compiler research
Authored by Jerry Baugh (Intel) Last updated on 05/12/2015 - 12:32

Introduction to OpenCL™

Open Compute Language (OpenCL™) provides a framework to write programs in C-like language that can run on heterogeneous cores such as CPUs, GPUs or specialized hardware.
Authored by Vinay Awasthi (Intel) Last updated on 09/18/2015 - 14:36
For more complete information about compiler optimizations, see our Optimization Notice.