Intel® Quartus® Prime Software
Intel® Quartus® Prime Design Software, Design Entry, Synthesis, Simulation, Verification, Timing Analysis, System Design (Platform Designer, formerly Qsys)
17254 Discussions

large number of small work-groups vs small number of large work-groups

Altera_Forum
Honored Contributor II
‎03-24-2018 01:36 PM
1,090 Views

Hello, 

I appreciate it if anyone can answer my question.  

I have a ND-range configuration, with 1 CU, and without SIMD (I mean a single PE in the single CU). Work-items access only to global memory (no local memory access).  

After some tests, I reach to this conclusion that for every CU, it is enough to have large number of work-items to have good performance, specifically, no matter that those work-items are organized in small number of large work-groups, or large number of small work-groups. In other words, there is only one pipeline in work-items level, and there is NO additional pipeline in work-group level. 

Is it right?
0 Kudos

Link Copied

1 Reply
Altera_Forum
Honored Contributor II
‎03-24-2018 08:02 PM
385 Views

Yes, every CU only has one pipeline, and every work-item, regardless of which work-group it belongs to, goes through that pipeline. With one CU, if you are not using SIMD or local memory, the size of your work-group will not affect performance.

0 Kudos
Copy link
Reply

Community support is provided Monday to Friday. Other contact methods are available here.

Intel does not verify all solutions, including but not limited to any file transfers that may appear in this community. Accordingly, Intel disclaims all express and implied warranties, including without limitation, the implied warranties of merchantability, fitness for a particular purpose, and non-infringement, as well as any warranty arising from course of performance, course of dealing, or usage in trade.

For more complete information about compiler optimizations, see our Optimization Notice.