Hi All, I'm launching 4 kernels with 4 different command queues. For a single thread, it is consuming close to ~250,micro sec.

Application Acceleration With FPGAs

Programmable Acceleration Cards (PACs), DCP, FPGA AI Suite, Software Stack, and Reference Designs

Hi All, I'm launching 4 kernels with 4 different command queues. For a single thread, it is consuming close to ~250,micro sec.

1,488 Views

When I enable multithreading, clenqueueTask time increases to 1250 micro secs.

Before launching the kernel i'm printing the status of all the events. All are printing 0 means COMPLETED (it means nothing is pending in commandQueue). I'm not understanding why enqueueTask is consuming more time when I enable threading even if there is no pending commands in command queue.

NOTE: processing() function where ClEnqueueTask is present is always executed by single thread (multi-threading is disabled for this function).

Thanks in advance

Link Copied

0 Replies

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.