- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
I have to map the OpenCL application with a lot of flow control statements, it works well on GPU. However, it incurs deadlock on FPGA.
What is the difference? What should I do? What should I read? Merry Christmas.Link Copied
1 Reply
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Without seeing the code I'm not sure we'll be much help. Make sure you don't have any barriers or fences inside a conditional statement. The scheduling of work-items on an FPGA can vary with respect to a GPU so perhaps there is a hazard not being addressed in the kernel.

Reply
Topic Options
- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page