Forum Discussion

Altera_Forum's avatar
Altera_Forum
Icon for Honored Contributor rankHonored Contributor
8 years ago

NDRnage Kernels Global Memory Write Pattern

I came up with some basic questions, which I would like to discuss: 1) I still don't understand how SIMD is being implemented in FPGA. In GPU, workitems being assigned to SIMDs are being execut...
Altera_Forum's avatar
Altera_Forum
Icon for Honored Contributor rankHonored Contributor
8 years ago

You should post your kernel code; what you are observing is very likely because you have something in your code that is preventing vectorization (e.g. work-item ID-dependent branching) and hence, SIMD is not being applied at all. If this is indeed the case, you will see a message form the compiler about this in the log.