OpenCL* for CPU
Ask questions and share information on Intel® SDK for OpenCL™ Applications and OpenCL™ implementations for Intel® CPU.
Announcements
This forum covers OpenCL* for CPU only. OpenCL* for GPU questions can be asked in the GPU Compute Software forum. Intel® FPGA SDK for OpenCL™ questions can be ask in the FPGA Intel® High Level Design forum.
1686 Discussions

Too imprecise native_sin/native_cos implementation.

Raistmer
Beginner
‎11-02-2013 02:46 AM
197 Views

Running my OpenCL app on Intel GPUs I encountered precision issue. Results were too imprecise and often failed to pass validation vs CPU-based (or AMD/nVidia GPU based) ones.

Considerable improvement was only when I refused from native_cos/native_sin in oclFFT  (Apple's FFT release for OpenCL) and in other parts of app code.

I have no such issues with same OpenCL code on GPUs from other vendors (both AMD and nVidia).

Please consider some improvements for native trigonometric function presion in future SDK/hardware releases. Too low precision makes them just un-useful no matter how speedy they are. Make precision at least in line with other vendors.

0 Kudos

Link Copied

1 Reply
Raghupathi_M_Intel
Employee
‎11-04-2013 04:46 PM
197 Views

Native functions should be faster but not necessarily precise. I am not sure how much difference is acceptable. Are you seeing precision issues with native_sin and native_cos only? Thanks for the feedback.

Raghu

0 Kudos
Copy link
Reply

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