Jack Pien has taken AMD’s new OpenCL driver for x86 CPU’s and put it through it’s paces with an Intel processor, using a modified version of the standard SimpleConvolution kernel.
I used the SDK’s SimpleConvolution sample as a testbench to get some performance measurements compared to the very straight forward reference CPU implementation also included the SDK (compiled w/ just the -O3 gcc flag in release mode). The regular CPU implementation is also used to validate the OpenCL results.
The results show a nice boost to performance at the higher parallelization levels, but not as nice as you would expect. He’s got a nice writeup, and he’s looking for comments on where to go next. Head on over and help him out.
via Jack Pien» Blog Archive » A look at AMD’s x86 OpenCL perf on an Intel system.
