Genoil - I KNOW this is a nitpick - but I noticed as I was going through and rewriting a lot of the Ethash OpenCL... this one just bugs the shit outta me:
Were it performance critical, that would be ouch. As is, on AMD, it just is a little eww, when you could:
Code:
bool update_share = thread_id == ((a >> 2) & (THREADS_PER_HASH - 1));
Were it performance critical, that would be ouch. As is, on AMD, it just is a little eww, when you could:
Code:
bool update_share = thread_id == amd_bfe(a, 2U, 3U)
Thanks I'll have a look at it. Up until now it's been highly demotivating to try and optimize the OpenCL kernel, because nothing really made a difference. CUDA has been much more willing to give me a few % improvement over the baseline.
That in particular doesn't, but it's nicer. Anyways, the AMD OCL compiler really, REALLY hates this. For the first time, instead of using the AMD OCL compiler, and then modifying the output, I'm considering straight up just rewriting the whole thing and bypassing the OCL compiler entirely.
maybe with a custom build of sgminer?
(did read claymore's thread... 
) would be really nice !