hash count 0 (problem or NOT?) & DAG file speed up

[RezaAhmadi0117]

Hi Ed, I've 2 question. when I try to run search kernel on u50, I get hash count 0 in each step on searching process. it that ok ? look like below:

Search: target 0x15798ee230
Search: start nonce            0, hash count 0
Search: Hash rate  0.03 Mh 
Search: start nonce      8388608, hash count 0
Search: Hash rate  0.07 Mh 
Search: start nonce     16777216, hash count 0
Search: Hash rate  0.07 Mh 
Search: start nonce     25165824, hash count 0
Search: Hash rate  0.07 Mh 
Search: start nonce     33554432, hash count 0
Search: Hash rate  0.07 Mh 
Search: start nonce     41943040, hash count 0
Search: Hash rate  0.07 Mh 
Search: start nonce     50331648, hash count 0

and I made a few change in your code and pass DAG generation to CPU, now it going soo faster that u50 to generate DAG. now how can I send DAG in m_context to another context?

i put my issue and files in this link

[Ed-Yang]

For Xilinx, I cannot find "atomic_inc" equivalent function, so the hashCount is not increased.

https://github.com/Ed-Yang/xilinx-ethash/blob/08fc61113f295bfaa294f7396bc67f0ba62a70e2/xleth/kernel/ethash.cl#L404

[Ed-Yang]

For transferring the DAG, it looks like programming on host memory and pass the DAG memory to HBM on U50. It is suggested to check the OpenCL API, it seems could be achieved by passing different parameters.