Bitslice status and broken nvcc
#7
The claimed 967 MH/s (on a 980Ti +250MHz) was using CUDA. Did you try that code with your tool chain? BTW the version that doesn't need a kernel per salt is not that much slower: 826 MH/s under same conditions.

With that speed you'd get 24 GH/s for LM, that would be some record...


Messages In This Thread
Bitslice status and broken nvcc - by atom - 10-24-2015, 11:04 PM
RE: Bitslice status and broken nvcc - by royce - 10-25-2015, 07:40 AM
RE: Bitslice status and broken nvcc - by atom - 10-25-2015, 09:07 PM
RE: Bitslice status and broken nvcc - by Rolf - 10-26-2015, 10:12 AM
RE: Bitslice status and broken nvcc - by atom - 10-26-2015, 01:00 PM
RE: Bitslice status and broken nvcc - by Rolf - 10-26-2015, 10:21 PM
RE: Bitslice status and broken nvcc - by magnum - 10-30-2015, 03:24 AM
RE: Bitslice status and broken nvcc - by atom - 10-30-2015, 05:42 PM
RE: Bitslice status and broken nvcc - by magnum - 10-31-2015, 02:13 AM
RE: Bitslice status and broken nvcc - by atom - 11-02-2015, 03:25 PM
RE: Bitslice status and broken nvcc - by magnum - 10-31-2015, 02:21 AM
RE: Bitslice status and broken nvcc - by Xanadrel - 10-31-2015, 11:42 AM
RE: Bitslice status and broken nvcc - by magnum - 11-01-2015, 02:03 PM
RE: Bitslice status and broken nvcc - by Rolf - 11-04-2015, 10:19 AM
RE: Bitslice status and broken nvcc - by atom - 11-04-2015, 10:50 AM
RE: Bitslice status and broken nvcc - by Rolf - 11-04-2015, 05:15 PM
RE: Bitslice status and broken nvcc - by atom - 11-10-2015, 09:23 AM