Iβve just tested the current version with a 1070 GTX:
eqcuda (8192 threads): ~15,9 Sol/s
eqcuda (4096 threads): ~16,5 Sol/s
feqcuda (8192 threads): ~22,1 Sol/s
feqcuda (4096 threads): ~21,6 Sol/s
devcuda (8192 threads): ~15,9 Sol/s
devcuda (4096 threads): ~16,3 Sol/s
more threads were slower for all three variants
(i donβt have the output available right now, but a 960 GTX produced ~11.3 Sol/s with feqcuda and 4096 threads)
CUDA 8.0.44-1
Nvidia Driver: 370.28
[details=eqcuda]alex@btf:~/Git/tromp-equihash$ ./eqcuda
Looking for wagner-tree on (ββ,0) with 10 20-bits digits and 8192 threads (128 per block)
Digit 0
Digit 1
Digit 2
Digit 3
Digit 4
Digit 5
Digit 6
Digit 7
Digit 8
Digit 9
9 rounds completed in 0.115 seconds.
3 solutions
3 total solutions
alex@btf:~/Git/tromp-equihash$ ./eqcuda
Looking for wagner-tree on (ββ,0) with 10 20-bits digits and 8192 threads (128 per block)
Digit 0
Digit 1
Digit 2
Digit 3
Digit 4
Digit 5
Digit 6
Digit 7
Digit 8
Digit 9
9 rounds completed in 0.117 seconds.
3 solutions
3 total solutions
alex@btf:~/Git/tromp-equihash$ ./eqcuda
Looking for wagner-tree on (ββ,0) with 10 20-bits digits and 8192 threads (128 per block)
Digit 0
Digit 1
Digit 2
Digit 3
Digit 4
Digit 5
Digit 6
Digit 7
Digit 8
Digit 9
9 rounds completed in 0.119 seconds.
3 solutions
3 total solutions
alex@btf:~/Git/tromp-equihash$ ./eqcuda
Looking for wagner-tree on (ββ,0) with 10 20-bits digits and 8192 threads (128 per block)
Digit 0
Digit 1
Digit 2
Digit 3
Digit 4
Digit 5
Digit 6
Digit 7
Digit 8
Digit 9
9 rounds completed in 0.118 seconds.
3 solutions
3 total solutions
alex@btf:~/Git/tromp-equihash$ ./eqcuda
Looking for wagner-tree on (ββ,0) with 10 20-bits digits and 8192 threads (128 per block)
Digit 0
Digit 1
Digit 2
Digit 3
Digit 4
Digit 5
Digit 6
Digit 7
Digit 8
Digit 9
9 rounds completed in 0.118 seconds.
3 solutions
3 total solutions
alex@btf:~/Git/tromp-equihash$ ./eqcuda
Looking for wagner-tree on (ββ,0) with 10 20-bits digits and 8192 threads (128 per block)
Digit 0
Digit 1
Digit 2
Digit 3
Digit 4
Digit 5
Digit 6
Digit 7
Digit 8
Digit 9
9 rounds completed in 0.121 seconds.
3 solutions
3 total solutions
alex@btf:~/Git/tromp-equihash$ ./eqcuda
Looking for wagner-tree on (ββ,0) with 10 20-bits digits and 8192 threads (128 per block)
Digit 0
Digit 1
Digit 2
Digit 3
Digit 4
Digit 5
Digit 6
Digit 7
Digit 8
Digit 9
9 rounds completed in 0.118 seconds.
3 solutions
3 total solutions[/details]
[details=eqcuda -t 4096]alex@btf:~/Git/tromp-equihash$ ./eqcuda -t 4096
Looking for wagner-tree on (ββ,0) with 10 20-bits digits and 4096 threads (64 per block)
Digit 0
Digit 1
Digit 2
Digit 3
Digit 4
Digit 5
Digit 6
Digit 7
Digit 8
Digit 9
9 rounds completed in 0.114 seconds.
3 solutions
3 total solutions
alex@btf:~/Git/tromp-equihash$ ./eqcuda -t 4096
Looking for wagner-tree on (ββ,0) with 10 20-bits digits and 4096 threads (64 per block)
Digit 0
Digit 1
Digit 2
Digit 3
Digit 4
Digit 5
Digit 6
Digit 7
Digit 8
Digit 9
9 rounds completed in 0.114 seconds.
3 solutions
3 total solutions
alex@btf:~/Git/tromp-equihash$ ./eqcuda -t 4096
Looking for wagner-tree on (ββ,0) with 10 20-bits digits and 4096 threads (64 per block)
Digit 0
Digit 1
Digit 2
Digit 3
Digit 4
Digit 5
Digit 6
Digit 7
Digit 8
Digit 9
9 rounds completed in 0.114 seconds.
3 solutions
3 total solutions
alex@btf:~/Git/tromp-equihash$ ./eqcuda -t 4096
Looking for wagner-tree on (ββ,0) with 10 20-bits digits and 4096 threads (64 per block)
Digit 0
Digit 1
Digit 2
Digit 3
Digit 4
Digit 5
Digit 6
Digit 7
Digit 8
Digit 9
9 rounds completed in 0.114 seconds.
3 solutions
3 total solutions
alex@btf:~/Git/tromp-equihash$ ./eqcuda -t 4096
Looking for wagner-tree on (ββ,0) with 10 20-bits digits and 4096 threads (64 per block)
Digit 0
Digit 1
Digit 2
Digit 3
Digit 4
Digit 5
Digit 6
Digit 7
Digit 8
Digit 9
9 rounds completed in 0.114 seconds.
3 solutions
3 total solutions
alex@btf:~/Git/tromp-equihash$ ./eqcuda -t 4096
Looking for wagner-tree on (ββ,0) with 10 20-bits digits and 4096 threads (64 per block)
Digit 0
Digit 1
Digit 2
Digit 3
Digit 4
Digit 5
Digit 6
Digit 7
Digit 8
Digit 9
9 rounds completed in 0.114 seconds.
3 solutions
3 total solutions[/details]
[details=feqcuda]alex@btf:~/Git/tromp-equihash$ ./feqcuda
Looking for wagner-tree on (ββ,0) with 10 20-bits digits and 8192 threads (128 per block)
Digit 0
Digit 1
Digit 2
Digit 3
Digit 4
Digit 5
Digit 6
Digit 7
Digit 8
Digit 9
9 rounds completed in 0.086 seconds.
3 solutions
3 total solutions
alex@btf:~/Git/tromp-equihash$ ./feqcuda
Looking for wagner-tree on (ββ,0) with 10 20-bits digits and 8192 threads (128 per block)
Digit 0
Digit 1
Digit 2
Digit 3
Digit 4
Digit 5
Digit 6
Digit 7
Digit 8
Digit 9
9 rounds completed in 0.085 seconds.
3 solutions
3 total solutions
alex@btf:~/Git/tromp-equihash$ ./feqcuda
Looking for wagner-tree on (ββ,0) with 10 20-bits digits and 8192 threads (128 per block)
Digit 0
Digit 1
Digit 2
Digit 3
Digit 4
Digit 5
Digit 6
Digit 7
Digit 8
Digit 9
9 rounds completed in 0.085 seconds.
3 solutions
3 total solutions
alex@btf:~/Git/tromp-equihash$ ./feqcuda
Looking for wagner-tree on (ββ,0) with 10 20-bits digits and 8192 threads (128 per block)
Digit 0
Digit 1
Digit 2
Digit 3
Digit 4
Digit 5
Digit 6
Digit 7
Digit 8
Digit 9
9 rounds completed in 0.085 seconds.
3 solutions
3 total solutions
alex@btf:~/Git/tromp-equihash$ ./feqcuda
Looking for wagner-tree on (ββ,0) with 10 20-bits digits and 8192 threads (128 per block)
Digit 0
Digit 1
Digit 2
Digit 3
Digit 4
Digit 5
Digit 6
Digit 7
Digit 8
Digit 9
9 rounds completed in 0.085 seconds.
3 solutions
3 total solutions
alex@btf:~/Git/tromp-equihash$ ./feqcuda
Looking for wagner-tree on (ββ,0) with 10 20-bits digits and 8192 threads (128 per block)
Digit 0
Digit 1
Digit 2
Digit 3
Digit 4
Digit 5
Digit 6
Digit 7
Digit 8
Digit 9
9 rounds completed in 0.085 seconds.
3 solutions
3 total solutions[/details]
[details=feqcuda -t 4096]alex@btf:~/Git/tromp-equihash$ ./feqcuda -t 4096
Looking for wagner-tree on (ββ,0) with 10 20-bits digits and 4096 threads (64 per block)
Digit 0
Digit 1
Digit 2
Digit 3
Digit 4
Digit 5
Digit 6
Digit 7
Digit 8
Digit 9
9 rounds completed in 0.087 seconds.
3 solutions
3 total solutions
alex@btf:~/Git/tromp-equihash$ ./feqcuda -t 4096
Looking for wagner-tree on (ββ,0) with 10 20-bits digits and 4096 threads (64 per block)
Digit 0
Digit 1
Digit 2
Digit 3
Digit 4
Digit 5
Digit 6
Digit 7
Digit 8
Digit 9
9 rounds completed in 0.087 seconds.
3 solutions
3 total solutions
alex@btf:~/Git/tromp-equihash$ ./feqcuda -t 4096
Looking for wagner-tree on (ββ,0) with 10 20-bits digits and 4096 threads (64 per block)
Digit 0
Digit 1
Digit 2
Digit 3
Digit 4
Digit 5
Digit 6
Digit 7
Digit 8
Digit 9
9 rounds completed in 0.087 seconds.
3 solutions
3 total solutions
alex@btf:~/Git/tromp-equihash$ ./feqcuda -t 4096
Looking for wagner-tree on (ββ,0) with 10 20-bits digits and 4096 threads (64 per block)
Digit 0
Digit 1
Digit 2
Digit 3
Digit 4
Digit 5
Digit 6
Digit 7
Digit 8
Digit 9
9 rounds completed in 0.087 seconds.
3 solutions
3 total solutions[/details]
[details=devcuda]alex@btf:~/Git/tromp-equihash$ ./devcuda
Looking for wagner-tree on (ββ,0) with 10 20-bits digits and 8192 threads (128 per block)
Digit 0
Digit 1
Digit 2
Digit 3
Digit 4
Digit 5
Digit 6
Digit 7
Digit 8
Digit 9
9 rounds completed in 0.119 seconds.
3 solutions
3 total solutions
alex@btf:~/Git/tromp-equihash$ ./devcuda
Looking for wagner-tree on (ββ,0) with 10 20-bits digits and 8192 threads (128 per block)
Digit 0
Digit 1
Digit 2
Digit 3
Digit 4
Digit 5
Digit 6
Digit 7
Digit 8
Digit 9
9 rounds completed in 0.117 seconds.
3 solutions
3 total solutions
alex@btf:~/Git/tromp-equihash$ ./devcuda
Looking for wagner-tree on (ββ,0) with 10 20-bits digits and 8192 threads (128 per block)
Digit 0
Digit 1
Digit 2
Digit 3
Digit 4
Digit 5
Digit 6
Digit 7
Digit 8
Digit 9
9 rounds completed in 0.119 seconds.
3 solutions
3 total solutions
alex@btf:~/Git/tromp-equihash$ ./devcuda
Looking for wagner-tree on (ββ,0) with 10 20-bits digits and 8192 threads (128 per block)
Digit 0
Digit 1
Digit 2
Digit 3
Digit 4
Digit 5
Digit 6
Digit 7
Digit 8
Digit 9
9 rounds completed in 0.118 seconds.
3 solutions
3 total solutions
alex@btf:~/Git/tromp-equihash$ ./devcuda
Looking for wagner-tree on (ββ,0) with 10 20-bits digits and 8192 threads (128 per block)
Digit 0
Digit 1
Digit 2
Digit 3
Digit 4
Digit 5
Digit 6
Digit 7
Digit 8
Digit 9
9 rounds completed in 0.118 seconds.
3 solutions
3 total solutions
alex@btf:~/Git/tromp-equihash$ ./devcuda
Looking for wagner-tree on (ββ,0) with 10 20-bits digits and 8192 threads (128 per block)
Digit 0
Digit 1
Digit 2
Digit 3
Digit 4
Digit 5
Digit 6
Digit 7
Digit 8
Digit 9
9 rounds completed in 0.118 seconds.
3 solutions
3 total solutions
alex@btf:~/Git/tromp-equihash$ ./devcuda
Looking for wagner-tree on (ββ,0) with 10 20-bits digits and 8192 threads (128 per block)
Digit 0
Digit 1
Digit 2
Digit 3
Digit 4
Digit 5
Digit 6
Digit 7
Digit 8
Digit 9
9 rounds completed in 0.117 seconds.
3 solutions
3 total solutions
alex@btf:~/Git/tromp-equihash$ ./devcuda
Looking for wagner-tree on (ββ,0) with 10 20-bits digits and 8192 threads (128 per block)
Digit 0
Digit 1
Digit 2
Digit 3
Digit 4
Digit 5
Digit 6
Digit 7
Digit 8
Digit 9
9 rounds completed in 0.118 seconds.
3 solutions
3 total solutions[/details]
[details=devcuda -t 4096]alex@btf:~/Git/tromp-equihash$ ./devcuda -t 4096
Looking for wagner-tree on (ββ,0) with 10 20-bits digits and 4096 threads (64 per block)
Digit 0
Digit 1
Digit 2
Digit 3
Digit 4
Digit 5
Digit 6
Digit 7
Digit 8
Digit 9
9 rounds completed in 0.087 seconds.
0 solutions
0 total solutions
alex@btf:~/Git/tromp-equihash$ ./devcuda -t 4096
Looking for wagner-tree on (ββ,0) with 10 20-bits digits and 4096 threads (64 per block)
Digit 0
Digit 1
Digit 2
Digit 3
Digit 4
Digit 5
Digit 6
Digit 7
Digit 8
Digit 9
9 rounds completed in 0.123 seconds.
3 solutions
3 total solutions
alex@btf:~/Git/tromp-equihash$ ./devcuda -t 4096
Looking for wagner-tree on (ββ,0) with 10 20-bits digits and 4096 threads (64 per block)
Digit 0
Digit 1
Digit 2
Digit 3
Digit 4
Digit 5
Digit 6
Digit 7
Digit 8
Digit 9
9 rounds completed in 0.117 seconds.
3 solutions
3 total solutions
alex@btf:~/Git/tromp-equihash$ ./devcuda -t 4096
Looking for wagner-tree on (ββ,0) with 10 20-bits digits and 4096 threads (64 per block)
Digit 0
Digit 1
Digit 2
Digit 3
Digit 4
Digit 5
Digit 6
Digit 7
Digit 8
Digit 9
9 rounds completed in 0.116 seconds.
3 solutions
3 total solutions
alex@btf:~/Git/tromp-equihash$ ./devcuda -t 4096
Looking for wagner-tree on (ββ,0) with 10 20-bits digits and 4096 threads (64 per block)
Digit 0
Digit 1
Digit 2
Digit 3
Digit 4
Digit 5
Digit 6
Digit 7
Digit 8
Digit 9
9 rounds completed in 0.115 seconds.
3 solutions
3 total solutions
alex@btf:~/Git/tromp-equihash$ ./devcuda -t 4096
Looking for wagner-tree on (ββ,0) with 10 20-bits digits and 4096 threads (64 per block)
Digit 0
Digit 1
Digit 2
Digit 3
Digit 4
Digit 5
Digit 6
Digit 7
Digit 8
Digit 9
9 rounds completed in 0.116 seconds.
3 solutions
3 total solutions
alex@btf:~/Git/tromp-equihash$ ./devcuda -t 4096
Looking for wagner-tree on (ββ,0) with 10 20-bits digits and 4096 threads (64 per block)
Digit 0
Digit 1
Digit 2
Digit 3
Digit 4
Digit 5
Digit 6
Digit 7
Digit 8
Digit 9
9 rounds completed in 0.116 seconds.
3 solutions
3 total solutions
alex@btf:~/Git/tromp-equihash$ ./devcuda -t 4096
Looking for wagner-tree on (ββ,0) with 10 20-bits digits and 4096 threads (64 per block)
Digit 0
Digit 1
Digit 2
Digit 3
Digit 4
Digit 5
Digit 6
Digit 7
Digit 8
Digit 9
9 rounds completed in 0.116 seconds.
3 solutions
3 total solutions
alex@btf:~/Git/tromp-equihash$ ./devcuda -t 4096
Looking for wagner-tree on (ββ,0) with 10 20-bits digits and 4096 threads (64 per block)
Digit 0
Digit 1
Digit 2
Digit 3
Digit 4
Digit 5
Digit 6
Digit 7
Digit 8
Digit 9
9 rounds completed in 0.114 seconds.
3 solutions
3 total solutions
alex@btf:~/Git/tromp-equihash$ ./devcuda -t 4096
Looking for wagner-tree on (ββ,0) with 10 20-bits digits and 4096 threads (64 per block)
Digit 0
Digit 1
Digit 2
Digit 3
Digit 4
Digit 5
Digit 6
Digit 7
Digit 8
Digit 9
9 rounds completed in 0.116 seconds.
3 solutions
3 total solutions
alex@btf:~/Git/tromp-equihash$ ./devcuda -t 4096
Looking for wagner-tree on (ββ,0) with 10 20-bits digits and 4096 threads (64 per block)
Digit 0
Digit 1
Digit 2
Digit 3
Digit 4
Digit 5
Digit 6
Digit 7
Digit 8
Digit 9
9 rounds completed in 0.116 seconds.
3 solutions
3 total solutions[/details]