Benchmark on Apple Silicon M1

[k06a]

./ERADICATE2.x64 -A 0x00000000000000000000000000000000deadbeef -I 0x00 --leading 0 

Devices:
  GPU0: Apple M1, 11453251584 bytes available, 8 compute units

Initializing OpenCL...
  Creating context...OK
  Compiling kernel...OK
  Building program...OK

Running...

  Time:     0s Score:  5 Salt: 0x5f5aafc533c1bcd263179c3c33d2a3e7d73ed9de8e7c0ce2f2d4dcd5bde15450 Address: 0x00000ed354bca8ae0bdb3138aad9dc77b83a6b8a
  Time:     1s Score:  6 Salt: 0x5f5aafc533c1bcb93c979c3d33d2a3e7d73ed9de8e7c0ce2f2d4dcd5bde15450 Address: 0x000000fa2afaf03a385b4a6ad31cfc37b182fc5e
  Time:     6s Score:  7 Salt: 0x5f5aafc533c1bc0b45ce9c4c33d2a3e7d73ed9de8e7c0ce2f2d4dcd5bde15450 Address: 0x00000009af1f04a3edf32096ef68b8a62fff1d62
  Time:    34s Score:  8 Salt: 0x5f5aafc533c1bcbb37849c9a33d2a3e7d73ed9de8e7c0ce2f2d4dcd5bde15450 Address: 0x00000000b6c277bf088bcba0e7d1cdf140f3ee06
Speed: 47.975 MH/s GPU0: 47.975 MH/s

[k06a]

I see profanity project is having the same speed: https://github.com/johguse/profanity/issues/36

But ERADICATE2 should work faster...

[Elyx0]

@k06a I get GPU0: 112.787 MH/s on M1 max

[Alchemyst0x]

I know this is a few months old now; regardless, I felt it might be interesting to other anons browsing through. I like benchmarks, myself. Anyway -

M1 Max, 64Gb RAM, running my usual suite of software in the background (VSCode, Docker+Dev Containers, Discord, Spotify, and naturally, too many Brave windows & tabs)

bash-5.2$ ./ERADICATE2.x64 -A 0x00000000000000000000000000000000deadbeef -I 0x00 --leading 0
Devices:
  GPU0: Apple M1 Max, 51539607552 bytes available, 32 compute units

Initializing OpenCL...
  Creating context...OK
  Compiling kernel...OK
  Building program...OK

Running...

  Time:     0s Score:  6 Salt: 0x6bbbb8c30b126d2c45bb679569cedb36c826e765c3c4d233e8094161335d830a Address: 0x0000003e82a20743ffe15de22180128b35a7470a
  Time:     3s Score:  7 Salt: 0x6bbbb8c30b126d09574768ab69cedb36c826e765c3c4d233e8094161335d830a Address: 0x0000000ffa124f1fef5d35a6f8e5819f16184f58
  Time:    54s Score:  8 Salt: 0x6bbbb8c30b126ddc748868296bcedb36c826e765c3c4d233e8094161335d830a Address: 0x00000000d1a7d3f55b31d3f48eebe27cdf40afc1
  Time:   199s Score:  9 Salt: 0x6bbbb8c30b126d2cf1c967536fcedb36c826e765c3c4d233e8094161335d830a Address: 0x00000000090a03e2d77cb36ccd03aa59010e9aba
Speed: 125.597 MH/s GPU0: 125.597 MH/s

I have yet to test out Profanity2 but I intend on doing so here relatively soon.

---

Edit: Went ahead and tested this with Profanity2 just now:

  Time:     7s Score:  5 Private: xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx Address: 0x00000xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
  Time:     7s Score:  6 Private: xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx Address: 0x000000xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
  Time:     7s Score:  8 Private: xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx Address: 0x00000000xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
  Time:   107s Score:  9 Private: xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx Address: 0x000000000xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
Total: 189.493 MH/s - GPU0: 189.493 MH/s

[k06a]

@Alchemyst0x that’s awkward, but I expected profanity2 result to be exactly the same as profanity. I am not sure that profanity2 changes could affect performance at all.

update:

Oh, I see you was comparing eradicate2 with profanity2. I expect performance of profanity and profanity2 should match, but that also means profanity2 should be much slower that eradicate2. Because eradicate2 was created as more optimized version than profanity.