Please note, this is a STATIC archive of website hashcat.net from October 2020, cach3.com does not collect or store any user information, there is no "phishing" involved.

hashcat Forum

Full Version: benchmarks different when run individually?
You're currently viewing a stripped down version of our content. View the full version with proper formatting.
Another trivial question, while I'm getting used to the new hashcat v3:

Back in the cudahashcat v1.3 era and through v2, I lost the ability to run all the benchmarks at once, so used a batch file to run a subset by individual commands. E.g., cudaHashcat64.exe --benchmark --hash-type=100

I ran the one by ones for v3, but then thought to try running them all, which now works for me.

What seems funny is that the benchmarks run indivually get higher readings that when run all at once.

Is this just a quirk of my system or something about how the benchmarks are programmed?
No, keep a close look at the clocks. Latest driver all have a directly influence between temperature and core clocks. The higher the temperature, the lower the clock. When you do a benchmark, the GPU heats up, the core clocks goes down. If you do only a single hash, you propably had a GPU idling for a while or at least long enough it can cool down. This gets even worse with GTX 10xx series because of the aggressive core clock throttling