laser VS john

It depends.

You need 2~3 accumulators to saturate instruction-level parallelism with a parallel sum reduction. But the compiler won't do it because it only creates those when the operation is associative, i.e. (a+b)+c = a+(b+c), which is true for integers but not for floats.

There is an escape hatch in -ffast-math.

I have extensive benches on this here: https://github.com/mratsim/laser/blob/master/benchmarks%2Ffp...

Ah,

It was from an older implementation that wasn't compatible with Nim v2. I've commented it out.

If you pull again it should work.

> Anyway the reason for your competitive performance is likely that you are benchmarking with very small matrices. OpenBLAS spends some time preprocessing the tiles which doesn't really pay off until they become really huge.

I don't get why you think it's impossible to reach BLAS speed. The matrix sizes are configured here: https://github.com/mratsim/laser/blob/master/benchmarks/gemm...

It defaults to 1920x1920 * 1920x1920. Note, if you activate the benchmarks versus PyTorch Glow, in the past it didn't support non-multiple of 16 or something, not sure today.

Packing is done here: https://github.com/mratsim/laser/blob/master/laser/primitive...

And it also support pre-packing which is useful to reimplement batch_matmul like what CuBLAS provides and is quite useful for convolution via matmul.

For convolutions: - https://github.com/numforge/laser/blob/e23b5d63/research/convolution_optimisation_resources.md

You can train yourself on matrix transposition first. It's straightforward to get 3x speedup between naive transposition and double loop tiling, see: https://github.com/numforge/laser/blob/d1e6ae6/benchmarks/transpose/transpose_bench.nim#L238

John The Ripper

🔗Kali Linux Wordlist: What you need to know 🔗crunch 🔗WordLists - Kali-Tools 🔗WordLists - GitLab - repository 🔗John - Kali-Tools . 🔗Openwall -github repository -John 🔗John-The-Ripper-Tutorial - Techy Rick 🔗Openwall -John - Offical Website . 🔗Hash Cat - Wiki 🔗Cap 2 Hashcat 🔗Markov - Chain 🔗Hash Cat - Forums 🔗Security Stack Exchange - Question 260773 🔗StationX - How to use Hashcat 🔗MSF/Wordlists - charlesreid 🔗MSFConsole 🔗How to use hashcat 🔗MSF/Wordlists - charlesreid1 🔗Where do the words in /usr/share/dict/words come from? 🔗SCOWL (Spell Checker Oriented Word Lists) 🔗The spell utility -spell - find spelling errors (LEGACY) - UNIX What are Different Types of Cryptography? sha1-vs-sha2-the-technical-difference-explained-by-ssl-experts/ 🔗password-encryption 🔗Secure-Programs SHA-1 🔗What-are-computer-algorithms 🔗What Are MD5, SHA-1, and SHA-256 Hashes, and How Do I Check Them? - howtogeek.com 🔗kali-linux-wordlist-what-you-need-to-know

Ok, both John the ripper, hashcat and other tools seem to support extracting the hash, or directly trying to discover the password.

With the root hash you can crack the root password using tools like John The Ripper[0]. More generally, I assume, this exploit can be used to read any arbitrary files on the system, bypassing regular access control, and plenty of other stuff you aren't supposed to be able to do as a non-privileged user.

0: https://www.openwall.com/john/

use (John the Ripper)[https://github.com/openwall/john] and (rockyou.txt)[https://github.com/rockyou.txt]

this actually seems to have been reported as a bug and fixed years ago but it is still affecting me on a version freshly downloaded from the AUR, is there a way around this or another program i can use?

John the Ripper

Since I used to work for the employer in question, I decide to crack my own password-protected pay statements. I downloaded and built John the Ripper jumbo and then all I had to do was run a few commands after looking at the documentation, and there was my SIN number almost instantly.

However, most credential brute forcing takes place offline against a leaked database from some site. A program like John the Ripper is used to try hashing each word in a dictionary until it matches the entries in the database. Because this all happens offline, there's no mechanism in place to delay the attempts or lock the user out.