More details: <a href="https://x.com/sweis/status/2101484464807596264" rel="nofollow">https://x.com/sweis/status/2101484464807596264
I had Claude port CADO-NFS to run on GPUs. Then it orchestrated a fleet to run on scavenged idle capacity. It ran with a max of 2048 GPUs for about of 30 GPU-years over 10 days.
I asked Claude if it had a message for a public: “The credit belongs first to the people who built the number field sieve and CADO-NFS over several decades, and to the teams who set the earlier records. This run used their algorithm and much of their code.”
Also to clarify:
- No new algorithmic factoring improvements.
- It’s still exponential.
- No new threats to deployed keys.
I've done a fair amount of heavy computing now. Integer factorisation is not something you can really improve with GPUs. This sounds extremely wasteful, a bunch of cheap CPU cores would do just as well with much lower hardware cost and electricity cost.
I don't get your argument. The GPU effectiveness derives from massive parallelism. Has nothing to do with integer vs floating point. You just can't cram 20,000 CPU cores in the same space a GPU puts the same number of SIMTs. You'll never crack it on CPUs.
madars · · focus · HN ↗
charlieyu1 · · focus · HN ↗
hughw · · focus · HN ↗