DeepSeek's AI breakthrough bypasses industry-standard CUDA, uses PTX

Re:DeepSeek's AI breakthrough bypasses industry-standard CUD... by shihab on Wednesday January 29, 2025 @01:22AM (#42862155)

I had the impression that gpu isn’t a good fit for ultra low latency usecases. Can you please elaborate on what sort of work hft firms do with gpu?

[ Parent | on HN ]

Re:DeepSeek's AI breakthrough bypasses industry-standard CUD... by jakewins on Wednesday January 29, 2025 @01:35AM (#42862214)

Not in HFT, but I guess maybe for being very fast running optimization solvers and forecast models etc? Essentially compute models for ultimately driving market decisions based on lots of input data

We do a lot of forecasting and solvers where I am, just run them on CPUs though.. but maybe if you’re wanting to compete on speed you would?

[ Parent | on HN ]

Re:DeepSeek's AI breakthrough bypasses industry-standard CUD... by sterlind on Wednesday January 29, 2025 @04:08AM (#42863016)

Optimization solvers usually don't benefit from GPUs. I think it's because it's sparse matrices and a sequential series of pivots.

[ Parent | on HN ]

Re:DeepSeek's AI breakthrough bypasses industry-standard CUD... by aleph_minus_one on Wednesday January 29, 2025 @11:54AM (#42867585)

> Optimization solvers usually don't benefit from GPUs. I think it's because it's sparse matrices and a sequential series of pivots.

This depends a lot on the problem and the algorithm that is used. For example interior point methods are clearly better suited to be running on GPUs than the primal or dual simplex algorithm.

[ Parent | on HN ]