21 GB/s CSV Parsing Using SIMD on AMD 9950X

Post by jstimpfle » Fri, May 09, 2025, 8:08 PM UTC

hermitcrab wrote: post #23

zzbn00 wrote: post #15

Earlier quoted context omitted.

Humans generate decisions / text information at rates of ~bytes per second at most. There is barely enough humans around to generate 21GB/s of information even if all they did was make financial decisions! So 21 GB/s would be solely algos talking to algos... Given all the investment in the algos, surely they don't need to be exchanging CSV around?

CSV is a questionable choice for a dataset that size. It's not very efficient in terms of size (real numbers take more bytes to store as text than as binary), it's not the fastest to parse (due to escaping) and a single delimiter or escape out of place corrupts everything afterwards. That not to mention all the issues around encoding, different delimiters etc.

Post by sitkack » Fri, May 09, 2025, 8:14 PM UTC

knowitnone wrote: post #81

sitkack wrote: post #70

Earlier quoted context omitted.

They go out their way to segment their markets, ECC, AVX, Optane support (only specific server class skus). I hate it, I hate as a home pc user, I hate it as an enterprise customer, I hate as a shareholder.

Every company does this. If you're grandma only uses a web browser, word processor, and excel, does she really want to spend an additional $50 on a feature she'll not use? Same with NPUs. Different consumers want different features for different prices.

Post by pdpi » Fri, May 09, 2025, 8:25 PM UTC

stabbles wrote: post #36

freeone3000 wrote: post #5

Earlier quoted context omitted.

They claim a 3GB/s improvement versus previous version of sep on equal hardware — and unlike “marketing” benchmarks, include the actual speed achieved and the hardware used.

Do note that this speed even before the 3GB/s improvement exceeds the bandwidth of most disks, so the bottleneck is loading data in memory. I don't know of many applications where CSV is produced and consumed in memory, so I wonder what the use is.

Post by cyral » Fri, May 09, 2025, 8:28 PM UTC

zzbn00 wrote: post #15

segmondy wrote: post #11

Earlier quoted context omitted.

lots of folks in Finance, you can share csv with any Finance company and they can process it. It's text.

Humans generate decisions / text information at rates of ~bytes per second at most. There is barely enough humans around to generate 21GB/s of information even if all they did was make financial decisions! So 21 GB/s would be solely algos talking to algos... Given all the investment in the algos, surely they don't need to be exchanging CSV around?

Post by vardump » Fri, May 09, 2025, 8:31 PM UTC

tedunangst wrote: post #86

chao- wrote: post #38

It feels crazy to me that Intel spent years dedicating die space on consumer SKUs to "make fetch happen" with AVX-512, and as more and more libraries are finally using it, as Intel's goal is achieved, they have removed AVX-512 from their consumer SKUs. It isn't that AMD has better AVX-512 support, which would be an impressive upset on it's own. Instead, it is only that AMD has AVX-512 on consumer CPUs, because Intel…

I mean, the most interesting part of the article for me: > A bit surprisingly the AVX2 parser on 9950X hit ~20GB/s! That is, it was better than the AVX-512 based parser by ~10%, which is pretty significant for Sep. They fixed it, that's the whole point, but I think there's evidence that AVX-512 doesn't actually benefit consumers that much. I would be willing to settle for a laptop that can only parse 20GB/s and not 2…