Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

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

nietras.com

Post reply on HN
Print view View original

71–80 of 176 posts

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

#71

Post by sitkack »

etaioinshrdlu wrote: post #66
sitkack wrote: post #49

Earlier quoted context omitted.

That is what Intel does, they build up a market (Optane) and then do a rug pull (Depth Cameras). They continue to do this thing where they do a huge push into a new technology, then don't see the uptake and let it die. Instead of building slowly and then at the right time, doing a big push. Optane support was just getting mature in the Linux kernel when they pulled it. And they focused on some weird cost cutting move…

Well, Itanium might be a counterexample, they probably tried to make that work for far too long..

Itanium worked as intended.

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

#72

Post by devmor »

adra wrote: post #39
hermitcrab wrote: post #17

Earlier quoted context omitted.

For all its many weaknesses, I believe CSV is still the most common data interchange format.

Erm, maybe file based? JSON is the king if you count exchanges worldwide a sec. Maybe no 2 is form-data which is basically email multipart, and if course there's email as a format. Very common =)

I honestly wonder if JSON is king. I used to think so until I started working in fintech. XML is unfortunately everywhere.

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

#73

Post by mrweasel »

etaioinshrdlu wrote: post #66
sitkack wrote: post #49

Earlier quoted context omitted.

That is what Intel does, they build up a market (Optane) and then do a rug pull (Depth Cameras). They continue to do this thing where they do a huge push into a new technology, then don't see the uptake and let it die. Instead of building slowly and then at the right time, doing a big push. Optane support was just getting mature in the Linux kernel when they pulled it. And they focused on some weird cost cutting move…

Well, Itanium might be a counterexample, they probably tried to make that work for far too long..

Itanium was more of an HP product than an Intel one.

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

#74

Post by paddy_m »

sitkack wrote: post #71
etaioinshrdlu wrote: post #66

Earlier quoted context omitted.

Well, Itanium might be a counterexample, they probably tried to make that work for far too long..

Itanium worked as intended.

So far as killing HP PA-Risc, SGI MIPS, DEC Alpha, and seriously hurting the chance for adoption of Sparc, and POWER outside of their respective parents (did I miss any)?

Thing is, they could have killed it by 1998, without ever releasing anything, that would have killed the other architectures it was trying to compete with. Instead they waited until 2020 to end support.

What the VLIW of Itanium needed and never really got was proper compiler support. Nvidia has this in spades with CUDA. It's easy to port to Nvidia where you do get serious speedups. AVX-512 never offered enough of a speedup from what I could tell, even though it was well supported by at least ICC (and numpy/scipy when properly compiled)

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

#79

Post by anthk »

mihular wrote: post #65
speed_spread wrote: post #50

Earlier quoted context omitted.

True. But also Excel probably collapses into a black hole going straight to hell trying to handle 21GB of data.

21GB/s, not 21GB ...

mawk would handle a 21 GB csv (or maybe one true awk) fast enough.

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

#80

Post by knowitnone »

paddy_m wrote: post #74
sitkack wrote: post #71

Earlier quoted context omitted.

Itanium worked as intended.

So far as killing HP PA-Risc, SGI MIPS, DEC Alpha, and seriously hurting the chance for adoption of Sparc, and POWER outside of their respective parents (did I miss any)? Thing is, they could have killed it by 1998, without ever releasing anything, that would have killed the other architectures it was trying to compete with. Instead they waited until 2020 to end support. What the VLIW of Itanium needed and never real…

"they could have killed it by 1998, without ever releasing anything"

perhaps Intel really wanted it to work and killing other architectures was only a side effect?

Post reply on HN