Seven Silicon Highlights from SC23. And a Llama
Ғылым және технология
The best bit about Supercomputing is looking at all the odd stuff. This year, we saw Bunny - a Llama showcasing large language models. Technically this was Llama2, as Bunny was pregnant. My only question is - how do you hire a llama for the day ?!
[00:00] Fujitsu Monaka 2nm CPU
[01:47] Groq LPU with Llama
[03:20] Cornelis Networks Omnipath
[05:26] Tenstorrent Galaxy
[07:04] NeuReality NR1
[08:41] Nimbus Data ExaNODE
[10:45] Ayar Labs TeraPHY
-----------------------
Need POTATO merch? There's a chip for that!
merch.techtechpotato.com
more-moore.com : Sign up to the More Than Moore Newsletter
/ techtechpotato : Patreon gets you access to the TTP Discord server!
Follow Ian on Twitter at / iancutress
Follow TechTechPotato on Twitter at / techtechpotato
If you're in the market for something from Amazon, please use the following links. TTP may receive a commission if you purchase anything through these links.
Amazon USA : geni.us/AmazonUS-TTP
Amazon UK : geni.us/AmazonUK-TTP
Amazon CAN : geni.us/AmazonCAN-TTP
Amazon GER : geni.us/AmazonDE-TTP
Amazon Other : geni.us/TTPAmazonOther
Ending music: • An Jone - Night Run Away
-----------------------
Welcome to the TechTechPotato (c) Dr. Ian Cutress
Ramblings about things related to Technology from an analyst for More Than Moore
#techtechpotato #llama #sc23
------------
More Than Moore, as with other research and analyst firms, provides or has provided paid research, analysis, advising, or consulting to many high-tech companies in the industry, which may include advertising on TTP. The companies that fall under this banner include AMD, Armari, Baidu, Facebook, IBM, Infineon, Intel, Lattice Semi, Linode, MediaTek, NordPass, ProteanTecs, Qualcomm, SiFive, Supermicro, Tenstorrent, TSMC.
Пікірлер: 15
I think Wendell is actually 6 identical sextuplets - its just impossible for one person to get everywhere he does
Real shame Fujitsu never sold small systems with A64FX. It was super awesome chip when it showed up in Fugaku. First CPU with SVE, and a lot of cool interconnect. Apparently HPE was (and still is) actually selling smaller systems (including single 2U chasis, hosting 8 blades each with one CPU) with A64FX, but I never knew of that before (i.e. Fujitsu never mentioned that on their news). And of course pricing unknown. I hope that Monaka would be more accessible.
Ex-Australian PM John Howard told me, be a lert, not a Llama-d.
Jeff Minter might disagree regarding what is the Llama company. (Well, you are wearing a C-64 t-shirt.)
Okay, that Nimbus Data ethernet products are interesting. Could use a box (or ten) full of these at work.
Uhhh, at the State Fair where I live a bunch of people show up with their llamas in costumes for a llama costume contest....
6:00 what do you mean when you're talking about 2d vs 3d scaling? Thanks for all of the great videos!
@TechTechPotato
6 ай бұрын
Speaking with JK, he was saying that the brain isn't a 2D array of nodes. It actually has a small amount of 3D. Right now we're looking at ML scaleout purely in 2D.
No chips were bitten... must not be that good
NS^3 Networked Solid State Storage
🦙
Nothing say serious professional like showing up and presenting in a $5 T-shirt!
@TechTechPotato
6 ай бұрын
Spent 15 years going around in a suit. Live a little!
@thepastrecedes1635
6 ай бұрын
You clearly haven't been to SC, most people are dressed like this