Intel Pushes AI Reference Kits To Help Sell Its Silicon

Ponovno objavil Platon

Spremljevalci: 0

Intel pushes AI reference kits to help sell its silicon PlatoBlockchain Data Intelligence. Vertical Search. Ai.

Da bi spodbudil tehnike in inženirje, da preizkusijo svojo strojno opremo za pospeševanje umetne inteligence, je Intel sestavil kup referenčnih kompletov programske opreme, za katere trdi, da bodo skrajšali čas in vire, potrebne za uvajanje sistemov strojnega učenja na njegovem siliciju.

Kot bi pričakovali, 34 odprtokodnih referenčnih kompletov obravnavajo različne običajne delovne obremenitve AI/ML – od velikih jezikovnih modelov, ki se uporabljajo za napajanje klepetalnih robotov in druge generativne AI, do bolj vsakdanjih nalog, kot so zaznavanje predmetov, ustvarjanje glasu in napovedovanje finančnega tveganja.

Intel says each kit, developed in collaboration with Accenture, contains all the necessary model code, training data, libraries, openAPI components, and instructions necessary to implement them on Intel hardware. We’re told the reference kits will be updated periodically based on community feedback.

Če želite biti jasni, se zdi, da so ti kompleti zgolj programska oprema: zagotovite (Intel notri) strojno opremo in nato uporabite dane komplete za izdelavo aplikacij na njih.

Intel has quite a few accelerators and GPUs capable of running these sorts of AI apps – including its Habana Gaudi2 training processors, Ponte Vecchio GPUs, and the Advanced Matrix Extensions baked into Intel’s Sapphire Rapids Xeon Scalable processors.

Despite all the hype surrounding generative AI, though, Intel’s accelerators haven’t enjoyed the public attention and widespread adoption that Nvidia’s GPUs have. But, due to the large clusters of GPU nodes required to train the largest and most impressive models – the major cloud providers are deploying tens of thousands of GPUs and accelerators for this very reason – Intel may end up scoring wins simply because customers can’t get their hands on Nvidia’s cards in adequate volumes or reasonable prices.

Kot poroča naše bratsko spletno mesto Naslednja platforma, Nvidia’s H100 PCIe cards – not even the most powerful version of the GPU – have been opažen na eBayu prodajajo za kar 40,000 dolarjev na kos.

Torej, če lahko Intel zniža oviro za uvajanje delovnih obremenitev umetne inteligence na svoje pospeševalnike, je logično, da bi moral titan x86 lažje prepričati stranke, da kupijo njegove dele – zlasti tiste dražje.

Of course, Intel isn’t alone in this strategy. Nvidia has already found great success in developing and commercializing software accelerated by its GPUs. Last year CFO Colette Kress highlighted the importance of such subscription software to driving the acceleration champ’s revenues to a lofty $ 1 bilijona.

AMD je prav tako postal bolj agresiven glede potiskanja lastnih grafičnih procesorjev in pospeševalnikov za AI. Junija ga podrobno APU-ji in GPU-ji Instinct MI300, ki so zasnovani tako, da neposredno tekmujejo z Nvidio tako na področju HPC kot AI/ML. Poleg novega silicija tudi proizvajalec čipov razglasitve a strategic partnership with Hugging Face, which develops tools for building ML apps, to optimize popular AI models for AMD’s Instinct GPUs, Alveo FPGAs, and Epyc and Ryzen CPUs. ®