HPC & Quantum
26 subscribers
11.4K photos
668 videos
3 files
30.6K links
Download Telegram
HPC Guru (Twitter)

.@LisaSu: In 2026, @AMD plans to launch #MI400 - “powerful rack-scale solutions that tightly integrate #networking, #CPU and #GPU capabilities at the silicon level to support Instinct solutions at data center scale

https://www.crn.com/news/components-peripherals/2025/amd-fourth-quarter-2024-earnings

#HPC #AI via @DylanOnChips
HPCwire (Twitter)

At the 2025 #CES event, #Nvidia announced a new $3,000 desktop computer developed in collaboration with MediaTek that is powered by a new, cut-down Arm-based Grace #CPU and Blackwell #GPU Superchip. ow.ly/BGLX50UVgfB
HPCwire (Twitter)

Nvidia used its GTC conference to introduce new #GPU #superchips, including the second generation of its current Grace Blackwell chip, as well as the next generation, dubbed the Vera Rubin. ow.ly/cZZr50Vnsgu
HPCwire (Twitter)

Hewlett Packard Enterprises recently rolled out a reimagining of its #HPE data fabric offering, bolstered its #Alletra storage appliances, and launched a new #GPU compute offering. Read more: ow.ly/68LP50Vt5mm
HPCwire (Twitter)

The HPC market has been a big driver for #GPU designs, including features like #ECC memory and fast 64-bit double precision, not to mention toolsets aimed at languages like Fortran and C. ow.ly/8Nmg50VF2BV #highperformancecomputing
HPC Guru (Twitter)

.@nvidia will sell over 18,000 of its latest #AI chips to Saudi Arabian company Humain, CEO Jensen Huang announced on Tuesday

Blackwell chips will be used in a 500 megawatt data center in Saudi Arabia

https://www.cnbc.com/2025/05/13/nvidia-blackwell-ai-chips-saudi-arabia.html

#HPC #GPU
HPC Guru (Twitter)

UAE and the US sign an agreement for the Gulf country to build the largest #AI campus outside the US

Sources told Reuters the UAE could be allowed to import 500,000 of @nvidia’s most advanced AI chips per year

https://www.theguardian.com/us-news/2025/may/15/trump-artificial-intelligence-uae

#HPC #GPU
HPC Guru (Twitter)

LLNL’s Center for Applied Scientific Computing (CASC) has developed a new JIT approach that leverages LLVM intermediate representation (IR) to optimize #GPU kernels at runtime

https://computing.llnl.gov/about/newsroom/proteus

#HPC #AI via @Livermore_Comp @Livermore_Lab
HPC Guru (Twitter)

RT @HatemLtaief: Guess what?
#SIAMPP26 is back to Europe!

@HartwigAnzt and I are building an exciting program.

So, build your MS, line up your speakers, submit your proposal, and join us in Berlin.

🗓️ Mark your calendar: March 3–6 , 2026

#HPC4ALL #GPU #HPC https://twitter.com/TheSIAMNews/status/1925551860863173032#m
HPC Guru (Twitter)

.@nvidia Dynamo: If disaggregation is Dynamo’s backbone, the smart management of the KV cache is its brain

At around 300 tokens per second per user, you can generate 30 times more tokens per normalized per #GPU

https://www.vastdata.com/sharedeverything/why-everyones-talking-about-nvidia-dynamo-and-why-it-actually-matters

#AI #Inference via @NicoleHemsoth