HPC & Quantum
27 subscribers
11.4K photos
668 videos
3 files
30.7K links
Download Telegram
HPC Guru (Twitter)

RT @spcl_eth: Join Roberto at #SC23 on Nov 16 at 11:30AM as he unveils VENOM - a new sparse matrix format enabling arbitrary N:M patterns on Sparse Tensor Cores, natively restricted to 2:4. Plus, explore Spatha 🗡️, our sparse library for VENOM achieving up to 37x over SOTA dense methods.
HPC Guru (Twitter)

RT @DrJimFan: Expectation for Google Gemini is now ridiculously high. In contrast, all @Meta needs to do to impress us is simply open-sourcing Llama-3.

Gemini has to check off at least ONE of the following:
- 120% IQ of textual GPT-4; or
- 100% of GPT-4 but at half the cost or 2x speed of turbo; or
- 100% of visual GPT-4; or
- Natively support long videos.

AND ship the API in Q1 of 2024!

It's about time that DeepMind recovers the glory of AlphaGo in 2016. I'm looking forward to it.
HPC Guru (Twitter)

RT @thoefler: Horst Simon opens the ADIA Lab symposium in Abu Dhabi. An impressive lineup of speakers, Nobel Laureates, Turing award winners, Excellencies from the Emirates as well as the Kingdom of Spain. Very well organized!
HPC Guru (Twitter)

RT @EuroHPC_JU: 📢 Open for Registrations!

The @EuroHPC_JU is organising its first EuroHPC User Day!

📍Brussels, Belgium
📆11 December 2023

More details to book your spot: eurohpc-ju.europa.eu/news-ev…

Mark your calendars!
HPC Guru (Twitter)

JUPITER’s general-purpose Cluster Module will use SiPearl’s first-generation processor, Rhea1, based on the @Arm Neoverse V1 platform

#Rhea1 is characterized by high memory bandwidth, great compute performance and efficiency for a decent Byte/Flop ratio

#HPC #AI via @HPCwire
HPC Guru (Twitter)

.@nvidia is showing off its new #supercomputer, Eos, a 10,752 #H100 #GPU system connected via 400Gbps Quantum-2 #InfiniBand

Such a system would cost $400+ million on the open market

servethehome.com/nvidia-show…

#AI #HPC via @ServeTheHome
HPC Guru (Twitter)

.@intel Scores a Huge #Gaudi2 Win in NVIDIA #MLPerf Training v3.1

NVIDIA’s marketing slide shows Intel is up to 4x better performance per dollar versus NVIDIA (~8x the performance for ~32x the cost)

servethehome.com/nvidia-show…

#AI #ML via @ServeTheHome
HPC Guru (Twitter)

China has a comprehensive plan to develop domestic chips around @risc_v

Shandong University deployed a cluster with 3072 cores over 48 nodes of 64-bit RISC-V CPU - accessible to #cloud users

hpcwire.com/2023/11/08/china…

#RISCV via @HPCwire
HPC Guru (Twitter)

👇@Supermicro_SMCI makes hay while the #AI sun shines

Supermicro is shipping 4,000+ racks per month, expects to ship 5,000 racks monthly

#HPC #AI #ML via @TDaytonPM
HPCwire (Twitter)

Our managing editor is bringing the class to #SC23. See you next week! #hpcnews