could ever possibly know. It is at least plausible that human level AGI might initially run in a box instead of an entire data center. Some still hope for quantum magic in the neurons; I think it more likely that they are actually kind of crappy computational elements.
AI HARDWARE
-
Training Transformers at Scale for Scientific Applications
By
–
Transformers and other large language models have shown impressive capabilities as foundation models for domains such as NLP and CV. Join Andy Hock, our VP of Product, at #SC22, as he discusses new algorithms, software, and hardware for training transformers at scale for science
-
IBM announces most powerful quantum processor Osprey with 433 qubits
By
–
[INNOVER]
#IBM annonce le processeur #quantique le plus puissant et de loin https://
buff.ly/3hs9KVk v/ @engadget Le nouveau processeur #Osprey affiche 433 qubits, soit le triple de la version Eagle de 2021, en attendant 10k qubits en 2026 #Tech #FlashTweet -
Untether AI showcases inference performance at ECCV Tel Aviv
By
–
Had a great time at @eccvconf in Tel Aviv last week! Thank you to our incredible partner, #Eastronics, and everyone who visited our booth! To learn more about our #ai #inference #performance and how to purchase our products through #Eastronics, visit http://
untether.ai. -
CS-2 System 470x Faster Than Joule Supercomputer
By
–
Today, in partnership with @NETL_DOE
, we demonstrated that our CS-2 system is 470 times faster than the Joule Supercomputer in field equation modeling, delivering speeds beyond what either CPUs or GPUs are able to achieve! Read about this milestone here: -
Qualcomm Achieves 5G Standalone mmWave Milestone in China
By
–
Qualcomm Achieves Critical 5G Standalone mmWave Milestone in China: Qualcomm Technologies, Inc. announced it achieved groundbreaking 5G standalone (SA) mmWave performance, laying the groundwork for expanded commercial mmWave deployments. https://
microwavejournal.com/articles/39166
-qualcomm-achieves-critical-5g-standalone-mmwave-milestone-in-china?utm_source=dlvr.it&utm_medium=twitter
… #5G #Network #IoT -
Tensorrent showcases AI at SC Conference Dallas booth 3020
By
–
Come find us at SC Conference Series in Dallas, we will be at booth 3020. #SuperComputing #artificialintelligence #machinelearning #tenstorrent https://
sc22.supercomputing.org -
NVIDIA TAO Reduces Manufacturing Defect Detection False Negatives
By
–
NVIDIA Metropolis and #NVIDIAInception partner @covisionquality have created #visionAI software using NVIDIA #TAOToolkit capable of reducing false-negative rates in manufacturing defect detection by up to 90%. Learn more: https://
nvda.ws/3TmMh54 -
Novel Stencil Algorithm Exploits Cerebras Wafer-Scale Engine
By
–
Stencil computations lie at the heart of many scientific and industrial applications. Join Mathias Jacquelin, member of our kernel team, at #SC22 as he discusses his research on a novel stencil algorithm that effectively exploits the second-generation Cerebras Wafer-Scale Engine.
-
Groq and Argonne Panel on AI Accelerators for Scientific Computing
By
–
Join us for a panel with @argonne on programming new AI accelerators for scientific computing. Hear from Victoria Godsoe, Manager of CX Engineering, about recent advances at @GroqInc
. @Supercomputing #HPC #AI #SuperComputing #HPCaccelerates #SCinet #SCInclusivity