We’re proud to have helped set a new standard for Generative AI by building a cluster with 3,584 @NVIDIA H100 GPUs in the debut MLPerf benchmark. Our system completed the massive GPT-3-based training benchmark in under eleven minutes. Read more: https://
blogs.nvidia.com/blog/2023/06/2
7/generative-ai-debut-mlperf/
…
COMPUTING
-
Inflection AI Sets New Generative AI Standard with H100 GPU Cluster
By
–
-
Breaking Data Silos: IoT and Machine Learning in Business
By
–
In my new #BetterTogetherStories podcast from @SAP we discuss Business Without Boundaries w/ Jason Taylor of @GatesIndustrial
, Nathan Williams of @NIMBLnews
, and @chuckmartin to discuss how to break down data silos. https://
bit.ly/37duSXW #IoT #MachineLearning #COVID19 -
Dijkstra on Abstraction: Precision Through Semantic Layers
By
–
“The purpose of abstraction is not to be vague, but to create a new semantic level in which one can be absolutely precise.” — Edsger Dijkstra
-
High-speed tensor core inference with massive memory bandwidth
By
–
So, you have a 200 TB/s fire hose of recycling information, which you would have to “pump up” over many cycles from much slower conventional memory, but it could then feed straight in to a field of tensor core registers for real time model inference. Fun to think about!
-
AI Models Trading Latency for Bandwidth Using Delay Line Memory
By
–
Last month I commented about how AI models could trade latency for bandwidth in memory systems. Some ancient computers used acoustic delay lines for memory: https://
en.m.wikipedia.org/wiki/Delay-lin
e_memory
… Surprisingly, a fiber optic delay line memory is not completely absurd today! -
Industrial IoT Value in Oil and Gas Industry
By
–
Curious about the real value of #IIoT in the #oilandgasindustry? Join our session to gain practical knowledge. Explore case studies, key considerations, and tangible benefits. https://
ow.ly/TF0g50OPsKk Sponsored by @HiveMQ and Trackonomy. #hivemq_iiot #trackonomy_iiot #energy -
Tenstorrent CEO discusses RISC-V strategy to challenge Nvidia
By
–
@tenstorrent CEO @jimkxa talks to @ojoyoshida about #riscv, #opensource and the #tenstorrent roadmap. https://
ojoyoshidareport.com/jim-keller-ske
tches-ai-strategy-to-bypass-nvidia/
… -
ExploreSAS Conference Las Vegas September 2026
By
–
4 days, 100 + sessions, 2.5k of your tech peers, coming up at #ExploreSAS in Las Vegas this September, SAS users! First mover discount rate through June 30. Save $500 off the standard rate http://
2.sas.com/6018PBFJI -
60% of Organizations Experience Multiple Security Breaches Yearly
By
–
#ad BT for Global Business's "Future of Infrastructure in a Cloud-Centric World" research reveals that 60% of organisations have experienced between 5 and 14 security breaches in the past year. Download the research > https://
bit.ly/3PfCTSq Paid partnership with @bt_global -
SLURM cluster management: benefits and challenges for experimentation
By
–
That’s an interesting one. I have both fond and not so fond memories using SLURM on the departmental cluster. It’s actually great if you know exactly what you want to run. But yeah also make sure you have access to an interactive node for experimentation or you’ll go crazy 😛