Dion Harris

tech, music, sports, family, and fun

[Dion Harris @Dion2730]

In my latest article, I unpack why extreme hardware-software co-design is becoming the real competitive edge: driving lower latency, higher throughput, and dramatically better token economics for the next generation of AI workloads.

Read here: 

https://t.co/iU5hw8t7VO

[NVIDIA @nvidia]

Water usage has been a hot topic in the AI data center world, but the numbers may surprise you.

According to the Manhattan Institute, data centers use 0.2 percent of daily water usage in the U.S. and that number has dramatically decreased in the past few years due to a new method: liquid cooling.

By moving to 45°C liquid cooling, AI factories in favorable climates can use dry coolers instead of conventional cooling-tower-based systems, cutting facility cooling water use from roughly 2.6M gallons per MW per year to near zero.

Liquid cooling enables AI factories to be both water and energy efficient, while creating opportunities for heat reuse and dispersal to local communities, allowing these factories to become energy grid assets.

Learn more below ⬇️

https://t.co/7WanoPNKTR

[NVIDIA AI Infrastructure @NVIDIAAIInfra]

👏 @CoreWeave is the first cloud provider to bring up and validate NVIDIA Vera Rubin NVL72.

Training MoE models with ¼ the GPUs. Inference at ⅒ the cost per token versus NVIDIA Blackwell.

Learn more ⤵️

[Stuart Pitts @stpitts]

Going deep on @nvidia + @GroqInc with
@TickerSymbolYOU & @Dion2730.

Agentic systems demand more from AI infra.

This is exactly what we're delivering with the Vera Rubin supercomputer + Groq 3 LPX inference accelerator.

[Tarik Glenn @78tglenn]

It’s an honor to be apart of the Cal HOF. Go Bears

[Dion Harris @Dion2730]

Generative AI is impacting every industry today - from renewable energy forecasting to drug discovery, and more. Read this blog to see the business requirements for putting #generativeAI into practice: AI expertise, tons of data, and accelerated computing. https://t.co/3y8ElTV8It

[Dion Harris @Dion2730]

NVIDIA Made a CPU.. I’m Holding It. https://t.co/LxgZlqhCUO

[Dion Harris @Dion2730]

Our CEO, Jensen Huang, delivered a live keynote at #COMPUTEX2023 unveiling generative #AI platforms for every industry. Catch up on new systems, software and services enabling more efficient workflows. Watch the keynote now: https://t.co/ul7HBGmAau https://t.co/W1YJseLLZa

[Dion Harris @Dion2730]

NVIDIA Bluefield DPUs For HPC https://t.co/zq9IUjqhHm

[Dion Harris @Dion2730]

Supercomputing-Scale quantum simulations are now available with the NVIDIA DGX cuQuantum appliance. https://t.co/qMDxjKcEz1

[Dion Harris @Dion2730]

Growing Range of Researchers, Scientists Adopt NVIDIA cuQuantum and QODA https://t.co/Y0chlboEFE

[NVIDIA HPC Developer @NVIDIAHPCDev]

Join NVIDIA's Sam Stanwyck and Bryce Lelback at QCWare's #Q2B22 this Wednesday as they dive into the future of quantum computing. Learn more: https://t.co/hUAqPIFHKK

[Dion Harris @Dion2730]

@hpcprogrammer 😂

[Dion Harris @Dion2730]

Learn best practices for using parallelism in standard languages for #acceleratedcomputing using Fortran at the link. https://t.co/AoeeunMmVI

[Dion Harris @Dion2730]

NVIDIA Special Address at ISC22: Accelerating AI Innovation and Scientific Discovery https://t.co/39dHulFAsL

[Dion Harris @Dion2730]

NVIDIA Special Address at ISC22: Accelerating AI Innovation and Scientific Discovery https://t.co/Lcy6kjoAGR

[Dion Harris @Dion2730]

Get a look into the future of #digitaltwins at the #ISC22 opening keynote on May 30, featuring @BMWGroup's Michele Melchiorre and NVIDIA's @RevLebaredian as they discuss the future of Digital Twins and AI. @NVIDIAOmniverse @ISChpc https://t.co/hKSlrXjKkt

[Dion Harris @Dion2730]

Don't miss the NVIDIA Special Address at #ISC22 on Monday! Plus, attendees will get complementary codes for #NVDLI AI and HPC training. https://t.co/0IZc73JbHC

[Dion Harris @Dion2730]

This was fun...looking forward to doing this in person soon at SC'21 #AskPerlmutter

[Dion Harris @Dion2730]

@Rangan_Sukumar @Carlos_I_Rojas @HPE_Cray @NERSC Agreed...DeepMD Kit is one that comes to mind