The Latest News in AI

We publish news articles on Forbes, which are copied here for your convenience.  

Nvidia Sweeps Benchmarks. AMD Is MIA, Again

It should not surprise anyone: Nvidia is still the fastest AI and HPC accelerator across all MLPerf benchmarks. And while Google submitted results, AMD was a no-show. This blog has been corrected on 11/14 with a fresh TPU Trillium vs. Blackwell comparison. Say what...

Using AI To Build Better Chips

With so many startups and large semiconductor firms racing to get new AI chips to market, electronic tool and design service firms like Synopsys, Cadence and Mentor Graphics are looking for new approaches to help designers speed their time to market. Ironically, one...

Qualcomm Cloud AI100 Ultra: 4 Times The Performance For Large Models

We haven't heard from Qualcomm in a while regarding their power-efficient data center inference accelerator, which still holds the record for power efficiency, according to MLCommons benchmarking. Now Qualcomm has announced a new “Ultra” version that delivers four...

Why Can’t NVIDIA Be Bested In MLPerf?

MLPerf, an industry consortium of over 70 companies and institutions, has released the second round of AI Inference processing results. These benchmarks now represent production applications from all major areas of AI deployment today. But only a few technologies...

The Graphcore Data Center Architecture

The Graphcore disaggregated accelerator could be a game changer. I have recently finished a research paper looking into the data center architecture for deploying the Graphcore IPU-Machine, which is a network-attached accelerator for highly-parallel workloads. Lets...

AI Hardware: Harder Than It Looks

The second AI HW Summit took place in the heart of Silicon Valley on September 17-18, with nearly fifty speakers presenting to over 500 attendees (almost twice the size of last year’s inaugural audience). While I cannot possibly cover all the interesting companies on...

NVIDIA And Intel Publish First GPT3 Benchmarks; AMD, AWS, And Google Are MIA

Let’s look into the results and explore why so many competitors chose not to play ball. Those who follow me know the drill: MLCommons publishes benchmarking results every 3 months, alternating between inferencing and training. Then I explain the results and whine...

How Enfabrica Is Reimagining, And Disrupting, The AI Data Center

The AIHW and Edge AI Summit had a treasure trove of insightful presentations from luminaries such as Andrew Ng, Lip-Bu Tan, Marc Tremblay, and many others. I hope to get around to writing about what I learned, but first, I want to share the innovations from a startup...

The IBM Research AI Hardware Center: An Update

Celebrating its two-year anniversary, the Center announces innovative AI acceleration technologies along with nearly tripling its cadre of memberships. The IBM Research AI Hardware Center is the nexus of a group of academic and industry leaders contributing to the...

Story Correction: TechSpot Now Says AMD Believes That “AI Will Be Important To All Our Products Going Forward”

TechSpot has issued a retraction, says the reporter ‘misrepresented’ AMD spokesperson… this article has been subsequently updated…. TechSpot issued a correction on their interview with Justin Galton of AMD, noting “…unfortunately the source for that story...