Karl Freund, Patrick Moorhead

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 of the approaches being taken is to use AI to help build …

Using AI To Build Better Chips Read More »

The US arsenal of supercomputers has officially been opened up for COVID-19 research. The White House recently announced the new COVID-19 High Performance Computing Consortium, which will allow researchers worldwide to access to the world’s most powerful HPC resources and leverage them to combat the novel coronavirus. The White House believes that these high performance computing …

Putting HPC To Work To Accelerate COVID-19 Research Read More »

What the heck is that you ask?  So, did I; but it looks promising! I continue to be amazed at the innovations that are coming to market to accelerate deep learning workloads.  GraphCore, Habana Labs, Cerebras, Blaize, Groq, Perceive and others are now being joined by a new entrant with radically new ideas: Tenstorrent out …

Tenstorrent Launches AI Chip With Conditional Execution Read More »

While the IBM hardware business today is limited to POWER and Mainframe chips and systems, the technology giant is quietly building its expertise and capabilities in AI hardware. Where this could end up is anybody’s guess, but here are a few thoughts about what IBM is doing and speculation as to why. IBM research in …

IBM Invests In AI Hardware Read More »

Intel certainly has a lot of irons in the AI fireplace, including Xeon CPUs, Movidius computer vision chips, MobileEye chips for autonomous driving and Deep Neural Network training and inference processing technology from the newly acquired Habana Labs. With all of this going on, one might wonder why Intel is pursuing yet another approach—neuromorphic computing. …

Why Intel Is Investing In Neuromorphic Computing Read More »

Last fall, as Cray was being acquired by Hewlett-Packard Enterprise for $1.6B, the company announced that it had been selected by the US DOE for two more exa-scale supercomputers based on the processor-agnostic Cray Shasta architecture. The Lawrence Livermore National Labs (LLNL) El Capitan supercomputer, costing some $600M, and planned for 2023, will be based …

AMD To Power ‘El Capitan’ Super Computer From HPE’s Cray Read More »

The CPU in today’s data center is increasingly burdened by the need to process networking jobs. According to Xilinx’s VP Marketing for Data Center Products, Donna Yasay, networking stacks can tax CPUs up to 30%, robbing them of the cycles needed to run users’ applications. Tier 1 cloud service providers have invested in custom ASICs …

Xilinx Enters The SmartNIC Market Read More »

As we approach NVIDIA’s annual GPU Technology Conference, everyone is anxious to see what CEO Jensen Huang has up his trademark black leather sleeves. I have no idea, but as usual, I have an opinion.    An intro to GTC GTC is NVIDIA’s partners’ big annual opportunity to show off and explain how they leverage …

NVIDIA GTC ’20 Could Be Massive Read More »

NVIDIA reported renewed growth overall last week. Its Data Center segment (where most of the AI hardware is reported) grew 43% to a record $968M in the last quarter, and gaming rose 56% to $1.49 billion. The stock market appreciated the news, sending NVIDIA up over 6%, and many analysts revised their price targets higher. …

NVIDIA Data Center Growth Returns Read More »

Last week, I reported that Intel plans to switch its AI acceleration from Nervana technology to Habana Labs, which it acquired in December. Since Intel had planned to bring out both the inference and the training versions of Nervana’s second generation, this came as quite a surprise to many in the industry. I just got an update from …

An Update On Intel And Habana Labs Read More »

Last month, Intel announced that it would acquire Israeli AI chip startup Habana Labs for $2B. At the time, I opined that this probably spelled the end for chips from the 2016 Nervana acquisition. Intel planned to bring out both the inference and the training versions of Nervana’s second attempt to out-perform NVIDIA by the end of …

Intel Lays Out Strategy For AI: It’s Habana Read More »

In a strategic move in its datacenter AI plans, Intel has announced that it will acquire Israeli chip startup Habana Labs for $2 billion. Intel had reaffirmed its plans to deliver its Nervana chips as recently as last month, but the acquisition of Habana likely signals that early lighthouse accounts preferred the startup’s approach over …

Intel Acquires Habana Labs For $2 Billion Read More »

For the last decade, a “smart phone” was defined by its ability to run applications locally on the device. These days, however, “smart” means features powered by AI, with intelligent applications such as enhanced computational photography, voice processing and gaming with AR features. It appears that Qualcomm’s next generation mobile processors are about to take …

Qualcomm Doubles The Smart In Smartphones Read More »

As we approach the end of a year full of promises from AI startups, a few companies are meeting their promised 2019 launch dates. These include Intel, with its long-awaited Nervana platform, UK startup Graphcore and the stealthy Groq from Silicon Valley. Some of these announcements fall a bit short on details, but all claim …

Intel, GraphCore And Groq: Let The AI Cambrian Explosion Begin Read More »

When the mlperf (machine learning performance) organization released the first standardized AI training benchmarks, which NVIDIA dominated last December, we were somewhat disappointed that only a few companies, namely NVIDIA, Google and Intel, were able to muster the working chips and software needed to complete the benchmarks. Last week, the open-source mlperf community released the first round of …

NVIDIA Runs The Mlperf Table Read More »

Throughout 2020, a wave of AI hardware startups will launch their companies and products. Cerebras started this wave with its wafer-scale engine last September. This week, Intel announced its AI chips from Nervana, Groq (founded by the inventors of Google TPU) announced its quadrillion ops per second TSP, and Graphcore announced that its chip is available on Microsoft Azure …

Blaize AI Emerges From Stealth Read More »

As I covered in a recent article on the status of startups building chips for AI, the AI accelerator market will become quite crowded over the next 12-18 months. Not to be outdone, Arm is now extending its neural network processor family, adding logic designs for mid-range and entry-level devices to the flagship Ethos-N77, which targets higher-end …

Arm Adds More AI Firepower Read More »