GPUs are damn tricky
Intel is finding out just how tricky they can be!
Varjo gathers $40 million to develop industrial metaverse
The high-resolution Aero is Varjo’s professional-grade XR headset. For $1,990, you get dual mini-LED displays, edge-to-edge clarity, a 90-Hz refresh rate, and active cooling. (Source: Varjo) Varjo, a producer of high-end virtual reality (VR) hardware, has acquired $40 million in funds to expand the Varjo Reality Cloud. Their service is a platform that allows off-site compute power and GPUs to … Read more
Intel’s wonderful Flex AIBs
(Source: Intel) A few weeks ago, Intel rebranded the Artic Sound-M data center GPU as the Flex series. The first products introduced are the Flex Series 170 and 140—how wonderful is that? The name change was made almost the same time Intel launched its new slogan campaign, How Wonderful Is That? Intel’s new campaign. (Source: Intel) The Flex 170 and … Read more
Nvidia announces another blockbuster GPU—Ada Lovelace
This week (#38 of the year), Nvidia dominated the news with their GTC announcements. Top among them was the introduction of the long-awaited and rumored RTX 40 series and associated AD100 series GPUs known as the Ada Lovelace architecture. Everything about the AD100 is supersized—compare the current GPU with the previous generation. RTX 4090 RTX 3090 Difference Architecture Ada … Read more
GPUs change the engineering simulation landscape
Since the start of the year, Jon Peddie Research has been conducting a series of interviews with leading CAE software vendors such as Altair, Ansys, Dassault Systèmes, Hexagon, and Siemens Digital Industries Software. We’ve been working with Nvidia to understand how the industry is changing in response to GPU acceleration now available in many CAE applications and workflows. The results … Read more
The hottest chips conference
This was the 34th year of the Hot Chips conference, which has traditionally been presented in Silicon Valley during August. The name “Hot” is a play on words for the weather and the performance of the latest designs. Hot Chips is like a second act to ISSCC during February in San Francisco. ISSCC is a formal academic research paper presentation … Read more
Nvidia Q2 FY23 results
Nvidia reported revenue for the second quarter ending July 31, 2022, of $6.7 billion, up 3% from a year ago and down 19% from the previous quarter. GAAP earnings per diluted share for the quarter were $0.26, down 72% from a year ago and down 59% from the previous quarter. Non-GAAP earnings per diluted share were $0.51, down 51% from … Read more
Intel claims its 2nd-gen DL Habana Gaudi2 outperforms Nvidia A100
That’s just crazy talk on Intel’s part. Nothing can beat a GPU, everybody knows that. If that weren’t true, why would Intel have invested so many millions in developing a GPU? Surely, not just for some computer project. But in December 2019, Intel acquired Habana Labs, which was founded in 2016 in Tel Aviv, Israel. At the time, Habana was … Read more
Nvidia jazzed over new research
Nvidia Research is striking a chord with its work on an inverse rendering pipeline. (Source: Nvidia) Nvidia is certainly getting into the swing of things at the Conference on Computer Vision and Pattern Recognition in New Orleans this week. At the conference, Nvidia Research is presenting a paper on what it calls 3D MoMa, an inverse rendering pipeline that … Read more
Once again Nvidia provides us with the most powerful GPU in the solar system
Mount Tiburon Testing Labs puts EVGA’s RTX 3090 Ti FTW3 Ultra Gaming AIB through its paces
Chiplets need a home—UCIe has one for them
Intel creates a universal interconnect consortium
Chiplets need a home—UCIe has one for them
Universal Chiplet Interconnect Express (UCIe) is an open specification that defines the interconnect between chiplets within a package, enabling an open chiplet ecosystem and ubiquitous interconnect at the package level. Forming an open industry standard organization around UCIe are Advanced Semiconductor Engineering (ASE), AMD, Arm, Google Cloud, Intel, Meta, Microsoft, Qualcomm, Samsung, and TSMC. The feasibility of implementing complex systems … Read more