Covering Scientific & Technical AI | Saturday, November 2, 2024

MLPerf Training 3.0 Showcases LLM; Nvidia Dominates, Intel/Habana Also Impress

As promised, MLCommons added a large language model (based on GPT-3) to its MLPerf training suite (v3.0) and released the latest round of results yesterday. Only two chips took ...Full Article

Cerebras Builds ‘Exascale’ AI Supercomputer

Cerebras is putting down stakes to be a player in the AI cloud computing with a supercomputer called Andromeda, which achieves over an exaflops of “AI performance.” The company ...Full Article

Nvidia Introduces New Ada Lovelace GPU Architecture, OVX Systems, Omniverse Cloud

In his GTC keynote today, Nvidia CEO Jensen Huang launched another new Nvidia GPU architecture: Ada Lovelace, named for the legendary mathematician regarded as the first computer programmer. The ...Full Article

Cerebras Proposes AI Megacluster with Billions of AI Compute Cores

Chipmaker Cerebras is patching its chips – already considered the world’s largest – to create what could be the largest-ever computing cluster for AI computing. A reasonably sized “wafer-scale ...Full Article

Groq Designs Chip that Hands Over Controls to Software

Groq has deconstructed the conventional CPU, and designed its chip in which software takes over control of the chip. The Groq Tensor Streaming Processor Architecture follows a growing trend ...Full Article

Intel Gives a Name to Data Center GPUs for Cloud Gaming and AI

Intel has been hyping up its media delivery and cloud gaming GPUs codenamed Arctic Sound-M, and has given a formal name: Flex Series GPUs. The Flex Series GPUs will ...Full Article

Microsoft Azure Adds Ampere Arm-based Virtual Machines

Further evidence of the blossoming diversity of architectures offered in the cloud arrived this week with the news that Ampere Altra Arm-based processors have been added to Microsoft’s Azure ...Full Article

Nvidia Reportedly Backing Away From its Proposed $40B Arm Acquisition

For GPU-maker Nvidia, it was not supposed to end this way, with the company giving up on its grandiose plans to acquire chip IP vendor, Arm Ltd. But after ...Full Article

Ceremorphic Touts Its HPC Silicon Technology for Supercomputing and Exits Stealth

In a market still filling with fledging silicon chips, Ceremorphic, Inc. has exited stealth and is telling the world about what it calls its patented new ThreadArch multi-thread processor ...Full Article

Are the Wheels Falling Off on the Nvidia-Arm Deal?

Nvidia’s 14-month-long, $40 billion proposal to acquire chip IP vendor Arm has hit another potential regulatory roadblock after being hit with two earlier challenges in Europe since October. This ...Full Article
Page 1 of 2812345...1020...Last »
AIwire