inference

Groq Tensor Streaming Processor Delivers 1 PetaOPS of Compute

Architectures November 15, 2019 0

AI startup Groq makes an initial disclosure of their Tensor Streaming Processor (TSP); a single chip capable of 1 petaOPS or 250 teraFLOPS of compute.

Intel Announces Keem Bay: 3rd Generation Movidius VPU

Neural Processors November 12, 2019 0

Intel announces Keem Bay, its 3rd-generation Movidius VPU edge inference processor.

Intel Spring Hill: Morphing Ice Lake SoC Into A Power-Efficient Data Center Inference Accelerator

Architectures Hot Chips 31 Neural Processors October 20, 2019 5

First detailed at Hot Chips 31, Intel Spring Hill morphs the Ice Lake SoC into a highly power-efficient data center inference accelerator.

Analog AI Startup Mythic To Compute And Scale In Flash

Architectures Neural Processors October 6, 2019 0

A look at the IPU architecture of analog AI startup Mythic which attempts to significantly reduce the power consumption by computing directly in analog in flash.

Alibaba Launches DC Inference Accelerators

Architectures Neural Processors September 28, 2019 0

Alibaba launches its own homegrown inference accelerator for their own cloud.

Inside Tesla’s Neural Processor In The FSD Chip

Architectures Hot Chips 31 Neural Processors September 22, 2019 0

A deep dive into the custom-designed Tesla neural processing units integrated inside the company’s full self-driving (FSD) chip based on the Tesla Hot Chips 31 talk.

Nvidia Inference Research Chip Scales to Dozens of Chiplets

Architectures Interconnects Neural Processors VLSI 2019 June 30, 2019 0

Nvidia recently presented a research chip comprising dozens of chiplets that enables them to scale from milliwatts to hundreds of watts in order to cater to different markets such as edge, mobile, automotive, and data center.

Intel’s Spring Crest NNP-L Initial Details

Architectures Neural Processors April 14, 2019 0

An initial look into Intel’s upcoming Nervana Neural Network Processor (NNP) accelerators.

Hot Chips 30: Nvidia Xavier SoC

Architectures Floorplanning Hot Chips 30 September 8, 2018 0

An overview of the Xavier SoC which was detailed by Nvidia at Hot Chips 30.

Cambricon Reaches for the Cloud With a Custom AI Accelerator, Talks 7nm IPs

Neural Processors May 26, 2018 0

Cambricon has announced their first high-performance and high-power AI accelerator for the data center in an effort to gain market share in the growing Chinese AI market.