neural processors

Inside PFN’s AI Processor And The World’s Most Power-Efficient Supercomputer

September 20, 2021September 20, 2021 David Schor neural processors, Preferred Networks, subscriber only (general), Supercomputers

[Subscriber Content] Inside Preferred Networks’ AI processor and the world’s most power-efficient supercomputer it powers.

Architectures Hot Chips 33 Linley Processor Conference Neural Processors

A Look At Qualcomm’s Data Center Inference Accelerator

September 12, 2021September 13, 2021 David Schor 7 nm, Cloud AI 100, Hot Chips, Hot Chips 33, Linley Processor Conference, neural processors, Qualcomm

A look at Qualcomm’s Data Center Inference Accelerator, the Cloud AI 100.

Neural Processors

Mythic Rolls Out M1000-Series Analog AI Accelerators; Raises $70M Along The Way

August 22, 2021August 22, 2021 David Schor 40 nm, analog, Analog Compute Engine (ACE), Analog Matrix Processor (AMP), eFlash, embedded flash, Mythic, neural processors

Mythic rolls out its 1000-series true analog AI accelerators; raises $70M along the way

Neural Processors Subscriber Only Content

Inside Baidu’s In-House Neural Processor

July 11, 2021July 12, 2021 David Schor 14 nm, 14LPP, 2.5D packaging, Baidu, HBM, Kunlun, neural processors, subscriber only (general)

A peek inside Baidu’s in-house neural processor

Architectures Manycore Processors

A Look At The ET-SoC-1, Esperanto’s Massively Multi-Core RISC-V Approach To AI

July 10, 2021August 2, 2021 David Schor 7 nm, Esperanto, ET-Maxion, ET-Minion, ET-SoC-1, neural processors, RISC-V, TSMC

A look at Esperanto’s ET-SoC-1, the startup’s first AI inference accelerator for the data center. The company took a unique RISC-V approach with a massively multi-core chip with nearly 1,100 custom-designed CPU cores.

Architectures Neural Processors

Arm Launches the Cortex-M55 and Its MicroNPU Companion, the Ethos-U55

February 10, 2020May 25, 2021 David Schor ARM, Arm Ethos, Cortex, Cortex-M55, inference, neural processors

Arm launches two new IPs for deeply-embedded AI: the Cortex-M55 with the new M-Profile Vector Extension (Helium), and the Ethos-U55, an ultra-low-power dedicated NPU for embedded applications.