Architectures – WikiChip Fuse

Architectures Neural Processors

Samsung-Esperanto Concept AI-SSD Prototype

November 21, 2021November 21, 2021 David Schor AI-SSD, ASPLOS, ASPLOS 2021, Esperanto, Facebook, Samsung

Esperanto demonstrates a concept AI-SSD prototype in collaboration with Samsung aimed at accelerating data center workloads such as recommendation engines.

Architectures Desktop Processors

Intel Launches 12th Gen Core Desktop Alder Lake Processors

October 27, 2021November 3, 2021 David Schor 10 nm, 12 Generation Core, Alder Lake, Core i5, Core i7, Core i9, Intel, Intel 7

Intel launches 12th Gen Core desktop processors based on the Alder Lake microarchitecture.

Architectures Server Processors

Alibaba Open Source XuanTie RISC-V Cores, Introduces In-House Armv9 Server Chip

October 20, 2021October 20, 2021 David Schor 5 nm, Alibaba, Apsara Conference 2021, ARM, ARMv9, Panjiu, RISC-V, T-Head, TSMC, Xuantie, Yitian 710

Alibaba open-source its high-performance XuanTie RISC-V Cores; introduces a new in-house Armv9 server chip

Architectures Neural Processors

Intel Introduces 2nd Gen Neuromorphic Research Chip: Loihi 2 on Intel 4 EUV Process

September 30, 2021September 30, 2021 David Schor Intel 4, Kapoho Point, Lava, Loihi, Loihi 2, neuromorphic chip, Oheo Gulch

Intel introduces Loihi 2, its second-generation neuromorphic research chip. First chip fabricated on their Intel 4 EUV process, Loihi 2 brings faster processing and synaptic operations, new algorithm support, and increases the neurons count to 1 million.

Architectures Neural Processors Packaging Subscriber Only Content

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.

Architectures Data Processing Unit Subscriber Only Content

YouTube Accelerates Transcoding

August 21, 2021August 21, 2021 David Schor accelerator, ASPLOS 2021, google, H.264, subscriber only (general), video acceleration, Video Coding Unit (VCU), VP9, YouTube

Google accelerates YouTube and other video services with custom silicon.

Architectures Server Processors

Intel Unveils Sapphire Rapids: Next-Generation Server CPUs

August 19, 2021August 19, 2021 David Schor Advanced Matrix Extension (AMX), AVX-512, Golden Cove, Intel, Intel 7, Sapphire Rapids, x86

Intel unveiled Sapphire Rapids, its next-generation server CPUs

Architectures Data Processing Unit Desktop Processors Mobile Processors

Intel’s Gracemont Small Core Eclipses Last-Gen Big Core Performance

August 19, 2021August 21, 2021 David Schor Alder Lake, Gracemont, Intel, Intel 7, Tremont, x86

Intel’s Gracemont small core eclipses last-generation Skylake big core performance and energy efficiency

Architectures Desktop Processors Mobile Processors

Intel Unveils Alder Lake: Next-Generation Mainstream Heterogeneous Multi-Core SoC

August 19, 2021August 19, 2021 David Schor Alder Lake, DDR5, Golden Cove, Gracemont, Intel, Intel 7, LPDDR5x, PCIe 5.0, x86

Intel unveiled Alder Lake, the company’s next-generation mainstream heterogeneous multi-core SoC for mobile through desktop

← Previous