Electronics | Free Full-Text | Accelerating Neural Network Inference on FPGA-Based Platforms—A Survey | HTML
Imagination Announces First PowerVR Series2NX Neural Network Accelerator Cores: AX2185 and AX2145
Sticker: A 0.41-62.1 TOPS/W 8Bit Neural Network Processor with Multi-Sparsity Compatible Convolution Arrays and Online Tuning Acceleration for Fully Connected Layers | Semantic Scholar
Nuit Blanche: A 2.9 TOPS/W Deep Convolutional Neural Network SoC in FD-SOI 28nm for Intelligent Embedded Systems (and a Highly Technical Reference page on Neural Networks in silicon.)
A 617-TOPS/W All-Digital Binary Neural Network Accelerator in 10-nm FinFET CMOS | Semantic Scholar
VeriSilicon's Neural Network Processor IP Embedded in Over 100 AI Chips | Business Wire
Summary of benchmarks. GOPS for each neural network is estimated under... | Download Table
Atomic, Molecular, and Optical Physics | Department of Physics | City University of Hong Kong
A Deep Dive into AI Chip Arithmetic Engines - Semiconductor Digest
When “TOPS” are Misleading. Neural accelerators are often… | by Jan Werth | Towards Data Science
A 0.11 pJ/Op, 0.32-128 TOPS, Scalable Multi-Chip-Module-based Deep Neural Network Accelerator Designed with a High-Productivity VLSI Methodology | Research
As AI chips improve, is TOPS the best way to measure their power? | VentureBeat
Renesas Electronics Develops New Processing-In-Memory Technology for Next-Generation AI Chips that Achieves AI Processing Performance of 8.8 TOPS/W | Renesas
PDF] A 3.43TOPS/W 48.9pJ/pixel 50.1nJ/classification 512 analog neuron sparse coding neural network with on-chip learning and classification in 40nm CMOS | Semantic Scholar
TOPS, Memory, Throughput And Inference Efficiency
Are Tera Operations Per Second (TOPS) Just hype? Or Dark AI Silicon in Disguise? - KDnuggets
Synchronous firing activities of the coupling neural network with... | Download Scientific Diagram
TOPS, Memory, Throughput And Inference Efficiency
VLSI 2018] A 4M Synapses integrated Analog ReRAM based 66.5 TOPS/W Neural- Network Processor with Cell Current Controlled Writing and Flexible Network Architecture
When “TOPS” are Misleading. Neural accelerators are often… | by Jan Werth | Towards Data Science
PowerVR Series3NX is a powerful follow up to our successful Series2NX
Sticker: A 0.41-62.1 TOPS/W 8Bit Neural Network Processor with Multi-Sparsity Compatible Convolution Arrays and Online Tuning Acceleration for Fully Connected Layers | Semantic Scholar
Not all TOPs are created equal. Deep Learning processor companies often… | by Forrest Iandola | Analytics Vidhya | Medium
後藤弘茂のWeekly海外ニュース】iPhone Xの深層学習コア「Neural Engine」の方向性 - PC Watch
Mipsology Zebra on Xilinx FPGA Beats GPUs, ASICs for ML Inference Efficiency - Embedded Computing Design