Imagination Announces First PowerVR Series2NX Neural Network Accelerator Cores: AX2185 and AX2145
Figure 5 from 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
A 17–95.6 TOPS/W Deep Learning Inference Accelerator with Per-Vector Scaled 4-bit Quantization for Transformers in 5nm | Research
Are Tera Operations Per Second (TOPS) Just hype? Or Dark AI Silicon in Disguise? - KDnuggets
TOPS, Memory, Throughput And Inference Efficiency
Figure 1 from 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