|Dimensions||2000μm x 2000μm|
|Power||245 mw @1.2V 25C|
Residual network ACcelerator leveraging extended bit-plane COmpressiON (Raccoon) is a ternary weight CNN accelerator with integrated compression for both the ternary weights and the feature maps. For compressionddd EBPC (extended bit plane compression) that forces a minimum spatial resolution to be compressed which deviates from the more traditional convolutional acceleration which typically output a single pixel at once.
RACCOON has taken the ResNet architecture as reference and features 3x3 convolution, 1x1 convolution, stride two, residual skip-connections, batch normalization and Rectified Linear Unit (ReLU) activation.
An I/O compression ratio of 1.45 for ResNet-34 feature maps has been achieved. Core energy effiency has been determined to be 2.54 TOp/s/W at 1.2 V & 25C and device energy efficiency is at an estimated 1.24 TOp/s/W.