The Arm Machine Learning processor provides up to 4.6 Trillions of Machine Learning Operations Per Second in a mobile power enveloppe, as part of the Project Trillium, Arm’s Machine Learning (ML) platform, enables a new era of advanced, ultra-efficient inference at the edge with Programmable layer engines for future-proofing, Highly tuned for advanced geometry implementations, Specifically designed for ML and neural network (NN) capabilities, the architecture is versatile enough to scale to any device, from IoT to connected cars and servers.
Built from the ground up for optimal performance and efficiency, Project Trillium completes the Arm Heterogenous ML compute platform with the Arm ML processor, the second-generation Arm Object Detection (OD) processor and open-source Arm NN software.
The Arm Machine Learning processor consists of state-of-the-art optimized fixed-function engines that provide best-in-class performance within a constrained power envelope. Additional programmable layer engines support the execution of non-convolution layers, and the implementation of selected primitives and operators, along with future innovation and algorithm generation. The network control unit manages the overall execution and traversal of the network and the DMA moves data in and out of the main memory. Onboard memory allows central storage for weights and feature maps, thus reducing traffic to the external memory and therefore, power.
