IBM Research has developed a mixed-signal analog chip for AI inferencing that it claims may be able to match the performance of digital counterparts such as GPUs, while consuming considerably less power.published last week in Nature Electronics. It uses a combination of phase-change memory and digital circuits to perform matrix–vector multiplications directly on network weights stored on the chip.
IBM’s chip follows an approach called analog in-memory computing , using phase-change memory cells to store the weights as an analog value and also perform computations. The digital components are made up of a row of eight global digital processing units that provide additional digital post-processing capabilities needed when processing networks with convolutional and long short-term memory layers.
The paper also demonstrates how the chip achieves the near-software-equivalent inference accuracy, said to be 92.81 percent on the CIFAR-10 image dataset.