Power-aware Deep Learning Model Serving with µ-Serve
Haoran Qiu, Weichao Mao, et al.
USENIX ATC 2024
Power ISA™ Version 3.1 has introduced a new family of matrix math instructions, collectively known as the Matrix-Multiply Assist (MMA) facility. The instructions in this facility implement numerical linear algebra operations on small matrices and are meant to accelerate computation-intensive kernels, such as matrix multiplication, convolution and discrete Fourier transform. These instructions have led to a power- and area-efficient implementation of a high throughput math engine in the future POWER10 processor. Performance per core is 4 times better, at constant frequency, than the previous generation POWER9 processor. We also advocate the use of compiler built-ins as the preferred way of leveraging these instructions, which we illustrate through case studies covering matrix multiplication and convolution.
Haoran Qiu, Weichao Mao, et al.
USENIX ATC 2024
Dionysios Diamantopoulos, Burkhard Ringlein, et al.
CLOUD 2023
Matthew Jones, Yuji Watanabe, et al.
Red Hat Summit 2024
Jose Santos, Chen Wang, et al.
IEEE TNSM