KubeFlux: An HPC scheduler plugin for Kubernetes
Claudia Misale, Daniel Milroy
KubeCon + CloudNativeCon EU 2022
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.
Claudia Misale, Daniel Milroy
KubeCon + CloudNativeCon EU 2022
Burkhard Ringlein, Thomas Parnell
Ray Summit 2024
Pravein Govindan Kannan, Brent Salisbury, et al.
arXiv
Haoran Qiu, Weichao Mao, et al.
USENIX ATC 2024