Scaling the “Memory Wall” for Multi-Dimensional Seismic Processing with Algebraic Compression on Cerebras CS-2 Systems

Abstract
We exploit the high memory bandwidth of AIcustomized Cerebras CS-2 systems for seismic processing. By leveraging low-rank matrix approximation, we fit memoryhungry seismic applications onto memory-austere SRAM waferscale hardware, thus addressing a challenge arising in many wave-equation-based algorithms that rely on Multi-Dimensional Convolution (MDC) operators. Exploiting sparsity inherent in seismic data in the frequency domain, we implement embarrassingly parallel tile low-rank matrix-vector multiplications (TLRMVM), which account for most of the elapsed time in MDC operations, to successfully solve the Multi-Dimensional Deconvolution (MDD) inverse problem. By reducing memory footprint along with arithmetic complexity, we fit a standard seismic benchmark dataset into the small local memories of Cerebras processing elements. Deploying TLR-MVM execution onto 48 CS-2 systems in support of MDD gives a sustained memory bandwidth of 92.58PB/s on 35, 784, 000 processing elements, a significant milestone that highlights the capabilities of AIcustomized architectures to enable a new generation of seismic algorithms that will empower multiple technologies of our lowcarbon future.

Acknowledgements
For computer time, this research used the resources of the Ibex NVIDIA GPU cluster of the Supercomputing Laboratory (KSL) at King Abdullah University of Science and Technology (KAUST) in Thuwal, Saudi Arabia and the Condor Galaxy-1 CS-2 cluster provided by G42.

Publisher
ACM/IEEE

Conference/Event Name
ACM/IEEE International Conference for High Performance Computing, Networking, Storage, and Analysis (SC'23)

Permanent link to this record