KAUST and Cerebras Named Gordon Bell Award Finalist for Solving Multi-Dimensional Seismic Processing at Record-Breaking Speeds
September 20 2023 - 12:00PM
Business Wire
Run on Condor Galaxy 1 AI Supercomputer, seismic processing
workloads achieve application-worthy accuracy at unparalleled
memory bandwidth, enabling a new generation of seismic
algorithms
King Abdullah University of Science and Technology (KAUST),
Saudi Arabia’s premier research university, and Cerebras Systems,
the pioneer in accelerating generative AI, announced that its
pioneering work on multi-dimensional seismic processing has been
selected as a finalist for the 2023 Gordon Bell Prize, the most
prestigious award for outstanding achievements in HPC. By
developing a Tile Low-Rank Matrix-Vector Multiplications (TLR-MVM)
kernel that takes full advantage of the unique architecture of the
Cerebras CS-2 systems in the Condor Galaxy AI supercomputer, built
by Cerebras and their strategic partner G42, researchers at KAUST
and Cerebras achieved production-worthy accuracy for seismic
applications with a record-breaking sustained bandwidth of 92.58
PB/s, highlighting how AI-customized architectures can enable a new
generation of seismic algorithms.
“In partnership with KAUST researchers, we are honored to be
recognized by Gordon Bell for setting a new record in what is
possible for multi-dimensional seismic processing. This work will
unlock world-changing advancements across climate and weather
modeling, computational astronomy, wireless communication, seismic
imaging and more,” said Andrew Feldman, co-founder and CEO of
Cerebras Systems. “This is the third year in a row that Cerebras,
alongside its partners, has been selected as a finalist for the
distinguished Gordon Bell Prize, and we plan to continue delivering
groundbreaking innovations in the years to come.”
Seismic applications are vital in shaping our understanding of
Earth's resources and can accelerate the world toward a low-carbon
future. Seismic processing of geophysical data collected from the
Earth's subsurface enables us to identify buried hydrocarbon
reservoirs, drill for oil with greater accuracy, and optimize for
CO2 sequestration sites by identifying potential leakage risks.
Modern seismic processing techniques are computationally
challenging because they require repeated access to the entire
collection of multi-dimensional data. This problem, commonly known
as time-domain Multi-Dimensional Deconvolution (MDD), has become
tractable thanks to compression techniques that relax the inherent
memory and computational burden, such as Tile Low-Rank
Matrix-Vector Multiplication (TLR-MVM).
Researchers at KAUST and Cerebras approached this problem by
re-designing the TLR-MVM algorithm to take advantage of Cerebras’
CS-2 system, which exhibits high memory throughput to deliver high
performance for intrinsically memory-bound applications. Cerebras
CS-2 contains 850,000 AI compute cores and 40GB of SRAM on-chip and
is ideal for problems that are memory bottlenecked and can be
heavily parallelized. The re-designed TLR-MVM algorithm was tested
on an openly available 3D geological model and ran on 48 Cerebras
CS-2 systems in the Condor Galaxy AI supercomputer, which was built
by Cerebras and their strategic partner G42. Researchers reported
accurate responses at a sustained bandwidth of 92.58 PB/s. This is
3x faster than the aggregated theoretical bandwidth of Leonardo or
Summit, two of the world’s current top five supercomputers.
Additionally, this result resembles the estimated upper bound
(95.38 PB/s) for Frontier, another top-five supercomputer, at a
fraction of the energy consumption. TLR-MVM running on Cerebras
systems achieved a steady low power consumption of 36.50GFlops per
watt, which compares favorably with the 52GFlops per watt of
Frontier. These results indicate that production-grade seismic
applications can achieve top five supercomputer performance on
Cerebras CS-2s at a fraction of the cost and energy
consumption.
Researchers re-designed the TLR-MVM algorithm using
communication-avoiding principles that favor local SRAM data motion
over cross-fabric communications. Researchers mapped the new
TLR-MVM algorithm onto the disaggregated memory resources and
extracted the desired high-memory bandwidth to deliver
unprecedented processing capabilities for enhancing the imaging of
seismic data acquired in complex geology. This was done using the
Cerebras SDK, which offers lower-level programmatic access to the
Cerebras CS-2.
"Disaggregated memory requires fine-grained algorithmic
innovations,” said lead author Hatem Ltaief, Principal Research
Scientist of KAUST's Extreme Computing Research Center (ECRC),
expressed his excitement with the research achievement. “Working
with Cerebras engineers to deploy them and extract the hardware's
full potential was a dream."
ECRC Director David Keyes added, “It is exciting to discover the
versatility of wafer-scale hardware beyond neural network training
for which it was conceived and optimized. We join other examples of
such architectural crossover in Gordon Bell Prize history.”
Other KAUST co-investigators include Professor Matteo Ravasi of
Earth and Environmental Sciences and Engineering and 2023 KAUST
Computer Science PhD graduate Yuxi Hong, who now exercises his HPC
skills in Lawrence Berkeley National Laboratory’s Exascale
Computing Program.
Performing TLR-MVM has been challenging for traditional
hardware. It requires significant computational power and yields
slow processing times, even on modern supercomputers. Additionally,
TLR-MVMs require large amounts of memory to store intermediate
results and matrices, which challenges the limitations of
traditional CPU and GPU hardware. Finally, TLR-MVMs need to be
heavily parallelized to achieve industrial-grade performance. While
GPUs are normally well-suited for parallel processing, they are
unsuitable in this application because their limited support for
batched execution reduces the practical efficiency of TLR-MVM with
real-world complex precision and variable ranks. The work conducted
by KAUST and Cerebras validates the Cerebras CS-2 as a viable
alternative that can achieve record-breaking performance for
historically memory-bound applications.
More information on this multi-dimensional seismic processing
workload can be found at
https://repository.kaust.edu.sa/handle/10754/694388. This research
was made possible by G42’s grant of system time on the Condor
Galaxy 1 AI supercomputer.
About King Abdullah University of Science and Technology
(KAUST)
Established in 2009, KAUST is a graduate research university
devoted to finding solutions for some of the world’s most pressing
scientific and technological challenges in the areas of food and
health, water, energy, environment, and the digital domain. The
University brings together the best minds and ideas from around the
world with the goal of advancing science and technology through
distinctive, collaborative research. KAUST is a catalyst for
innovation, economic development and social prosperity in Saudi
Arabia and the world. Visit www.kaust.edu.sa to learn more.
About Cerebras Systems
Cerebras Systems is a team of pioneering deep learning
researchers, computer architects, and solutions specialists of all
types. We have come together to bring generative AI to enterprises
and organizations of all sizes around the world. Our flagship
product, the CS-2 system, powered by WSE-2, the world’s largest and
fastest AI processor, makes training large models simple and easy,
by avoiding the complexity of distributed computing. Our software
tools simplify the deployment and training process, providing deep
insights and ensuring best in class accuracy. Through our team of
world-class ML researchers and practitioners who bring decades of
experience developing and deploying the most advanced AI models, we
help our customers stay on the cutting edge of AI. Cerebras
solutions are available in the cloud, through the Cerebras AI Model
Studio or on premise. For further information, visit
https://www.cerebras.net.
View source
version on businesswire.com: https://www.businesswire.com/news/home/20230920255837/en/
PR Contact: Anna Sikora pr@zmcommunications.com