Trailblazing Supercomputer Will Enable Scientists And Engineers To Optimize Its Hardware To Support Groundbreaking Research

Backed by a multi-million-dollar federal grant, a research team from three major universities will soon start working on a pioneering supercomputing system that allows scientists and engineers to align its processors, accelerators, memory and other hardware components to best serve their needs.

This innovative system will operate increasingly complex levels of software while sidestepping the hardware bottlenecks that often hinder high-level computations. This system will let researchers perform calculations and solve problems that current supercomputers cannot handle.

On Oct. 1, 2021, researchers from Texas A&M University, the University of Illinois Urbana-Champaign (UIUC) and the Texas Advanced Computing Center (TACC) at The University of Texas at Austin (UT Austin) will begin collaborating on a prototype for what they call the Accelerating Computing for Emerging Sciences (ACES) system.

The National Science Foundation (NSF) will provide $5 million for ACES’s development and an additional $1 million per year over five years to pay for system operation and support.

Texas A&M Interim Vice President for Research Jack Baldaulf expressed gratitude to the NSF for its substantial investment in the ACES project. “We are thankful to NSF for the opportunity to lead such an important initiative and to our Texas A&M HPRC staff and collaborators at UT Austin and UIUC for making this a successful effort,” Baldauf said. “Computational science is critical to our national needs and the ACES platform will not only advance research but also help educate the future workforce in this area.”

The team’s goal is to develop an all-inclusive system that will serve researchers across a wide range of scholarly disciplines and computer skills, according to Honggao Liu, executive director of Texas A&M’s High Performance Research Computing (HPRC) and the project’s principal investigator.

These disciplines include artificial intelligence and machine learning, cybersecurity, health population informatics, genomics and bioinformatics, human and agricultural life sciences, oil-and-gas simulations, new-materials design, climate modeling, molecular dynamics, quantum-computing architectures, imaging, smart and connected societies, geosciences and quantum chemistry.

“The ACES system will support the national research community through coordination systems supported by the NSF,” Liu said. “In this way, the ACES system will provide invaluable support to cutting-edge projects across a broad spectrum of research disciplines in the nation. ACES will also leverage HPRC’s efforts that promote science and broaden participation in computing at the K-12, collegiate and professional levels to have a transformative impact nationally by focusing on training, education and outreach.”

Researchers should think of ACES as a cyber-buffet, said Timothy M. Cockerill, director of user services, TACC at UT Austin, and a co-principal investigator on the ACES project. “They’ll be able to essentially build the custom environment they require on a per job basis and not be constrained to the contents of a physical server node,” Cockerill said.

ACES will open new avenues to scientific advancement, said Shaowen Wang, head of the Department of Geography and Geographic Information Science, professor at UIUC and a co-principal investigator on the ACES project. “Exciting advances on many science frontiers will become possible by harnessing the hybrid computing resources and highly adaptable framework offered by ACES to enable increasingly complex scientific workflows driven by geospatial big data and artificial intelligence,” Wang said.

Also serving as co-principal investigators are Lisa M. Perez, associate director for advanced computing enablement, and Dhruva Chakravorty, associate director for user services and research, both from HPRC at Texas A&M.

Research that generates breakthrough discoveries will require highly advanced computer designs that can meet the challenge, Texas A&M Senior Associate Vice President for Research Costas N. Georghiades said. “With the increasing complexity of computational problems in the big-data era we live in, it is no longer sufficient to use traditional supercomputers which rely only on optimizing the software,” Georghiades said. “The ACES system will also be able to adapt hardware resources on the fly to tackle complex computational tasks more efficiently. Texas A&M is proud to lead this effort in collaboration with our university partners at UT Austin and Illinois.”

Technical description

ACES leverages an innovative composable framework via PCIe (Peripheral Component Interconnect Express) Gen5 on Intel’s upcoming Sapphire Rapid (SPR) processors to offer a rich accelerator testbed consisting of Intel Ponte Vecchio (PVC) GPUs (Graphics Processing Units), Intel FPGAs (Field Programmable Gate Arrays), NEC Vector Engines, NextSilicon co-processors and Graphcore IPUs (Intelligence Processing Units).

The accelerators are coupled with Intel Optane memory and DDN Lustre storage interconnected with Mellanox NDR 400Gbps InfiniBand to support workflows that benefit from optimized devices. ACES will allow applications and workflows to dynamically integrate the different accelerators, memory and in-network computing protocols to glean new insights by rapidly processing large volumes of data and provide researchers with a unique platform to produce complex hybrid programming models for effectively supporting calculations that were not feasible before.

About Research at Texas A&M University: As one of the world’s leading research institutions, Texas A&M is at the forefront in making significant contributions to scholarship and discovery, including science and technology. Research conducted at Texas A&M generated annual expenditures of more than $1.131 billion in fiscal year 2020. Texas A&M ranked in the top 25 of the most recent National Science Foundation Higher Education Research and Development survey based on expenditures of more than $952 million in fiscal year 2019. Texas A&M’s research creates new knowledge that provides basic, fundamental, and applied contributions resulting in economic benefits to the state, nation, and world. research.tamu.edu