Sandia LabNews

Sandia, Intel seek novel memory tech to support stockpile mission


MAXIMIZED MEMORY — A Sandia team is collaborating with Los Alamos and Lawrence Livermore national labs and Intel Federal LLC to optimize DRAM packages, pictured here and found in many consumer laptops, to increase compute platform performance. (Photo by Craig Fritz)
MAXIMIZED MEMORY — A Sandia team is collaborating with Los Alamos and Lawrence Livermore national labs and Intel Federal LLC to optimize DRAM packages, pictured here and found in many consumer laptops, to increase compute platform performance. (Photo by Craig Fritz)

In pursuit of novel advanced memory technologies that would accelerate simulation and computing applications in support of the nation’s stockpile stewardship mission, Sandia, in partnership with Los Alamos and Lawrence Livermore national labs, has announced a research and development contract awarded to Intel Federal LLC, a wholly owned subsidiary of Intel Corp.

Sponsored by the NNSA’s Advanced Simulation and Computing program, the three national labs will collaborate with Intel Federal on the project.

“ASC’s Advanced Memory Technology research projects are developing technologies that will impact future computer system architectures for complex modeling and simulation workloads,” said program director Thuc Hoang. “We have selected several technologies that have the potential to deliver more than 40 times the application performance of our forthcoming NNSA exascale systems.”

Sandia project lead James Laros said, “This effort will focus on improving bandwidth and latency characteristics of future memory systems, which should have a direct impact on application performance for a wide range of ASC mission codes.”

Anil Rao, vice president and general manager of Intel’s Systems Architecture and Engineering group, said, “We are already anticipating what future platform challenges must be solved for the next generation. We believe the Advanced Memory Technology program will help us generate support for the next decade of innovation.”

SMARTER PREDICTIONS — Developed at Sandia, a high-fidelity simulation of the hypersonic turbulent flow over a notional hypersonic flight vehicle, colored grey, depicts the speed of the air surrounding the body, with red as high and blue as low. The turbulent motions that impose harsh, unsteady loading on the vehicle body are depicted in the back portion of the vehicle. Accurately predicting these loads are critical to vehicle survivability, and for practical applications, billions of degrees of freedom are required to predict physics of interest, inevitably requiring massive computing capabilities for realistic turnaround times. The work conducted as part of the contract awarded to Intel Federal LLC aims to improve memory performance that can greatly benefit mission applications like this one. (Simulation by Cory Stack)
SMARTER PREDICTIONS — Developed at Sandia, a high-fidelity simulation of the hypersonic turbulent flow over a notional hypersonic flight vehicle, colored grey, depicts the speed of the air surrounding the body, with red as high and blue as low. The turbulent motions that impose harsh, unsteady loading on the vehicle body are depicted in the back portion of the vehicle. Accurately predicting these loads are critical to vehicle survivability, and for practical applications, billions of degrees of freedom are required to predict physics of interest, inevitably requiring massive computing capabilities for realistic turnaround times. The work conducted as part of the contract awarded to Intel Federal LLC aims to improve memory performance that can greatly benefit mission applications like this one. (Simulation by Cory Stack)

Intel Fellow Josh Fryman said, “We are rethinking fundamental aspects of how DRAM — dynamic random-access memory — is organized and coupled with compute platforms for breakthrough performance. We intend to fundamentally advance computer system architecture by studying the hardest problems from scientists at Sandia, Lawrence Livermore and Los Alamos national laboratories. Mainstream memory isn’t designed for today’s compute platforms, and this multiyear effort will help us to extract orders-of-magnitude performance gains from the basic DRAM design itself – thus enabling a new class of performance across all industry segments. We hope to see these innovations pushed into industry standards to lift the entire ecosystem.”

The new contract is part of NNSA’s post-Exascale-Computing-Initiative investment portfolio, which seeks to sustain the technology research and development momentum, and strong engagement with industry that the initiative had started via its PathForward program. It aims to foster a more robust domestic high-performance computing ecosystem by increasing U.S. industry competitiveness in next-generation technologies.

“Intel and the ASC program have a long history of partnering to explore new technologies for our HPC system deployments. The project with Intel being announced today will provide important improvements in memory technologies that can support our production workloads,” said Simon Hammond, federal program manager for the Advanced Simulation and Computing Computational Systems and Software Environments program.

“Investing in technologies that have the potential to increase the efficiency of our ASC mission applications is critically important in support of our stockpile stewardship mission,” said Robert Hoekstra, senior manager of the extreme scale computing group at Sandia. “This collaboration shows great promise in supporting our future mission goals.”

Recent articles by Neal Singer