Optimizations for Intel solutions in upcoming releases of GridGain In-Memory Computing Platform will enable performance increases of up to 100x for high-performance computing, analytics and machine learning workloads
FOSTER CITY, Calif., April 22, 2021 – GridGain® Systems, provider of enterprise-grade in-memory computing solutions powered by the Apache® Ignite® distributed database, today announced it is partnering with Intel to deliver the industry’s first in-memory computing platform to natively support vectorized computations over Intel Optane persistent memory 200 series (PMem). Early testing of the PMem support suggests GridGain Platform users can achieve an extraordinary performance increase for high-performance computing, analytics and machine learning workloads.
GridGain’s native support for Intel Optane persistent memory 200 series will enable joint customers to implement an advanced, vectorized computing architecture that uses persistent memory as a high-density, low-latency storage tier for analytical data and training data sets. Tests utilizing PMem series 200 showed up to a 10x increase in performance compared to using Intel® SSD DC P4510 Series. When combined with GridGain’s native support of SIMD instructions of Intel processors, such as AVX-512, users can expect projected performance increases of up to 100x for suitable workloads.
The Intel-specific storage engine optimizations available in the GridGain 9 In-Memory Computing Platform will include the following:
- Intel Optane persistent memory 200 series will be supported natively in the App Direct mode as a separate storage layer to enable byte-addressable access to data. (Block-level access to data in PMem is already supported in GridGain 8.)
- SIMD instructions, such as AVX-512, of contemporary Intel processors including Intel Xeon, will be supported by GridGain natively to accelerate vectorized computations over the data stored in both PMem and DRAM layers of the GridGain storage engine.
“Many years ago I was excited about the potential of DRAM as a storage layer, and once it became more affordable, we founded GridGain and accelerated digital transformation for thousands of companies that have gained 10x to 100x performance increases thanks to our in-memory computing platform,” said Nikita Ivanov, founder and CTO of GridGain Systems. “At GridGain, we relentlessly innovate new ways to add an extra 10x to 100x boost in performance for our customers. Native support in GridGain for affordable Intel Optane persistent memory combined with vectorized computations is the ultimate solution for advancing our vision and gaining that extra boost. It eliminates the need to copy data from PMem to DRAM and enables much more data to be processed within a single CPU cycle, delivering a tremendous increase in performance for financial institutions, telcos, transportation companies, animation and gaming studios, and more.”
“We are extremely pleased to be collaborating with GridGain to build native support for Intel Optane persistent memory and SIMD instructions AVX-512 into the GridGain platform,” said Alper Ilkbahar, Vice President, Data Platforms Group and General Manager, Intel Optane Group. “This is definitely a situation where the whole is greater than the sum of the parts. The extraordinary performance gained by Intel Optane persistent memory 200 series and AVX-512 instructions in combination with the GridGain In-Memory Computing Platform will help transform data processing in the industry.”
As a result of the collaboration between GridGain and Intel, the advanced architectural changes to the storage engine will be introduced in GridGain 9. Initial optimizations will support Intel Optane persistent memory 200 series and the latest 3rd Gen Intel Xeon Scalable processors.
To learn more about the Intel portfolio of products:
To learn more about the GridGain in-memory computing platform:
- Read the “Introducing the GridGain In-Memory Computing Platform” white paper
- Gain knowledge from the GridGain Developer Portal and GridGain Webinars
- See how GridGain helps CTOs & CIOs, Architects, Business Decision Makers and Developers
- Read GridGain customer success stories and industry use cases
About GridGain Systems
GridGain Systems is revolutionizing real-time data access and processing by offering an in-memory computing platform powered by the Apache® Ignite® distributed database. Common use cases for the GridGain platform include application acceleration and digital integration hubs for real-time data access across data sources and applications. GridGain solutions are used by global enterprises in financial services, software, e-commerce, retail, online business services, healthcare, telecom, transportation and other major sectors, with a client list that includes ING, Citibank, American Express, Finastra, UPS, Hewlett Packard Enterprise, Microsoft, American Airlines, Agilent and UnitedHealthcare.
GridGain delivers unprecedented speed, massive scalability, and real-time data access for both legacy and greenfield applications. Deployed on a distributed cluster of commodity servers, GridGain software can reside between the application and data layers (RDBMS, NoSQL and Apache® Hadoop®), requiring no rip-and-replace of the existing databases, or it can be deployed as a distributed database for high performance computing with in-memory speed. For more information, visit gridgain.com.
For GridGain Systems
GridGain is a trademark or registered trademark of GridGain Systems, Inc. Apache, Apache Ignite, and Ignite are trademarks of The Apache Software Foundation. Intel, the Intel logo, and other Intel marks are trademarks of Intel Corporation or its subsidiaries. All other product and company names herein may be trademarks of their registered owners.