Powerful trinity of SQream DB, IBM POWER9 and NVIDIA Tesla GPUs achieves unprecedented performance improvements and increased throughput
NEW YORK, UNITED STATES — (October 3, 2018) – SQream, developer of SQream DB, the GPU-accelerated data warehouse for rapidly analyzing massive data stores at a fraction of the cost, announced today at the OpenPOWER Foundation Summit in Europe, that SQream DB now includes optimized support for the IBM POWER9 multi-core architecture.
The powerful trinity of SQream DB, IBM POWER9 and NVIDIA GPUs results in advanced performance, with SQL query performance improvements of up to 150% versus GPU-equipped x86 servers, with reduced cost and systems complexity.
“GPU-accelerated analytics are an increasingly important part of our industry,” said Sumit Gupta, VP of HPC and AI for IBM Cognitive Systems. “The announcement of SQream on the IBM POWER9 platform takes this concept to another level of performance, as the POWER9 CPU with embedded NVIDIA NVLink interface to NVIDIA’s GPUs allows SQream to enable even faster processing of data on POWER9 servers.”
The integration of SQream DB with IBM Power Systems is the latest in a series of collaborations between SQream and IBM, which started with SQream DB on IBM’s Bluemix service. The latest offering on IBM POWER9 takes advantage of POWER9’s industry-exclusive CPU-to-GPU high speed NVIDIA NVLink interface to offer increased throughput performance both for data loading and SQL query execution.
“Our customers are asking us for solutions that can handle massive data growth and real-time analytics to support data-driven decision making,” said Charlie Cox, President of Datatrend, an IBM Platinum and Elite Power Partner. “GPU acceleration is quite possibly one of the most important advances in helping businesses make quicker and better decisions by analyzing more data faster. IBM’s POWER9 architecture combined with SQream’s solution yields price/performance at scales we have never seen before.”
SQream DB on IBM POWER9, combined with IBM Flash Storage solutions and integrated into the technology stack, provides a reference architecture that allows organizations to perform SQL analytics for business intelligence and machine learning workloads at massive scale and speed.
“SQream DB is designed for multi-core processors such as POWER9 with its strong and robust multi-core architecture,” said Ami Gal, CEO of SQream. “As data stores increase exponentially, so does the need to process more data while reducing complexity and footprint. This joint effort with IBM provides users with a super-charged combination of IBM’s powerful processor and SQream’s DB data warehouse for unparalleled speed, performance and scale, while enabling significantly improved analytics.”
Many large enterprises and Fortune 100 companies already use IBM Power Systems, including top retailers, insurance companies, telecoms and banks. By combining NVIDIA’s market leading GPUs, together with IBM POWER9 and SQream DB, organizations can reach new levels of analytics performance while significantly reducing their environmental footprint, costs and complexity.
On October 4th, SQream will present at the OpenPOWER Foundation Summit a session entitled “Tackling the Challenges of Massive Data Analytics,” which will highlight using POWER9 as the base computing platform for significantly reducing the time of complex SQL queries while greatly increasing the amount of data analyzed.
SQream develops and markets SQream DB, a GPU data warehouse designed to enable unparalleled business intelligence from massive data stores. Global enterprises use SQream DB to analyze more data than ever before, while achieving improved performance, reduced footprint, significant cost savings and the ability to scale the amount of data they analyze to hundreds of terabytes and more. SQream DB is available both on premise and in the cloud. To learn more, visit sqream.com or follow us on Twitter @sqreamtech