Fastdata.io’s FDIO Engine Leverages NVIDIA GPUs to Provide the Fastest Real-time Stream Processing of Big Data-in-Motion
SANTA MONICA, Calif., March 27, 2018 - Fastdata.io, a real-time stream processing company, today announced the launch of its high performance computing software, FDIO Engine™, the first GPU-native software, which exploits the massively parallel processing capability of NVIDIA GPUs to provide real-time stream processing of big data in motion.
FDIO Engine is the world’s fastest and most efficient stream processing software to meet the critical and growing need for efficient, real-time big data processing. FDIO is the first data processing engine to execute more than 80% of its operations on GPUs. Fastdata.io will exhibit and demo its FDIO Engine at the NVIDIA GPU Technology Conference on March 26-29 in San Jose.
By processing complex algorithms against terabytes of live streaming data, FDIO Engine will:
- Accelerate stream processing up to 1,000 times faster than any CPU-based software.
- Cut total real-time data processing costs more than 70%.
- Run Apache Spark Structured Streaming workloads without any recoding required.
- Reduce power and space requirements more than 98% in the data center whether running in the public cloud or on private servers. This new level of efficiency will save billions of dollars in power costs while tremendously reducing greenhouse emissions.
“Traditional batch data processing which used to take weeks or days, has been reduced to minutes or even subsecond with FDIO Engine,” said Alen Capalik, CEO and founder of fastdata.io. “The rapidly evolving power of NVIDIA GPU technology, combined with FDIO Engine, provides the ability to leverage real-time data for business intelligence, more efficiently than ever before, and opens endless opportunities for growth and new revenue.”
FDIO Engine offers unmatched efficiency and cost savings, allowing new applications to truly exploit data processing at the speed of thought for the first time. This paradigm shift, from traditional batch processing where you must store data before processing to true real-time processing where you can process data before deciding to store it, will open exciting new possibilities for application development in industries that need real-time stream processing like finance, security, ad-tech, telecom, cloud, AI, Internet of Things, autonomous vehicles, and robotics.
NVIDIA’s GPU Ventures invested early into fastdata.io as it recognized the importance of bringing real-time stream processing capability into the GPU-accelerated analytics ecosystem. As FDIO Engine is the first software to natively run on Apache Arrow, the GPU Data Frame format of the GPU Open Analytics Initiative (GOAI), fastdata.io is paving the way for faster and highly efficient data communication between GPU-based analytic software solutions.
“Leveraging NVIDIA's GPU-based platform, fastdata.io’s FDIO Engine processes data in motion with unprecedented speed and efficiency, transforming the ways businesses can produce intelligence and interact with their customers,” said Jim McHugh, vice president and general manager of Deep Learning Systems at NVIDIA. “Businesses are exploring many innovative ways to implement FDIO Engine to develop breakthrough analytics and AI technologies and grow new revenue from real-time data processing.”
Fastdata.io is led by CEO and founder Alen Capalik, an industry veteran who has significant expertise directing low-level kernel development for high-frequency trading financial systems and advanced cybersecurity technology.
Fastdata.io has developed the world’s fastest and most efficient stream processing software engine. Leveraging general-purpose computing on graphics processing units, fastdata.io has developed its FDIO Engine™, a high performance computing software engine, to exploit the massively parallel processing capability of NVIDIA’s GPU platform. The FDIO Engine scales stream processing potentially up to three orders of magnitude faster, while simultaneously cutting power and space requirements in the data center by more than 98%. The company was founded in 2016 by Alen Capalik. Fastdata.io is headquartered in Santa Monica, California with offices in Seattle, Washington. For more information, visit http://fastdata.io/