Inaccel presented the new version of the scalable accelerators for Apache Spark on October 2nd at Xilinx's premier event XDF in San Jose. The new version of the ML accelerators for Apache Spark are scalable to a high number of FPGA nodes without and it is fully integrated with Spark. The new version of the accelerators in the cloud allows up to 3x speedup and 2x lower OpEx compared to contemporary processors.
Check the presentation from Inaccel at XDF in the following link:
InAccel raises $600,000 seed round from Marathon Venture Capital to accelerate cloud workloads using FPGAs.
Athens, Greece (July 5, 2018) - InAccel Inc. (https://www.inaccel.com/), provider of FPGA accelerators on the cloud, announces today the completion of a $600,000 seed investment round by Marathon Venture Capital (https://marathon.vc/). InAccel will use the investment to accelerate product development and distribution of its flagship products across public cloud vendors.
Emerging applications like data analytics, machine learning, and genomics are extremely computationally intensive and require a large amount of processing power. To face this challenge, warehouse data centers and cloud providers have recently started to adopt the use of hardware accelerators. Hardware accelerators, e.g. Field-Programmable Gate Arrays (FPGAs), speed up application processing and reduce energy consumption in data centers. Tech titans, in the likes of Amazon, IBM, Intel, Baidu and Alibaba, have been using FPGAs internally for some time and are now proceeding to host hardware accelerators in their marketplaces, in the form of Intellectual Property (IP) cores.
“Big data analytics and machine learning are crucial to the success of a company, however, associated costs are skyrocketing and computation intensive algorithms are too slow in typical processors”, said Chris Kachris, co-founder and CEO at InAccel. “Our mission is to boost the performance of mission-critical algorithms with the use of FPGAs in the public cloud. The use of cloud accelerators can help companies speed up their applications to gain a competitive advantage, and also to significantly reduce related operational expenses.”
Chris Kachris has over 17 years of experience in the field of FPGAs. He started at FPGA-pioneer Xilinx (NASDAQ:XLNX) and continued his research in Athens Information Technology (AIT), FORTH (CARV) and the Microlab of the National Technical University of Athens (NTUA). The founding team also consists of NTUA graduates and researchers Elias Koromilas and Ioannis Stamelos. InAccel has already deployed its first accelerators via the AWS Marketplace.
“InAccel is riding the wave of the proliferation of FPGAs, driven by their availability in public clouds, and the fast adoption of industry-wide algorithms in popular open-source computation frameworks, like Apache Spark.”, said Panos Papadopoulos, partner at Marathon Venture Capital. “The company wants to become the default solution for running FPGAs on the public cloud, and we look forward to accelerating its potential.”
InAccel’s mission is to boost the performance of mission-critical algorithms with the use of FPGAs in the public cloud. Its first products include high performance accelerators for Machine Learning workloads - running on Apache Spark - based on novel FPGA engines available on the new AWS FPGA instances (F1). For more information, contact email@example.com.
About Marathon Venture Capital
Marathon Venture Capital (https://marathon.vc) is an early-stage venture capital fund, helping ambitious founders build world-class technology companies. Its latest investments are Cube Revenue Management, Landoop, and Norbloc. Marathon partners’ track record includes Bugsense, Taxibeat, Workable and Resin.io, among others. For more information, contact firstname.lastname@example.org.