In the era of big data, deep learning is the main driving force of artificial intelligence. Research company Gartner pointed out that by 2018, 80% of data scientists will integrate deep learning into their toolkits. The success of machine learning and artificial intelligence projects need more than just Relying on data and algorithms also requires integration of skills, infrastructure, and business recognition.
Accelerating Cloud founder and CEO Yu Gang said: 'Artificial intelligence has entered our lives, but there are still bottlenecks in the future development, and we need breakthroughs in hardware technology and algorithms. Heterogeneous computing is the future trend of computing architecture, while FPGAs are different implementations. The perfect choice for structured computing. Heterogeneous computing accelerates cloud innovation Accelerated platform solutions, with high performance, high efficiency, low latency and programmability and remote reconfigurability, are ideally suited to the needs of resilient services in the cloud. We hope that through our technology, we can help more companies achieve deep learning and win opportunities in the era of big data.
Accelerating Cloud's four major products are: Two series of hardware acceleration products (SC-OPS, SC-VPX), two IP libraries (FDNN, FBLAS), three solutions (deep learning solution, high performance computing And Digital Signal Processing Solutions, Edge Computing Solutions).
Product introduction: • SC-OPS is the world's first Intel Stratix 10 FPGA accelerator card from Accelerated Cloud. It uses Intel's latest 14nm process Stratix10 GX2800 FPGA device, which can be widely used in data centers, cloud computing, machine vision, deep learning, high Performance calculation, simulation, finance and other fields.
• SC-VPX is the world's highest computational density VPX blade acceleration platform. It uses Intel Stratix 10 GX2800 devices and is compatible with GX1650. It is the industry's most advanced, flexible, efficient signal processing and deep learning architecture. It mainly locates radars in universities and other institutions. Communication, rapid prototyping and algorithm development and application in deep learning related fields.
• Deep Learning Acceleration Library FDNN is the first FPGA acceleration library supporting general convolutional neural network in China. Based on RTL level code, it can provide high performance and flexible configuration features. High Performance Computing Acceleration Library FBLAS is the industry's higher performance RTL Grade math acceleration library.
Solution Description • Deep Learning Acceleration Solution - Accelerated Cloud introduced a complete set of FPGA-based deep learning acceleration solutions, including SC-OPM/SC-OPF/SC-OPS Accelerator Card and FDNN Acceleration Library to meet customers' high performance in deep learning. Flexibility requirements are accelerated. In order to facilitate the use of high-level language development, Accelerated Cloud provides a complete OpenCL heterogeneous development environment based on FPGA, and quickly implements user-defined deep learning acceleration solutions. At the same time, Accelerating Cloud also provides fast and deep neural network customization and acceleration services.
• Digital Signal Processing Solutions - Requirements for digital signal processing systems such as radar and communications, combined with Intel's latest 14nm process Stratix 10 FPGA family, Accelerated Cloud provides a complete solution combining hardware and software to achieve high performance Matrix operations (matrix multiplication, transposition, inversion, QR decomposition) and ultra-fast FFT (Fourier transform). To facilitate high-level language development for customers, Accelerated Cloud provides a complete FPGA-based OpenCL heterogeneous development environment for rapid user customization. The signal processing acceleration program.
• Edge Computing Solution - Accelerated Cloud Intelligent Industrial Control Solution adopts high-performance Intel Arria 10 GX660 devices with modular design, strong real-time features and high performance algorithm IP acceleration, complete OpenCL heterogeneous development environment, enabling next-generation high performance Edge computing gateways, used in various industrial environments.
'Accelerating new technologies, driving the wisdom of the future' was held on April 17-27, 2018. It not only accelerated the new product launch of the cloud, but also attracted the participation of many key industry players and organizations, including Intel, Cytech, Tencent, JD, U.S. Group, Kingsoft, HKUST, Lenovo, Sogou, UESTC, Tsinghua University, Beijing University of Science and Technology, Chinese Academy of Sciences Institute of Computing, etc., have become important in accelerating the future prospects of heterogeneous computing with customers and industry leaders. Summit.