The heterogeneous computing technology is evolving rapidly in the field of big data and AI in recent years. To cope with this technology revolution, Alibaba Cloud Heterogeneous Computing has made great achievements in both product type and application.
Pan Yue, a senior product expert of Alibaba Cloud, made an in-depth presentation on Alibaba Cloud Heterogeneous Computing in the era of big data and AI at the Computing Conference Shenzhen summit on the morning of March 29, 2018.
Pan Yue introduced that Alibaba Cloud provides a wide range of "heterogeneous acceleration platforms for multiple scenarios", including GA1 instance (AMD S7150) for graphic and image rendering, GN5 (Tesla P100) instance for AI training and reasoning, GN5i (Tesla P4) instance for AI reasoning and video transcoding applications and GN6 (Tesla V100) instance for advanced computational capabilities in the fields of AI and high-performance computing, and multiple FPGA instances for image transcoding, genetic computing, and database acceleration. GN6 instance is specifically designed for deep learning training and high-performance computing. With Tesla V100 in the latest NVIDIA Volta architecture, GN6 instance delivers 12X higher computing performance Tesla P100 (the previous generation), solving the outstanding problems for engineers and experts. GN6 (Tesla V100) is now available for public beta and will be coming soon.
Alibaba Cloud has been and will be always professional and precise towards issues related to heterogeneous products. Most people may choose Pascal-Based Tesla P40 as the GPU because of its higher single-precision floating-point capability, which is 12 teraFLOPS (TFLOPS) while only 10.6 TFLOPS for Tesla P100, according to the product manuals. However Alibaba Cloud performed tests in different scenarios and methods and found that the performance of Tesla P100 is 20% higher in AI application. Here are the test results:In the main forum at the Computing Conference Shenzhen, Alibaba Cloud and NVIDIA reached an agreement to enhance their cooperation in the GPU ecosystem, including the setup and promotion of NVIDIA Deep Learning Institute (DLI) at Alibaba Cloud University and NGC container images, a new feature released for AI.
NGC is a deep learning ecosystem developed by NVIDIA, which allows developers to access the deep learning software stack for free and to establish a development environment suitable for deep learning. The developers can get various NGC software from the Alibaba Cloud marketplace, including Caffe, Caffe2, CNTK, MXNet, TensorFlow, Theano, and Torch.
FPGA is getting the recognition of the public and applied in the general computing field from the special computing field. Alibaba Cloud FPGA as a Service is an FPGA heterogeneous computing service that supports the mainstream FPGA platforms. It is designed as a systematic platform with uniform interfaces for computing capability output under the premise of ensuring cloud security.
It provides an integrated cloud development environment for more FPGA engineers to develop products on the cloud. Alibaba Cloud is still making use of the strengths of Alibaba and her partners to establish and improve an FPGA ecosystem with a view to serve more customers with better FPGA computing capabilities.
Currently, Alibaba Cloud FPGA as a Service can be found in image transcoding and compression, database acceleration, genetic computing, and other fields.
Alibaba Cloud heterogeneous platform for elastic computing aims to provide high-quality products and services, help organizations to realize scientific and technological innovation, and make computing and AI a true inclusive technology in a secure and stable environment.