Following 5G and HarmonyOS, AI computing has become Huawei's latest venture.\nAt HUAWEI CONNECT 2019, Huawei launched Atlas 900, another superstar AI product.\nAt an interview with foreign media, Mr. Ren Zhengfei, founder of Huawei, announced that Atlas 900 is the world's fastest AI platform.\n https:\/\/www.huawei.com\/en\/ \nIt takes Atlas 900 only 59.8 seconds to train a ResNet-50 model.\nWith the same precision, it is 15% faster than the second fastest product.\nKen Hu, Huawei's Deputy Chairman, said that the powerful computing is perfect for scientific research and business innovation fields, including astronomical exploration, weather forecasting, autonomous driving, and oil exploration.\nHuawei also announced that the Atlas 900 cluster services would be available to scientific research institutions and universities worldwide at a customer-friendly price.\nThe release of Atlas 900 is accompanied by Huawei's first glimpse at the computing strategy that has turned Huawei into a tech giant.\nIntegration of Thousands of AI Chips with Industry's Best Computing Power\nAtlas 900 integrates thousands of in-house developed Ascend 910 processors, another premium product by Huawei, helping to deliver 256\u20131024 PFLOPS at FP16.\n https:\/\/www.huawei.com\/en\/ \nAtlas 900 is taking the computing world by storm, and not just in test settings. For instance, for customers who used to complete an astronomical exploration task in 169 days, with Atlas 900 it takes just 10.02 seconds.\nDebuting at HUAWEI CONNECT 2018, the Ascend 910 processor was officially put into commercial use in August this year. It is the third AI training processor in the world, and the first in China.\nAscend 910 leverages the Huawei-developed Da Vinci architecture, features 7nm manufacturing process, and consumes up to 350 W of power (310 W actually tested). It is the AI processor that represents the pinnacle of computing power.\nBenchmarked against the NVIDIA Tesla V100 GPU, Ascend 910 aims to meet deep learning training scenario requirements and serve users such as AI data scientists and engineers.\n\n\n\n\nItem\n\n\nNVIDIA Tesla V100\n\n\nGoogle TPU V3\n\n\nHuawei Ascend 910\n\n\n\n\nPerformance\n\n\nDouble-precision: 7 TFLOPS; single-precision: 14 TFLOPS; half-precision: 125 TFLOPS\n\n\nHalf-precision: 105 TFLOPS (4-processor module)\n\n\nHalf-precision: 256 TFLOPS; integer precision: 512 TFLOPS\n\n\n\n\nPower consumption\n\n\n250\u2013300 W\n\n\n200 W\n\n\n350 W\n\n\n\n\nTransmission bandwidth\n\n\n32 Gbits\/s\n\n\n128 Gbits\/s\n\n\n240 Gbits\/s\n\n\n\n\nStorage\n\n\n16, 32 GB HBM2\n\n\n32 GB HBM\n\n\n16, 32 GB HBM2E\n\n\n\n\nManufacturing process\n\n\n12nm\n\n\n16\/12nm\n\n\n7nm\n\n\n\n\nInterfaces\n\n\nPCIe 3.0, NVLink\n\n\nPCIe 3.0\n\n\nPCIe 4.0, HCCS, RoCE\n\n\n\n\nDate of release\n\n\nJune 2017\n\n\nMay 2018\n\n\nMass production in 2019\n\n\n\n\nSupported frameworks\n\n\nTensorFlow, PyTorch, Caffe2, and MXNet\n\n\nTensorFlow, PyTorch\n\n\nTensorFlow, PyTorch, PaddlePaddle, Keras, ONNX, Caffe, Caffe2, and MXNet\n\n\n\n\nPrice\n\n\nUSD10,000\n\n\nOn the cloud: USD8\/hr\n\n\nN\/A\n\n\n\n\nThe preceding statistics showcases how Ascend 910 far outperforms industry counterparts.\nWith the same power consumption, Ascend 910 provides computing power twice that of V100. With faster training speed, the required training period is shorter. In typical cases, Ascend 910 doubles and even triples the computing speed of V100.\nThe release of Atlas 900 signals the completion of Huawei's computing layout, and the beginning of the complete computing strategy.\nHow will Huawei implement the solution? Now Huawei is ready to reveal the answer.\nFirst Disclosure of Huawei's Computing Strategy\nCentered on processors, Huawei's computing strategy will focus on four key areas: architecture innovation, investment in all-scenario processors, clear business boundaries, and open ecosystem.\nArchitecture innovation:\nHuawei will intensively invest in basic research, such as the Da Vinci architecture, to enable an intelligent architecture that covers all scenarios.\nInvestment in all-scenario processors:\nCurrently, Huawei has a full lineup of processors: Kunpeng (general-purpose computing), Ascend (AI), Kirin (smart devices), and Honghu (smart screens).\nThis was a conscious decision for Ken Hu and Huawei, who plan to invest more in processors because it allows Huawei to accommodate a broader range of scenarios in the future.\nClear business boundaries:\nHuawei has reaffirmed its processor business model that is designed for hardware openness, open-source software, and application development and migration.\nHowever, Huawei will not sell its processors directly. Instead, it will provide them to its customers in the form of cloud services, and to its partners in the form of components, prioritizing support for integrated solutions.\nBuilding an open ecosystem:\nOver the next 5 years, Huawei will invest another USD1.5 billion in Huawei Developer Program 2.0. The goal of this program is to support and harness the skills of 5 million developers across the globe, and enable Huawei's worldwide partners to develop intelligent applications and solutions.\nThe new strategy aims to seize new business opportunities and unleash greater potential, displaying the evolution of Huawei from a communications equipment provider to a tech giant.\nAt the beginning of his keynote speech, Hu noted that Huawei used to be known for being simply good at "connectivity" before. However, to grab the new opportunities in the intelligent era, Huawei is committed to developing intelligent industry and extending the focus from connection to computing.\n\u00a0\nInsights into the Future\nWhen launching the strategy, Hu also explained the logic and expressed his insights into the future.\nHe commented that computing oriented to machine learning has become the mainstream, as the computing model continues to evolve.\nIntelligent computing has three features: brute force computing, pervasive computing from data centers to devices, and efficient device-edge-cloud collaborative computing.\nThe ideal solution would be doing brute force computing at the central node, training general-purpose models, and enabling personalized deployment at the edge side.\nHowever, before this plan can be implemented, Huawei has to tackle many issues, including developing a new architecture that supports intelligent computing in all scenarios. This is a huge challenge to the current computing industry, and also a great opportunity.\nAccording to Gartner's report, the future computing industry is a massive market worth over USD2 trillion.\nHu regards this market as an ocean of boundless potential. To fully tap into such potential, Huawei will continue to invest intensively in computing and implement computing solutions.\nHuawei Delivers on Its Promise of Breakthrough AI Progress\nAt HUAWEI CONNECT 2019, Huawei reflected on the promises made last year.\nAt HUAWEI CONNECT 2018, Huawei launched the full-stack, all-scenario AI strategy, which has become the cornerstone of mainstream computing. However, as Hu noted then, "this is just the first step for Huawei".\nAnd that proved to be true. Since then Huawei has gone from strength to strength. Today, Hu demonstrates Huawei's achievements over the past year. The release of Ascend 910 and MindSpore this August signed the completion of Huawei's AI solution.\nTo provide a full-stack solution, Huawei has released the Ascend series IPs and processors, compute architecture for neural networks (CANN, a chip operators library and highly automated operators development toolkit) that enables processors, ModelArts that enables applications, and AI computing framework MindSpore.\nHuawei's cutting-edge products and solutions run on Ascend processors and cover all scenarios, supporting devices, edge, and cloud applications. Inference and training services are also available on HUAWEI CLOUD.\nThe Atlas series accelerator cards, modules, and servers have been a huge hit in multiple markets. Processors powered by Ascend IP cores have been applied extensively in Huawei smartphones, and have allowed customers to supercharge their business.\nAt the event, Huawei also introduces its four-step plan for general-purpose computing implementation:\nFirst, Huawei will develop competitive general-purpose computing processors.\nSecond, Huawei will continue to invest in key technologies and products, such as accelerator cards, servers, operating systems, databases, and compilers. By connecting the whole ecosystem value chain and completing system-level verification, Huawei aims to help partners better sell their integrated solutions.\nHu promised that Huawei will not cease to be the first choice for customers looking to turn digital. Huawei is a brand you can trust, and is a reliable partner with its solid progress in AI and solutions.\nHow do you like Huawei's superstar product that takes the intelligent world by storm this year?