On November 29, 2019, Huawei and Peng Cheng Laboratory (PCL) presented together Peng Cheng Brain Cloud II Phase 1, officially launching the journey to clusters of 1000 petaFLOPS scale AI (PFLOPS). This sets a new milestone in the field of scientific research for the Kunpeng computer industry. The clusterHuawei’s IA Atlas 900 operates at the base of Cloud Brain II, powered by Huawei’s Kunpeng and Ascend processors. Atlas 900 infuses robust computing power into Cloud Brain II, supporting basic AI research and exploration such as computer vision, natural language, autonomous driving, smart transportation, and smart healthcare. The computing power of the Peng Cheng Cloud Brain is currently 100 PFLOPS, planned to scale to 1000 PFLOPS and higher next year.
“In September, Huawei embarked on the dual-engine computing strategy with Kunpeng and Ascend. Inspired by this strategy, we committed to making the computing power available to the world. We also launched Atlas 900, the AI training cluster . world’s fastest, “said Huawei Senior Vice President and Huawei Cloud & AI Products and Services President Hou Jinlong.
“Today, we are proud to see the Atlas 900 chosen for the Peng Cheng Cloud Brain II project. It lays the foundation for Cloud Brain II. Cloud Brain II is an industry-leading AI research platform. PCL has brought together many talents. AI will join PCL in leading cutting-edge scientific research into a smart world, “Hou added.
Hou further said: “We are currently developing Cloud Brain II Phase 1. I believe that with our joint effort this will pave the way for Cloud Brain II on a 1000 PFLOPS scale in the near future. We are confident that it will become the world’s leading AI research platform. ”
Huawei’s Intelligent Computing Business Department chairman Michael Ma said: “Huawei develops the Ascend processor-based AI computing platform Atlas, providing a broad portfolio of modules, boards, edge stations, AI servers and clusters . Our AI infrastructure for all scenarios covers the cloud-edge-device (cloud-edge-device), supporting the inference flow and complete training for deep learning. ”
“Our flagship Atlas product, Atlas 900, stands as the pinnacle of AI computing in the world. The combination of Atlas 900 and Cloud Brain II will embark on a new chapter for 1000 PFLOPS scale AI clusters and unleash the magnificent power of computing to drive smart transformation faster across industries, “said Ma.
The Peng Cheng Cloud Brain is an essential technological instrument in the field of AI. It is a basic research platform for exploring the frontier of AI technology. It currently boasts 100 PFLOPS AI computing power and is expected to reach the 1000 PFLOPS scale in the Cloud Brain II project next year.
Cloud Brain II is jointly built by PCL and Huawei. Operating on Huawei’s Kunpeng and Ascend processors, the Atlas 900 AI cluster provides superior computing power. PCL develops technologies for Cloud Brain in 1000 PFLOPS.
The Atlas 900 AI cluster has inherited Huawei’s technology know-how from over a decade. Composed of thousands of Ascend 910 AI processors, the Atlas 900 completes the training of a ResNet image classification model in 59.8 seconds, 10 seconds faster than the previous world record, with the same accuracy. Atlas 900’s powerful computing power makes the difference in scientific research and technological innovation, such as astronomical exploration, weather forecasting, autonomous driving and oil exploration. Atlas 900 Highlights:
- Powerful Computing: Combining thousands of Ascend 910 AI processors, the Atlas 900 delivers 256–1024 PFLOPS at half precision (FP16), which equals the computing power of 500,000 PCs. The SoC design integrates AI computing, general purpose computing. and I / O functionality to effectively improve training efficiency.
- High-speed clusternetwork : It supports three types of high-speed network interfaces: Huawei Cache Coherence System (HCCS), PCIe 4.0, and 100G RoCE, reducing gradient synchronization latency from 10% to 70% for one jump. in model training efficiency. It leverages an innovative iLossless intelligent switching algorithm to enable real-time learning and training of network-wide traffic, achieving zero packet loss and end-to-end microsecond latency.
- Complete heat dissipation: Atlas 900 uses a cabinet-level adiabatic system, achieving a net cooling coefficient of over 95% and a system power usageefficiency (PUE ) of less than 1, 1 (an ideal PUE is 1.0).
So far, based on Ascend 910 and 310 AI processors, Huawei has launched the IA Atlas 900 cluster , Atlas 800 IA server, Atlas 500 IA edge station, Atlas 300 IA accelerator card and accelerator module. IA Atlas 200. Atlas’s holistic portfolio provides powerful computing for training and inference in all cloud-edge-device scenarios.
Going forward, Huawei will continue to increase investment and innovation in infrastructure such as processors, operating systems, databases for the Kunpeng computing industry and provide AI computing to Peng Cheng Cloud Brain to together, make AI technology faster for a broader scope of applications.
Archive
- March 2024(112)
- February 2024(109)
- January 2024(95)
- December 2023(56)
- November 2023(86)
- October 2023(97)
- September 2023(89)
- August 2023(101)
- July 2023(104)
- June 2023(113)
- May 2023(103)
- April 2023(93)
- March 2023(129)
- February 2023(77)
- January 2023(91)
- December 2022(90)
- November 2022(125)
- October 2022(117)
- September 2022(137)
- August 2022(119)
- July 2022(99)
- June 2022(128)
- May 2022(112)
- April 2022(108)
- March 2022(121)
- February 2022(93)
- January 2022(110)
- December 2021(92)
- November 2021(107)
- October 2021(101)
- September 2021(81)
- August 2021(74)
- July 2021(78)
- June 2021(92)
- May 2021(67)
- April 2021(79)
- March 2021(79)
- February 2021(58)
- January 2021(55)
- December 2020(56)
- November 2020(59)
- October 2020(78)
- September 2020(72)
- August 2020(64)
- July 2020(71)
- June 2020(74)
- May 2020(50)
- April 2020(71)
- March 2020(71)
- February 2020(58)
- January 2020(62)
- December 2019(57)
- November 2019(64)
- October 2019(25)
- September 2019(24)
- August 2019(14)
- July 2019(23)
- June 2019(54)
- May 2019(82)
- April 2019(76)
- March 2019(71)
- February 2019(67)
- January 2019(75)
- December 2018(44)
- November 2018(47)
- October 2018(74)
- September 2018(54)
- August 2018(61)
- July 2018(72)
- June 2018(62)
- May 2018(62)
- April 2018(73)
- March 2018(76)
- February 2018(8)
- January 2018(7)
- December 2017(6)
- November 2017(8)
- October 2017(3)
- September 2017(4)
- August 2017(4)
- July 2017(2)
- June 2017(5)
- May 2017(6)
- April 2017(11)
- March 2017(8)
- February 2017(16)
- January 2017(10)
- December 2016(12)
- November 2016(20)
- October 2016(7)
- September 2016(102)
- August 2016(168)
- July 2016(141)
- June 2016(149)
- May 2016(117)
- April 2016(59)
- March 2016(85)
- February 2016(153)
- December 2015(150)