번역 위젯 여러 언어로이 블로그의 영어 버전의 번역을 촉진 하기 위하여 당신의 편의 위해 제공 됩니다.. 이 자동된 번역 기능을 활용 하려는 경우, 자동된 번역 원래 영어 버전 간의 편차가 있을 수 있습니다 이해 하시기 바랍니다. IBM 같은 자동된 번역 편차에 대 한 책임을 지지 않습니다 및 번역된 버전 제공 "그대로" 어떠한 종류의 보증 없이.
IBM POWER9는 여기! 기업 AI에 가장 적합한 서버를 발표
This is an exciting time for IBM Business Partners and their customers, as IBM unveils its next-generation Power Systems servers incorporating its newly designed POWER9 processor. Built specifically for compute-intensive AI workloads, the new POWER9 systems are capable of improving the training times of deep learning frameworks by nearly 4x,[나는] allowing enterprises to build more accurate AI applications, faster.
Say hello to the new POWER9 processor-based server
This is game-changing technology. The new POWER9-based AC922 Power Systems are the first to embed PCI-Express 4.0, next-generation NVIDIA NVLink and OpenCAPI, which combined can accelerate data movement, calculated at 9.5x[II] faster than PCI-E 3.0-based x86 systems.
The system was designed to drive demonstrable performance improvements across popular AI frameworks such as Chainer, TensorFlow and Caffe, as well as accelerated databases such as Kinetica. 결과적으로, data scientists can build applications faster, ranging from deep learning insights in scientific research to real-time fraud detection and credit risk analysis.
Meet the best server for enterprise AI
Enterprise AI requires a new breed of servers. Servers that enable the cutting-edge AI innovation data scientists desire, with the dependability IT requires. IBM Power Systems AC922 offers the fastest way to deploy accelerated databases and deep learning frameworks—with enterprise-class support.
Educate yourself and take this offering to your customers and prospects today
Help your customers access hidden data that will enable them to leap ahead of their competition. Get started by understanding this new trailblazing technology and become that trusted advisor that can help your customers fully exploit artificial intelligence to unleash business insights.
In addition to a rich set of sales enablement assets in IBM SmartSeller, we have two education modules in IBM PartnerWorld University. The first is an introduction to the new IBM Power Systems AC922 with POWER9 processor-based technology. The second takes the discussion to a more technical level. Take the time to familiarize yourself with the next big step forward for enterprise AI, and take this offering out to your customers and prospects.
2018 will be an exciting year as IBM rolls out the rest of the POWER9 family of Power System servers. Get started today with this first POWER9 offering:
IBM은 항상 고객이 디지털 전환을 가속화 돕는 데 관심 신규 및 기존 비즈니스 파트너를 찾고 있습니다. 당신은 질문이 있거나 추가 정보를 원하시면, 에서 IBM 담당자 밖으로 나 나에게 도달 주시기 바랍니다 [email protected]. 또한 내가 당신이 의견은 아래의 기능을 사용하여 생각을 알려 주시기 바랍니다.
밥 신선한 (@bobfriske)
글로벌 채널 마케팅 매니저, IBM 전원 시스템
[나는] Results of 3.8x are based on IBM internal measurements running 1,000 iterations of Enlarged GoogleNet model (mini-batch size=5) on Enlarged Imagenet Dataset (2240×2240). Power AC922; 40 코어 (2 x 20c chips), POWER9 with NVLink 2.0; 2.25 GHz의, 1024 GB 메모리, 4xTesla V100 GPU; Red Hat Enterprise Linux 7.4 for Power Little Endian (POWER9) with CUDA 9.1/ CUDNN 7. 경쟁 스택: 2x Xeon E5-2640 v4; 20 코어 (2 X 10C 칩)/40 스레드; 인텔 제온 E5-2640의 V4; 2.4 GHz의; 1024 GB 메모리, 4xTesla V100 GPU, 우분투 16.04 with CUDA .9.0/ CUDNN 7. Software: IBM Caffe with LMS Source code https://github.com/ibmsoe/caffe/tree/master-lms
[II] POWER9 and next-generation NVIDIA NVLink peak transfer rate is 150 GB/sec = 48 lanes x 3.2265625 GB/sec x 64 bit/66 bit encoding. x86 PCI Express 3.0 (x16) peak transfer rate is 15.75 GB/sec = 16 lanes x 1GB/sec/lane x 128 bit/130 bit encoding.