General computing, heterogeneous computing, collaborative computing, edge computing and other diversified product layout
PR4904P1, the new generation of high-density AI accelerated computing server, is mainly used in the fields of enterprise virtualization, automatic reasoning, deep learning and high-performance computing. With GPU taking part in the heavy and time-consuming code, it can accelerate the application running on CPU, helping you to complete more computing tasks, process larger data sets and shorten the application running time.
PR4904P1 is suitablefor the mainstream 32-bit and 64-bit HPC applications at present, mainly aimingat the applications in traditional HPC fields such as bio-informatics,computational chemistry, computational finance, computational fluid dynamics,computational architecture, data science, security monitoring, electronicdesign automation, perception and computer vision, machine learning, medicalimaging, numerical analysis, weather and climate, etc.
As a new application field, Deep Learningis the hot point of machine learning in recent years, and it has madebreakthrough progress in the fields of image and voice recognition. It makesthe combination of big data and deep neural network model, parallelizes thedata or deep network model in GPU cluster to accelerate the program executionefficiency. Using GPU to accelerate deep learning and train deep learningnetwork can give full play to the efficient parallel computing capability ofthousands of computing cores of GPU. In the case of massive data trainingscenarios, it is characterized by shorter time and fewer occupied servers. It hasbecome the preferred solution in this field and is widely used in the Internetindustry that using GPU cluster as infrastructure to build deep learning/machinelearning platform.
With the use of GPU in the field of highperformance computing, CPU is no longer the only choice for computing chips. Comparedwith CPU, GPU has more powerful computing power (at present, NVIDIA's latestV100 has 5,120 CUDA cores and 640 Tensor cores), with simper task processingmode. Now it is gradually applied to various fields of high-performancecomputing, helping the Internet industry to develop rapidly. With its powerfulcomputing power, GPU attracts users to use GPU to improve the executionefficiency of applications. At the same time, GPU also has the advantages oflow cost, high performance and low power consumption, which reduces the overallcost of ownership of users.
| Model | PR4904P1 |
|---|---|
| Form Factor | 4U Rack/Tower Server |
| Processors | Up to 2 x 2nd Generation Intel® Xeon® Scalable Processor Family（3 UPI up to 10.4GT/s）; Dual Socket P (LGA 3647) |
| Chipsets | Intel® C621 Series Chipsets |
| Memory | Up to 16 x DDR4 ECC 3DS LRDIMM 4TB Max Intel® Optane™DCPMM optional Specifications supported: 128GB/64GB/32GB/16GB/8GB per memory module with low voltage of 1.2V Supports RDIMM of 2933/2666/2400/2133MHz (The working frequency of memory will also change with different CPU and the number of memory per channel.) |
| Disk Bays | Up to 8 x 3.5”Hot-Plug SAS/SATA drivers SATA controller on Motherboard, providing 8 x SATA3 (6Gbps) ports and supporting RAID 0, 1, 5, 10 Optional: supports SAS RAID 0, 1, 10, 5, 50, 6, 60, etc. Optional: power-down protection for cache data; 1GB/2GB (cache) |
| I/O Ports | Rear ports: 2x 10 GE RJ45 network port, compatible with GE, incompatible with FE(Fast Ethernet) network ports Rear ports: IPMI 2.0 RJ45 management network port Rear ports: 2 x USB 3.0 Rear ports: 2 x USB 2.0 Rear ports: 1 x VGA Rear ports: 1 x cluster communication port |
| PCIEexpansion | 6 X 16 slot PCIe Gen3 ( in x 16), double wide 1 x 4 slot PCIe Gen3 (in x 8) Supports up to 4 professional graphics cards or accelerator cards; Optional: SAS RAID, HBA, HCA and HFI cards. |
| GraphicsCards | integrated graphics chips |
| Pro Graphics Card | Optional: NVIDIA Quadro® graphics cards (Note 1: The adaptability test of software and application is required before adding more than one pro graphic card.) (Note 2: Only professional graphics cards of the same model and specification are supported within one system) |
| Accelerator cards | Optional: NVIDIA Tesla accelerator cards, Supports the CPU of up to 145W when the operating environment is not higher than 35℃ Optional: NVIDIA Grid Virtualization Authorization Supports the CPU of up to 145W when the operating environment is not higher than 30℃ Optional: Intel Phi Supports the CPU of up to 145W when the operating environment is not higher than 30℃ (Note 1: The adaptability test of software and application is required to make sure the adaptation of various accelerator cards.) |
| Fans | 4 x Heavy-duty Fans, 4 x Exhaust Fans Dual Heatsink Fans with adaptive wind speed control |
| Power Supplies | 1600W/2000W Redundant Power Supply 220 V (AC) 50-60Hz |
| External Equipment | Optional: Chassis Slide Rail Optional: USB keyboards and mouses |
| Supported Operating Systems | Windows Server 2016 Linux OS: Redhat 7.3 (Note 1: The compatibility of operating system is effected by system configuration. For detailed component compatibility information, please refer to the PowerLeader product compatibility list) (Note 2: For the latest driver of special graphics card, please refer to the website support information related to the selected graphics card) |
| Environmental Specifications | 10–35°C (50–95°F) while operating; -40 - 55°C(-40 - 135°F) while in storage. 8%~90% relative humidity while operating 5%~95% relative humidity while in storage (non-condensing) |
| Dimensions | 462mm(height)×178mm(width)×673mm(depth) |
| Net Weight | 21kg |
| Vibration | Vibration frequency: 5Hz～150Hz Acceleration:≤20m/s2 Amplitude (of vibration):≤0.15mm |
| Impact | Peak acceleration:150m/s2～300m/s2 ; lasting time:≤11ms |
| Collision | Peak acceleration:100m/s2～150m/s2 ; times: within 1000 |
PowerLeader Server
PowerLeader Ziqiang
4008-870-872
Click Inquire