Introducing the Intel® Server System D50TNP Family

One powerful and flexible HPC platform. Limitless HPC and AI possibilities.

Extraordinary performance, capacity and versatility—combined with four distinct, purpose-built modules for compute, management, storage, and acceleration—make the Intel® Server System D50TNP Family the easy server choice for your HPC and AI workloads.

Compute performance is delivered by 3rd Gen Intel® Xeon® Scalable processors—with up to 40%1 higher performance than the previous generation. The new accelerator module supports up to four 300W PCIe accelerator cards. And the storage module provides high-speed storage with up to 1PB capacity in a single 2U chassis.

Read the solution brief ›

Introducing the Intel® Server System D50TNP Family

Key Features

  • 3rd Gen Intel® Xeon® Scalable processors: Deliver outstanding per-core performance, with up to 40 cores per processor. Delivers up to 40% higher performance (SPECrate2017_int_base) versus previous generation.1
  • Intel® Deep Learning Boost: Accelerate AI inferencing, enabling you to run those workloads on versatile, general-purpose processors without compromise.
  • Up to 3 Intel® Ultra Path Interconnects (Intel® UPI): Accelerate I/O between processors versus previous generation.
  • Up to 3200 MT/s throughput with up to 2TB of DRAM capacity per module.
  • Intel® Optane™ persistent memory 200 series enables up to 2 TB of additional memory capacity per module and provides an average of 25%2 higher memory bandwidth versus the first generation.
  • Up to one 500TB of high-performance NVMe storage per storage module.
  • High-speed networking and I/O: Accelerate network throughput between cluster nodes with high-throughput Intel® Omni-Path, ethernet, and InfiniBand support. PCIe 4.0 support delivers extraordinary data throughput for storage and networking.
  • Hardware-enhanced security: Help protect against malicious exploits and accelerate data encryption with built-in security features, while maintaining workload integrity with reduced performance overhead.

Product and Performance Information

1

40% higher performance (SPECrate2017_int_base): Configuration: SPEC CPU2017, memory at 3200 MT/s, 3rd Gen Intel® Xeon® Scalable processors compared to prior generation of Intel® Xeon® Scalable processors. 3rd Gen Intel® Xeon® Scalable processor SKUs ending in (H) or (L) are not supported. For more complete information about performance and benchmark results, visit www.intel.com/benchmarks.

2

Average of 25% higher memory bandwidth vs prior gen: Baseline: 1-node, 1x Intel® Xeon® 8280L 28C @ 2.7GHz processor on Neon City with Single PMem module config (6x32GB DRAM; 1x{128GB,256GB,512GB} Intel Optane PMem 100 Series module at 15W) ucode Rev: 04002F00 running Fedora 29 kernel 5.1.18-200.fc29.x86_64, and MLC ver 3.8 with App-Direct. Source: 2020ww18_CPX_BPS_DI. Tested by Intel, on 27 Apr 2020. New configuration: 1-node, 1x Intel® Xeon® pre-production CPX6 28C @ 2.9GHz processor on Cooper City with Single PMem module config (6x32GB DRAM; 1x{128GB,256GB,512GB} Intel Optane PMem 200 Series module at 15W), ucode pre-production running Fedora 29 kernel 5.1.18-200.fc29.x86_64, and MLC ver 3.8 with App-Direct. Source: 2020ww18_CPX_BPS_BG. Tested by Intel, on 31 Mar 2020.