NVIDIA DGX-2, the fastest path to AI scale on a whole new level

DGX-2 faster, more scalability

Today’s business needs to scale-out AI, without scaling-up cost or complexity

  • Powered by DGX software
  • Accelerated AI-at-scale deployment and effortless operations
  • Unrestricted model parallelism and faster time-to-solution

The DGX-2 builds on its predecessor DGX-1 in several respects, but features a new, revolutionary NVSwitch with 300 GB/s chip-to-chip communication at 12 times PCIe speed. With NVLink2, sixteen GPUs with a total width of 14 TB/s can be combined into a single GPU.
With two Xeon CPUs, 1.5 TB RAM and 30 TB NVMe memory, the DGX-2 consumes ~ 10KW, weighs a little less than 159 KG and offers a computing power of ~2 PFLOPs per single system when using the tensor cores.

DGX-2 one of a kind, going beyond the norm

Unbeatable Compute power for unprecedented training

AI is getting increasingly complex and demands unprecedented levels of compute power. NVIDIA® DGX-2 packs the power of 16 of the world’s most advanced GPUs to accelerate new AI model types that were previously untrainable. Plus, it enables groundbreaking GPU scalability, so you can train 4X bigger models on a single node with 10X the performance of an 8-GPU system.

DGX-2 unified memory

Unified Memory

  • Single memory view shared by all GPUs
  • Automatic migration of data between GPUs
  • User control of data location/usage

DGX-2 NVMe SSD Storage

Rapidly ingest the largest datasets into cache:

  • Faster than SATA SSD, optimized for transferring huge datasets
  • Dramataically larger user scratch space
  • The protocol of choice for next-gen storage technologies
  • 8x 3.84TB NVMe in RAID0 (DATA)
  • 25.5 GB/sec Sequential Read bandwidth (vs 2GB/sec for 7TB of SAS SSDs on DGX-1)

DGX-2 Latest generation CPU and 1.5TB system memory

Faster, more resilient, boot and storage management:

  • More system memory to handle larger DL and HPC
  • 2x Intel Skylake Xeon Platinum 8168 - 2.7GHz, 24 cores
  • 24x 64GB DIMM System Memory

DGX-2 The ultimate in networking flexibility

Grow your DL cluster effortlessly, using the connectivity you prefer:

  • Support for RDMA over COnverged Ethernet (ROCE)
  • 8 EDR Infiniband 100GbE
  • 1600 Gb/sec Total Bi-directional Bandwidth with low-latency
  • Also supports Ethernet mode: Dual 10/25 Gb/sex

DGX-2 Part overview

DGX, a common software stack for all systems

One Software stack for the whole DGX family

  • Single, unified stack for deep learning frameworks
  • Predictable execution across platforms
  • The protocol of choice for next-gen storage technologies
  • Pervasise reach Support for RDMA over Converged Ethernet (ROCE)


Optimized Stacks for every Cloud

  • Various use cases like HPC, Deep Learning, Gaming and Analytics
  • All usable for free
DGX-2 @ sysGen More Info @ NVIDIA

Related Posts

Building an Enterprise-grade HPC and AI...

#gpu #ai #appliance #datacenter #hpc #nvidia-rtx #nvidia-tesla #storage 04.04.2020


#gpu #ai #bigdataanalytics #datacenter #hpc #nvidia-tesla 04.04.2020

GPU accelerated Applications and their...

#gpu #ai #cluster #datacenter #nvidia-rtx #nvidia-tesla #workload 04.04.2020