Administrator Guide

ManualsBrandsDell ManualsConverged InfrastructureEnterprise Solution Resources

Direct from Development

Server and Infrastructure

Engineering

NVIDIA GPU & Dell EMC

Server Recommendations by Workload

PowerEdge servers support various NVIDIA GPU models. Each model is

designed to accelerate demanding applications by acting as a powerful

assistant to the CPU. It is vital to understand which GPUs and PowerEdge

products work best together to enable breakthrough performance for an

intended workload. This paper will compare four popular NVIDIA GPUs on the

market today, as shown in Figure 1, as well as educate Dell EMC customers on

PowerEdge servers and specific workloads best suited for each GPU.

1. Quadro RTX 6000 & 8000

The latest additions to the

NVIDIA datacenter roadmap

are the RTX 6000 and 8000.

The Quadro RTX 6000/8000

will best accelerate

performance graphics,

render farms and Edge

computing. In addition to

having high CUDA core

counts, memory speeds and

floating-point performances,

these GPUs have unique

features that make them

ideal for graphics, such ray

tracing cores and NVLINK

capability for supporting large

memory capacities.

It is important to remember that the workload dictates which server to choose for best results. The RTX 6000/8000

supports high-performance graphics workloads and optimizing this type of workload will require sourcing as many GPUs

as possible into datacenter racks. For this

reason, we recommend the DSS8440 as a first

option, as it can support up to 10 GPUs, with the

R740 and R7525 as second options, which are

commonly used compute nodes in render farms.

Tech Note by

Matt Ogle

Ramesh Radhakrishnan

Summary

The NVIDIA product portfolio

includes GPU models to

address different use cases and

applications. Deciding which

GPU model and Dell EMC

server to purchase based on

intended workloads can become

very complex for customers

looking to leverage GPU

acceleration.

Workload categories that

leverage GPUs to improve

application performance and

achieve better TCO include

compute intensive use cases

like AI training and inference,

High-Performance Computing

(HPC) and Database Analytics.

VDI, rendering and ray tracing

are use cases that leverage the

graphical computing capability

of GPUs.

This DfD will educate Dell EMC

customers on four popular

NVIDIA GPU models and how-

to best pair them to PowerEdge

servers based on the intended

workload.

Supported Workloads: Graphics, Render Farms, Edge Computing Training,

AI Inference, IVA, VDI, Video Analytics

Recommended Workloads: Graphics, Render Farms, Edge Computing

Recommended PowerEdge Servers: DSS8440, R740, R7525

Figures 2 & 3 – RTX 6000 (left) and RTX 8000 (right)

specifications

Figure 1 – Table comparing popular NVIDIA GPU specifications

GPU Model

CUDA

Cores

Single

Precision

(FP32)

Mixed Precision

(FP16/FP32)

Double

Precision

(FP64)

Memory Size /

Bus

Memory

Bandwidth

Power

Consumption

RTX6000 4608 15 TFLOPS 120 TFLOPS N/A 24GB GDDR6 624 GB/s 250W

RTX8000 4608 15 TFLOPS 120 TFLOPS N/A 48GB GDDR6 624 GB/s 250W

T4 2560 8.1 TFLOPS 65 TFLOPS N/A 16GB GDDR6 300 GB/s 70W

V100 (PCIe) 5120 14 TFLOPS 112 TFLOPS 7 TFLOPS 32GB HBM2 900 GB/s 250W

V100 (SXM2) 5120 15.7 TFLOPS 125 TFLOPS 7.8 TFLOPS 32GB HBM2 900 GB/s 300W

V100S 5120 16.4 TFLOPS 130 TFLOPS 8.2 TFLOPS 32GB HBM2 1134 GB/s 250W

M10 2560 5 TFLOPS N/A N/A 32GB GDDR5 332 GB/s 225W

Summary of content (3 pages)

PAGE 1
Direct from Development Server and Infrastructure Engineering NVIDIA GPU & Dell EMC Server Recommendations by Workload Tech Note by Matt Ogle Ramesh Radhakrishnan Summary The NVIDIA product portfolio includes GPU models to address different use cases and applications. Deciding which GPU model and Dell EMC server to purchase based on intended workloads can become very complex for customers looking to leverage GPU acceleration.
PAGE 2
. Tesla T4 The Tesla T4 will best accelerate AI inference, training, general-purpose compute applications and graphics. The T4 introduced the Turing Tensor Core technology with multi-precision computing ranging from FP32/FP16 for floating point arithmetic to INT8/INT4 integer precision capability to handle diverse workloads.
PAGE 3
4. Tesla M10 The M10 will best accelerate Virtual Desktop Infrastructure (VDI) and mainstream graphics applications. This legacy GPU has maintained popularity with customers due to its large 32GB memory capacity and affordable price point, giving it a compelling TCO for VDI and mainstream graphics. For VDI applications, we suggest running the M10 on a PowerEdge server that has enough CPU cores, memory and PCIe cores to support a large number of virtual desktop users, such as the R7425.