Concept Guide

Copyright © 2020 Dell Inc. or its subsidiaries. All Rights Reserved.
Dell, EMC and other trademarks are trademarks of Dell Inc. or its subsidiaries
Direct from Development
Server and Infrastructure Engineering
1S PowerEdge R7515 has Equivalent T4 GPU
Performance to 2S PowerEdge R7425
Distinguished Next Gen AMD EPYC
TM
CPU
The launch of AMDs 2
nd
Generation EPYC
TM
(Rome) CPUs shook up the
CPU industry by refining their proprietary Zen microarchitecture to new
limits. With up to 64 cores, twice the amount of its predecessor (Naples),
AMD went above and beyond the traditional tech mold by delivering a
product truly worth of the term “next-gen”.
From a component-spec standpoint, the Rome CPU is 2x as capable as
the Naples CPU. However, Dell Technologies wanted to confirm its ability
to manage dense workloads that stress the processor. This led to various
tests executed on the PowerEdge R7515 server, which supports 1 Rome
CPU, and the PowerEdge R7425 server, which supports 2 Naples CPUs,
to record and compare the performance of each CPU generation. Object
detection, image classification and machine translation workloads were
run with the support of NVIDIA T4 GPUs assisting the CPU(s).
VDI, IVA and Inference Studies
By executing tests on both servers (Figure 2) for various workloads (Figures 3-7), two factors are examined:
1. How the R7515 (Rome) and R7425 (Naples) solutions performed across various Machine Learning
inference workloads. This accounts for the reduction of eight memory modules in the R7515 solution.
2. How NVIDIA T4 GPU performance compared between both solutions (QPS and inputs per second).
Tech Note by
Matt Ogle
Bhavesh Patel
Ramesh Radhakrishnan
Summary
The 2
nd
Gen AMD EPYC
TM
CPU is a 7nm processor
loaded with 64 threads,
making it a powerhouse for
any server. Its impressive
specs give it room for
generational growth, as its
supporting server hardware
progress to become
capable of fully utilizing it.
This DfD analyzes how one
64-core AMD CPU in a 1S
R7515 produces equivalent
T4 GPU performance to
two 32-core AMD CPUs in
a 2S R7425, and why
users looking to run ML
inference workloads should
consider utilizing this 64-
core CPU in a 1S server.
Figure 1 – AMD Rome CPU architecture graphic (large I/O die in the center
with 8 chip dies containing 8 cores bordering the I/O die)