SlideShare a Scribd company logo
1 of 10
Download to read offline
Realize 2.1X the performance
with 20% less power with AMD
EPYC processor-backed clusters
Three AMD EPYC processor-based two-processor solutions
outshined comparable Intel Xeon Scalable processor-based
solutions by handling more Redis workload transactions and
requests while consuming less power
Handle more
Redis work
Up to 2.1X the
requests per second*
*From servers with AMD EPYC 9684X processors vs. servers with Intel Xeon Platinum 8480+ processors
Processing more transactions for Redis could mean more real-time analytics,
faster retrieval of files, or caching service to reduce repetitive generative
AI computations. This advantage came from the server cluster backed
by AMD EPYC™
9684X processors, which features AMD 3D V-Cache
technology designed to help keep Redis data closer to the core.
Spend less on
data center power
Up to 20% less
power under load*
*From servers with AMD EPYC 9534 processors vs. servers with Intel Xeon Platinum 8480+ processors
The cost of energy is rising rapidly, so slashing any data center spending
could be a boon for your bottom line. In addition, consuming less
power could help advance your organization’s sustainability goals.
Use less energy to get
better performance
Up to 2X the
performance per watt*
*From servers with AMD EPYC 9684X processors vs. servers with Intel Xeon Platinum 8480+ processors
What happens when you combine better Redis performance with less
power consumption? You get a more efficient hardware cluster: more
processed transactions per watt. More efficient clusters could then
contribute to making your data center more efficient on the whole,
allowing your organization to meet performance demands with fewer
physical servers while also helping to reduce data center sprawl.
Realize 2.1X the data intensive workload performance with 20% less power with AMD EPYC processor-backed clusters May 2024 (Revised)
A Principled Technologies report: Hands-on testing. Real-world results.
Overview
When choosing processors for server clusters that run data-intensive
workloads, such as Redis, performance is often the number one
consideration. A faster processor could enable data-intensive workloads
to handle large volumes of data with low latency for responsive caching,
session storage, or real-time analytics/AI workload performance. CPU
power consumption plays a significant factor as well due to rising data
center power costs.1
We created two clusters of four worker nodes to compare Redis
performance and power consumption in three CPU scenarios. The
four worker nodes in the first cluster used 4th
Generation AMD EPYC
processors, and the four nodes in the second cluster used 4th
Gen Intel®
Xeon®
Scalable processors. All worker nodes had the same amount of
RAM on the same number of DIMMs. We installed Red Hat®
OpenShift®
to containerize the VMs running workloads for each cluster configuration.
In each test scenario, the AMD EPYC processor-based cluster supported
better performance—up to 2.1 times the requests per second (RPS).
In two of the three scenarios, the AMD EPYC processor-based cluster
consumed less power (up to 20 percent less watts) while achieving
better performance. Furthermore, each configuration of the AMD EPYC
processor-based cluster supported more RPS per watt—up to 2 times
the RPS per watt in our second scenario. These outcomes suggest that
processors from the AMD EPYC 9004 series in your servers could help
your Redis or data-intensive applications and workloads do things like
support more messages or detect fraud sooner, all while potentially saving
on data center power costs.
We tested the following processors from the EPYC family:
AMD EPYC 9534
This data center
processor has 64 cores
and 128 threads, with a
max boost clock speed
up to 3.7Ghz.2
AMD EPYC 9684X
This server processor
has 96 cores and 192
threads, with a max
boost clock speed
also up to 3.7Ghz.
The processor also
features AMD 3D
V-Cache™
Technology,
which stacks cache
vertically for up to 1.15
GB of L3 cache.3
AMD EPYC 9174F
This processor has 16
cores and 32 threads,
with a max boost clock
speed up to 4.4Ghz.4
About Red Hat OpenShift
Red Hat OpenShift is an
enterprise-grade, commercial
distribution of the open-
source Kubernetes container
orchestration platform. We used
OpenShift Virtualization, which
is a feature that allows IT teams
to run VMs alongside containers
on the same platform, which
could simplify management and
improve time to production.
Containerization with OpenShift
can also enable organizations to
enhance application reliability
and reduce maintenance
complexity, potentially resulting
in lower support costs. To learn
more about Red Hat OpenShift,
visit https://www.redhat.
com/en/technologies/cloud-
computing/openshift.
About the AMD
EPYC processors
The portfolio of fourth generation
of AMD EPYC processors offers
a range of choices to help meet
the many evolving workload
demands in today’s data centers.
The 9004 series in particular, from
which we chose the processors we
tested, comes available with 16
to 128 cores and up to 1.15 GB
of L3 cache.5
All three AMD EPYC
processors we tested leverage
AMD Infinity Fabric interconnect
and offer security features with
AMD Infinity Guard.
Realize 2.1X the data intensive workload performance with 20% less power with AMD EPYC processor-backed clusters May 2024 (Revised) | 2
How we tested
Understanding how a generation of processors could impact any
organization’s operations requires more than just a single view of
performance. To help paint that picture, we crafted three comparison
scenarios of CPU. The section “Our three test scenarios” explains our
reasoning for choosing different processors and the detailed differences
between them. In each scenario, we used a different processor from the
4th
Generation AMD EPYC 9004 Series. In two scenarios, we compared the
AMD EPYC processor-based clusters to a cluster backed by the same model
of 4th
Gen Intel Xeon Scalable processor. In the last scenario, we chose a
second 4th
Gen Intel Xeon Scalable processor for the comparison cluster.
In each test scenario, we used two input/output (I/O) profiles. Doing so
provides further information on how processors can affect performance,
because each individual I/O profile has different characteristics and offers
different I/O operation patterns. We first ran a 100 percent read profile,
which is common for data analysis or data warehouse workloads. These can
sometimes be part of online analytical processing (OLAP) applications or
business intelligence (BI) tools. We then ran an 80-20 read-write I/O profile.
This read-heavy profile can appear in general use database workloads or
in online transaction processing (OLTP) workloads—workloads that require
frequent data retrieval with some updating or modification.
We used the in-memory data structure store Redis as a database because
it is a versatile platform that has many use cases, such as fraud detection,
gaming leaderboards, caching, messaging, and more.6
Redis performance
directly influences application interactions, including data retrieval and
balancing the load of backend services through caching. Using Redis’ multi-
model database capabilities, the platform can also empower developers to
construct low-latency microservice architectures that scale based on user
demand. And although the general Redis platform works well with a single
CPU core, we chose Redis Cluster to scale up our workloads and make use
of the multi-core CPUs we tested.
To create the Redis database and workload, we used the benchmarking tool
memtier_benchmark. We also captured power metrics during testing using
ExTech 380801 power monitors.
About Redis and
Redis Cluster
Redis, an open-source, in-memory
data structure store, functions
as a database, cache, message
broker, and streaming engine.
It operates with an in-memory
dataset and offers various data
structures including strings,
hashes, and lists. It can also offer
built-in replication and different
levels of on-disk persistence in
addition to options for achieving
high availability through Redis
Sentinel or supporting automatic
partitioning with Redis Cluster.
Additionally, Redis also supports
asynchronous replication, which
can help reduce latency and
bandwidth requirements and
boost write performance.
In our testing, we used Redis
Cluster to leverage more of the
capabilities of the multi-core
clusters and scale the number of
workloads. Redis Cluster enables
users to distribute their dataset
across multiple Redis nodes
automatically. Furthermore,
Redis claims that Redis Cluster
can also offer some availability
during partitions.7
This means that
operations could persist even if
some nodes within the cluster fail
or lose communication with the
rest of the cluster.
Realize 2.1X the data intensive workload performance with 20% less power with AMD EPYC processor-backed clusters May 2024 (Revised) | 3
Our three test scenarios
Clusters with the closest possible core counts
For the first CPU comparison, we configured a server cluster
with 64-core AMD EPYC 9534 processors and a cluster of
servers with 56-core Intel Xeon Platinum 8480+ processors. We
considered both processors to have the closest core counts we
could find, offering similar levels of performance characteristics
such as operating speed, power consumption, and more. The
Intel processor had a higher max frequency at 3.8 GHz, while
the AMD processor had a max frequency of 3.7 GHz. The AMD
processor in this configuration typically has a lower retail cost
than the Intel processor.8, 9
Clusters with processors that
typically have similar retail prices
For the second CPU comparison, we configured the AMD
EPYC-based server cluster with AMD EPYC 9684X processors.
This AMD processor had 96 cores and 192 threads. We did
not change the Intel Xeon Platinum 8480+ processor for this
comparison. As this AMD processor typically has a retail cost
about the same as the Intel processor,10
the goal for this test
scenario was to compare the performance between processors
at similar price points.
Clusters with processors that
have the same number of cores
For the third CPU comparison, we configured the AMD EPYC-
based cluster of servers with AMD EPYC 9174F processors and
configured the Intel processor-based server cluster with Intel
Xeon Gold 6444Y processors. Both processors had 16 cores and
32 threads. Our aim here was to demonstrate performance when
processors from the two OEMs matched on core count. The
two processors typically have a similar retail cost, with the Intel
processor costing slightly more.11, 12
About memtier_benchmark
Redis developed this tool to help
users understand the performance
of their systems running Redis
workloads. According to Redis,
memtier_benchmark “provides a
robust set of customization and
reporting capabilities all wrapped
into a convenient and easy-to-
use command-line interface.”13
The tool outputs operations
per second, latency, and more.
To learn more about memtier_
benchmark, visit https://redis.
com/blog/memtier_benchmark-a-
high-throughput-benchmarking-
tool-for-redis-memcached/.
Realize 2.1X the data intensive workload performance with 20% less power with AMD EPYC processor-backed clusters May 2024 (Revised) | 4
What we found
For each scenario, we gathered the requests per second
(RPS) output from memtier_benchmark and the power
under load wattage using ExTech 380801 power meters.
We then divided the RPS by the wattage to create a
performance per watt metric. Table 1 shows the results
from each scenario in both I/O profiles.
More RPS could translate to better Redis workload
performance, potentially improving response times and
the customer experience for the use cases we previously
discussed. Using less watts under load could mean
spending less on powering your data center, thus helping
your departmental bottom line. The performance per
watt metric helps quantify the value of each solution’s
Redis performance.
Table 1: RPS, watts under load, and performance per watt for each cluster configuration in both I/O profiles.
For RPS and performance per watt, higher is better. For watts under load, lower is better.
Intel Xeon Scalable
processor-based cluster
AMD EPYC
processor-based cluster
Win % for the AMD
processor-based cluster
Test scenario 1
100%
read
RPS 84,355,048 122,389,531 45%
Watts under load 1,002 801 20%
Performance/watt 84,162 152,745 81%
80-20
read/
write
RPS 76,761,057 112,596,334 46%
Watts under load 1,003 796 20%
Performance/watt 76,499 141,282 84%
Test scenario 2
100%
read
RPS 84,355,048 177,763,205 110%
Watts under load 1,002 1,010 -0.8%
Performance/watt 84,162 175,894 108%
80-20
read/
write
RPS 76,761,057 157,999,207 105%
Watts under load 1,003 1,016 -1.3%
Performance/watt 76,499 155,396 103%
Test scenario 3
100%
read
RPS 37,980,229 38,807,375 2.1%
Watts under load 744 709 4.7%
Performance/watt 50,990 54,702 7.2%
80-20
read/
write
RPS 35,450,081 36,722,284 3.5%
Watts under load 749 710 5.1%
Performance/watt 47,320 51,655 9.1%
We assigned each scenario a unique color to help differentiate the comparisons.
Realize 2.1X the data intensive workload performance with 20% less power with AMD EPYC processor-backed clusters May 2024 (Revised) | 5
Test scenario 1: Clusters
with the closest possible
core counts
In this scenario, the 64-core AMD
EPYC 9534 processor-based
cluster supported more RPS than
the 56-core Intel Xeon Platinum
8480+ processor-based cluster
in both I/O profiles (see Figure
1). Additionally, as Figure 2
shows, the AMD processor-based
cluster consumed less power
while running the two workloads,
resulting in better performance
per watt for the AMD processor-
backed cluster (see Figure 3).
When you consider that the
AMD EPYC 9534 processor
typically has a lower retail cost
than the Intel Xeon Platinum
8480+ processor,14,15
you could
potentially spend less to see
better Redis performance while
drawing less power.
Redis requests per second
Higher is better
Intel Xeon Platinum 8480+ processor-based cluster
AMD EPYC 9534 processor-based cluster
100% read
45% more RPS
84,355,048
122,389,531
80% read / 20% write
46% more RPS
76,761,057
112,596,334
Figure 1: The RPS each solution achieved in the first test scenario under both I/O profiles.
Higher is better. Source: Principled Technologies.
Redis power under load
Watts (Lower is better)
Intel Xeon Platinum 8480+ processor-based cluster
AMD EPYC 9534 processor-based cluster
100% read
20% less power
1,002
801
80% read / 20% write
20% less power
1,003
796
Figure 2: The power each solution consumed while running the workloads in the first scenario.
Lower is better. Source: Principled Technologies.
Redis performance per watt
RPS per watt (Higher is better)
Intel Xeon Platinum 8480+ processor-based cluster
AMD EPYC 9534 processor-based cluster
100% read
81% greater RPS/watt
84,162
152,745
80% read / 20% write
84% greater RPS/watt
76,499
141,282
Figure 3: The performance per watt each solution delivered in the first test scenario under both
I/O profiles. Higher is better. Source: Principled Technologies.
Realize 2.1X the data intensive workload performance with 20% less power with AMD EPYC processor-backed clusters May 2024 (Revised) | 6
Test scenario 2:
Clusters with processors
that typically have similar
retail prices
In this scenario, the AMD EPYC
9684X processor-based cluster
supported significantly more
RPS than the Intel Xeon Platinum
8480+ processor-based cluster
in both I/O profiles (see Figure
4). Plus as Figure 5 shows, the
AMD processor-based cluster
consumed a similar amount of
power while running the two
workloads. Due to handling
more RPS, the AMD processor-
backed cluster offered better
performance per watt (see Figure
6). Investing in higher-bin AMD
EPYC 9684X processors for your
servers could yield better Redis
performance and thus a better
value in terms of performance
and power consumption than
if you spent a similar amount
on Intel Xeon Platinum 8480+
processors for the servers.16,17
Redis requests per second
Higher is better
Intel Xeon Platinum 8480+ processor-based cluster
AMD EPYC 9684X processor-based cluster
100% read
2.1X the RPS
84,355,048
177,763,205
80% read / 20% write
More than 2X the RPS
76,761,057
157,999,207
Figure 4: The RPS each solution achieved in the second test scenario under both I/O profiles.
Higher is better. Source: Principled Technologies.
Redis power under load
Watts (Lower is better)
Intel Xeon Platinum 8480+ processor-based cluster
AMD EPYC 9684X processor-based cluster
100% read
Only 0.8% more power
1,002
1,010
80% read / 20% write
Only 1.3% more power
1,003
1,016
Figure 5: The power each solution consumed while running the workloads in the second scenario.
Lower is better. Source: Principled Technologies.
Redis performance per watt
RPS per watt (Higher is better)
Intel Xeon Platinum 8480+ processor-based cluster
AMD EPYC 9684X processor-based cluster
100% read
More than 2X the RPS/watt
84,162
175,894
80% read / 20% write
More than 2X the RPS/watt
76,499
155,396
Figure 6: The performance per watt each solution delivered in the second test scenario under both
I/O profiles. Higher is better. Source: Principled Technologies.
Realize 2.1X the data intensive workload performance with 20% less power with AMD EPYC processor-backed clusters May 2024 (Revised) | 7
Test scenario 3: Clusters with processors
that have the same number of cores
As the two processors both had 16 cores, the AMD EPYC 9174F processor-
based cluster supported better per-core performance than the Intel Xeon
Gold 6444Y processor-based cluster. Considering that the cluster with the
AMD EPYC 9174F delivered slightly better performance, consumed slightly
less power under load, and typically has a per-processor retail cost slightly
lower than the Intel Xeon Gold 6444Y processor,18,19
choosing the AMD
processor for your servers could be a smarter investment and give you
processors with the same core and thread counts.
Table 2 shows the results for this scenario.
Table 2: RPS, watts under load, and performance per watt for both cluster configuration in
both I/O profiles for the third test scenario. For RPS and performance per watt, higher is
better. For watts under load, lower is better. Source: Principled Technologies.
Intel
Xeon Gold
6444Y processor-
based cluster
AMD
EPYC 9174F
processor-based
cluster
Win %
for the AMD
processor-based
cluster
Test scenario 3
100%
read
RPS 37,980,229 38,807,375 2.1%
Watts under load 744 709 4.7%
Performance/watt 50,990 54,702 7.2%
80-20
read/
write
RPS 35,450,081 36,722,284 3.5%
Watts under load 749 710 5.1%
Performance/watt 47,320 51,655 9.1%
Realize 2.1X the data intensive workload performance with 20% less power with AMD EPYC processor-backed clusters May 2024 (Revised) | 8
Conclusion
Performance and energy efficiency are significant factors in processor
selection for servers running data-intensive workloads, such as Redis. We
compared the Redis performance and energy consumption of a server
cluster in three AMD EPYC two-processor configurations against that of a
server cluster in two Intel Xeon Scalable two-processor configurations. In
each of our three test scenarios, the server cluster backed by AMD EPYC
processors outperformed the server cluster backed by Intel Xeon Scalable
processors. In addition, one of the AMD EPYC processor-based clusters
consumed 20 percent less power than its Intel Xeon Scalable processor-
based counterpart. Combining these measurements gave us power
efficiency metrics that demonstrate how valuable AMD EPYC processor-
based servers could be—you could see better performance per watt with
these AMD EPYC processor-based server clusters and potentially get more
from your Redis or other data intensive applications and workloads while
reducing data center power costs.
Realize 2.1X the data intensive workload performance with 20% less power with AMD EPYC processor-backed clusters May 2024 (Revised) | 9
1. Paul Bubny, “Data Centers See Sharp Rises in Power
Costs, Lease Rates,” accessed April 2, 2024,
https://www.connectcre.com/stories/data-centers-see-
sharp-rises-in-power-costs-lease-rates/.
2. AMD, “AMD EPYC™
9534,” accessed March 29, 2024,
https://www.amd.com/en/products/cpu/amd-epyc-9534.
3. AMD, “AMD EPYC™
9684X,” accessed March 29, 2024,
https://www.amd.com/en/products/cpu/amd-epyc-9684x.
4. AMD, “AMD EPYC™
9174F,” accessed March 29, 2024,
https://www.amd.com/en/products/cpu/amd-epyc-9174f.
5. AMD, “AMD EPYC™
9004 SERIES PROCESSORS,” ac-
cessed March 29, 2024, https://www.amd.com/content/
dam/amd/en/documents/products/epyc/epyc-9004-se-
ries-processors-data-sheet.pdf.
6. Ajeet Raina, “Redis Use Case Examples for Developers,”
accessed April 1, 2024, https://redis.com/blog/5-indus-
try-use-cases-for-redis-developers/.
7. Redis, “Scale with Redis Cluster,” accessed April 4, 2024,
https://redis.io/docs/latest/operate/oss_and_stack/man-
agement/scaling/.
8. Price captured from ServerSupply on April 4, 2024
(https://www.serversupply.com/PROCESSORS/
AMD%20EPYC%2064-Core/2.45GHz/AM-
D/100-100000799WOF_370868.htm).
9. Price captured from ServerSupply on April 4, 2024
(https://www.serversupply.com/PROCESSORS/Intel%20
Xeon%2056-Core/2.0GHz%20-%2016GT%20UPI/INTEL/
SRM7H_371122.htm).
10. Price captured from ServerSupply on April 4, 2024
(https://www.serversupply.com/PROCESSORS/
AMD%20EPYC%2096-Core/2.55GHz/AMD/100-
000001254_381212.htm).
11. Price captured from ServerSupply on April 4, 2024
(https://www.serversupply.com/PROCESSORS/
AMD%20EPYC%2016-core/4.1GHz/AMD/100-
000000796_368285.htm).
12. Price captured from ServerSupply on April 4, 2024
(https://www.serversupply.com/PROCESSORS/Intel%20
Xeon%2016-Core/3.6GHz%20-%2016GT%20UPI/INTEL/
PK8071305121400_371183.htm).
13. Redis, “memtier_benchmark: A High-Throughput Bench-
marking Tool for Redis & Memcached,” accessed April 4,
2024, https://redis.com/blog/memtier_benchmark-a-high-
throughput-benchmarking-tool-for-redis-memcached/.
14. Price captured from ServerSupply on April 4, 2024
(https://www.serversupply.com/PROCESSORS/
AMD%20EPYC%2064-Core/2.45GHz/AM-
D/100-100000799WOF_370868.htm).
15. Price captured from ServerSupply on April 4, 2024
(https://www.serversupply.com/PROCESSORS/Intel%20
Xeon%2056-Core/2.0GHz%20-%2016GT%20UPI/INTEL/
SRM7H_371122.htm).
16. Price captured from ServerSupply on April 4, 2024
(https://www.serversupply.com/PROCESSORS/
AMD%20EPYC%2096-Core/2.55GHz/AMD/100-
000001254_381212.htm).
17. Price captured from ServerSupply on April 4, 2024
(https://www.serversupply.com/PROCESSORS/Intel%20
Xeon%2056-Core/2.0GHz%20-%2016GT%20UPI/INTEL/
SRM7H_371122.htm).
18. Price captured from ServerSupply on April 4, 2024
(https://www.serversupply.com/PROCESSORS/
AMD%20EPYC%2016-core/4.1GHz/AMD/100-
000000796_368285.htm).
19. Price captured from ServerSupply on April 4, 2024
(https://www.serversupply.com/PROCESSORS/Intel%20
Xeon%2016-Core/3.6GHz%20-%2016GT%20UPI/INTEL/
PK8071305121400_371183.htm).
Principled Technologies is a registered trademark of Principled Technologies, Inc.
All other product names are the trademarks of their respective owners.
For additional information, review the science behind this report.
Principled
Technologies®
Facts matter.®
Principled
Technologies®
Facts matter.®
This project was commissioned by AMD.
Read the science behind this report at https://facts.pt/XbgM65a
Realize 2.1X the data intensive workload performance with 20% less power with AMD EPYC processor-backed clusters May 2024 (Revised) | 10

More Related Content

Similar to Realize 2.1X the performance with 20% less power with AMD EPYC processor-backed clusters

Get stronger SQL Server performance for less with Dell EMC PowerEdge R6515 cl...
Get stronger SQL Server performance for less with Dell EMC PowerEdge R6515 cl...Get stronger SQL Server performance for less with Dell EMC PowerEdge R6515 cl...
Get stronger SQL Server performance for less with Dell EMC PowerEdge R6515 cl...Principled Technologies
 
Database performance and cost comparison: AMD-based Open Compute 3.0 server v...
Database performance and cost comparison: AMD-based Open Compute 3.0 server v...Database performance and cost comparison: AMD-based Open Compute 3.0 server v...
Database performance and cost comparison: AMD-based Open Compute 3.0 server v...Principled Technologies
 
Improve performance and gain room to grow by easily migrating to a modern Ope...
Improve performance and gain room to grow by easily migrating to a modern Ope...Improve performance and gain room to grow by easily migrating to a modern Ope...
Improve performance and gain room to grow by easily migrating to a modern Ope...Principled Technologies
 
Grid rac preso 051007
Grid rac preso 051007Grid rac preso 051007
Grid rac preso 051007Sal Marcus
 
Blbs tn-double-the-power-half-the-space-uslet-en
Blbs tn-double-the-power-half-the-space-uslet-enBlbs tn-double-the-power-half-the-space-uslet-en
Blbs tn-double-the-power-half-the-space-uslet-enBloombase
 
Intel Ethernet 800 Series Network Adapters in Dell EMC PowerEdge R740xd serve...
Intel Ethernet 800 Series Network Adapters in Dell EMC PowerEdge R740xd serve...Intel Ethernet 800 Series Network Adapters in Dell EMC PowerEdge R740xd serve...
Intel Ethernet 800 Series Network Adapters in Dell EMC PowerEdge R740xd serve...Principled Technologies
 
Speeding time to insight: The Dell PowerEdge C6620 with Dell PERC 12 RAID con...
Speeding time to insight: The Dell PowerEdge C6620 with Dell PERC 12 RAID con...Speeding time to insight: The Dell PowerEdge C6620 with Dell PERC 12 RAID con...
Speeding time to insight: The Dell PowerEdge C6620 with Dell PERC 12 RAID con...Principled Technologies
 
Research OnThe IT Infrastructure Of Globe Pharmaceutical Ltd - All Server
Research OnThe IT Infrastructure Of Globe Pharmaceutical Ltd - All ServerResearch OnThe IT Infrastructure Of Globe Pharmaceutical Ltd - All Server
Research OnThe IT Infrastructure Of Globe Pharmaceutical Ltd - All ServerZiaul Hoque Prince
 
Virtual Private Server Documentation
Virtual Private Server DocumentationVirtual Private Server Documentation
Virtual Private Server Documentationwebhostingguy
 
Virtual Private Server Documentation
Virtual Private Server DocumentationVirtual Private Server Documentation
Virtual Private Server Documentationwebhostingguy
 
Apache Cassandra performance advantages of the new Dell PowerEdge C6620 with ...
Apache Cassandra performance advantages of the new Dell PowerEdge C6620 with ...Apache Cassandra performance advantages of the new Dell PowerEdge C6620 with ...
Apache Cassandra performance advantages of the new Dell PowerEdge C6620 with ...Principled Technologies
 
A single-socket Dell EMC PowerEdge R7515 solution delivered better value on a...
A single-socket Dell EMC PowerEdge R7515 solution delivered better value on a...A single-socket Dell EMC PowerEdge R7515 solution delivered better value on a...
A single-socket Dell EMC PowerEdge R7515 solution delivered better value on a...Principled Technologies
 
Consolidating Oracle database servers on the Dell PowerEdge R930
Consolidating Oracle database servers on the Dell PowerEdge R930Consolidating Oracle database servers on the Dell PowerEdge R930
Consolidating Oracle database servers on the Dell PowerEdge R930Principled Technologies
 
Get higher performance for your MySQL databases with Dell APEX Private Cloud
Get higher performance for your MySQL databases with Dell APEX Private CloudGet higher performance for your MySQL databases with Dell APEX Private Cloud
Get higher performance for your MySQL databases with Dell APEX Private CloudPrincipled Technologies
 
Scalability: Lenovo ThinkServer RD540 system and Lenovo ThinkServer SA120 sto...
Scalability: Lenovo ThinkServer RD540 system and Lenovo ThinkServer SA120 sto...Scalability: Lenovo ThinkServer RD540 system and Lenovo ThinkServer SA120 sto...
Scalability: Lenovo ThinkServer RD540 system and Lenovo ThinkServer SA120 sto...Principled Technologies
 
22by7 and DellEMC Tech Day July 20 2017 - Power Edge
22by7 and DellEMC Tech Day July 20 2017 - Power Edge22by7 and DellEMC Tech Day July 20 2017 - Power Edge
22by7 and DellEMC Tech Day July 20 2017 - Power EdgeSashikris
 
Dell PowerEdge R660xs: Maximize VDI density while delivering a strong user ex...
Dell PowerEdge R660xs: Maximize VDI density while delivering a strong user ex...Dell PowerEdge R660xs: Maximize VDI density while delivering a strong user ex...
Dell PowerEdge R660xs: Maximize VDI density while delivering a strong user ex...Principled Technologies
 
Get insight from document-based distributed MongoDB databases sooner and have...
Get insight from document-based distributed MongoDB databases sooner and have...Get insight from document-based distributed MongoDB databases sooner and have...
Get insight from document-based distributed MongoDB databases sooner and have...Principled Technologies
 
Better email response time using Microsoft Exchange 2013 with the Dell PowerE...
Better email response time using Microsoft Exchange 2013 with the Dell PowerE...Better email response time using Microsoft Exchange 2013 with the Dell PowerE...
Better email response time using Microsoft Exchange 2013 with the Dell PowerE...Principled Technologies
 

Similar to Realize 2.1X the performance with 20% less power with AMD EPYC processor-backed clusters (20)

Get stronger SQL Server performance for less with Dell EMC PowerEdge R6515 cl...
Get stronger SQL Server performance for less with Dell EMC PowerEdge R6515 cl...Get stronger SQL Server performance for less with Dell EMC PowerEdge R6515 cl...
Get stronger SQL Server performance for less with Dell EMC PowerEdge R6515 cl...
 
Database performance and cost comparison: AMD-based Open Compute 3.0 server v...
Database performance and cost comparison: AMD-based Open Compute 3.0 server v...Database performance and cost comparison: AMD-based Open Compute 3.0 server v...
Database performance and cost comparison: AMD-based Open Compute 3.0 server v...
 
Improve performance and gain room to grow by easily migrating to a modern Ope...
Improve performance and gain room to grow by easily migrating to a modern Ope...Improve performance and gain room to grow by easily migrating to a modern Ope...
Improve performance and gain room to grow by easily migrating to a modern Ope...
 
Grid rac preso 051007
Grid rac preso 051007Grid rac preso 051007
Grid rac preso 051007
 
Blbs tn-double-the-power-half-the-space-uslet-en
Blbs tn-double-the-power-half-the-space-uslet-enBlbs tn-double-the-power-half-the-space-uslet-en
Blbs tn-double-the-power-half-the-space-uslet-en
 
Intel Ethernet 800 Series Network Adapters in Dell EMC PowerEdge R740xd serve...
Intel Ethernet 800 Series Network Adapters in Dell EMC PowerEdge R740xd serve...Intel Ethernet 800 Series Network Adapters in Dell EMC PowerEdge R740xd serve...
Intel Ethernet 800 Series Network Adapters in Dell EMC PowerEdge R740xd serve...
 
Speeding time to insight: The Dell PowerEdge C6620 with Dell PERC 12 RAID con...
Speeding time to insight: The Dell PowerEdge C6620 with Dell PERC 12 RAID con...Speeding time to insight: The Dell PowerEdge C6620 with Dell PERC 12 RAID con...
Speeding time to insight: The Dell PowerEdge C6620 with Dell PERC 12 RAID con...
 
Research OnThe IT Infrastructure Of Globe Pharmaceutical Ltd - All Server
Research OnThe IT Infrastructure Of Globe Pharmaceutical Ltd - All ServerResearch OnThe IT Infrastructure Of Globe Pharmaceutical Ltd - All Server
Research OnThe IT Infrastructure Of Globe Pharmaceutical Ltd - All Server
 
E880 datasheet
E880 datasheetE880 datasheet
E880 datasheet
 
Virtual Private Server Documentation
Virtual Private Server DocumentationVirtual Private Server Documentation
Virtual Private Server Documentation
 
Virtual Private Server Documentation
Virtual Private Server DocumentationVirtual Private Server Documentation
Virtual Private Server Documentation
 
Apache Cassandra performance advantages of the new Dell PowerEdge C6620 with ...
Apache Cassandra performance advantages of the new Dell PowerEdge C6620 with ...Apache Cassandra performance advantages of the new Dell PowerEdge C6620 with ...
Apache Cassandra performance advantages of the new Dell PowerEdge C6620 with ...
 
A single-socket Dell EMC PowerEdge R7515 solution delivered better value on a...
A single-socket Dell EMC PowerEdge R7515 solution delivered better value on a...A single-socket Dell EMC PowerEdge R7515 solution delivered better value on a...
A single-socket Dell EMC PowerEdge R7515 solution delivered better value on a...
 
Consolidating Oracle database servers on the Dell PowerEdge R930
Consolidating Oracle database servers on the Dell PowerEdge R930Consolidating Oracle database servers on the Dell PowerEdge R930
Consolidating Oracle database servers on the Dell PowerEdge R930
 
Get higher performance for your MySQL databases with Dell APEX Private Cloud
Get higher performance for your MySQL databases with Dell APEX Private CloudGet higher performance for your MySQL databases with Dell APEX Private Cloud
Get higher performance for your MySQL databases with Dell APEX Private Cloud
 
Scalability: Lenovo ThinkServer RD540 system and Lenovo ThinkServer SA120 sto...
Scalability: Lenovo ThinkServer RD540 system and Lenovo ThinkServer SA120 sto...Scalability: Lenovo ThinkServer RD540 system and Lenovo ThinkServer SA120 sto...
Scalability: Lenovo ThinkServer RD540 system and Lenovo ThinkServer SA120 sto...
 
22by7 and DellEMC Tech Day July 20 2017 - Power Edge
22by7 and DellEMC Tech Day July 20 2017 - Power Edge22by7 and DellEMC Tech Day July 20 2017 - Power Edge
22by7 and DellEMC Tech Day July 20 2017 - Power Edge
 
Dell PowerEdge R660xs: Maximize VDI density while delivering a strong user ex...
Dell PowerEdge R660xs: Maximize VDI density while delivering a strong user ex...Dell PowerEdge R660xs: Maximize VDI density while delivering a strong user ex...
Dell PowerEdge R660xs: Maximize VDI density while delivering a strong user ex...
 
Get insight from document-based distributed MongoDB databases sooner and have...
Get insight from document-based distributed MongoDB databases sooner and have...Get insight from document-based distributed MongoDB databases sooner and have...
Get insight from document-based distributed MongoDB databases sooner and have...
 
Better email response time using Microsoft Exchange 2013 with the Dell PowerE...
Better email response time using Microsoft Exchange 2013 with the Dell PowerE...Better email response time using Microsoft Exchange 2013 with the Dell PowerE...
Better email response time using Microsoft Exchange 2013 with the Dell PowerE...
 

More from Principled Technologies

Workstations powered by Intel can play a vital role in CPU-intensive AI devel...
Workstations powered by Intel can play a vital role in CPU-intensive AI devel...Workstations powered by Intel can play a vital role in CPU-intensive AI devel...
Workstations powered by Intel can play a vital role in CPU-intensive AI devel...Principled Technologies
 
Enable security features with no impact to OLTP performance with Dell PowerEd...
Enable security features with no impact to OLTP performance with Dell PowerEd...Enable security features with no impact to OLTP performance with Dell PowerEd...
Enable security features with no impact to OLTP performance with Dell PowerEd...Principled Technologies
 
Improving energy efficiency in the data center: Endure higher temperatures wi...
Improving energy efficiency in the data center: Endure higher temperatures wi...Improving energy efficiency in the data center: Endure higher temperatures wi...
Improving energy efficiency in the data center: Endure higher temperatures wi...Principled Technologies
 
Dell APEX Cloud Platform for Red Hat OpenShift: An easily deployable and powe...
Dell APEX Cloud Platform for Red Hat OpenShift: An easily deployable and powe...Dell APEX Cloud Platform for Red Hat OpenShift: An easily deployable and powe...
Dell APEX Cloud Platform for Red Hat OpenShift: An easily deployable and powe...Principled Technologies
 
Investing in GenAI: Cost‑benefit analysis of Dell on‑premises deployments vs....
Investing in GenAI: Cost‑benefit analysis of Dell on‑premises deployments vs....Investing in GenAI: Cost‑benefit analysis of Dell on‑premises deployments vs....
Investing in GenAI: Cost‑benefit analysis of Dell on‑premises deployments vs....Principled Technologies
 
Dell APEX Cloud Platform for Red Hat OpenShift: An easily deployable and powe...
Dell APEX Cloud Platform for Red Hat OpenShift: An easily deployable and powe...Dell APEX Cloud Platform for Red Hat OpenShift: An easily deployable and powe...
Dell APEX Cloud Platform for Red Hat OpenShift: An easily deployable and powe...Principled Technologies
 
Upgrade your cloud infrastructure with Dell PowerEdge R760 servers and VMware...
Upgrade your cloud infrastructure with Dell PowerEdge R760 servers and VMware...Upgrade your cloud infrastructure with Dell PowerEdge R760 servers and VMware...
Upgrade your cloud infrastructure with Dell PowerEdge R760 servers and VMware...Principled Technologies
 
Upgrade your cloud infrastructure with Dell PowerEdge R760 servers and VMware...
Upgrade your cloud infrastructure with Dell PowerEdge R760 servers and VMware...Upgrade your cloud infrastructure with Dell PowerEdge R760 servers and VMware...
Upgrade your cloud infrastructure with Dell PowerEdge R760 servers and VMware...Principled Technologies
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityPrincipled Technologies
 
Deploy with confidence: VMware Cloud Foundation 5.1 on next gen Dell PowerEdg...
Deploy with confidence: VMware Cloud Foundation 5.1 on next gen Dell PowerEdg...Deploy with confidence: VMware Cloud Foundation 5.1 on next gen Dell PowerEdg...
Deploy with confidence: VMware Cloud Foundation 5.1 on next gen Dell PowerEdg...Principled Technologies
 
Upgrade your cloud infrastructure with Dell PowerEdge R760 servers and VMware...
Upgrade your cloud infrastructure with Dell PowerEdge R760 servers and VMware...Upgrade your cloud infrastructure with Dell PowerEdge R760 servers and VMware...
Upgrade your cloud infrastructure with Dell PowerEdge R760 servers and VMware...Principled Technologies
 
A comparison of security features in Dell, HP, and Lenovo PC systems
A comparison of security features in Dell, HP, and Lenovo PC systemsA comparison of security features in Dell, HP, and Lenovo PC systems
A comparison of security features in Dell, HP, and Lenovo PC systemsPrincipled Technologies
 
Increase security, sustainability, and efficiency with robust Dell server man...
Increase security, sustainability, and efficiency with robust Dell server man...Increase security, sustainability, and efficiency with robust Dell server man...
Increase security, sustainability, and efficiency with robust Dell server man...Principled Technologies
 
Increase security, sustainability, and efficiency with robust Dell server man...
Increase security, sustainability, and efficiency with robust Dell server man...Increase security, sustainability, and efficiency with robust Dell server man...
Increase security, sustainability, and efficiency with robust Dell server man...Principled Technologies
 
Scale up your storage with higher-performing Dell APEX Block Storage for AWS ...
Scale up your storage with higher-performing Dell APEX Block Storage for AWS ...Scale up your storage with higher-performing Dell APEX Block Storage for AWS ...
Scale up your storage with higher-performing Dell APEX Block Storage for AWS ...Principled Technologies
 
Scale up your storage with higher-performing Dell APEX Block Storage for AWS
Scale up your storage with higher-performing Dell APEX Block Storage for AWSScale up your storage with higher-performing Dell APEX Block Storage for AWS
Scale up your storage with higher-performing Dell APEX Block Storage for AWSPrincipled Technologies
 
Get in and stay in the productivity zone with the HP Z2 G9 Tower Workstation
Get in and stay in the productivity zone with the HP Z2 G9 Tower WorkstationGet in and stay in the productivity zone with the HP Z2 G9 Tower Workstation
Get in and stay in the productivity zone with the HP Z2 G9 Tower WorkstationPrincipled Technologies
 
Open up new possibilities with higher transactional database performance from...
Open up new possibilities with higher transactional database performance from...Open up new possibilities with higher transactional database performance from...
Open up new possibilities with higher transactional database performance from...Principled Technologies
 
Improving database performance and value with an easy migration to Azure Data...
Improving database performance and value with an easy migration to Azure Data...Improving database performance and value with an easy migration to Azure Data...
Improving database performance and value with an easy migration to Azure Data...Principled Technologies
 
Realize better value and performance migrating from Azure Database for Postgr...
Realize better value and performance migrating from Azure Database for Postgr...Realize better value and performance migrating from Azure Database for Postgr...
Realize better value and performance migrating from Azure Database for Postgr...Principled Technologies
 

More from Principled Technologies (20)

Workstations powered by Intel can play a vital role in CPU-intensive AI devel...
Workstations powered by Intel can play a vital role in CPU-intensive AI devel...Workstations powered by Intel can play a vital role in CPU-intensive AI devel...
Workstations powered by Intel can play a vital role in CPU-intensive AI devel...
 
Enable security features with no impact to OLTP performance with Dell PowerEd...
Enable security features with no impact to OLTP performance with Dell PowerEd...Enable security features with no impact to OLTP performance with Dell PowerEd...
Enable security features with no impact to OLTP performance with Dell PowerEd...
 
Improving energy efficiency in the data center: Endure higher temperatures wi...
Improving energy efficiency in the data center: Endure higher temperatures wi...Improving energy efficiency in the data center: Endure higher temperatures wi...
Improving energy efficiency in the data center: Endure higher temperatures wi...
 
Dell APEX Cloud Platform for Red Hat OpenShift: An easily deployable and powe...
Dell APEX Cloud Platform for Red Hat OpenShift: An easily deployable and powe...Dell APEX Cloud Platform for Red Hat OpenShift: An easily deployable and powe...
Dell APEX Cloud Platform for Red Hat OpenShift: An easily deployable and powe...
 
Investing in GenAI: Cost‑benefit analysis of Dell on‑premises deployments vs....
Investing in GenAI: Cost‑benefit analysis of Dell on‑premises deployments vs....Investing in GenAI: Cost‑benefit analysis of Dell on‑premises deployments vs....
Investing in GenAI: Cost‑benefit analysis of Dell on‑premises deployments vs....
 
Dell APEX Cloud Platform for Red Hat OpenShift: An easily deployable and powe...
Dell APEX Cloud Platform for Red Hat OpenShift: An easily deployable and powe...Dell APEX Cloud Platform for Red Hat OpenShift: An easily deployable and powe...
Dell APEX Cloud Platform for Red Hat OpenShift: An easily deployable and powe...
 
Upgrade your cloud infrastructure with Dell PowerEdge R760 servers and VMware...
Upgrade your cloud infrastructure with Dell PowerEdge R760 servers and VMware...Upgrade your cloud infrastructure with Dell PowerEdge R760 servers and VMware...
Upgrade your cloud infrastructure with Dell PowerEdge R760 servers and VMware...
 
Upgrade your cloud infrastructure with Dell PowerEdge R760 servers and VMware...
Upgrade your cloud infrastructure with Dell PowerEdge R760 servers and VMware...Upgrade your cloud infrastructure with Dell PowerEdge R760 servers and VMware...
Upgrade your cloud infrastructure with Dell PowerEdge R760 servers and VMware...
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivity
 
Deploy with confidence: VMware Cloud Foundation 5.1 on next gen Dell PowerEdg...
Deploy with confidence: VMware Cloud Foundation 5.1 on next gen Dell PowerEdg...Deploy with confidence: VMware Cloud Foundation 5.1 on next gen Dell PowerEdg...
Deploy with confidence: VMware Cloud Foundation 5.1 on next gen Dell PowerEdg...
 
Upgrade your cloud infrastructure with Dell PowerEdge R760 servers and VMware...
Upgrade your cloud infrastructure with Dell PowerEdge R760 servers and VMware...Upgrade your cloud infrastructure with Dell PowerEdge R760 servers and VMware...
Upgrade your cloud infrastructure with Dell PowerEdge R760 servers and VMware...
 
A comparison of security features in Dell, HP, and Lenovo PC systems
A comparison of security features in Dell, HP, and Lenovo PC systemsA comparison of security features in Dell, HP, and Lenovo PC systems
A comparison of security features in Dell, HP, and Lenovo PC systems
 
Increase security, sustainability, and efficiency with robust Dell server man...
Increase security, sustainability, and efficiency with robust Dell server man...Increase security, sustainability, and efficiency with robust Dell server man...
Increase security, sustainability, and efficiency with robust Dell server man...
 
Increase security, sustainability, and efficiency with robust Dell server man...
Increase security, sustainability, and efficiency with robust Dell server man...Increase security, sustainability, and efficiency with robust Dell server man...
Increase security, sustainability, and efficiency with robust Dell server man...
 
Scale up your storage with higher-performing Dell APEX Block Storage for AWS ...
Scale up your storage with higher-performing Dell APEX Block Storage for AWS ...Scale up your storage with higher-performing Dell APEX Block Storage for AWS ...
Scale up your storage with higher-performing Dell APEX Block Storage for AWS ...
 
Scale up your storage with higher-performing Dell APEX Block Storage for AWS
Scale up your storage with higher-performing Dell APEX Block Storage for AWSScale up your storage with higher-performing Dell APEX Block Storage for AWS
Scale up your storage with higher-performing Dell APEX Block Storage for AWS
 
Get in and stay in the productivity zone with the HP Z2 G9 Tower Workstation
Get in and stay in the productivity zone with the HP Z2 G9 Tower WorkstationGet in and stay in the productivity zone with the HP Z2 G9 Tower Workstation
Get in and stay in the productivity zone with the HP Z2 G9 Tower Workstation
 
Open up new possibilities with higher transactional database performance from...
Open up new possibilities with higher transactional database performance from...Open up new possibilities with higher transactional database performance from...
Open up new possibilities with higher transactional database performance from...
 
Improving database performance and value with an easy migration to Azure Data...
Improving database performance and value with an easy migration to Azure Data...Improving database performance and value with an easy migration to Azure Data...
Improving database performance and value with an easy migration to Azure Data...
 
Realize better value and performance migrating from Azure Database for Postgr...
Realize better value and performance migrating from Azure Database for Postgr...Realize better value and performance migrating from Azure Database for Postgr...
Realize better value and performance migrating from Azure Database for Postgr...
 

Recently uploaded

Microsoft CSP Briefing Pre-Engagement - Questionnaire
Microsoft CSP Briefing Pre-Engagement - QuestionnaireMicrosoft CSP Briefing Pre-Engagement - Questionnaire
Microsoft CSP Briefing Pre-Engagement - QuestionnaireExakis Nelite
 
Introduction to FDO and How It works Applications _ Richard at FIDO Alliance.pdf
Introduction to FDO and How It works Applications _ Richard at FIDO Alliance.pdfIntroduction to FDO and How It works Applications _ Richard at FIDO Alliance.pdf
Introduction to FDO and How It works Applications _ Richard at FIDO Alliance.pdfFIDO Alliance
 
ASRock Industrial FDO Solutions in Action for Industrial Edge AI _ Kenny at A...
ASRock Industrial FDO Solutions in Action for Industrial Edge AI _ Kenny at A...ASRock Industrial FDO Solutions in Action for Industrial Edge AI _ Kenny at A...
ASRock Industrial FDO Solutions in Action for Industrial Edge AI _ Kenny at A...FIDO Alliance
 
Your enemies use GenAI too - staying ahead of fraud with Neo4j
Your enemies use GenAI too - staying ahead of fraud with Neo4jYour enemies use GenAI too - staying ahead of fraud with Neo4j
Your enemies use GenAI too - staying ahead of fraud with Neo4jNeo4j
 
Choosing the Right FDO Deployment Model for Your Application _ Geoffrey at In...
Choosing the Right FDO Deployment Model for Your Application _ Geoffrey at In...Choosing the Right FDO Deployment Model for Your Application _ Geoffrey at In...
Choosing the Right FDO Deployment Model for Your Application _ Geoffrey at In...FIDO Alliance
 
Easier, Faster, and More Powerful – Alles Neu macht der Mai -Wir durchleuchte...
Easier, Faster, and More Powerful – Alles Neu macht der Mai -Wir durchleuchte...Easier, Faster, and More Powerful – Alles Neu macht der Mai -Wir durchleuchte...
Easier, Faster, and More Powerful – Alles Neu macht der Mai -Wir durchleuchte...panagenda
 
Oauth 2.0 Introduction and Flows with MuleSoft
Oauth 2.0 Introduction and Flows with MuleSoftOauth 2.0 Introduction and Flows with MuleSoft
Oauth 2.0 Introduction and Flows with MuleSoftshyamraj55
 
Event-Driven Architecture Masterclass: Challenges in Stream Processing
Event-Driven Architecture Masterclass: Challenges in Stream ProcessingEvent-Driven Architecture Masterclass: Challenges in Stream Processing
Event-Driven Architecture Masterclass: Challenges in Stream ProcessingScyllaDB
 
Secure Zero Touch enabled Edge compute with Dell NativeEdge via FDO _ Brad at...
Secure Zero Touch enabled Edge compute with Dell NativeEdge via FDO _ Brad at...Secure Zero Touch enabled Edge compute with Dell NativeEdge via FDO _ Brad at...
Secure Zero Touch enabled Edge compute with Dell NativeEdge via FDO _ Brad at...FIDO Alliance
 
Hyatt driving innovation and exceptional customer experiences with FIDO passw...
Hyatt driving innovation and exceptional customer experiences with FIDO passw...Hyatt driving innovation and exceptional customer experiences with FIDO passw...
Hyatt driving innovation and exceptional customer experiences with FIDO passw...FIDO Alliance
 
Breaking Down the Flutterwave Scandal What You Need to Know.pdf
Breaking Down the Flutterwave Scandal What You Need to Know.pdfBreaking Down the Flutterwave Scandal What You Need to Know.pdf
Breaking Down the Flutterwave Scandal What You Need to Know.pdfUK Journal
 
How we scaled to 80K users by doing nothing!.pdf
How we scaled to 80K users by doing nothing!.pdfHow we scaled to 80K users by doing nothing!.pdf
How we scaled to 80K users by doing nothing!.pdfSrushith Repakula
 
State of the Smart Building Startup Landscape 2024!
State of the Smart Building Startup Landscape 2024!State of the Smart Building Startup Landscape 2024!
State of the Smart Building Startup Landscape 2024!Memoori
 
Simplified FDO Manufacturing Flow with TPMs _ Liam at Infineon.pdf
Simplified FDO Manufacturing Flow with TPMs _ Liam at Infineon.pdfSimplified FDO Manufacturing Flow with TPMs _ Liam at Infineon.pdf
Simplified FDO Manufacturing Flow with TPMs _ Liam at Infineon.pdfFIDO Alliance
 
The Metaverse: Are We There Yet?
The  Metaverse:    Are   We  There  Yet?The  Metaverse:    Are   We  There  Yet?
The Metaverse: Are We There Yet?Mark Billinghurst
 
Continuing Bonds Through AI: A Hermeneutic Reflection on Thanabots
Continuing Bonds Through AI: A Hermeneutic Reflection on ThanabotsContinuing Bonds Through AI: A Hermeneutic Reflection on Thanabots
Continuing Bonds Through AI: A Hermeneutic Reflection on ThanabotsLeah Henrickson
 
AI mind or machine power point presentation
AI mind or machine power point presentationAI mind or machine power point presentation
AI mind or machine power point presentationyogeshlabana357357
 
Introduction to FIDO Authentication and Passkeys.pptx
Introduction to FIDO Authentication and Passkeys.pptxIntroduction to FIDO Authentication and Passkeys.pptx
Introduction to FIDO Authentication and Passkeys.pptxFIDO Alliance
 
Collecting & Temporal Analysis of Behavioral Web Data - Tales From The Inside
Collecting & Temporal Analysis of Behavioral Web Data - Tales From The InsideCollecting & Temporal Analysis of Behavioral Web Data - Tales From The Inside
Collecting & Temporal Analysis of Behavioral Web Data - Tales From The InsideStefan Dietze
 

Recently uploaded (20)

Microsoft CSP Briefing Pre-Engagement - Questionnaire
Microsoft CSP Briefing Pre-Engagement - QuestionnaireMicrosoft CSP Briefing Pre-Engagement - Questionnaire
Microsoft CSP Briefing Pre-Engagement - Questionnaire
 
Introduction to FDO and How It works Applications _ Richard at FIDO Alliance.pdf
Introduction to FDO and How It works Applications _ Richard at FIDO Alliance.pdfIntroduction to FDO and How It works Applications _ Richard at FIDO Alliance.pdf
Introduction to FDO and How It works Applications _ Richard at FIDO Alliance.pdf
 
ASRock Industrial FDO Solutions in Action for Industrial Edge AI _ Kenny at A...
ASRock Industrial FDO Solutions in Action for Industrial Edge AI _ Kenny at A...ASRock Industrial FDO Solutions in Action for Industrial Edge AI _ Kenny at A...
ASRock Industrial FDO Solutions in Action for Industrial Edge AI _ Kenny at A...
 
Your enemies use GenAI too - staying ahead of fraud with Neo4j
Your enemies use GenAI too - staying ahead of fraud with Neo4jYour enemies use GenAI too - staying ahead of fraud with Neo4j
Your enemies use GenAI too - staying ahead of fraud with Neo4j
 
Choosing the Right FDO Deployment Model for Your Application _ Geoffrey at In...
Choosing the Right FDO Deployment Model for Your Application _ Geoffrey at In...Choosing the Right FDO Deployment Model for Your Application _ Geoffrey at In...
Choosing the Right FDO Deployment Model for Your Application _ Geoffrey at In...
 
Easier, Faster, and More Powerful – Alles Neu macht der Mai -Wir durchleuchte...
Easier, Faster, and More Powerful – Alles Neu macht der Mai -Wir durchleuchte...Easier, Faster, and More Powerful – Alles Neu macht der Mai -Wir durchleuchte...
Easier, Faster, and More Powerful – Alles Neu macht der Mai -Wir durchleuchte...
 
Oauth 2.0 Introduction and Flows with MuleSoft
Oauth 2.0 Introduction and Flows with MuleSoftOauth 2.0 Introduction and Flows with MuleSoft
Oauth 2.0 Introduction and Flows with MuleSoft
 
Event-Driven Architecture Masterclass: Challenges in Stream Processing
Event-Driven Architecture Masterclass: Challenges in Stream ProcessingEvent-Driven Architecture Masterclass: Challenges in Stream Processing
Event-Driven Architecture Masterclass: Challenges in Stream Processing
 
Secure Zero Touch enabled Edge compute with Dell NativeEdge via FDO _ Brad at...
Secure Zero Touch enabled Edge compute with Dell NativeEdge via FDO _ Brad at...Secure Zero Touch enabled Edge compute with Dell NativeEdge via FDO _ Brad at...
Secure Zero Touch enabled Edge compute with Dell NativeEdge via FDO _ Brad at...
 
Hyatt driving innovation and exceptional customer experiences with FIDO passw...
Hyatt driving innovation and exceptional customer experiences with FIDO passw...Hyatt driving innovation and exceptional customer experiences with FIDO passw...
Hyatt driving innovation and exceptional customer experiences with FIDO passw...
 
Breaking Down the Flutterwave Scandal What You Need to Know.pdf
Breaking Down the Flutterwave Scandal What You Need to Know.pdfBreaking Down the Flutterwave Scandal What You Need to Know.pdf
Breaking Down the Flutterwave Scandal What You Need to Know.pdf
 
Overview of Hyperledger Foundation
Overview of Hyperledger FoundationOverview of Hyperledger Foundation
Overview of Hyperledger Foundation
 
How we scaled to 80K users by doing nothing!.pdf
How we scaled to 80K users by doing nothing!.pdfHow we scaled to 80K users by doing nothing!.pdf
How we scaled to 80K users by doing nothing!.pdf
 
State of the Smart Building Startup Landscape 2024!
State of the Smart Building Startup Landscape 2024!State of the Smart Building Startup Landscape 2024!
State of the Smart Building Startup Landscape 2024!
 
Simplified FDO Manufacturing Flow with TPMs _ Liam at Infineon.pdf
Simplified FDO Manufacturing Flow with TPMs _ Liam at Infineon.pdfSimplified FDO Manufacturing Flow with TPMs _ Liam at Infineon.pdf
Simplified FDO Manufacturing Flow with TPMs _ Liam at Infineon.pdf
 
The Metaverse: Are We There Yet?
The  Metaverse:    Are   We  There  Yet?The  Metaverse:    Are   We  There  Yet?
The Metaverse: Are We There Yet?
 
Continuing Bonds Through AI: A Hermeneutic Reflection on Thanabots
Continuing Bonds Through AI: A Hermeneutic Reflection on ThanabotsContinuing Bonds Through AI: A Hermeneutic Reflection on Thanabots
Continuing Bonds Through AI: A Hermeneutic Reflection on Thanabots
 
AI mind or machine power point presentation
AI mind or machine power point presentationAI mind or machine power point presentation
AI mind or machine power point presentation
 
Introduction to FIDO Authentication and Passkeys.pptx
Introduction to FIDO Authentication and Passkeys.pptxIntroduction to FIDO Authentication and Passkeys.pptx
Introduction to FIDO Authentication and Passkeys.pptx
 
Collecting & Temporal Analysis of Behavioral Web Data - Tales From The Inside
Collecting & Temporal Analysis of Behavioral Web Data - Tales From The InsideCollecting & Temporal Analysis of Behavioral Web Data - Tales From The Inside
Collecting & Temporal Analysis of Behavioral Web Data - Tales From The Inside
 

Realize 2.1X the performance with 20% less power with AMD EPYC processor-backed clusters

  • 1. Realize 2.1X the performance with 20% less power with AMD EPYC processor-backed clusters Three AMD EPYC processor-based two-processor solutions outshined comparable Intel Xeon Scalable processor-based solutions by handling more Redis workload transactions and requests while consuming less power Handle more Redis work Up to 2.1X the requests per second* *From servers with AMD EPYC 9684X processors vs. servers with Intel Xeon Platinum 8480+ processors Processing more transactions for Redis could mean more real-time analytics, faster retrieval of files, or caching service to reduce repetitive generative AI computations. This advantage came from the server cluster backed by AMD EPYC™ 9684X processors, which features AMD 3D V-Cache technology designed to help keep Redis data closer to the core. Spend less on data center power Up to 20% less power under load* *From servers with AMD EPYC 9534 processors vs. servers with Intel Xeon Platinum 8480+ processors The cost of energy is rising rapidly, so slashing any data center spending could be a boon for your bottom line. In addition, consuming less power could help advance your organization’s sustainability goals. Use less energy to get better performance Up to 2X the performance per watt* *From servers with AMD EPYC 9684X processors vs. servers with Intel Xeon Platinum 8480+ processors What happens when you combine better Redis performance with less power consumption? You get a more efficient hardware cluster: more processed transactions per watt. More efficient clusters could then contribute to making your data center more efficient on the whole, allowing your organization to meet performance demands with fewer physical servers while also helping to reduce data center sprawl. Realize 2.1X the data intensive workload performance with 20% less power with AMD EPYC processor-backed clusters May 2024 (Revised) A Principled Technologies report: Hands-on testing. Real-world results.
  • 2. Overview When choosing processors for server clusters that run data-intensive workloads, such as Redis, performance is often the number one consideration. A faster processor could enable data-intensive workloads to handle large volumes of data with low latency for responsive caching, session storage, or real-time analytics/AI workload performance. CPU power consumption plays a significant factor as well due to rising data center power costs.1 We created two clusters of four worker nodes to compare Redis performance and power consumption in three CPU scenarios. The four worker nodes in the first cluster used 4th Generation AMD EPYC processors, and the four nodes in the second cluster used 4th Gen Intel® Xeon® Scalable processors. All worker nodes had the same amount of RAM on the same number of DIMMs. We installed Red Hat® OpenShift® to containerize the VMs running workloads for each cluster configuration. In each test scenario, the AMD EPYC processor-based cluster supported better performance—up to 2.1 times the requests per second (RPS). In two of the three scenarios, the AMD EPYC processor-based cluster consumed less power (up to 20 percent less watts) while achieving better performance. Furthermore, each configuration of the AMD EPYC processor-based cluster supported more RPS per watt—up to 2 times the RPS per watt in our second scenario. These outcomes suggest that processors from the AMD EPYC 9004 series in your servers could help your Redis or data-intensive applications and workloads do things like support more messages or detect fraud sooner, all while potentially saving on data center power costs. We tested the following processors from the EPYC family: AMD EPYC 9534 This data center processor has 64 cores and 128 threads, with a max boost clock speed up to 3.7Ghz.2 AMD EPYC 9684X This server processor has 96 cores and 192 threads, with a max boost clock speed also up to 3.7Ghz. The processor also features AMD 3D V-Cache™ Technology, which stacks cache vertically for up to 1.15 GB of L3 cache.3 AMD EPYC 9174F This processor has 16 cores and 32 threads, with a max boost clock speed up to 4.4Ghz.4 About Red Hat OpenShift Red Hat OpenShift is an enterprise-grade, commercial distribution of the open- source Kubernetes container orchestration platform. We used OpenShift Virtualization, which is a feature that allows IT teams to run VMs alongside containers on the same platform, which could simplify management and improve time to production. Containerization with OpenShift can also enable organizations to enhance application reliability and reduce maintenance complexity, potentially resulting in lower support costs. To learn more about Red Hat OpenShift, visit https://www.redhat. com/en/technologies/cloud- computing/openshift. About the AMD EPYC processors The portfolio of fourth generation of AMD EPYC processors offers a range of choices to help meet the many evolving workload demands in today’s data centers. The 9004 series in particular, from which we chose the processors we tested, comes available with 16 to 128 cores and up to 1.15 GB of L3 cache.5 All three AMD EPYC processors we tested leverage AMD Infinity Fabric interconnect and offer security features with AMD Infinity Guard. Realize 2.1X the data intensive workload performance with 20% less power with AMD EPYC processor-backed clusters May 2024 (Revised) | 2
  • 3. How we tested Understanding how a generation of processors could impact any organization’s operations requires more than just a single view of performance. To help paint that picture, we crafted three comparison scenarios of CPU. The section “Our three test scenarios” explains our reasoning for choosing different processors and the detailed differences between them. In each scenario, we used a different processor from the 4th Generation AMD EPYC 9004 Series. In two scenarios, we compared the AMD EPYC processor-based clusters to a cluster backed by the same model of 4th Gen Intel Xeon Scalable processor. In the last scenario, we chose a second 4th Gen Intel Xeon Scalable processor for the comparison cluster. In each test scenario, we used two input/output (I/O) profiles. Doing so provides further information on how processors can affect performance, because each individual I/O profile has different characteristics and offers different I/O operation patterns. We first ran a 100 percent read profile, which is common for data analysis or data warehouse workloads. These can sometimes be part of online analytical processing (OLAP) applications or business intelligence (BI) tools. We then ran an 80-20 read-write I/O profile. This read-heavy profile can appear in general use database workloads or in online transaction processing (OLTP) workloads—workloads that require frequent data retrieval with some updating or modification. We used the in-memory data structure store Redis as a database because it is a versatile platform that has many use cases, such as fraud detection, gaming leaderboards, caching, messaging, and more.6 Redis performance directly influences application interactions, including data retrieval and balancing the load of backend services through caching. Using Redis’ multi- model database capabilities, the platform can also empower developers to construct low-latency microservice architectures that scale based on user demand. And although the general Redis platform works well with a single CPU core, we chose Redis Cluster to scale up our workloads and make use of the multi-core CPUs we tested. To create the Redis database and workload, we used the benchmarking tool memtier_benchmark. We also captured power metrics during testing using ExTech 380801 power monitors. About Redis and Redis Cluster Redis, an open-source, in-memory data structure store, functions as a database, cache, message broker, and streaming engine. It operates with an in-memory dataset and offers various data structures including strings, hashes, and lists. It can also offer built-in replication and different levels of on-disk persistence in addition to options for achieving high availability through Redis Sentinel or supporting automatic partitioning with Redis Cluster. Additionally, Redis also supports asynchronous replication, which can help reduce latency and bandwidth requirements and boost write performance. In our testing, we used Redis Cluster to leverage more of the capabilities of the multi-core clusters and scale the number of workloads. Redis Cluster enables users to distribute their dataset across multiple Redis nodes automatically. Furthermore, Redis claims that Redis Cluster can also offer some availability during partitions.7 This means that operations could persist even if some nodes within the cluster fail or lose communication with the rest of the cluster. Realize 2.1X the data intensive workload performance with 20% less power with AMD EPYC processor-backed clusters May 2024 (Revised) | 3
  • 4. Our three test scenarios Clusters with the closest possible core counts For the first CPU comparison, we configured a server cluster with 64-core AMD EPYC 9534 processors and a cluster of servers with 56-core Intel Xeon Platinum 8480+ processors. We considered both processors to have the closest core counts we could find, offering similar levels of performance characteristics such as operating speed, power consumption, and more. The Intel processor had a higher max frequency at 3.8 GHz, while the AMD processor had a max frequency of 3.7 GHz. The AMD processor in this configuration typically has a lower retail cost than the Intel processor.8, 9 Clusters with processors that typically have similar retail prices For the second CPU comparison, we configured the AMD EPYC-based server cluster with AMD EPYC 9684X processors. This AMD processor had 96 cores and 192 threads. We did not change the Intel Xeon Platinum 8480+ processor for this comparison. As this AMD processor typically has a retail cost about the same as the Intel processor,10 the goal for this test scenario was to compare the performance between processors at similar price points. Clusters with processors that have the same number of cores For the third CPU comparison, we configured the AMD EPYC- based cluster of servers with AMD EPYC 9174F processors and configured the Intel processor-based server cluster with Intel Xeon Gold 6444Y processors. Both processors had 16 cores and 32 threads. Our aim here was to demonstrate performance when processors from the two OEMs matched on core count. The two processors typically have a similar retail cost, with the Intel processor costing slightly more.11, 12 About memtier_benchmark Redis developed this tool to help users understand the performance of their systems running Redis workloads. According to Redis, memtier_benchmark “provides a robust set of customization and reporting capabilities all wrapped into a convenient and easy-to- use command-line interface.”13 The tool outputs operations per second, latency, and more. To learn more about memtier_ benchmark, visit https://redis. com/blog/memtier_benchmark-a- high-throughput-benchmarking- tool-for-redis-memcached/. Realize 2.1X the data intensive workload performance with 20% less power with AMD EPYC processor-backed clusters May 2024 (Revised) | 4
  • 5. What we found For each scenario, we gathered the requests per second (RPS) output from memtier_benchmark and the power under load wattage using ExTech 380801 power meters. We then divided the RPS by the wattage to create a performance per watt metric. Table 1 shows the results from each scenario in both I/O profiles. More RPS could translate to better Redis workload performance, potentially improving response times and the customer experience for the use cases we previously discussed. Using less watts under load could mean spending less on powering your data center, thus helping your departmental bottom line. The performance per watt metric helps quantify the value of each solution’s Redis performance. Table 1: RPS, watts under load, and performance per watt for each cluster configuration in both I/O profiles. For RPS and performance per watt, higher is better. For watts under load, lower is better. Intel Xeon Scalable processor-based cluster AMD EPYC processor-based cluster Win % for the AMD processor-based cluster Test scenario 1 100% read RPS 84,355,048 122,389,531 45% Watts under load 1,002 801 20% Performance/watt 84,162 152,745 81% 80-20 read/ write RPS 76,761,057 112,596,334 46% Watts under load 1,003 796 20% Performance/watt 76,499 141,282 84% Test scenario 2 100% read RPS 84,355,048 177,763,205 110% Watts under load 1,002 1,010 -0.8% Performance/watt 84,162 175,894 108% 80-20 read/ write RPS 76,761,057 157,999,207 105% Watts under load 1,003 1,016 -1.3% Performance/watt 76,499 155,396 103% Test scenario 3 100% read RPS 37,980,229 38,807,375 2.1% Watts under load 744 709 4.7% Performance/watt 50,990 54,702 7.2% 80-20 read/ write RPS 35,450,081 36,722,284 3.5% Watts under load 749 710 5.1% Performance/watt 47,320 51,655 9.1% We assigned each scenario a unique color to help differentiate the comparisons. Realize 2.1X the data intensive workload performance with 20% less power with AMD EPYC processor-backed clusters May 2024 (Revised) | 5
  • 6. Test scenario 1: Clusters with the closest possible core counts In this scenario, the 64-core AMD EPYC 9534 processor-based cluster supported more RPS than the 56-core Intel Xeon Platinum 8480+ processor-based cluster in both I/O profiles (see Figure 1). Additionally, as Figure 2 shows, the AMD processor-based cluster consumed less power while running the two workloads, resulting in better performance per watt for the AMD processor- backed cluster (see Figure 3). When you consider that the AMD EPYC 9534 processor typically has a lower retail cost than the Intel Xeon Platinum 8480+ processor,14,15 you could potentially spend less to see better Redis performance while drawing less power. Redis requests per second Higher is better Intel Xeon Platinum 8480+ processor-based cluster AMD EPYC 9534 processor-based cluster 100% read 45% more RPS 84,355,048 122,389,531 80% read / 20% write 46% more RPS 76,761,057 112,596,334 Figure 1: The RPS each solution achieved in the first test scenario under both I/O profiles. Higher is better. Source: Principled Technologies. Redis power under load Watts (Lower is better) Intel Xeon Platinum 8480+ processor-based cluster AMD EPYC 9534 processor-based cluster 100% read 20% less power 1,002 801 80% read / 20% write 20% less power 1,003 796 Figure 2: The power each solution consumed while running the workloads in the first scenario. Lower is better. Source: Principled Technologies. Redis performance per watt RPS per watt (Higher is better) Intel Xeon Platinum 8480+ processor-based cluster AMD EPYC 9534 processor-based cluster 100% read 81% greater RPS/watt 84,162 152,745 80% read / 20% write 84% greater RPS/watt 76,499 141,282 Figure 3: The performance per watt each solution delivered in the first test scenario under both I/O profiles. Higher is better. Source: Principled Technologies. Realize 2.1X the data intensive workload performance with 20% less power with AMD EPYC processor-backed clusters May 2024 (Revised) | 6
  • 7. Test scenario 2: Clusters with processors that typically have similar retail prices In this scenario, the AMD EPYC 9684X processor-based cluster supported significantly more RPS than the Intel Xeon Platinum 8480+ processor-based cluster in both I/O profiles (see Figure 4). Plus as Figure 5 shows, the AMD processor-based cluster consumed a similar amount of power while running the two workloads. Due to handling more RPS, the AMD processor- backed cluster offered better performance per watt (see Figure 6). Investing in higher-bin AMD EPYC 9684X processors for your servers could yield better Redis performance and thus a better value in terms of performance and power consumption than if you spent a similar amount on Intel Xeon Platinum 8480+ processors for the servers.16,17 Redis requests per second Higher is better Intel Xeon Platinum 8480+ processor-based cluster AMD EPYC 9684X processor-based cluster 100% read 2.1X the RPS 84,355,048 177,763,205 80% read / 20% write More than 2X the RPS 76,761,057 157,999,207 Figure 4: The RPS each solution achieved in the second test scenario under both I/O profiles. Higher is better. Source: Principled Technologies. Redis power under load Watts (Lower is better) Intel Xeon Platinum 8480+ processor-based cluster AMD EPYC 9684X processor-based cluster 100% read Only 0.8% more power 1,002 1,010 80% read / 20% write Only 1.3% more power 1,003 1,016 Figure 5: The power each solution consumed while running the workloads in the second scenario. Lower is better. Source: Principled Technologies. Redis performance per watt RPS per watt (Higher is better) Intel Xeon Platinum 8480+ processor-based cluster AMD EPYC 9684X processor-based cluster 100% read More than 2X the RPS/watt 84,162 175,894 80% read / 20% write More than 2X the RPS/watt 76,499 155,396 Figure 6: The performance per watt each solution delivered in the second test scenario under both I/O profiles. Higher is better. Source: Principled Technologies. Realize 2.1X the data intensive workload performance with 20% less power with AMD EPYC processor-backed clusters May 2024 (Revised) | 7
  • 8. Test scenario 3: Clusters with processors that have the same number of cores As the two processors both had 16 cores, the AMD EPYC 9174F processor- based cluster supported better per-core performance than the Intel Xeon Gold 6444Y processor-based cluster. Considering that the cluster with the AMD EPYC 9174F delivered slightly better performance, consumed slightly less power under load, and typically has a per-processor retail cost slightly lower than the Intel Xeon Gold 6444Y processor,18,19 choosing the AMD processor for your servers could be a smarter investment and give you processors with the same core and thread counts. Table 2 shows the results for this scenario. Table 2: RPS, watts under load, and performance per watt for both cluster configuration in both I/O profiles for the third test scenario. For RPS and performance per watt, higher is better. For watts under load, lower is better. Source: Principled Technologies. Intel Xeon Gold 6444Y processor- based cluster AMD EPYC 9174F processor-based cluster Win % for the AMD processor-based cluster Test scenario 3 100% read RPS 37,980,229 38,807,375 2.1% Watts under load 744 709 4.7% Performance/watt 50,990 54,702 7.2% 80-20 read/ write RPS 35,450,081 36,722,284 3.5% Watts under load 749 710 5.1% Performance/watt 47,320 51,655 9.1% Realize 2.1X the data intensive workload performance with 20% less power with AMD EPYC processor-backed clusters May 2024 (Revised) | 8
  • 9. Conclusion Performance and energy efficiency are significant factors in processor selection for servers running data-intensive workloads, such as Redis. We compared the Redis performance and energy consumption of a server cluster in three AMD EPYC two-processor configurations against that of a server cluster in two Intel Xeon Scalable two-processor configurations. In each of our three test scenarios, the server cluster backed by AMD EPYC processors outperformed the server cluster backed by Intel Xeon Scalable processors. In addition, one of the AMD EPYC processor-based clusters consumed 20 percent less power than its Intel Xeon Scalable processor- based counterpart. Combining these measurements gave us power efficiency metrics that demonstrate how valuable AMD EPYC processor- based servers could be—you could see better performance per watt with these AMD EPYC processor-based server clusters and potentially get more from your Redis or other data intensive applications and workloads while reducing data center power costs. Realize 2.1X the data intensive workload performance with 20% less power with AMD EPYC processor-backed clusters May 2024 (Revised) | 9
  • 10. 1. Paul Bubny, “Data Centers See Sharp Rises in Power Costs, Lease Rates,” accessed April 2, 2024, https://www.connectcre.com/stories/data-centers-see- sharp-rises-in-power-costs-lease-rates/. 2. AMD, “AMD EPYC™ 9534,” accessed March 29, 2024, https://www.amd.com/en/products/cpu/amd-epyc-9534. 3. AMD, “AMD EPYC™ 9684X,” accessed March 29, 2024, https://www.amd.com/en/products/cpu/amd-epyc-9684x. 4. AMD, “AMD EPYC™ 9174F,” accessed March 29, 2024, https://www.amd.com/en/products/cpu/amd-epyc-9174f. 5. AMD, “AMD EPYC™ 9004 SERIES PROCESSORS,” ac- cessed March 29, 2024, https://www.amd.com/content/ dam/amd/en/documents/products/epyc/epyc-9004-se- ries-processors-data-sheet.pdf. 6. Ajeet Raina, “Redis Use Case Examples for Developers,” accessed April 1, 2024, https://redis.com/blog/5-indus- try-use-cases-for-redis-developers/. 7. Redis, “Scale with Redis Cluster,” accessed April 4, 2024, https://redis.io/docs/latest/operate/oss_and_stack/man- agement/scaling/. 8. Price captured from ServerSupply on April 4, 2024 (https://www.serversupply.com/PROCESSORS/ AMD%20EPYC%2064-Core/2.45GHz/AM- D/100-100000799WOF_370868.htm). 9. Price captured from ServerSupply on April 4, 2024 (https://www.serversupply.com/PROCESSORS/Intel%20 Xeon%2056-Core/2.0GHz%20-%2016GT%20UPI/INTEL/ SRM7H_371122.htm). 10. Price captured from ServerSupply on April 4, 2024 (https://www.serversupply.com/PROCESSORS/ AMD%20EPYC%2096-Core/2.55GHz/AMD/100- 000001254_381212.htm). 11. Price captured from ServerSupply on April 4, 2024 (https://www.serversupply.com/PROCESSORS/ AMD%20EPYC%2016-core/4.1GHz/AMD/100- 000000796_368285.htm). 12. Price captured from ServerSupply on April 4, 2024 (https://www.serversupply.com/PROCESSORS/Intel%20 Xeon%2016-Core/3.6GHz%20-%2016GT%20UPI/INTEL/ PK8071305121400_371183.htm). 13. Redis, “memtier_benchmark: A High-Throughput Bench- marking Tool for Redis & Memcached,” accessed April 4, 2024, https://redis.com/blog/memtier_benchmark-a-high- throughput-benchmarking-tool-for-redis-memcached/. 14. Price captured from ServerSupply on April 4, 2024 (https://www.serversupply.com/PROCESSORS/ AMD%20EPYC%2064-Core/2.45GHz/AM- D/100-100000799WOF_370868.htm). 15. Price captured from ServerSupply on April 4, 2024 (https://www.serversupply.com/PROCESSORS/Intel%20 Xeon%2056-Core/2.0GHz%20-%2016GT%20UPI/INTEL/ SRM7H_371122.htm). 16. Price captured from ServerSupply on April 4, 2024 (https://www.serversupply.com/PROCESSORS/ AMD%20EPYC%2096-Core/2.55GHz/AMD/100- 000001254_381212.htm). 17. Price captured from ServerSupply on April 4, 2024 (https://www.serversupply.com/PROCESSORS/Intel%20 Xeon%2056-Core/2.0GHz%20-%2016GT%20UPI/INTEL/ SRM7H_371122.htm). 18. Price captured from ServerSupply on April 4, 2024 (https://www.serversupply.com/PROCESSORS/ AMD%20EPYC%2016-core/4.1GHz/AMD/100- 000000796_368285.htm). 19. Price captured from ServerSupply on April 4, 2024 (https://www.serversupply.com/PROCESSORS/Intel%20 Xeon%2016-Core/3.6GHz%20-%2016GT%20UPI/INTEL/ PK8071305121400_371183.htm). Principled Technologies is a registered trademark of Principled Technologies, Inc. All other product names are the trademarks of their respective owners. For additional information, review the science behind this report. Principled Technologies® Facts matter.® Principled Technologies® Facts matter.® This project was commissioned by AMD. Read the science behind this report at https://facts.pt/XbgM65a Realize 2.1X the data intensive workload performance with 20% less power with AMD EPYC processor-backed clusters May 2024 (Revised) | 10