A server cluster with 3rd Gen AMD EPYC processors achieved higher throughput and took less time to prepare images for classification than a server cluster with 3rd Gen Intel Xeon Platinum 8380 processors
Boosting performance with the Dell Acceleration Appliance for DatabasesPrincipled Technologies
If your business is expanding and you need to support more users accessing your databases, it’s time to act. Upgrading your database infrastructure with a flash storage-based solution is a smart way to improve performance without adding more servers or taking up very much rack space, which comes at a premium. The Dell Acceleration Appliance for Databases addresses this by providing strong performance when combined with your existing infrastructure or on its own.
We found that adding a highly available DAAD solution to our database application provided up to 3.01 times the Oracle Database 12c performance, which can make a big difference to your bottom line. Additionally, the DAAD delivered 3.14 times the database performance when replacing traditional storage completely, which could enable your infrastructure to keep up with your growing business’ needs.
The benefits of value SAS and data center NVMe drives with Dell EMC PowerEdgePrincipled Technologies
In Principled Technologies testing across 4 different workloads and Dell EMC PowerEdge platforms, configurations with value SAS and data center NVMe SSDs from KIOXIA provided better performance and per-system value than a configuration with SATA SSDs.
AWS EC2 M6i instances with 3rd Gen Intel Xeon Scalable processors accelerated...Principled Technologies
At multiple instance sizes, M6i instances classified more frames per second than M5n instances with previous-gen processors or M6a instances with 3rd Gen AMD EPYC processors
Consolidate SAS 9.4 workloads with Intel Xeon processor E7 v3 and Intel SSD t...Principled Technologies
A key to modernizing your data center is to consolidate your legacy workloads through virtualization, which can help reduce complexity for your business. Fewer servers require fewer physical resources, such as power, cabling, and switches, and reduce the burden on IT for ongoing management tasks such as updates. In addition, integrating newer hardware technology into your data center can provide new features that strengthen your infrastructure, such as RAS features on the processor and disk performance improvements. Finally, using SAS 9.4 ensures that you have the latest features and toolsets that SAS can offer.
Compared to a legacy server, we found that a modern four-socket server powered by Intel Xeon processors E7-8890 v3 with Intel SSD DC P3700 Series provided 12 times the amount of SAS work, nearly 14 times the relative performance, and a shorter average time to complete the SAS workload. Running 12 virtual SAS instances also left capacity on the server for additional work. Consolidating your SAS workloads from legacy servers onto servers powered by Intel Xeon processors E7 v3 and SAS 9.4 can provide your business with the latest hardware and software features, reduce complexity in your data center, and potentially reduce costs for your business.
Reap better SQL Server OLTP performance with next-generation Dell EMC PowerEd...Principled Technologies
These new servers achieved up to 36.1 percent more OLTP database work than current-generation Dell EMC PowerEdge MX servers, while also lowering application response time
Ensure greater uptime and boost VMware vSAN cluster performance with the Del...Principled Technologies
The Dell EMC PowerEdge MX with VMware vSAN Ready Nodes delivered a 55.9% faster response time than a Cisco UCS solution and a 41.3% faster response time than an HPE Synergy solution
Boosting performance with the Dell Acceleration Appliance for DatabasesPrincipled Technologies
If your business is expanding and you need to support more users accessing your databases, it’s time to act. Upgrading your database infrastructure with a flash storage-based solution is a smart way to improve performance without adding more servers or taking up very much rack space, which comes at a premium. The Dell Acceleration Appliance for Databases addresses this by providing strong performance when combined with your existing infrastructure or on its own.
We found that adding a highly available DAAD solution to our database application provided up to 3.01 times the Oracle Database 12c performance, which can make a big difference to your bottom line. Additionally, the DAAD delivered 3.14 times the database performance when replacing traditional storage completely, which could enable your infrastructure to keep up with your growing business’ needs.
The benefits of value SAS and data center NVMe drives with Dell EMC PowerEdgePrincipled Technologies
In Principled Technologies testing across 4 different workloads and Dell EMC PowerEdge platforms, configurations with value SAS and data center NVMe SSDs from KIOXIA provided better performance and per-system value than a configuration with SATA SSDs.
AWS EC2 M6i instances with 3rd Gen Intel Xeon Scalable processors accelerated...Principled Technologies
At multiple instance sizes, M6i instances classified more frames per second than M5n instances with previous-gen processors or M6a instances with 3rd Gen AMD EPYC processors
Consolidate SAS 9.4 workloads with Intel Xeon processor E7 v3 and Intel SSD t...Principled Technologies
A key to modernizing your data center is to consolidate your legacy workloads through virtualization, which can help reduce complexity for your business. Fewer servers require fewer physical resources, such as power, cabling, and switches, and reduce the burden on IT for ongoing management tasks such as updates. In addition, integrating newer hardware technology into your data center can provide new features that strengthen your infrastructure, such as RAS features on the processor and disk performance improvements. Finally, using SAS 9.4 ensures that you have the latest features and toolsets that SAS can offer.
Compared to a legacy server, we found that a modern four-socket server powered by Intel Xeon processors E7-8890 v3 with Intel SSD DC P3700 Series provided 12 times the amount of SAS work, nearly 14 times the relative performance, and a shorter average time to complete the SAS workload. Running 12 virtual SAS instances also left capacity on the server for additional work. Consolidating your SAS workloads from legacy servers onto servers powered by Intel Xeon processors E7 v3 and SAS 9.4 can provide your business with the latest hardware and software features, reduce complexity in your data center, and potentially reduce costs for your business.
Reap better SQL Server OLTP performance with next-generation Dell EMC PowerEd...Principled Technologies
These new servers achieved up to 36.1 percent more OLTP database work than current-generation Dell EMC PowerEdge MX servers, while also lowering application response time
Ensure greater uptime and boost VMware vSAN cluster performance with the Del...Principled Technologies
The Dell EMC PowerEdge MX with VMware vSAN Ready Nodes delivered a 55.9% faster response time than a Cisco UCS solution and a 41.3% faster response time than an HPE Synergy solution
Business-critical applications on VMware vSphere 6, VMware Virtual SAN, and V...Principled Technologies
Moving to the virtualized, software-defined datacenter can offer real benefits to today’s organizations. As our testing showed, virtualizing business-critical applications with VMware vSphere, VMware Virtual SAN, and VMware NSX not only delivered reliable performance in a peak utilization scenario, but also delivered business continuity during and after a simulated site evacuation.
Using this VMware Validated Design with QCT hardware and Intel SSDs, we demonstrated a virtualized critical Oracle Database application environment delivering strong performance, even when under extreme duress.
Recognizing that many organizations have multiple sites, we also proved that our environment performed reliably under a site evacuation scenario, migrating the primary site VMs to the secondary in just over eight minutes with no downtime.
With these features and strengths, the VMware Validated Design SDDC is a proven solution that allows for efficient deployment of components and can help improve the reliability, flexibility, and mobility of your multi-site environment.
A single-socket Dell EMC PowerEdge R7515 solution delivered better value on a...Principled Technologies
If your company is running important business applications in VMware vSAN clusters of servers that are several years old, chances are good that you’re considering upgrading to newer hardware. Our testing demonstrated that our clusters of single-socket Dell EMC PowerEdge R7515 servers and clusters of dual-socket HPE ProLiant DL380 Gen10 servers could both improve upon the database performance of a legacy cluster with five-year-old servers by more than 50 percent, with the Dell EMC cluster achieving 93.4 percent of the performance of the HPE cluster.
3 key wins: Dell EMC PowerEdge MX with OpenManage Enterprise over Cisco UCS a...Principled Technologies
In head-to-head tests, the modular Dell EMC™ PowerEdge™ MX7000 with
OpenManage™ Enterprise reduced admin time and effort on repetitive tasks when compared to Cisco UCS® 5108 with Cisco UCS Manager and HPE Synergy with OneView.
Proper resource allocation is critical to achieving top application performance in a virtualized environment. Resource contention degrades performance and underutilization can lead to costly server sprawl.
We found that adding VMTurbo to a VMware vSphere 5.5 cluster and following its reallocation recommendations gave our application performance a big boost. After reducing vCPU count, increasing memory allocation to active databases, and moving VMs to more responsive storage as VMTurbo directed, online transactions increased by 23.7 percent while latency dropped significantly. Avoid the pitfalls of poorly allocated VM resources and give your virtualized application every advantage by gaining control of your environment at every level.
Your datacenter is capable of doing great things—if you let it. Upgrades from Intel for compute, storage, and networking components can help your business support new services and expand your customer base. In our hands-on testing, we found that new Intel processors, high-bandwidth network components, and SATA or PCIe SSDs working together can boost your datacenter’s capabilities, which could translate to better business operations for your organization.
SQL Server 2016 database performance on the Dell EMC PowerEdge FC630 QLogic 1...Principled Technologies
Upgrading the hardware running your SQL Server to a space-efficient modular Dell EMC modern environment can help your company achieve a great deal of database work in a small amount of space. With the Dell Express Flash technology, adding a caching solution such as Samsung AutoCache can make the environment even more efficient.
In the PT labs, we ran a mixed database workload on six Dell EMC PowerEdge FC630 servers, powered by Intel Xeon E5-2667 processors, in three PowerEdge FX2 enclosures. The solution included the QLogic QLE2692 16Gb FC adapter with StorFusion Technology, Dell EMC Storage SC9000 all-flash storage, and Dell EMC PowerEdge Express Flash NVMe Performance PCIe SSDs.
With no caching solution, the 36 SQL Server 2016 VMs on the six servers achieved a total of 431,839 orders per minute while an Oracle workload ran on 12 VMs. When we added a caching solution to accelerate the SQL database volumes, the performance across the 36 SQL Server 2016 VMs doubled to 871,580. These numbers show the power of server-side caching to alleviate pressure on the storage array allowing you to get even more out of the Dell EMC modern environment.
Get improved performance and new features from Dell EMC PowerEdge servers wit...Principled Technologies
We put 3rd Gen AMD EPYC processor-powered Dell EMC PowerEdge servers to the test with a variety of workloads to see the benefits and features your organization could expect from this latest offering
Component upgrades from Intel and Dell can increase VM density and boost perf...Principled Technologies
As the needs of your business grow, so must the power of your server infrastructure. Rather than purchasing replacement servers with base configurations, consider upgrading key components to ensure you get the performance you need.
We found that upgrading to the Dell PowerEdge R730 with the Intel Xeon processor E5-2699 v3, Microsoft Windows Server 2012 R2 operating system, Intel SSD DC S3700 series drive, and Intel Ethernet CNA X520 series adapters supported an extra 16 VMs, 67 percent more VMs than the previous-generation Dell PowerEdge R720 solution.
When you purchase a server, wisely selecting these components offered by Dell and Intel can allow your business to hit the sweet spot of supporting all your users without breaking the bank. The option to upgrade server components can provide your infrastructure with room to grow in the future, as your business needs increase.
Finally, these select upgrades could translate to savings for your business—fewer servers you need to purchase now to meet performance demands and a longer lifespan for these servers as your business continues to grow.
Watch your transactional database performance climb with Intel Optane DC pers...Principled Technologies
Dell EMC PowerEdge R740xd servers with Intel Optane DC persistent memory handled more transactions per minute than configurations with NAND flash NVMe drives or SATA SSDs
Symantec NetBackup 7.6 benchmark comparison: Data protection in a large-scale...Principled Technologies
The footprint of a VM can grow quickly in an enterprise environment and large-scale VM deployments in the thousands are common. As this number of deployed systems grows, so does the risk of failure. Critical failures can become unavoidable and offering data protection from a backup solution promotes business continuity. Elongated protection windows requiring multiple jobs of different types can create resource contention with production environments and may require valuable IT admin time, so a finite window for system backups can have plenty of importance.
In our hands-on SAN backup testing, the Symantec NetBackup Integrated Appliance running NetBackup 7.6 offered application protection to 1,000 VMs in 66.8 percent less time than Competitor “E” did. In addition, the Symantec NetBackup Integrated Appliance with NetBackup 7.6 created backup images that offered granular recovery without additional steps. These time and effort savings can scale as your VM footprint grows, allowing you to execute both system protection and user-friendly, simplified recovery.
Get higher transaction throughput and better price/performance with an Amazon...Principled Technologies
In addition, the EBS gp3-backed EC2 r5b.16xlarge instance delivered a lower average transaction latency to offer more consistent transactional database performance than two Microsoft Azure E64ds_v4 VM configurations
Keep remote desktop power users productive with Dell EMC PowerEdge R840 serve...Principled Technologies
When the Dell EMC™ PowerEdge™ R840 launched, we found that companies could get more power for their CPU-intensive workloads with this 2U four-socket rack server.1 Now, it presents an opportunity for you to support more power users, speed desktop responsiveness, and grow your employee base.
A company’s success depends on critical application performance and availability. Upgrades and patches can improve application efficiency and user experience, but making the necessary changes requires resource intensive environments to test updates before deploying them. What’s more, these applications need to continue accessing data even in the event of an on-premises crisis.
Our Dell EMC VMAX 250F and PowerEdge server solution supported test/dev environments and production database applications simultaneously without affecting the production applications’ performance. Storage latency for the VMAX 250F peaked at a millisecond in our testing while IOPS stayed within an acceptable range. The solution also kept data highly available with no downtime or performance drop when we initiated a lost host connection for the primary storage. Consider the Dell EMC VMAX 250F array for your datacenter to support the critical database applications that drive your company.
Run compute-intensive Apache Hadoop big data workloads faster with Dell EMC P...Principled Technologies
Moving compute-intensive, Hadoop big data workloads to current-generation Dell EMC PowerEdge R640 servers powered by 2nd Generation Intel Xeon Scalable processors could allow your organization to better meet the data analysis challenges of today. Faster analysis of large data sets means getting insight into your organization, products, and services sooner, which could help your organization grow and beat its competition.
The switching method you choose for your SBC environment can help determine performance and the experience that end-users have. We found that unifying switching with Cisco VM-FEX resulted in up to 29 percent lower latency than a solution using a traditional vSwitch when running a Citrix XenApp hosted shared desktop farm. Furthermore, the Cisco VM-FEX solution used up to 53 percent less CPU than the vSwitch solution did under extreme network conditions. In addition to these performance advantages, Cisco UCS Manager provides a central point of management and a simplified method to add vSphere hosts to the VM-FEX-enabled vSwitch, which can reduce management time and costs.
As our results show, switching to Cisco VM-FEX can provide your users with a more responsive environment.
Slow performance and unavailable critical applications can impinge a company’s progress. You can apply patches and updates to improve application quality and user experience, but these changes need to be tested in resource-intensive environments before deployment. Keeping these applications accessing data is vital, too, as on-premises events can put availability at risk.
Our Dell EMC VMAX 250F and PowerEdge server solution supported test/dev environments and production database applications simultaneously without affecting the production applications’ performance. As we added VMs designed for test/dev environments, the production workload maintained an acceptable level of IOPS and achieved an average storage latency of less than a millisecond. The solution also kept data highly available with no downtime and no performance drop when we initiated a lost host connection for the primary storage. To run critical database applications of your company, consider the Dell EMC VMAX 250F for your datacenter.
AMD EPYC 7763 processor-based servers can offer a better value for MySQL work...Principled Technologies
A cluster of servers with 3rd Gen AMD EPYC 7763 processors costs less and offered better performance per dollar than comparably configured servers with 3rd Gen Intel Xeon Platinum 8380 processors
Get competitive logistic regression performance with servers with AMD EPYC 75...Principled Technologies
Compared to servers powered by 3rd Gen Intel Xeon Platinum 8380 processors, a cluster of 3rd Gen AMD EPYC 75F3 processor-based servers offeredcomparable logistic regression performance at a lower solution cost to processmore data per hour for each dollar spent
Business-critical applications on VMware vSphere 6, VMware Virtual SAN, and V...Principled Technologies
Moving to the virtualized, software-defined datacenter can offer real benefits to today’s organizations. As our testing showed, virtualizing business-critical applications with VMware vSphere, VMware Virtual SAN, and VMware NSX not only delivered reliable performance in a peak utilization scenario, but also delivered business continuity during and after a simulated site evacuation.
Using this VMware Validated Design with QCT hardware and Intel SSDs, we demonstrated a virtualized critical Oracle Database application environment delivering strong performance, even when under extreme duress.
Recognizing that many organizations have multiple sites, we also proved that our environment performed reliably under a site evacuation scenario, migrating the primary site VMs to the secondary in just over eight minutes with no downtime.
With these features and strengths, the VMware Validated Design SDDC is a proven solution that allows for efficient deployment of components and can help improve the reliability, flexibility, and mobility of your multi-site environment.
A single-socket Dell EMC PowerEdge R7515 solution delivered better value on a...Principled Technologies
If your company is running important business applications in VMware vSAN clusters of servers that are several years old, chances are good that you’re considering upgrading to newer hardware. Our testing demonstrated that our clusters of single-socket Dell EMC PowerEdge R7515 servers and clusters of dual-socket HPE ProLiant DL380 Gen10 servers could both improve upon the database performance of a legacy cluster with five-year-old servers by more than 50 percent, with the Dell EMC cluster achieving 93.4 percent of the performance of the HPE cluster.
3 key wins: Dell EMC PowerEdge MX with OpenManage Enterprise over Cisco UCS a...Principled Technologies
In head-to-head tests, the modular Dell EMC™ PowerEdge™ MX7000 with
OpenManage™ Enterprise reduced admin time and effort on repetitive tasks when compared to Cisco UCS® 5108 with Cisco UCS Manager and HPE Synergy with OneView.
Proper resource allocation is critical to achieving top application performance in a virtualized environment. Resource contention degrades performance and underutilization can lead to costly server sprawl.
We found that adding VMTurbo to a VMware vSphere 5.5 cluster and following its reallocation recommendations gave our application performance a big boost. After reducing vCPU count, increasing memory allocation to active databases, and moving VMs to more responsive storage as VMTurbo directed, online transactions increased by 23.7 percent while latency dropped significantly. Avoid the pitfalls of poorly allocated VM resources and give your virtualized application every advantage by gaining control of your environment at every level.
Your datacenter is capable of doing great things—if you let it. Upgrades from Intel for compute, storage, and networking components can help your business support new services and expand your customer base. In our hands-on testing, we found that new Intel processors, high-bandwidth network components, and SATA or PCIe SSDs working together can boost your datacenter’s capabilities, which could translate to better business operations for your organization.
SQL Server 2016 database performance on the Dell EMC PowerEdge FC630 QLogic 1...Principled Technologies
Upgrading the hardware running your SQL Server to a space-efficient modular Dell EMC modern environment can help your company achieve a great deal of database work in a small amount of space. With the Dell Express Flash technology, adding a caching solution such as Samsung AutoCache can make the environment even more efficient.
In the PT labs, we ran a mixed database workload on six Dell EMC PowerEdge FC630 servers, powered by Intel Xeon E5-2667 processors, in three PowerEdge FX2 enclosures. The solution included the QLogic QLE2692 16Gb FC adapter with StorFusion Technology, Dell EMC Storage SC9000 all-flash storage, and Dell EMC PowerEdge Express Flash NVMe Performance PCIe SSDs.
With no caching solution, the 36 SQL Server 2016 VMs on the six servers achieved a total of 431,839 orders per minute while an Oracle workload ran on 12 VMs. When we added a caching solution to accelerate the SQL database volumes, the performance across the 36 SQL Server 2016 VMs doubled to 871,580. These numbers show the power of server-side caching to alleviate pressure on the storage array allowing you to get even more out of the Dell EMC modern environment.
Get improved performance and new features from Dell EMC PowerEdge servers wit...Principled Technologies
We put 3rd Gen AMD EPYC processor-powered Dell EMC PowerEdge servers to the test with a variety of workloads to see the benefits and features your organization could expect from this latest offering
Component upgrades from Intel and Dell can increase VM density and boost perf...Principled Technologies
As the needs of your business grow, so must the power of your server infrastructure. Rather than purchasing replacement servers with base configurations, consider upgrading key components to ensure you get the performance you need.
We found that upgrading to the Dell PowerEdge R730 with the Intel Xeon processor E5-2699 v3, Microsoft Windows Server 2012 R2 operating system, Intel SSD DC S3700 series drive, and Intel Ethernet CNA X520 series adapters supported an extra 16 VMs, 67 percent more VMs than the previous-generation Dell PowerEdge R720 solution.
When you purchase a server, wisely selecting these components offered by Dell and Intel can allow your business to hit the sweet spot of supporting all your users without breaking the bank. The option to upgrade server components can provide your infrastructure with room to grow in the future, as your business needs increase.
Finally, these select upgrades could translate to savings for your business—fewer servers you need to purchase now to meet performance demands and a longer lifespan for these servers as your business continues to grow.
Watch your transactional database performance climb with Intel Optane DC pers...Principled Technologies
Dell EMC PowerEdge R740xd servers with Intel Optane DC persistent memory handled more transactions per minute than configurations with NAND flash NVMe drives or SATA SSDs
Symantec NetBackup 7.6 benchmark comparison: Data protection in a large-scale...Principled Technologies
The footprint of a VM can grow quickly in an enterprise environment and large-scale VM deployments in the thousands are common. As this number of deployed systems grows, so does the risk of failure. Critical failures can become unavoidable and offering data protection from a backup solution promotes business continuity. Elongated protection windows requiring multiple jobs of different types can create resource contention with production environments and may require valuable IT admin time, so a finite window for system backups can have plenty of importance.
In our hands-on SAN backup testing, the Symantec NetBackup Integrated Appliance running NetBackup 7.6 offered application protection to 1,000 VMs in 66.8 percent less time than Competitor “E” did. In addition, the Symantec NetBackup Integrated Appliance with NetBackup 7.6 created backup images that offered granular recovery without additional steps. These time and effort savings can scale as your VM footprint grows, allowing you to execute both system protection and user-friendly, simplified recovery.
Get higher transaction throughput and better price/performance with an Amazon...Principled Technologies
In addition, the EBS gp3-backed EC2 r5b.16xlarge instance delivered a lower average transaction latency to offer more consistent transactional database performance than two Microsoft Azure E64ds_v4 VM configurations
Keep remote desktop power users productive with Dell EMC PowerEdge R840 serve...Principled Technologies
When the Dell EMC™ PowerEdge™ R840 launched, we found that companies could get more power for their CPU-intensive workloads with this 2U four-socket rack server.1 Now, it presents an opportunity for you to support more power users, speed desktop responsiveness, and grow your employee base.
A company’s success depends on critical application performance and availability. Upgrades and patches can improve application efficiency and user experience, but making the necessary changes requires resource intensive environments to test updates before deploying them. What’s more, these applications need to continue accessing data even in the event of an on-premises crisis.
Our Dell EMC VMAX 250F and PowerEdge server solution supported test/dev environments and production database applications simultaneously without affecting the production applications’ performance. Storage latency for the VMAX 250F peaked at a millisecond in our testing while IOPS stayed within an acceptable range. The solution also kept data highly available with no downtime or performance drop when we initiated a lost host connection for the primary storage. Consider the Dell EMC VMAX 250F array for your datacenter to support the critical database applications that drive your company.
Run compute-intensive Apache Hadoop big data workloads faster with Dell EMC P...Principled Technologies
Moving compute-intensive, Hadoop big data workloads to current-generation Dell EMC PowerEdge R640 servers powered by 2nd Generation Intel Xeon Scalable processors could allow your organization to better meet the data analysis challenges of today. Faster analysis of large data sets means getting insight into your organization, products, and services sooner, which could help your organization grow and beat its competition.
The switching method you choose for your SBC environment can help determine performance and the experience that end-users have. We found that unifying switching with Cisco VM-FEX resulted in up to 29 percent lower latency than a solution using a traditional vSwitch when running a Citrix XenApp hosted shared desktop farm. Furthermore, the Cisco VM-FEX solution used up to 53 percent less CPU than the vSwitch solution did under extreme network conditions. In addition to these performance advantages, Cisco UCS Manager provides a central point of management and a simplified method to add vSphere hosts to the VM-FEX-enabled vSwitch, which can reduce management time and costs.
As our results show, switching to Cisco VM-FEX can provide your users with a more responsive environment.
Slow performance and unavailable critical applications can impinge a company’s progress. You can apply patches and updates to improve application quality and user experience, but these changes need to be tested in resource-intensive environments before deployment. Keeping these applications accessing data is vital, too, as on-premises events can put availability at risk.
Our Dell EMC VMAX 250F and PowerEdge server solution supported test/dev environments and production database applications simultaneously without affecting the production applications’ performance. As we added VMs designed for test/dev environments, the production workload maintained an acceptable level of IOPS and achieved an average storage latency of less than a millisecond. The solution also kept data highly available with no downtime and no performance drop when we initiated a lost host connection for the primary storage. To run critical database applications of your company, consider the Dell EMC VMAX 250F for your datacenter.
AMD EPYC 7763 processor-based servers can offer a better value for MySQL work...Principled Technologies
A cluster of servers with 3rd Gen AMD EPYC 7763 processors costs less and offered better performance per dollar than comparably configured servers with 3rd Gen Intel Xeon Platinum 8380 processors
Get competitive logistic regression performance with servers with AMD EPYC 75...Principled Technologies
Compared to servers powered by 3rd Gen Intel Xeon Platinum 8380 processors, a cluster of 3rd Gen AMD EPYC 75F3 processor-based servers offeredcomparable logistic regression performance at a lower solution cost to processmore data per hour for each dollar spent
Realize 2.1X the performance with 20% less power with AMD EPYC processor-back...Principled Technologies
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
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.
MySQL and Spark machine learning performance on Azure VMsbased on 3rd Gen AMD...Principled Technologies
If your organization is one of the many that are shifting critical applications to the cloud, you know that cloud service providers offer a staggering number of virtual machine options. In your quest for the best performance, an important factor to consider is the processor that powers the VMs.
Combine containerization and GPU acceleration on VMware: Dell PowerEdge R750 ...Principled Technologies
Our results running a vGPU-accelerated deep learning image-classification workload in this environment
We ran a deep learning image-classification workload on a Dell PowerEdge R750 server with an NVIDIA A100 Tensor Core GPU that was in a VMware vSphere with Tanzu Kubernetes container environment along with two other servers. Using GPU virtualization to allow 10 containers to share the single GPU, our test solution achieved a maximum of 29,896 samples per second. With a single container using all of the GPU resources and a larger batch size, the solution achieved a maximum of 34,352 samples per second. These results show that the PowerEdge R750 with an NVIDIA A100 Tensor Core GPU in a VMware Kubernetes environment with GPU virtualization can support flexibly apportioning GPU compute capability across multiple machine learning workloads in Kubernetes clusters.
Amazon EC2 provides a broad selection of instance types to deliver high performance for a diverse mix of applications. In this session, we overview the drivers of system performance and discuss in depth how Amazon EC2 instances deliver system performance while also providing elasticity and complete control over your infrastructure. We also detail best practices and share performance tips for getting the most out of your Amazon EC2 instances.
Boosting virtualization performance with Intel SSD DC Series P3600 NVMe SSDs ...Principled Technologies
When it comes time to make your server purchase or if you’re looking for an easy way to boost performance of existing infrastructure, consider upgrading your server’s internal storage. As our hands-on tests with a Dell EMC PowerEdge R630 environment running VMware Virtual SAN proved, Intel SSD DC P3600 Series NVMe SSDs could increase virtualized mixed-workload performance by as much as 59.9 percent compared to SATA SSDs while allowing you to run a large additional number of VMs. When you improve performance for your virtualized workloads, your employees and customers will benefit. By increasing performance with Intel NVMe SSDs on your Dell EMC PowerEdge R630 servers, you can potentially slash wait times and do more work on your servers without having to expand your infrastructure with additional storage arrays, which can translate to happier users and a more efficient infrastructure.
Do more Apache Cassandra distributed database work with AMD EPYC 7601 processorsPrincipled Technologies
Private clouds require an investment in hardware that can often be costly—a cost that grows along with the size of distributed database workloads a business deploys. The new AMD EPYC processor architecture can help ease that burden by increasing the available number of cores per socket, which could let businesses get more distributed database work done per server compared to a previous generation Intel Xeon E5-2699 v4 processor architecture. In our tests, we found that a cluster based on 32-core AMD EPYC 7601 processors increased the operations per second an Apache Cassandra distributed database could process by 50 percent over a same-sized cluster based on 22-core Intel Xeon processors E5-2699 v4.3 This means that businesses seeking to run these reliable, elastic databases on a private cloud setup could do so on an AMD EPYC 7601 processor-based server platform and experience faster updates and shorter data load times.
Choosing the Right EC2 Instance and Applicable Use Cases - AWS June 2016 Webi...Amazon Web Services
Amazon Elastic Compute Cloud (Amazon EC2) provides a broad selection of instance types to accommodate a diverse mix of workloads. In this technical session, we provide an overview of the Amazon EC2 instance platform, key platform features, and the concept of instance generations. We dive into the design choices of the different instance families, including the General Purpose, Compute Optimized, Storage Optimized, and Memory Optimized families. We also detail best practices and share performance tips for getting the most out of your Amazon EC2 instances.
Learning Objectives: • Understand the differences between instances • Learn best practices and tips for getting the most out of EC2 instances
Join us for an exciting and informative preview of the broadest range of next-generation systems optimized for tomorrow’s data center workloads, Powered by 4th Gen Intel® Xeon® Scalable Processors (formerly codenamed Sapphire Rapids).
Experts from Supermicro and Intel will discuss how the upcoming Supermicro X13 systems will enable new performance levels utilizing state-of-the-art technology, including DDR5, PCIe 5.0, Compute Express Link™ 1.1, and Intel® Advanced Matrix Extensions (Intel AMX).
Amazon EC2 provides a broad selection of instance types to deliver high performance for a diverse mix of applications. In this session, we overview the drivers of system performance and discuss in depth how Amazon EC2 instances deliver system performance while also providing elasticity and complete control over your infrastructure. We also detail best practices and share performance tips for getting the most out of your Amazon EC2 instances.
The Supermicro X12 product line, powered by 3rd Gen Intel® Xeon® Scalable processors, contains many innovations that gives organizations more performance for a variety of workloads.
Join this webinar to learn more about the outstanding performance you can get by using Supermicro X12 servers and storage systems using the latest technologies from Intel®.
Watch the webinar: https://www.brighttalk.com/webcast/17278/514618
Investing in GenAI: Cost‑benefit analysis of Dell on‑premises deployments vs....Principled Technologies
Conclusion
Diving into the world of GenAI has the potential to yield a great many benefits for your organization, but it first requires consideration for how best to implement those GenAI workloads. Whether your AI goals are to create a chatbot for online visitors, generate marketing materials, aid troubleshooting, or something else, implementing an AI solution requires careful planning and decision-making. A major decision is whether to host GenAI in the cloud or keep your data on premises. Traditional on-premises solutions can provide superior security and control, a substantial concern when dealing with large amounts of potentially sensitive data. But will supporting a GenAI solution on site be a drain on an organization’s IT budget?
In our research, we found that the value proposition is just the opposite: Hosting GenAI workloads on premises, either in a traditional Dell solution or using a managed Dell APEX pay-per-use solution, could significantly lower your GenAI costs over 3 years compared to hosting these workloads in the cloud. In fact, we found that a comparable AWS SageMaker solution would cost up to 3.8 times as much and an Azure ML solution would cost up to 3.6 times as much as GenAI on a Dell APEX pay-per-use solution. These results show that organizations looking to implement GenAI and reap the business benefits to come can find many advantages in an on-premises Dell solution, whether they opt to purchase and manage it themselves or choose a subscription-based Dell APEX pay-per-use solution. Choosing an on-premises Dell solution could save your organization significantly over hosting GenAI in the cloud, while giving you control over the security and privacy of your data as well as any updates and changes to the environment, and while ensuring your environment is managed consistently.
Workstations powered by Intel can play a vital role in CPU-intensive AI devel...Principled Technologies
In three AI development workflows, Intel processor-powered workstations delivered strong performance, without using their GPUs, making them a good choice for this part of the AI process
Conclusion
We executed three AI development workflows on tower workstations and mobile workstations from three vendors, with each workflow utilizing only the Intel CPU cores, and found that these platforms were suitable for carrying out various AI tasks. For two of the workflows, we learned that completing the tasks on the tower workstations took roughly half as much time as on the mobile workstations. This supports the idea that the tower workstations would be appropriate for a development environment for more complex models with a greater volume of data and that the mobile workstations would be well-suited for data scientists fine-tuning simpler models. In the third workflow, we explored tower workstation performance with different precision levels and learned that using 16-bit floating point precision allowed the workstations to execute the workflow in less time and also reduced memory usage dramatically. For all three AI workflows we executed, we consider the time the workstations needed to complete the tasks to be acceptable, and believe that these workstations can be appropriate, cost-effective choices for these kinds of activities.
Enable security features with no impact to OLTP performance with Dell PowerEd...Principled Technologies
Get comparable online transaction processing (OLTP) performance with or without enabling AMD Secure Memory Encryption and AMD Secure Encrypted Virtualization - Encrypted State
Conclusion
You’ve likely already implemented many security measures for your servers, which may include physical security for the data center, hardware-level security, and software-level security. With the cost of data breaches high and still growing, however, wise IT teams will consider what additional security measures they may be able to implement.
AMD SME and SEV-ES are technologies that are already available within your AMD processor-powered 16th Generation Dell PowerEdge servers—and in our testing, we saw that they can offer extra layers of security without affecting performance. We compared the online transaction processing performance of a Dell PowerEdge R7625 server, powered by AMD EPYC 9274F processors, with and without these two security features enabled. We found that enabling AMD Secure Memory Encryption and Secure Encrypted Virtualization-Encrypted State did not impact performance at all.
If your team is assessing areas where you might be able to enhance security—without paying a large performance cost—consider enabling AME SME and AMD SEV-ES in your Dell PowerEdge servers.
Improving energy efficiency in the data center: Endure higher temperatures wi...Principled Technologies
In high-temperature test scenarios, a Dell PowerEdge HS5620 server continued running an intensive workload without component warnings or failures, while a Supermicro SYS‑621C-TN12R server failed
Conclusion: Remain resilient in high temperatures with the Dell PowerEdge HS5620 to help increase efficiency
Increasing your data center’s temperature can help your organization make strides in energy efficiency and cooling cost savings. With servers that can hold up to these higher everyday temperatures—as well as high temperatures due to unforeseen circumstances—your business can continue to deliver the performance your apps and clients require.
When we ran an intensive floating-point workload on a Dell PowerEdge HS5620 and a Supermicro SYS-621CTN12R in three scenario types simulating typical operations at 25°C, a fan failure, and an HVAC malfunction, the Dell server experienced no component warnings or failures. In contrast, the Supermicro server experienced warnings in all three scenario types and experienced component failures in the latter two tests, rendering the system unusable. When we inspected and analyzed each system, we found that the Dell PowerEdge HS5620 server’s motherboard layout, fans, and chassis offered cooling design advantages.
For businesses aiming to meet sustainability goals by running hotter data centers, as well as those concerned with server cooling design, the Dell PowerEdge HS5620 is a strong contender to take on higher temperatures during day-to-day operations and unexpected malfunctions.
Dell APEX Cloud Platform for Red Hat OpenShift: An easily deployable and powe...Principled Technologies
The 4th Generation Intel Xeon Scalable processor‑powered solution deployed in less than two hours and ran a Kubernetes container-based generative AI workload effectively
Dell APEX Cloud Platform for Red Hat OpenShift: An easily deployable and powe...Principled Technologies
The 4th Generation Intel Xeon Scalable processor‑powered solution deployed in less than two hours and ran a generative AI workload effectively
Conclusion
The appeal of incorporating GenAI into your organization’s operations is likely great. Getting started with an efficient solution for your next LLM workload or application can seem daunting because of the changing hardware and software landscape, but Dell APEX Cloud Platform for Red Hat OpenShift powered by 4th Gen Intel Xeon Scalable processors could provide the solution you need. We started with a Dell Validated Design as a reference, and then went on to modify the deployment as necessary for our Llama 2 workload. The Dell APEX Cloud Platform for Red Hat OpenShift solution worked well for our LLM, and by using this deployment guide in conjunction with numerous Dell documents and some flexibility, you could be well on your way to innovating your next GenAI breakthrough.
Upgrade your cloud infrastructure with Dell PowerEdge R760 servers and VMware...Principled Technologies
Compared to a cluster of PowerEdge R750 servers running VMware Cloud Foundation (VCF)
For organizations running clusters of moderately configured, older Dell PowerEdge servers with a previous version of VCF, upgrading to better-configured modern servers can provide a significant performance boost and more.
Upgrade your cloud infrastructure with Dell PowerEdge R760 servers and VMware...Principled Technologies
Compared to a cluster of PowerEdge R750 servers running VMware Cloud Foundation 4.5
If your company is struggling with underperforming infrastructure, upgrading to 16th Generation Dell PowerEdge servers running VCF 5.1 could be just what you need to handle more database throughput and reduce vSAN latencies. As an additional benefit to IT admins, we also found that the embedded VMware Aria Operation adapter provided useful infrastructure insights.
Improve performance and gain room to grow by easily migrating to a modern Ope...Principled Technologies
We deployed this modern environment, then migrated database VMs from legacy servers and saw performance improvements that support consolidation
Conclusion
If your organization’s transactional databases are running on gear that is several years old, you have much to gain by upgrading to modern servers with new processors and networking components and an OpenShift environment. In our testing, a modern OpenShift environment with a cluster of three Dell PowerEdge R7615 servers with 4th Generation AMD EPYC processors and high-speed 100Gb Broadcom NICs outperformed a legacy environment with MySQL VMs running on a cluster of three Dell PowerEdge R7515 servers with 3rd Generation AMD EPYC processors and 25Gb Broadcom NICs. We also easily migrated a VM from the legacy environment to the modern environment, with only a few steps required to set up and less than ten minutes of hands-on time. The performance advantage of the modern servers would allow a company to reduce the number of servers necessary to perform a given amount of database work, thus lowering operational expenditures such as power and cooling and IT staff time for maintenance. The high-speed 100Gb Broadcom NICs in this solution also give companies better network performance and networking capacity to grow as they embrace emerging technologies such as AI that put great demands on networks.
Boost PC performance: How more available memory can improve productivityPrincipled Technologies
With more memory available, system performance of three Dell devices increased, which can translate to a better user experience
Conclusion
When your system has plenty of RAM to meet your needs, you can efficiently access the applications and data you need to finish projects and to-do lists without sacrificing time and focus. Our test results show that with more memory available, three Dell PCs delivered better performance and took less time to complete the Procyon Office Productivity benchmark. These advantages translate to users being able to complete workflows more quickly and multitask more easily. Whether you need the mobility of the Latitude 5440, the creative capabilities of the Precision 3470, or the high performance of the OptiPlex Tower Plus 7010, configuring your system with more RAM can help keep processes running smoothly, enabling you to do more without compromising performance.
Deploy with confidence: VMware Cloud Foundation 5.1 on next gen Dell PowerEdg...Principled Technologies
A Principled Technologies deployment guide
Conclusion
Deploying VMware Cloud Foundation 5.1 on next gen Dell PowerEdge servers brings together critical virtualization capabilities and high-performing hardware infrastructure. Relying on our hands-on experience, this deployment guide offers a comprehensive roadmap that can guide your organization through the seamless integration of advanced VMware cloud solutions with the performance and reliability of Dell PowerEdge servers. In addition to the deployment efficiency, the Cloud Foundation 5.1 and PowerEdge solution delivered strong performance while running a MySQL database workload. By leveraging VMware Cloud Foundation 5.1 and PowerEdge servers, you could help your organization embrace cloud computing with confidence, potentially unlocking a new level of agility, scalability, and efficiency in your data center operations.
Upgrade your cloud infrastructure with Dell PowerEdge R760 servers and VMware...Principled Technologies
Compared to a cluster of PowerEdge R750 servers running VMware Cloud Foundation 4.5
Conclusion
If your company is struggling with underperforming infrastructure, upgrading to 16th Generation Dell PowerEdge servers running VCF 5.1 could be just what you need to handle more database throughput and reduce vSAN latencies. We found that a Dell PowerEdge R760 server cluster running VCF 5.1 processed over 78 percent more TPM and 79 percent more NOPM than a Dell PowerEdge R750 server cluster running VCF 4.5. It’s also worth noting that the PowerEdge R750 cluster bottlenecked on vSAN storage, with max write latency at 8.9ms. For reference, the PowerEdge R760 cluster clocked in at 3.8ms max write latency. This higher latency is due in part to the single disk group per host on the moderately configured PowerEdge R750 cluster, while the better-configured PowerEdge R760 cluster supported four disk groups per host. As an additional benefit to IT admins, we also found that the embedded VMware Aria Operation adapter provided useful infrastructure insights.
Based on our research using publicly available materials, it appears that Dell supports nine of the ten PC security features we investigated, HP supports six of them, and Lenovo supports three features.
Increase security, sustainability, and efficiency with robust Dell server man...Principled Technologies
Compared to the Supermicro management portfolio
Conclusion
Choosing a vendor for server purchases is about more than just the hardware platform. Decision-makers must also consider more long-term concerns, including system/data security, energy efficiency, and ease of management. These concerns make the systems management tools a vendor offers as important as the hardware.
We investigated the features and capabilities of server management tools from Dell and Supermicro, comparing Dell iDRAC9 against Supermicro IPMI for embedded server management and Dell OpenManage Enterprise and CloudIQ against Supermicro Server Manager for one-to-many device and console management and monitoring. We found that the Dell management tools provided more comprehensive security, sustainability, and management/monitoring features and capabilities than Supermicro servers did. In addition, Dell tools automated more tasks to ease server management, resulting in significant time savings for administrators versus having to do the same tasks manually with Supermicro tools.
When making a server purchase, a vendor’s associated management products are critical to protect data, support a more sustainable environment, and to ease the maintenance of systems. Our tests and research showed that the Dell management portfolio for PowerEdge servers offered more features to help organizations meet these goals than the comparable Supermicro management products.
Increase security, sustainability, and efficiency with robust Dell server man...Principled Technologies
Compared to the Supermicro management portfolio
Conclusion
Choosing a vendor for server purchases is about more than just the hardware platform. Decision-makers must also consider more long-term concerns, including system/data security, energy efficiency, and ease of management. These concerns make the systems management tools a vendor offers as important as the hardware.
We investigated the features and capabilities of server management tools from Dell and Supermicro, comparing Dell iDRAC9 against Supermicro IPMI for embedded server management and Dell OpenManage Enterprise and CloudIQ against Supermicro Server Manager for one-to-many device and console management and monitoring. We found that the Dell management tools provided more comprehensive security, sustainability, and management/monitoring features and capabilities than Supermicro servers did. In addition, Dell tools automated more tasks to ease server management, resulting in significant time savings for administrators versus having to do the same tasks manually with Supermicro tools.
When making a server purchase, a vendor’s associated management products are critical to protect data, support a more sustainable environment, and to ease the maintenance of systems. Our tests and research showed that the Dell management portfolio for PowerEdge servers offered more features to help organizations meet these goals than the comparable Supermicro management products.
Scale up your storage with higher-performing Dell APEX Block Storage for AWS ...Principled Technologies
In our tests, Dell APEX Block Storage for AWS outperformed similarly configured solutions from Vendor A, achieving more IOPS, better throughput, and more consistent performance on both NVMe-supported configurations and configurations backed by Elastic Block Store (EBS) alone.
Dell APEX Block Storage for AWS supports a full NVMe backed configuration, but Vendor A doesn’t—its solution uses EBS for storage capacity and NVMe as an extended read cache—which means APEX Block Storage for AWS can deliver faster storage performance.
Scale up your storage with higher-performing Dell APEX Block Storage for AWSPrincipled Technologies
Dell APEX Block Storage for AWS offered stronger and more consistent storage performance for better business agility than a Vendor A solution
Conclusion
Enterprises desiring the flexibility and convenience of the cloud for their block storage workloads can find fast-performing solutions with the enterprise storage features they’re used to in on-premises infrastructure by selecting Dell APEX Block Storage for AWS.
Our hands-on tests showed that compared to the Vendor A solution, Dell APEX Block Storage for AWS offered stronger, more consistent storage performance in both NVMe-supported and EBS-backed configurations. Using NVMe-supported configurations, Dell APEX Block Storage for AWS achieved 4.7x the random read IOPS and 5.1x the throughput on sequential read operations per node vs. Vendor A. In our EBS-backed comparison, Dell APEX Block Storage for AWS offered 2.2x the throughput per node on sequential read operations vs. Vendor A.
Plus, the ability to scale beyond three nodes—up to 512 storage nodes with capacity of up to 8 PBs—enables Dell APEX Block Storage for AWS to help ensure performance and capacity as your team plans for the future.
Get in and stay in the productivity zone with the HP Z2 G9 Tower WorkstationPrincipled Technologies
We compared CPU performance and noise output of an HP Z2 G9 Tower Workstation in High Performance Mode to Dell Precision 3660 and 5860 tower workstations in optimized performance modes
Conclusion
HP Z2 G9 Tower Workstation users can change the BIOS settings to dial in the performance mode that best suits their needs: High Performance Mode, Performance Mode, or Quiet Mode. In good
news for both creative and technical professionals, we found that an Intel Core i9-13900 processor-powered HP Z2 G9 Tower Workstation set to High Performance mode received higher CPU-based benchmark scores than both a similarly configured Dell Precision 3660 and a Dell Precision 5860 equipped with an Intel Xeon w5-2455x processor. Plus, the HP Z2 G9 Tower Workstation was quieter while running CPU-intensive Cinebench 2024 and SPECapc for Solidworks 2022 workloads than both Dell Precision tower workstations. This means HP Z2 G9 Tower Workstation users who prize performance over everything else can do so without sacrificing a quiet workspace.
Open up new possibilities with higher transactional database performance from...Principled Technologies
In our PostgreSQL tests, R7i instances boosted performance over R6i instances with previous-gen processors
If you use the open-source PostgreSQL database to run your critical business operations, you have many cloud options from which to choose. While many of these instances can do the job, some can deliver stronger performance, which can mean getting a greater return on your cloud investment.
We conducted hands-on testing with the HammerDB TPROC-C benchmark to see how the PostgreSQL performance of Amazon EC2 R7i instances, enabled by 4th Gen Intel Xeon Scalable processors, stacked up to that of R6i instances with previous-generation processors. We learned that small, medium-sized, and large R7i instances with the newer processors delivered better OLTP performance, with improvements as high as 13.8 percent. By choosing the R7i instances, your organization has the potential to support more users, deliver a better experience to those users, and even lower your cloud operating expenditures by requiring fewer instances to get the job done.
Improving database performance and value with an easy migration to Azure Data...Principled Technologies
Migrating from Azure Database for MySQL – Single Server to a Flexible Server solution was quick and provided performance and cost benefits
Don’t put off migrating your databases from Azure Database for MySQL – Single Server until the last minute—which is September 2024, when the service will end. Our hands-on testing shows that moving to Azure Database for MySQL – Flexible Server is a simple process that can actually improve your overall database performance and offer better value. With as much as 117 percent better OLTP performance on sysbench and up to 266 percent better performance per dollar, migrating your database to Azure Database for MySQL – Flexible Server with AMD EPYC processors can help you serve more database users and potentially improve your operating budget compared to the expiring Single Server option.
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024Albert Hoitingh
In this session I delve into the encryption technology used in Microsoft 365 and Microsoft Purview. Including the concepts of Customer Key and Double Key Encryption.
Elevating Tactical DDD Patterns Through Object CalisthenicsDorra BARTAGUIZ
After immersing yourself in the blue book and its red counterpart, attending DDD-focused conferences, and applying tactical patterns, you're left with a crucial question: How do I ensure my design is effective? Tactical patterns within Domain-Driven Design (DDD) serve as guiding principles for creating clear and manageable domain models. However, achieving success with these patterns requires additional guidance. Interestingly, we've observed that a set of constraints initially designed for training purposes remarkably aligns with effective pattern implementation, offering a more ‘mechanical’ approach. Let's explore together how Object Calisthenics can elevate the design of your tactical DDD patterns, offering concrete help for those venturing into DDD for the first time!
State of ICS and IoT Cyber Threat Landscape Report 2024 previewPrayukth K V
The IoT and OT threat landscape report has been prepared by the Threat Research Team at Sectrio using data from Sectrio, cyber threat intelligence farming facilities spread across over 85 cities around the world. In addition, Sectrio also runs AI-based advanced threat and payload engagement facilities that serve as sinks to attract and engage sophisticated threat actors, and newer malware including new variants and latent threats that are at an earlier stage of development.
The latest edition of the OT/ICS and IoT security Threat Landscape Report 2024 also covers:
State of global ICS asset and network exposure
Sectoral targets and attacks as well as the cost of ransom
Global APT activity, AI usage, actor and tactic profiles, and implications
Rise in volumes of AI-powered cyberattacks
Major cyber events in 2024
Malware and malicious payload trends
Cyberattack types and targets
Vulnerability exploit attempts on CVEs
Attacks on counties – USA
Expansion of bot farms – how, where, and why
In-depth analysis of the cyber threat landscape across North America, South America, Europe, APAC, and the Middle East
Why are attacks on smart factories rising?
Cyber risk predictions
Axis of attacks – Europe
Systemic attacks in the Middle East
Download the full report from here:
https://sectrio.com/resources/ot-threat-landscape-reports/sectrio-releases-ot-ics-and-iot-security-threat-landscape-report-2024/
The Art of the Pitch: WordPress Relationships and SalesLaura Byrne
Clients don’t know what they don’t know. What web solutions are right for them? How does WordPress come into the picture? How do you make sure you understand scope and timeline? What do you do if sometime changes?
All these questions and more will be explored as we talk about matching clients’ needs with what your agency offers without pulling teeth or pulling your hair out. Practical tips, and strategies for successful relationship building that leads to closing the deal.
Connector Corner: Automate dynamic content and events by pushing a buttonDianaGray10
Here is something new! In our next Connector Corner webinar, we will demonstrate how you can use a single workflow to:
Create a campaign using Mailchimp with merge tags/fields
Send an interactive Slack channel message (using buttons)
Have the message received by managers and peers along with a test email for review
But there’s more:
In a second workflow supporting the same use case, you’ll see:
Your campaign sent to target colleagues for approval
If the “Approve” button is clicked, a Jira/Zendesk ticket is created for the marketing design team
But—if the “Reject” button is pushed, colleagues will be alerted via Slack message
Join us to learn more about this new, human-in-the-loop capability, brought to you by Integration Service connectors.
And...
Speakers:
Akshay Agnihotri, Product Manager
Charlie Greenberg, Host
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf91mobiles
91mobiles recently conducted a Smart TV Buyer Insights Survey in which we asked over 3,000 respondents about the TV they own, aspects they look at on a new TV, and their TV buying preferences.
UiPath Test Automation using UiPath Test Suite series, part 3DianaGray10
Welcome to UiPath Test Automation using UiPath Test Suite series part 3. In this session, we will cover desktop automation along with UI automation.
Topics covered:
UI automation Introduction,
UI automation Sample
Desktop automation flow
Pradeep Chinnala, Senior Consultant Automation Developer @WonderBotz and UiPath MVP
Deepak Rai, Automation Practice Lead, Boundaryless Group and UiPath MVP
Essentials of Automations: Optimizing FME Workflows with ParametersSafe Software
Are you looking to streamline your workflows and boost your projects’ efficiency? Do you find yourself searching for ways to add flexibility and control over your FME workflows? If so, you’re in the right place.
Join us for an insightful dive into the world of FME parameters, a critical element in optimizing workflow efficiency. This webinar marks the beginning of our three-part “Essentials of Automation” series. This first webinar is designed to equip you with the knowledge and skills to utilize parameters effectively: enhancing the flexibility, maintainability, and user control of your FME projects.
Here’s what you’ll gain:
- Essentials of FME Parameters: Understand the pivotal role of parameters, including Reader/Writer, Transformer, User, and FME Flow categories. Discover how they are the key to unlocking automation and optimization within your workflows.
- Practical Applications in FME Form: Delve into key user parameter types including choice, connections, and file URLs. Allow users to control how a workflow runs, making your workflows more reusable. Learn to import values and deliver the best user experience for your workflows while enhancing accuracy.
- Optimization Strategies in FME Flow: Explore the creation and strategic deployment of parameters in FME Flow, including the use of deployment and geometry parameters, to maximize workflow efficiency.
- Pro Tips for Success: Gain insights on parameterizing connections and leveraging new features like Conditional Visibility for clarity and simplicity.
We’ll wrap up with a glimpse into future webinars, followed by a Q&A session to address your specific questions surrounding this topic.
Don’t miss this opportunity to elevate your FME expertise and drive your projects to new heights of efficiency.
Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...Ramesh Iyer
In today's fast-changing business world, Companies that adapt and embrace new ideas often need help to keep up with the competition. However, fostering a culture of innovation takes much work. It takes vision, leadership and willingness to take risks in the right proportion. Sachin Dev Duggal, co-founder of Builder.ai, has perfected the art of this balance, creating a company culture where creativity and growth are nurtured at each stage.
Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...
Prepare images for machine learning faster with servers powered by AMD EPYC 75F3 processors
1. Commissioned by AMD
Prepare images for machine learning faster with
servers powered by AMD EPYC™
75F3 processors
A server cluster with 3rd
Gen AMD EPYC processors achieved higher
throughput and took less time to prepare images for classification than a
server cluster with 3rd
Gen Intel Xeon Platinum 8380 processors
Kubernetes®
environments can make it easy to deploy, scale, and manage the image preprocessing phase of
machine learning workflows. Choosing 3rd
Gen AMD EPYC™
processors could help you save time during that
phase and do more work by completing more image processing tasks.
We compared the performance of two four-node clusters: one comprising Supermicro AS-1124US-TNRP servers
with 32-core 3rd
Gen AMD EPYC 75F3 processors, and one comprising Supermicro SYS-620U-TNR servers with
40-core 3rd
Gen Intel®
Xeon®
Platinum 8380 processors. We used a synthetic workload that we designed for
Kubernetes containers, which emulates image processing tasks typical of the early phases of an image-based
machine learning workflow. The clusters used VMware®
vSphere®
7.0 Update 2, VMware vSAN™
pooled storage,
and VMware Tanzu™
Kubernetes Grid Service, which integrates Tanzu Kubernetes support directly into vSphere.
The AMD EPYC processor-based cluster handled 1,720 images in 7.2 percent less time than the cluster powered
by Intel Xeon processors, processing images at a 7.9 percent higher frames per second (FPS) rate. We also found
that the AMD EPYC processor-based cluster could offer a 30.2 percent lower hardware and support cost than the
Intel Xeon Scalable processor-based cluster.
Prepare images in
7.2% less time
while running a
workload of 1,720 images*
Get a 30.2%
lower cost
on hardware
and support*
Achieve a 7.9% higher
throughput rate
while processing more
frames per second*
$
*on the AMD EPYC processor-powered servers we tested vs. the Intel Xeon processor-powered servers we tested
Prepare images for machine learning faster with servers powered by AMD EPYC™ 75F3 processors March 2022
A Principled Technologies report: Hands-on testing. Real-world results.
2. Commissioned by AMD
How we approached testing
We compared the following four-node clusters:
• Supermicro SYS-620U-TNR servers powered by Intel Xeon
Platinum 8380 processors
y For one server, the total cost of hardware plus three
years of labor and support and a one-year CRS
warranty was $29,908.90—a total of $119,635.60 for a
four-node cluster1
• Supermicro AS-1124US-TNRP servers powered by AMD EPYC
75F3 processors
y For one server, the total cost of hardware plus three years
of support and labor and a one-year CRS warranty was
$20,870.90—a total of $83,483.60 for a four-node cluster2
Other than the processors, we configured the server clusters
identically. Each of the servers in both clusters had a 240GB 6Gbps
SATA SSD to use for the hypervisor and three PCIe®
4.0 NVMe™
SSDs
for the vSAN storage. We also equipped each server with 1,024 GB
of PC4-3200 RAM across 16 memory modules.
We configured a vSAN datastore on each cluster with a single disk
group comprising one 3.84TB NVMe SSD for cache and two 3.84TB
NVMe SSDs for capacity per server. The vSAN datastore served as
shared storage for our Tanzu Kubernetes environment. The vSphere
with Tanzu environments had one worker node per server. To account
for the core count differences between the two processors in our
comparison—that is, 32 cores per AMD EPYC processor and 40
cores per Intel Xeon processor—we assigned a different number of
CPU resources to each worker based on the CPU architecture. In the
cluster powered by 3rd
Gen AMD EPYC processors, each worker node
had 56 vCPUs and 512 GB of memory fully reserved. In the cluster
with 3rd
Gen Intel Xeon Scalable processors, each worker node had
70 vCPUs and 512 GB of memory fully reserved.
During testing, both clusters averaged 86 percent CPU utilization. For more details about our configurations,
testing methodologies, and CPU utilization, see the science behind the report.
About VMware vSAN
For organizations looking to reduce
the complexity and footprint of
their data center, hyperconverged
infrastructure (HCI) can help. As
part of their HCI portfolio, VMware
offers software-defined storage with
vSAN that eliminates the need for
bulky, expensive, external arrays and
instead brings compute and storage
resources together.
According to VMware, vSAN is “an
enterprise-class storage virtualization
software that provides the easiest
path to HCI and hybrid cloud.”3
To
learn more about VMware vSAN,
visit https://www.vmware.com/
products/vsan.html.
Prepare images for machine learning faster with servers powered by AMD EPYC™ 75F3 processors March 2022 | 2
3. Commissioned by AMD
Less time to process images
To use image-based machine learning algorithms, organizations must first prepare their data for analysis. For
manufacturing organizations using the algorithms during assembly, for example, this might include images
of various products taken at multiple angles. Our workload mimicked simple image processing tasks that a
company might run on Kubernetes with vSphere with Tanzu during this preparation phase, such as reading
images from storage, scaling the images to a machine-learning-friendly size, transposing the images, and
converting the images to grayscale. (For more on our custom workload, see the science behind the report.)
By sorting and preparing images more quickly, organizations could get insights sooner. As Figure 1 shows, the
cluster of AMD EPYC 75F3 processor-based servers took 107.2 seconds to process 1,720 images. That was 7.2
percent less than the cluster of servers backed by the Intel Xeon Platinum 8380 processors, which needed 115.6
seconds to complete the workload.
Figure 1: The time in seconds that each cluster needed to complete the image preprocessing tasks on 1,720 images.
Less time is better. Source: Principled Technologies.
Real-world benefits for manufacturers
Machine learning algorithms can help companies
perform quality control inspections, ensure product
safety compliance, and verify correct assemblage.
Saving time during any part of those workflows could
translate to reaching business goals sooner, improving
productivity, and reducing production costs. During
the image preprocessing phase for any part of the
manufacturing process, your company could save time
by running workloads in a vSphere, vSAN, and Tanzu
Kubernetes environment on 3rd
Gen AMD EPYC 75F3
processor-based servers. We saw better performance
from a cluster of these servers using this environment,
processing images in 7.2 percent less time and at a
7.9 percent higher FPS rate than the servers powered
by Intel Xeon Platinum 8380 processors.
About VMware vSphere with Tanzu
We used vSphere with Tanzu to run our
containerized image processing workload.
VMware states that vSphere with Tanzu
“bridges the gap between IT and developers
for cloud-native apps on-premises and in
the cloud.”4
Tanzu Kubernetes Grid Service
is part of the Kubernetes-focused VMware
Tanzu portfolio, which enables organizations
to “build, run and manage modern apps on
any cloud—and continuously deliver value to
your customers,” as well as to “simplify multi-
cloud operations and free developers to move
faster with easy access to the right resources,”
according to VMware.5
For more information,
visit https://tanzu.vmware.com/tanzu.
3rd
Gen AMD EPYC 75F3 processor-based servers
107.2
115.6
Seconds | Smaller is better
3rd
Gen Intel Xeon Platinum 8380 processor-based servers
Time to complete our image preprocessing tasks
Prepare images for machine learning faster with servers powered by AMD EPYC™ 75F3 processors March 2022 | 3
4. Commissioned by AMD
A higher FPS processing rate
Figure 2 shows the image processing rate that each solution achieved during our testing. The AMD EPYC 75F3
processor-based cluster offered a rate of 15,537 FPS. That’s an increase of 7.9 percent compared to the Intel
Xeon Platinum 8380 processor-powered cluster, which processed the images at a rate of 14,388 FPS.
Figure 2: The rate of FPS each solution delivered during our 1,720-image preprocessing workload. Higher numbers are
better. Source: Principled Technologies.
About VMware vSphere 7.0 Update 2
We used VMware vSphere 7.0 Update 2 for our test environment. According to VMware, this vSphere 7.0 update
includes a CPU scheduler that is optimized for AMD EPYC processors, as it is “designed to take advantage of the
multiple last-level caches (LLCs) per CPU socket offered by the AMD EPYC processors.” VMware also states that
vSphere 7.0 Update 2 with the CPU scheduler can achieve near-optimal performance on most applications and
benchmarks on AMD EPYC processors.6
For more information, visit https://www.vmware.com/products/vsphere.html.
3rd
Gen AMD EPYC 75F3 processor-based servers
15,537 FPS
14,388 FPS
Higher is better
3rd
Gen Intel Xeon Platinum 8380 processor-based servers
Frames per second while processing images
About AMD EPYC 75F3 processors
Part of the third-generation EPYC 7003 Series, the AMD EPYC 75F3 processor has 32 cores and 64 threads of
computing power. According to AMD, the processor features PCIe 4.0 I/O connectivity, supports up to eight
DDR4 memory channels per socket, and is well-suited for workloads such as VDI and HCI.7
The third generation
of AMD EPYC processors can also offer AMD Infinity Guard security features, such as Secure Encrypted
Virtualization (SEV), Secure Nested Paging (SEV-SNP), Secure Memory Encryption (SME), and more.8
To learn
more about the EPYC 75F3 processor, visit https://www.amd.com/en/products/cpu/amd-epyc-75f3.
Prepare images for machine learning faster with servers powered by AMD EPYC™ 75F3 processors March 2022 | 4
5. Commissioned by AMD
Conclusion
We compared the image preprocessing for machine learning performance of two server solutions powered by
different processors: the AMD EPYC 75F3 and the Intel Xeon Platinum 8380. When we ran our containerized
image preprocessing workload on each cluster, we found that the 3rd
Gen AMD EPYC processor-powered cluster
needed 7.2 percent less time to completely process 1,720 images while handling 7.9 percent more frames per
second. This kind of performance shows that an organization using vSphere with Tanzu and vSAN to run their
Kubernetes workloads could get better image processing performance with the servers powered by AMD EPYC
75F3 processors. Our price analysis also demonstrated that the hardware and support costs for the AMD EPYC
75F3 processor-powered Supermicro AS-1124US-TNRP server cluster was 30.2 less than the Intel Xeon Platinum
8380 processor-powered Supermicro SYS-620U-TNR server cluster.
1. We received a quote from Supermicro on February 2, 2022 for the hardware and support cost of the server minus drive
costs. To arrive at the total cost, we added this amount to a drive cost quote we had received from Supermicro on
August 9, 2021.
2. We received a quote from Supermicro on February 2, 2022 for the hardware and support cost of the server minus drive
costs. To arrive at the total cost, we added this amount to a drive cost quote we had received from Supermicro on
August 9, 2021.
3. VMware, “What is vSAN?” accessed February 15, 2022, https://www.vmware.com/products/vsan.html.
4. VMware, “vSphere with Tanzu,” accessed February 7, 2022,
https://www.vmware.com/products/vsphere/vsphere-with-tanzu.html.
5. VMware, “VMware Tanzu Solution Brief,” accessed February 7, 2022,
https://d1fto35gcfffzn.cloudfront.net/tanzu/VMware-Tanzu-Solution-Brief-0121.pdf.
6. VMware, “Performance Optimizations in VMware vSphere 7.0 U2 CPU Scheduler for AMD EPYC Processors,” accessed
Feburary 7, 2022, https://www.vmware.com/content/dam/digitalmarketing/vmware/en/pdf/techpaper/performance/
vsphere70u2-cpu-sched-amd-epyc.pdf.
7. AMD, “AMD EPYC™
75F3,” accessed February 7, 2022, https://www.amd.com/en/products/cpu/amd-epyc-75f3.
8. Server OEMs and cloud providers must enable AMD Infinity Guard features for use. In addition,
security features can vary by AMD EPYC processor generations. Learn more about Infinity Guard at
https://www.amd.com/en/technologies/infinity-guard.
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/pagvE8O
Prepare images for machine learning faster with servers powered by AMD EPYC™ 75F3 processors March 2022 | 5
6. Disclaimer:
The content on the following pages includes appendices
and methodologies from our hands-on work.
We will publish this content as a separate document linked
to the report.
We must receive your approval on both the report and this
document before taking them public simultaneously.
7. The science behind the report:
Prepare images for machine
learning faster with servers
powered by AMD EPYC™
75F3 processors
Commissioned by AMD
This document describes what we tested, how we tested, and what we found. To learn how these facts translate
into real-world benefits, read the report Prepare images for machine learning faster with servers powered by
AMD EPYC™
75F3 processors.
We concluded our hands-on testing on February 2, 2022. During testing, we determined the appropriate
hardware and software configurations and applied updates as they became available. The results in this report
reflect configurations that we finalized on January 24, 2022 or earlier. Unavoidably, these configurations may not
represent the latest versions available when this report appears.
Our results
To learn more about how we have calculated the wins in this report, go to http://facts.pt/calculating-and-highlighting-wins.
Unless we state otherwise, we have followed the rules and principles we outline in that document.
Table 1: Results of our testing
Supermicro SYS-620U-TNR cluster
powered by Intel®
Xeon®
Platinum
8380 processors
Supermicro AS-1124US-TNRP cluster
powered by AMD EPYC™
75F3 processors
Frames per second (FPS) 14,388.4 15,537.8
Percentage more FPS N/A 7.9%
Time to complete the workload (seconds) 115.6 107.2
Percentage less time N/A 7.2%
Average CPU utilization during median runs 86.3% 86.2%
Prepare images for machine learning faster with servers powered by AMD EPYC™ 75F3 processors March 2022
A Principled Technologies report: Hands-on testing. Real-world results.
8. Commissioned by AMD
CPU utilization statistics
Figure 1: The average CPU usage that the four AMD EPYC 75F3 processor-powered Supermicro AS-1124US-TNRP servers achieved during
testing. Source: Principled Technologies.
Figure 2: The average CPU usage that the four Intel Xeon Platinum 8380 processor-powered Supermicro SYS-620U-TNR servers achieved
during testing. Source: Principled Technologies.
0
10
20
30
40
50
60
70
80
90
100
0 10 20 30 40 50 60 70 80 90 100 110 120 130 140
Utilization
(%)
Seconds
Average CPU usage: AMD EPYC 75F3 processor-powered cluster
0
10
20
30
40
50
60
70
80
90
100
Utilization
(%)
Seconds
Average CPU usage: Intel Xeon Platinum 8380
processor-powered cluster
0 10 20 30 40 50 60 70 80 90 100 110 120 130 140
Prepare images for machine learning faster with servers powered by AMD EPYC™ 75F3 processors March 2022 | 2
9. Commissioned by AMD
System configuration information
Table 2: Detailed information on the systems we tested.
System configuration information 4 x Supermicro SYS-620U-TNR 4 x Supermicro AS-1124US-TNRP
BIOS name and version 1.1A American Megatrends Inc. 2.1
Non-default BIOS settings Maximum Performance Determinism Slider: Power
Operating system name and version/build
number
VMware®
ESXi®
7.0U2a-17867351-standard VMware ESXi-7.0U2a-17867351-standard
Date of last OS updates/patches applied 1/17/2022 1/17/2022
Power management policy Maximum Performance Determinism Slider: Power
Processor
Number of processors 2 2
Vendor and model Intel Xeon Platinum 8380 AMD EPYC 75F3
Core count (per processor) 40 32
Core frequency (GHz) 2.30 2.95
Stepping N/A N/A
Memory module(s)
Total memory in system (GB) 1,024 1,024
Number of memory modules 16 16
Vendor and model Micron MTA36ASF8G72PZ-3G2E1 Micron MTA36ASF8G72PZ-3G2E1
Size (GB) 64 64
Type PC4-3200 PC4-3200
Speed (MHz) 3,200 3,200
Speed running in the server (MHz) 3,200 3,200
Local storage (hypervisor)
Number of drives 1 1
Drive vendor and model Intel SSD SSDSC2KB240G8 Micron MTFDHBA256TCK
Drive size (GB) 240 240
Drive information (speed, interface, type) 6Gb, SATA, SSD PCIe 3.0, NVMe
Local storage (vSAN)
Number of drives 3 3
Drive vendor and model KIOXIA KCD6XLUL3T84 KIOXIA KCD6XLUL3T84
Drive size (GB) 3.84 3.84
Drive information (speed, interface, type) PCIe®
4.0, NVMe™
1.4, 64GT/s PCIe 4.0, NVMe 1.4, 64GT/s
Prepare images for machine learning faster with servers powered by AMD EPYC™ 75F3 processors March 2022 | 3
10. Commissioned by AMD
System configuration information 4 x Supermicro SYS-620U-TNR 4 x Supermicro AS-1124US-TNRP
Network adapter
Vendor and model Supermicro AOC-2UR68G4-I2XT Supermicro AOC-URG4N4-i4XTS
Number and type of ports 2 x 10GbE 4 x 10GbE
Driver version 8.10 0x80009661 N/A
Network adapter
Vendor and model Supermicro AOC-S25G-M2S-O Supermicro AOC-S25G-M2S-O
Number and type of ports 2 x 25GbE SFP28 2 x 25GbE SFP28
Driver version 14.28.2006 14.28.2006
Cooling fans
Vendor and model Sunon VF80381B1 Sunon PF40561BX-Q40U-S9H
Number of cooling fans 4 8
Power supplies
Vendor and model Supermicro PWS-2K08A-1R Supermicro PWS-1K22A-1R
Number of power supplies 2 2
Wattage of each (W) 2,000 1,200
Prepare images for machine learning faster with servers powered by AMD EPYC™ 75F3 processors March 2022 | 4
11. Commissioned by AMD
How we tested
We installed and configured the latest available version of VMware vSphere 7.0 Update 2 on a cluster of four Supermicro AS-1124US-TNRP
servers with AMD EPYC 75F3 processors, and a cluster of four Supermicro SYS-620U-TNR servers with Intel Xeon Platium 8380 processors.
We installed the OS on internal SSD drives. We ran each server using default BIOS settings with the exception of setting the BIOS to the
maximum performance power management settings available for each platform architecture. On each cluster, we configured and created
a 28TB VMware vSAN™
datastore using three NVMe drives on each server. The vSAN datastore served as a shared datastore for VMware
Tanzu deployment.
We used a Dell Networking 1Gb X1052 switch for the VM network and Management Network for Tanzu. We used a Dell 5048-ON switch
for vMotion®
, vSAN, and Workload Network for Tanzu. The Workload Network was isolated behind a NAT gateway, and it utilized private
addresses for all connectivity. We configured the Workload Network port group on a Distributed vSwitch, which is required for Tanzu
Kubernetes®
deployment. The VMware vCenter®
server and ESXi hosts were connected to the Management Network, while the Tanzu
Kubernetes Grid (TKG) workload clusters were connected to the Workload Network. We dual-networked the Tanzu Supervisor Cluster, the
Load Balancer, the NAT gateway, and the TKG CLI VM with a virtual NIC attached to both the Management Network and the Workload
Network. We deployed the two infrastructure VMs (vCenter and NAT gateway) on an infrastructure server. We deployed a TKG cluster with
four Kubernetes worker nodes (one worker on each Supermicro server). On the servers powered by AMD processors, each worker had 56
vCPUs and 512 GB of memory fully reserved. On the servers powered by Intel processors, each worker had 70 vCPUs and 512 GB of memory
fully reserved. We then deployed a Pod on each worker with one thread per core and 256 GB of memory reserved.
We compared the servers using a purpose-built preprocessing workload we wrote in Python using publicly available open-source libraries.
We define this workload in the Workload description section. We can provide the code on request.
Please contact info@principledtechnologies.com for more information.
Workload description
Our preparation workload emulates a simple image-processing workload by distributing dataset preparation tasks among M processes
running on N nodes, the exact number of which is up to the user. We specify our numbers in the methodologies below. Each process
produces a single shard of the final data set by taking input images, performing simple conversions, encoding the resulting image, and
appending it to the shard file.
This Python workload uses Pillow (https://python-pillow.org/) to perform image manipulations. The output format is a file with one Base64-
encoded image per line.
We designed this application to operate in single-node mode or clustered mode, and added built-in logic for discovering cluster members
when clustered. For this study, we used the application in single-node mode. We intended this preparation-stage application to be as
computationally lightweight as possible. However, the pipeline is still compute-limited, even when using relatively slow storage.
This workload is particularly well-suited to CPU comparisons with large thread/core-count disparity or large core frequency differences. Each
thread operates independently, performs the same work, and is CPU-bound. Additional threads and/or high frequency cores allow the server
to complete more work per unit time, showing clear differentiation for higher core/thread count CPUs and/or higher frequency CPUs.
Figure 3: Pipeline data flow and operations. Source: Principled Technologies.
Figure 3 shows how the system reads images from storage, scales the images to a machine-learning-friendly size of 300 x 300 pixels,
transposes the images, and finally, converts the images to grayscale. The system then encodes the transformed image into JPG, and then
converts the JPG-encoded to Base64 and writes it to the next line of the shard file. File systems for image-reading and shard-writing may be
local storage or HDFS, though we used local storage for testing. In addition to the shard files, the workload also outputs frame count, byte
count, frames per second, input and output bytes per second, and total runtime. In clustered mode, the workload also computes statistics
across the cluster.
Preprocessor (Python application using ZeroMQ, Pillow, HDFS, and more)
Read Scale Transpose Convert Write
(to 300 x 300) (RGB to gray)
Prepare images for machine learning faster with servers powered by AMD EPYC™ 75F3 processors March 2022 | 5
12. Commissioned by AMD
Installing vSphere 7.0 Update 2 on a Supermicro server
1. Download ESXi 7.0 Update 2 from the following link: https://my.vmware.com/group/vmware/evalcenter?p=vsphere-
eval-7#tab_download.
2. Open a new browser tab, and connect to the IP address of the Supermicro server BMC.
3. Log in with the BMC credentials.
4. In the main screen, click Launch Virtual Console.
5. In the console menu bar, select Virtual Media and then Virtual Storage.
6. In the Virtual Storage popup window, select ISO from the drop-down menu, and click Open Image to browse local computer to select
the image you downloaded in step 1.
7. Click Plug In to mount the ISO image, and click OK.
8. On the console menu bar, click the Power Control and select Power Reset.
9. The system will boot to the mounted image and the Loading ESXi installer screen will appear. When prompted, press Enter to continue.
10. To Accept the EULA and Continue, press F11.
11. Select the storage device to target for installation. We selected the internal SD card. To continue, press Enter.
12. To confirm the storage target, press Enter.
13. Select the keyboard layout, and press Enter.
14. Provide a root password, and confirm the password. To continue, press Enter.
15. To install, press F11.
16. Upon completion, reboot the server by pressing Enter.
Installing vCenter Server Appliance 7.0 Update 2
1. Download VMware vCenter 7.0 Update 2 from the VMware support portal: https://my.vmware.com.
2. Mount the image on your local system, and browse to the vcsa-ui-installer folder. Expand the folder for your OS, and launch the installer
if it doesn’t automatically begin.
3. When the vCenter Server Installer wizard opens, click Install.
4. To begin installation of the new vCenter server appliance, click Next.
5. Check the box to accept the license agreement, and click Next.
6. Enter the IP address of the infrastructure server with ESXi 7.0 Update 2. Provide the root password, and click Next.
7. To accept the SHA1 thumbprint of the server’s certificate, click Yes.
8. Accept the VM name, and provide and confirm the root password for the VCSA. Click Next.
9. Set the size for environment you’re planning to deploy. We selected Medium. Click Next.
10. Select the datastore on which to install vCenter. Accept the datastore defaults, and click Next.
11. Enter the FQDN, IP address information, and DNS servers you want to use for the vCenter server appliance. Click Next.
12. To begin deployment, click Finish.
13. When Stage 1 has completed, click Close. To confirm, click Yes.
14. Open a browser window and connect to https://[vcenter.FQDN:5480/.
15. On the Getting Started - vCenter Server page, click Set up.
16. Enter the root password, and click Log in.
17. Click Next.
18. Enable SSH access, and click Next.
19. To confirm the changes, click OK.
20. Enter vsphere.local for the Single Sign-On domain name. Enter a password for the administrator account, confirm it, and click Next.
21. Click Next.
22. Click Finish.
Creating a cluster in vSphere 7.0 Update 2
1. Open a browser, and enter the address of the vCenter server you deployed. For example: https://[vcenter.FQDN]/ui
2. In the left panel, select the vCenter server, right-click, and select New Datacenter.
3. Provide a name for the new data center, and click OK.
4. Select the data center you just created, right-click, and select New Cluster.
5. Give a name to the cluster, and enable vSphere DRS. Click OK.
6. In the cluster configuration panel, under Add hosts, click Add.
7. Check the box for Use the same credentials for all hosts. Enter the IP address and root credentials for the first host, and enter the IP
addresses of all remaining hosts. Click Next.
8. Check the box beside Hostname/IP Address to select all hosts. Click OK.
9. Click Next.
10. Click Finish.
Prepare images for machine learning faster with servers powered by AMD EPYC™ 75F3 processors March 2022 | 6
13. Commissioned by AMD
Configuring the vSAN datastore
1. In the left panel of the vCenter, right-click the test cluster, select vSAN, and select configuration.
2. Select single site cluster, and click Next.
3. In the Services screen, click Next.
4. In the Claim disks screen, click the Group by drop-down menu, and select Host.
5. Select disks for each host. We selected one drive for cache and two drives for capacity. Click Next.
6. In the Review screen, click Finish.
7. Click the test cluster from vCenter, and in the right panel, click the Configure tab .
8. In the vSAN section, select Services.
9. To create a distributed switch, in the Configure Cluster section, click the CONFIGURE button.
10. In the Physical adapters section, choose two uplink adapters for the distributed switch, and click Next.
11. In the Storage traffic screen, set the VLAN ID assigned for vSAN, choose Static IPs, and fill in the static IP address, Subnet mask, and
default gateway. Click Next.
12. In the Advanced options scree, click Next.
13. In the Claim disks screen, click Next.
14. In the Proxy settings screen, click next.
15. Click Finish.
Creating a distributed vSwitch and port group
1. From vSphere client, click HomeàNetworking.
2. Select your Datastore.
3. On the right panel, in the Actions drop-down menu, select Distributed vSwitchàNew Distributed vSwitch.
4. Give your vSwitch a name, or accept the default. Click Next.
5. Select 7.0.0 - ESXi 7.0 and later as the version, and click Next.
6. Select the number of uplinks per ESXi host you’ll give to the vSwitch. We selected 2. Click Next.
7. Click Finish.
8. Right-click the new DvSwitch, and select Add and Manage Hosts.
9. Leave Add hosts selected, and click Next.
10. To add new hosts, click the + sign.
11. To select all the hosts in your target cluster, check the box beside Host. Click OK. Click Next.
12. Select the NIC you want to use for this DvSwitch, and click Assign Uplink.
13. At the top of the panel, accept the defaults, but check the box for “Apply this uplink assignment to the rest of the hosts.” Click
OK. Click Next.
14. Do not assign vmkernel adapters at this time. Click Next.
15. Do not migrate any VM networking at this time. Click Next.
16. Click Finish.
17. Right-click the DvSwitch, and select Distributed Port GroupàNew Distributed Port Group.
18. Give it the name Workload Network and click Next.
19. Change the VLAN type to VLAN, and set the VLAN ID to VLAN 2. Click Next.
20. Click Finish.
Creating a DevOps user
1. From vSphere client, click HomeàAdministration.
2. In the left panel, click Users and Groups.
3. In the right panel, click Users, select the vsphere.local domain, and click Add.
4. Provide a username and password, and click Add.
5. For simplicity, we added the DevOps user to a group with Administrator privileges. Click Groups, and select the Administrators
group. Click Edit.
6. Under Add Members, search for the DevOps user you just created, and add them to the administrators group. Click Save.
Prepare images for machine learning faster with servers powered by AMD EPYC™ 75F3 processors March 2022 | 7
14. Commissioned by AMD
Creating the HAProxy content library
1. Click the following link to download the vSphere-compatible HAProxy ovf file (v0.1.8): https://github.com/haproxytech/vmware-haproxy.
2. From vSphere client, in the left menu pane, click Content Libraries.
3. In the Content Libraries panel on the right, click Create.
4. Name the content library HAproxy-cl, and click next
5. Accept the default, and click next.
6. Choose the storage location for the content library, and click Next.
7. Review, and click Finish.
8. Click the newly created HAproxy-cl content library.
9. In the upper portion of the right-side panel for HAproxy-cl, click the actions drop-down menu, and select Import Item.
10. Change the selection to local file, and click the upload files button.
11. Browse to the location of the ovf file you downloaded in step 1, and click Open.
12. Click Import.
Creating the TKG content library
1. From vSphere client, in the left menu pane, click Content Libraries.
2. In the Content Libraries panel on the right, click Create.
3. Name the content library TKG-cl and click Next.
4. Select Subscribed content library, and use https://wp-content.vmware.com/v2/latest/lib.json for the subscription URL. Click Next.
5. To verify, click Yes.
6. Choose the storage location for the content library, and click Next.
7. Review, and click Finish.
Creating the storage tag
1. From the vSphere client, select MenuàStorage.
2. From the left pane, select the vSAN datastore you created for Tanzu.
3. Under the Summary tab, locate the Tags panel, and click Assign.
4. Click Add Tag.
5. Name the tag Tanzu. Click Create New Category.
6. Give the category the name Tanzu Storage. Clear all object types except Datastore, and click Create.
7. Use the Category drop-down menu to select Tanzu Storage, and click Create.
8. Check the box beside the newly created tag, and click Assign.
Creating the VM storage policy
1. From the vSphere client, click MenuàPolicies and Profiles.
2. On the left panel, click VM Storage Policies.
3. Click Create.
4. Create a new VM Storage policy named tkg-clusters and click Next.
5. Check the box for Enable tag-based placement rules, and click Next.
6. Use the Tag Category drop-down menu, and select the Tanzu Storage policy you created. Click Browse Tags.
7. Click the Tanzu checkbox, and click OK.
8. Click Next.
9. Review the compatible storage, making sure your storage target is marked as compatible, and click Next.
10. Click Finish
Deploying HAProxy
1. From the vSphere client, click MenuàContent Libraries.
2. Click the HAproxy-cl library.
3. In the left panel, click OVF & OVA Templates, and right-click the HAProxy template that appears in the panel below. Select New VM
from This Template…
4. Provide a simple name—we used HAproxy—and select the Datacenter and/or folder to which you want to deploy. Click Next.
5. Select the cluster or compute resource where you want to deploy the HAproxy VM, and click Next.
6. Review details, and click Next.
Prepare images for machine learning faster with servers powered by AMD EPYC™ 75F3 processors March 2022 | 8
15. Commissioned by AMD
7. Check the box to accept all license agreements, and click Next.
8. Accept the default configuration, and click Next.
9. Select the target storage for the VM, and click Next.
10. Select VM Network for the Management network, and choose a network for the workload network. Choose the same network for the
Frontend network, and click Next.
11. Customize the template. We used the following:
• Appliance Configuration Section
y For the root password, we used Password1!
y Check the box for Permit Root Login.
y Leave the TLS CA blank.
• Network Configuration Section
y We left the default haproxy.local.
y For local DNS server, we used 10.41.0.10.
y For management IP, we used 10.210.201.200/16.
y For management gateway, we used 10.210.0.1.
Š Note: The description asks for the workload network gateway address. You should enter the management gateway
address instead.
y For Workload IP, we used 192.168.1.2/24.
y For Workload gateway, we used 192.168.1.1.
• Load Balancing Section
y For load balancer IP ranges, we used 192.168.1.240/29.
y Accept the default management port.
y For HAProxy User ID, we used admin.
y For the HAProxy password, we used Password1!
12. Click Next.
13. Review the summary, and click Finish. The deployment will take a few minutes to completely deploy and configure.
14. Power on the HAProxy VM.
Configuring Workload Management
1. From the vSphere client, click MenuàWorkload Management
2. Click Get Started.
3. Review the messages and warnings regarding supported configurations. Click Next.
4. Select the Cluster on which you want to enable workload management, and click Next.
5. Choose the capacity for the control plane VMs. We chose Small. Click Next.
6. Choose the storage policy you wish to use for the control plane nodes. We chose tkg-clusters. Click Next.
7. Configure the Load Balancer section with the following:
a. Name: haproxy
b. Type: HA proxy
c. Data plane API Addresses: 10.210.201.200:5556
d. User name: admin
e. Password: Password1!
f. IP Address Ranges for Virtual Servers: 192.168.1.240-192.168.1.247
g. Server Certificate Authority: [copied and pasted from the instructions below]
8. Open an SSH session to the HAProxy management address, and connect using root and Password1!
9. Type cat /etc/haproxy/ca.crt
10. Copy the entire output (including the first and last lines) and paste the contents into the Server Certificate Authority box
for step 7g above.
11. Close the SSH session.
12. Click Next.
Prepare images for machine learning faster with servers powered by AMD EPYC™ 75F3 processors March 2022 | 9
16. Commissioned by AMD
13. Configure Workload Management with the following:
a. Network: VM Network
b. Starting IP Address: 10.210.201.201
c. Subnet Mask: 255.255.0.0
d. Gateway: 10.210.0.1
e. DNS Server: 10.41.0.10
f. NTP Server: 10.40.0.1
14. Click Next.
15. Configure Workload Network with the following:
a. Leave the default for Services addresses.
b. DNS Servers: 10.41.0.10
c. Under Workload Network, click Add.
d. Accept default for network-1.
e. Port Group: Workload Network.
f. Gateway: 192.168.1.1
g. Subnet: 255.255.255.0
h. IP Address Ranges: 192.168.1.65-192.168.1.126
16. Click Save.
17. For TKG Configuration, use the following:
a. Beside Add Content Library, click Add.
b. Select the TKG-cl library, and click OK.
18. Click Next.
19. Click Finish. The workload management cluster will deploy and configure. You may see apparent errors during configuration, but these
will resolve upon successful completion.
Configuring Kubernetes namespace for service deployment
1. In Workload Management, click Namespaces.
2. Click Create Namespace.
3. Select the target cluster, and provide a name. We used tanzu-ns. Click Create.
4. Click the Permissions tab, and click Add.
5. Choose vSphere.local for the identity source. Search for the DevOps user you created, select the “can edit” role, and click OK.
6. Click the Storage tab.
7. In the Storage Policies section, click Edit.
8. Select the tkg-clusters policy, and click OK. The environment is ready for connection and deploying containers.
Configuring VM classes in vSphere with Tanzu
1. In Workload Management, click Services, and click Manage on the VM Service pane.
2. On the VM Service page, click VM Classes, and click Create VM Class.
3. On the Configuration page, specify the VM class attributes. In the cluster with AMD processors, we set the following attributes:
• Name: amd-vm-class
• vCPU Count: 56
• CPU resource reservation: 100%
• Memory: 512 GB
• Memory resource reservation: 100%
4. In the cluster with Intel processors, we set the following attributes:
• Name: intel-vm-class
• vCPU Count: 70
• CPU resource reservation: 100%
• Memory: 512GB
• Memory resource reservation: 100%
5. On the Review and Finish page, click Finish.
Prepare images for machine learning faster with servers powered by AMD EPYC™ 75F3 processors March 2022 | 10
17. Commissioned by AMD
Installing and configuring Ubuntu VM for Tanzu Kubernetes Grid CLI
1. Log into vCenter, and from the Menu drop-down menu, click Storage.
2. Select datastore1, and click Files.
3. Click Upload Files, and upload the Ubuntu 18.04.5 ISO image.
4. Right-click the cluster, and click New Virtual Machine.
5. Click Next.
6. Enter a name for the VM, and click Next.
7. Click Next.
8. Select datastore1, and click Next.
9. Click Next.
10. From the Guest OS Family drop-down menu, select Linux.
11. From the guest OS version drop-down menu, select Ubuntu Linux (64 bit), and click Next.
12. Assign the VM 2 vCPUs, 8 GB of memory, and a 40GB hard disk.
13. From the New CD/DVD Drive drop-down, select Datastore ISO File, and select the Ubuntu ISO you uploaded to the datastore
previously. Ensure Connect At Power On is checked, and click Next.
14. Click Finish.
15. Power on the VM, and click Launch Remote Console.
16. Click Install Ubuntu.
17. Click Continue.
18. Select Minimal installation, and click Continue.
19. Click Install now.
20. Click Continue.
21. Click Continue.
22. Enter your desired full name, computer name, username, and password, and click Continue.
23. Click Restart Now.
24. Press Enter.
25. Enter your password, and click Sign In.
26. When prompted by the Software Updater, install OS and software updates.
27. Click Restart Later, and power off the VM.
28. Right-click the VM in vCenter, and click Edit Settings.
29. Click Add New Device, and select Network Adapter.
30. From the New Network drop-down menu, select Browse.
31. Click Workload Network, and click OK.
32. Click OK.
33. Power on the VM, and click Launch Remote Console.
34. Enter your password, and click Sign In.
35. Click the network icon in the top right, and click Ethernet (ens192).
36. Click Wired Settings.
37. Next to Ethernet (ens192) click the gear icon.
38. Click IPv4.
39. Change IPv4 Method to Manual, and enter the IP address for this VM.
40. Click Apply, and close the settings window.
Installing Kubectl Plugin for vSphere
1. Open a browser on the VM, and navigate to the IP of one of the three Supervisor VMs. In our environment, the first control plane VM IP
was 10.210.201.201.
2. Click Advanced, and click Accept the Risk and Continue to bypass the certificate warning.
3. Click Download CLI Plugin Linux.
4. Select Save File, and click OK.
5. Open the Files app, and navigate to the Downloads folder.
6. Right-click vsphere-plugin.zip, and select Extract Here.
7. Open a terminal and navigate to the vsphere-plugin binary within the extracted folder:
cd Downloads/vsphere-plugin/bin
Prepare images for machine learning faster with servers powered by AMD EPYC™ 75F3 processors March 2022 | 11
18. Commissioned by AMD
8. Make the vsphere-plugin binary executable and add it to PATH:
sudo mv kubectl-vsphere /usr/local/bin/
sudo mv kubectl /usr/local/bin/
Creating the AI Workload
1. From the Ubuntu VM, log into the Supervisor Cluster:
kubectl vsphere login --insecure-skip-tls-verify --server=https://10.210.201.201--vsphere-
username administrator@vsphere.local
2. Create a yaml file for a cluster of four worker nodes with CPU and memory fully reserved:
cat cluster.yaml
apiVersion: run.tanzu.vmware.com/v1alpha1
kind: TanzuKubernetesCluster
metadata:
name: ai-cluster
namespace: tanzu-ns
spec:
topology:
controlPlane:
count: 1
class: best-effort-xlarge
storageClass: tkg-clusters
workers:
count: 4
class: [amd-vm-class|intel-vm-class]
storageClass: tkg-clusters
distribution:
version: v1.18
settings:
network:
cni:
name: antrea
services:
cidrBlocks: [“10.96.1.0/24”]
pods:
cidrBlocks: [“172.16.0.0/16”]
3. Create the cluster:
Kubectl apply -f cluster.yaml
4. Log into the new cluster:
kubectl vsphere login --insecure-skip-tls-verify --vsphere-username administrator@vsphere.local
--server=https://10.218.201.201 --tanzu-kubernetes-cluster-name ai-cluster --tanzu-kubernetes-
cluster-namespace tanzu-ns
Prepare images for machine learning faster with servers powered by AMD EPYC™ 75F3 processors March 2022 | 12
19. Commissioned by AMD
5. Create a yaml file for three PersistentVolumeClaims:
cat pvc.yaml
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: ai-pvc-data
spec:
accessModes:
- ReadWriteOnce
storageClassName: tkg-clusters
resources:
requests:
storage: 2Gi
---
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: ai-pvc-app
spec:
accessModes:
- ReadWriteOnce
storageClassName: tkg-clusters
resources:
requests:
storage: 1Gi
---
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
name: ai-pvc-out
spec:
accessModes:
- ReadWriteOnce
storageClassName: tkg-clusters
resources:
requests:
storage: 20Gi
6. Create four sets of PVCs (one set for each Pod) in the cluster:
Kubectl apply -f pvc.yaml
Prepare images for machine learning faster with servers powered by AMD EPYC™ 75F3 processors March 2022 | 13
20. Commissioned by AMD
7. Create a yaml file for the AI Pod in the AMD cluster with the following content:
cat amd-pod.yaml
apiVersion: v1
kind: Pod
metadata:
name: ai-pod
spec:
containers:
- name: ai
image: ptuser/preparation:latest
ports:
- containerPort: 80
resources:
requests:
memory: “256Gi”
cpu: “55”
limits:
memory: “256Gi”
cpu: “55”
volumeMounts:
- mountPath: “/app”
name: ai-app
- mountPath: “/data”
name: ai-data
- mountPath: “/out”
name: ai-out
volumes:
- name: ai-app
persistentVolumeClaim:
claimName: ai-pvc-app
- name: ai-data
persistentVolumeClaim:
claimName: ai-pvc-data
- name: ai-out
persistentVolumeClaim:
claimName: ai-pvc-out
8. Create four Pods, and mount the PVCs in the cluster:
Kubectl apply -f amd-pod.yaml
Prepare images for machine learning faster with servers powered by AMD EPYC™ 75F3 processors March 2022 | 14
21. Commissioned by AMD
9. Create a yaml file for the AI pod in the Intel cluster with the following content:
cat intel-pod.yaml
apiVersion: v1
kind: Pod
metadata:
name: ai-pod
spec:
containers:
- name: ai
image: ptuser/preparation:latest
ports:
- containerPort: 80
resources:
requests:
memory: "256Gi"
cpu: "69"
limits:
memory: "256Gi"
cpu: "69"
volumeMounts:
- mountPath: "/app"
name: ai-app
- mountPath: "/data"
name: ai-data
- mountPath: "/out"
name: ai-out
volumes:
- name: ai-app
persistentVolumeClaim:
claimName: ai-pvc-app
- name: ai-data
persistentVolumeClaim:
claimName: ai-pvc-data
- name: ai-out
persistentVolumeClaim:
claimName: ai-pvc-out
10. Create four Pods, and mount the PVCs in the cluster:
Kubectl apply -f intel-pod.yaml
11. To run the benchmark, navigate to the test code GitHub repository and follow the instructions in the testing/README.md file. For this
study, we used the application in single-node mode. See Workload description section for more information.
We ran the workload on each server three times. We reported the median performance score in our final report.
Prepare images for machine learning faster with servers powered by AMD EPYC™ 75F3 processors March 2022 | 15
22. Principled Technologies is a registered trademark of Principled Technologies, Inc.
All other product names are the trademarks of their respective owners.
DISCLAIMER OF WARRANTIES; LIMITATION OF LIABILITY:
Principled Technologies, Inc. has made reasonable efforts to ensure the accuracy and validity of its testing, however, Principled Technologies, Inc. specifically disclaims
any warranty, expressed or implied, relating to the test results and analysis, their accuracy, completeness or quality, including any implied warranty of fitness for any
particular purpose. All persons or entities relying on the results of any testing do so at their own risk, and agree that Principled Technologies, Inc., its employees and its
subcontractors shall have no liability whatsoever from any claim of loss or damage on account of any alleged error or defect in any testing procedure or result.
In no event shall Principled Technologies, Inc. be liable for indirect, special, incidental, or consequential damages in connection with its testing, even if advised of
the possibility of such damages. In no event shall Principled Technologies, Inc.’s liability, including for direct damages, exceed the amounts paid in connection with
Principled Technologies, Inc.’s testing. Customer’s sole and exclusive remedies are as set forth herein.
This project was commissioned by AMD.
Principled
Technologies®
Facts matter.®
Principled
Technologies®
Facts matter.®
Commissioned by AMD
Read the report at https://facts.pt/JQ4z3lH
Prepare images for machine learning faster with servers powered by AMD EPYC™ 75F3 processors March 2022 | 16