x265 on Azure Brief

Ampere^® Altra^® processors are designed from the ground up to deliver exceptional performance for Cloud Native applications such as video encoding. With an innovative architecture that delivers high performance, linear scalability, and amazing energy efficiency, Ampere Altra allows workloads to run in a predictable manner with minimal variance under increasing loads. This enables industry leading performance/watt and a smaller carbon footprint for real-world workloads such as video encoding.

Microsoft offers a comprehensive line of Azure Virtual Machines featuring the Ampere Altra Cloud Native processor that can run a diverse and broad set of scale-out workloads such as web servers, open-source databases, in-memory applications, big data analytics, gaming, media, and more. The Dpsv5 VMs powered by Ampere Altra processors are general-purpose VMs that provide 2 GB of memory per vCPU and a combination of vCPUs, memory, and local storage to cost-effectively run workloads that do not require larger amounts of RAM per vCPU. The Epsv5 VMs are memory-optimized VMs that provide 4 GB of memory per vCPU, which can benefit memory-intensive workloads, including open-source databases, in-memory caching applications, gaming, and data analytics engines.

This workload brief focuses on x265, which implements the H.265/MPEG-H Part2 standard, the second most widely used video codec today after H.264. Compared to x264, more advanced video codecs such as x265 provide greater video compression at the expense of greater computing resources and power usage.

The Microsoft Azure Dpsv5 VMs powered by Ampere Altra processors offer amazing value for Cloud Native workloads such as video encoding. We evaluated the performance of the x265 codec using three different input videos with resolutions of 480p, 720p, and 1080p from the UGC Dataset, uploaded to YouTube and distributed under the Creative Commons license, with the x265 medium, slower, and placebo presets.

As per Figure 1, the Dpsv5 VMs outperform the legacy x86 VMs in raw performance by up to 5%. We calculated the average performance running x265 with the three input videos and three x265 presets for a total of nine different configurations.

Comparing price-performance in Figure 2, the Dpsv5 VMs outperformed the x86 VMs by a higher margin. The Ampere Altra-based D16ps v5 VM has a 29% higher price-performance ratio than the Intel^® Xeon^® Ice Lake-based D16s v5 VM and 12% better than the AMD EPYC™ Milan-based D16as v5 VM.

Ampere Altra processors have been designed from the ground up to address challenges in multitenant cloud environments like noisy neighbors and scalability. To highlight this, we studied the aggregate FPS on the Ampere Altra-based D16ps v5 VM as the number of simultaneous x265 jobs running the placebo preset with the 1080p input video was increased. This is a computationally demanding x265 configuration, and the D16ps v5 VM demonstrated perfect, linear scaling all the way from 1 to 16 jobs. The D16s v5 VM, on the other hand, showed no improvement in FPS beyond 8 vCPUs due to contention from Hyper-Threading.

We used the following input files from the UGC Dataset, uploaded to YouTube distributed under the Creative Commons license:

1. 480p Input Video

2. 720p Input Video

3. 1080p Input Video

For each vCPU available in the VM, we ran the following command to evaluate x265 performance where we loop over PRESET and INPUT/INPUT_RES

Copy
x265 --preset veryslow --frame-threads 1 --no-wpp $INPUT --input-res $INPUT_RES --fps 30 -o $OUTPUT 

Video encoding is a key and popular workload in the cloud and advanced codecs that are compute intensive such as x265 are used frequently. The H.265/MPEG-H Part2 compression standard is the second most widely used video format today after H.264 and x265 is the leading H.265 implementation. In our tests, the Microsoft Azure Dpsv5 VMs powered by the Ampere Altra Cloud Native processors delivered perfect scaling by reducing noisy neighbor issues and provided better performance and price-performance compared to legacy x86 VMs running x265 – up to 5% higher performance and 31% higher price-performance.

For more information about Azure Virtual Machines with Ampere Altra Arm-based processors, visit the Azure blog.

All data and information contained herein is for informational purposes only and Ampere reserves the right to change it without notice. This document may contain technical inaccuracies, omissions and typographical errors, and Ampere is under no obligation to update or correct this information. Ampere makes no representations or warranties of any kind, including but not limited to express or implied guarantees of noninfringement, merchantability, or fitness for a particular purpose, and assumes no liability of any kind. All information is provided “AS IS.” This document is not an offer or a binding commitment by Ampere. Use of the products contemplated herein requires the subsequent negotiation and execution of a definitive agreement or is subject to Ampere’s Terms and Conditions for the Sale of Goods.

System configurations, components, software versions, and testing environments that differ from those used in Ampere’s tests may result in different measurements than those obtained by Ampere.

Price performance was calculated using Microsoft's Virtual Machines Pricing, in September of 2022. Refer to individual tests for more information.

©2022 Ampere Computing. All Rights Reserved. Ampere, Ampere Computing, Altra and the ‘A’ logo are all registered trademarks or trademarks of Ampere Computing. Arm is a registered trademark of Arm Limited (or its subsidiaries). All other product names used in this publication are for identification purposes only and may be trademarks of their respective companies.

Ampere Computing^® / 4655 Great America Parkway, Suite 601 / Santa Clara, CA 95054 / amperecomputing.com