Oracle Cloud Infrastructure (OCI) has recently launched the Ampere A1 Compute family of Arm Neoverse N1-based VMs and bare-metal instances. These A1 instances use Ampere Altra CPUs that were designed specifically to deliver performance, scalability, and security for cloud applications. The A1 Flex VM family supports an unmatched number of VM shapes that can be configured with 1-80 cores and 1-512GB of RAM (up to 64GB per core). A1 is also offered in bare-metal configurations with up to 2-sockets and 160-cores per instance.
In this blog, we compare x264 video encoding performance and price between three OCI families:
Despite the introduction of newer video encoding codecs, H.264 remains by far the most popular video codec for both live-streaming and video on demand (VOD) playback1. And it is supported across the widest range of playback devices. We benchmark x264 here as it is a popular open source H.264 video encoder. It is also worth noting that reducing costs remains the top priority of video developers as surveyed in 2020 by Bitmovin1.
The pricing2 for these Intel, AMD, and Ampere-based instances are listed in Table 1. One notable aspect of the OCI Ampere A1 Compute instances is they are the first family to offer $0.01 per-hour per-core pricing. Besides offering a lower price per physical CPU core (OCPU), A1 also provides a tiered pricing policy, where the first 3,000 OCPU hours and 18,000GB hours per month are free.
Table 1: OCI VM Pricing information
In our evaluation, we chose three kinds of instances featuring 8vCPUs (HW threads, SMT on for x86 instances) and 60GB memory, as listed in Table 2. All the instances run Oracle Linux 8.3 and GCC 8.3.1. We chose x2643, a popular open-source H.264 video encoder for comparison.
Table 2: OCI VM System configurations
Our test picks the software configurations that get the most performance for the selected hardware. From that we get the performance and price results shown in Figure 1. Specifically, our testing takes the aggregated frames per second of each instance, extrapolates that performance out to one hour, and then applies the price to rent that instance for one hour.
As a result, the Ampere A1 Compute instance is able to provide up to about 98% higher performance/cost than Optimized3 for x264 encoding.
Figure 1: x264 encode perf/cost for A1 and Optimized3 instances.
Table 3: Frames/$ for Optimized3, E4, and, A1 instances.
Figure 3 shows our measured performance (aggregate frames/sec) for Optimized3, E4, and A1 instances (8vCPU per instance) while encoding a reference input file (‘ducks_take_off_1080p50.y4m’) with ‘medium’ encoding preset using x264. To find the best performing configuration for the instances under test, we swept two parameters:
Figure 3: x264 encode performance (aggregated frames per second) for OCI Optimized3, E4, and A1 instances (p=jobs per instance, t=threads per job).
Typical encoding tasks use four or more threads per job, and run at least one job per vCPU. This will naturally move most encoding jobs to the right side of Figure 3. And we can see from Figure 3 that for the highest aggregated FPS achieved by each instance, A1 8vCPUs outperforms Optimized3 8vCPU and E4 8vCPUs instances by around 10%.
OCI's new family of Arm Neoverse-based Ampere A1 Compute instances deliver leading performance and exceptional performance per dollar compared to traditional x86-based instances. With reducing costs being the number one priority for video developers we believe these Ampere A1 Computes instances deserve serious customer consideration. OCI A1 delivers 98% higher frames per dollar compared to Xeon-based Optimized3 instances, and by taking advantage of OCI A1 tiered pricing customers can see even greater savings. Developers can get started for free today by taking advantage of OCI's A1 4vCPU, 24GB "always free" tier.
Learn more about OCI A1 Instances
1.Bitmovin Developer Report 2020: https://bitmovin.com/press-room/is-the-party-over-video-streaming-services
2.Oracle pricing Info. https://www.oracle.com/cloud/compute/pricing.html
In this blog we show how OCI A1 instances provide leading performance can significantly reduce video encoding costs versus modern CPUs.