[Features] Overview of the new generation CPU "AMD EPYC" for cloud/servers [Semiconductors]
This is Ohara from the Technical Sales Department
CPUs used in various cloud services/servers such as AWS and GCP AMD (Advanced Micro Devices)describes the characteristics of
*Information is current as of September 2021.
AMD EPYC Overview
● World's highest-performing x86 CPU
● Performance improvements with the latest "Zen3" core
● AMD EPYC™ 7003 PROCESSORS (development codename "MILAN")
● Drop-in compatibility for Rome platform (BIOS update required)
● Enhanced security features
● Support for 4ch/6ch/8ch channel memory
● Improved memory performance (maximum x86 capacity L3 cache of 32MB per core)
Characteristics of each cloud
| Cloud Name | Features | overview | Main target instances |
| ● AWS | • Pricing up to 10% to 45% lower than equivalent EC2 instances. • Seamless workload migration and flexibility. |
EC2 G4ad instances, equipped with an AMD Radeon Pro V520 GPU and a 2nd generation AMDEPYC processor, offer up to 45% lower costs compared to Nvidia G4dn instances for graphics-intensive applications such as virtual workstations, game streaming, and graphics rendering. |
M5a/M5ad (general purpose) , R5a/R5ad (memory optimized) , T3a (burstable general purpose) , C5a (comput optimized), G4ad (graphics-intensive), and more . *Coming soon |
| ● Microsoft Azure | • Supports a wide range of applications and workloads. • Up to 80,000 cores with HBv2 for HPC in the cloud. |
Azure D32as v4 virtual machines powered by 2nd Generation AMDEPYC processors are up to 53% less expensive than Azure D32ds v4 | • Dav4 (General Purpose) • Eav4 (Memory Optimized) • HBv2 (HPC Optimized) • HBv3 (HPC Optimized) *Coming Soon • Lsv2 (Storage Optimized) • NVv4 (GPU + CPU Optimized) |
| ● Google Cloud | • AMD-based N2D instances offer up to 13% savings compared to equivalent Intel N-series instances. • They deliver up to 39% performance improvements in Coremark benchmarks compared to equivalent Intel N1 instances. |
• AMD-based N2D VMs enhance performance for data management workloads by leveraging AMD's higher memory bandwidth and higher throughput per system (available in larger VM options), with up to 224 vCPUs, making them Google's largest general-purpose VMs. • Benchmarks show up to 2.5x improvements in benchmarks such as STREAM, which benefit from the improved memory bandwidth of AMD N2D, resulting in 20-30% performance improvements across many workload types. |
• N2D Standard (General Purpose) • N2D HighMEM (Memory Optimized) • N2D HighCPU (HPC Optimized) • Confidential VMs • N2D Milan * Coming Soon • C2D for HPC * Coming Soon • Tau T2D * Coming Soon |
| ● Oracle Cloud | - | - | ・E2 Standard (general purpose) ・E3 Standard (high performance) ・Elastic Block Storage V2 ・Standard E4 Flex Sizing (general purpose) *Coming soon |
| ● Alibaba Cloud | - | - | • g6a (general purpose) • c6a (computation optimized) • r6a (memory optimized) |
Reference materials
● AWS:AMD EPYC™ & AWS EC2 instances
● Microsoft Azure:AMD EPYC™ & Microsoft Azure Virtual Machines
● Google Cloud:AMD EPYC™ & Google Cloud Platform instances
summary
Recently, AMD CPU instances have been released for the cloud, so when you are developing services/content on the cloud, why not consider them as an option depending on the specifications of the applications that will run on the cloud?
1
Loading...1 
The person who wrote this article
About the author
