AWS has introduced Graviton5 processors, described as the company’s most advanced custom chip to date for a broad set of cloud workloads. According to the announcement, Graviton5 delivers up to 25% better compute performance than the previous generation while maintaining leading energy efficiency. The release is positioned to help organizations run applications faster, reduce costs, and meet sustainability goals without forcing the traditional trade-offs between speed and efficiency.
Graviton5 is available in EC2 M9g instances that the company says offer the highest CPU core density available in Amazon EC2, with 192 cores in a single package. The processor’s design reduces the distance data must travel between cores, cutting inter-core communication latency by up to 33% while increasing bandwidth. That combination is intended to improve efficiency for CPU-bound and latency-sensitive workloads by reducing data movement overhead inside the processor package.
AWS highlights a set of demanding workloads that should benefit from the new processor architecture, including real-time gaming, high-performance databases, big data analytics, application servers, and Electronic Design Automation (EDA). By enabling faster data exchange between processing cores and higher core counts per package, Graviton5-based instances are described as enabling scalable performance for these workloads while also contributing to cost and sustainability objectives. The announcement frames Graviton5 as a step toward meeting growing performance demands across cloud-native and scale-up applications.
