AWS lambda: Clarify Graviton processor generations for arm64 Lambda
Summary
Rewrites arm64 architecture guidance to remove Graviton2-specific claims, noting Lambda manages underlying hardware and does not guarantee a specific processor generation, and lists benefits including improved encryption performance via Arm cryptographic extensions.
Security assessment
The change is primarily a hardware/architecture clarification. The only security-tangential line mentions improved encryption performance from Arm crypto extensions, but this is a general performance benefit, not documentation of a security feature or fix.
Evidence
* Improved encryption performance through Arm cryptographic extensions.
Diff
diff --git a/lambda/latest/dg/foundation-arch.md b/lambda/latest/dg/foundation-arch.md index 9281fc0..97c64d6 100644 --- a//lambda/latest/dg/foundation-arch.md +++ b//lambda/latest/dg/foundation-arch.md @@ -13 +13 @@ The _instruction set architecture_ of a Lambda function determines the type of c - * arm64 – 64-bit ARM architecture, for the AWS Graviton2 processor. + * arm64 – 64-bit ARM architecture, for AWS Graviton processors. @@ -43 +43 @@ For an example of how to create a function with arm64 architecture, see [AWS Lam -Lambda functions that use arm64 architecture (AWS Graviton2 processor) can achieve significantly better price and performance than the equivalent function running on x86_64 architecture. Consider using arm64 for compute-intensive applications such as high-performance computing, video encoding, and simulation workloads. +Lambda functions that use arm64 architecture (AWS Graviton processors) can achieve significantly better price and performance than the equivalent function running on x86_64 architecture. Consider using arm64 for compute-intensive applications such as high-performance computing, video encoding, and simulation workloads. @@ -45 +45 @@ Lambda functions that use arm64 architecture (AWS Graviton2 processor) can achie -The Graviton2 CPU uses the Neoverse N1 core and supports Armv8.2 (including CRC and crypto extensions) plus several other architectural extensions. +Lambda manages the underlying hardware and does not guarantee a specific processor generation: your function might run on different generations of the Graviton processor depending on regional hardware availability. Your code does not target a specific chipset; it only needs to be compatible with the arm64 (AArch64) architecture. All Graviton generations provide these benefits over x86_64: @@ -47 +47 @@ The Graviton2 CPU uses the Neoverse N1 core and supports Armv8.2 (including CRC -Graviton2 reduces memory read time by providing a larger L2 cache per vCPU, which improves the latency performance of web and mobile backends, microservices, and data processing systems. Graviton2 also provides improved encryption performance and supports instruction sets that improve the latency of CPU-based machine learning inference. + * A larger L2 cache per vCPU, which reduces memory read time and improves latency for web and mobile backends, microservices, and data processing systems. @@ -49 +49,8 @@ Graviton2 reduces memory read time by providing a larger L2 cache per vCPU, whic -For more information about AWS Graviton2, see [AWS Graviton Processor](https://aws.amazon.com/ec2/graviton). + * Improved encryption performance through Arm cryptographic extensions. + + * Support for instruction sets that lower the latency of CPU-based machine learning inference. + + + + +For more information, see [AWS Graviton processors](https://aws.amazon.com/ec2/graviton).