AMD EPYC Milan Still Gives Intel Sapphire Rapids Tough Competition In The Cloud

Written by Michael Larabel in Processors on 30 March 2023 at 10:30 AM EDT. Page 5 of 8. 10 Comments.

Timed FFmpeg Compilation benchmark with settings of Time To Compile. t2d-standard-8 AMD was the fastest.

Timed Linux Kernel Compilation benchmark with settings of Build: defconfig. t2d-standard-8 AMD was the fastest.

For those looking at Google Cloud for continuous integration (CI) purposes or build farms, the existing AMD instances were outpacing the tested C3 Sapphire Rapids VM. Tau T2D with using all physical cores delivered the best results while even the C2D Milan was delivering similar build performance to the c3-highcpu-8 instance.

OSPRay Studio benchmark with settings of Camera: 1, Resolution: 4K, Samples Per Pixel: 1, Renderer: Path Tracer. c3-highcpu-8 SPR was the fastest.

OSPRay Studio benchmark with settings of Camera: 3, Resolution: 4K, Samples Per Pixel: 1, Renderer: Path Tracer. c3-highcpu-8 SPR was the fastest.

Intel's OSPRay Studio is optimized for the latest Xeon Scalable processors, including with AVX-512, but even with the T2D Milan instance having just AVX2 it was hitting a mid-point between Cascade Lake and Sapphire Rapids. With Genoa it will be interesting to repeat this testing in Google Cloud at the same vCPU sizes.

OpenSSL benchmark with settings of Algorithm: SHA256. t2d-standard-8 AMD was the fastest.

OpenSSL benchmark with settings of Algorithm: SHA512. t2d-standard-8 AMD was the fastest.

OpenSSL benchmark with settings of Algorithm: RSA4096. c3-highcpu-8 SPR was the fastest.

OpenSSL benchmark with settings of Algorithm: ChaCha20. t2d-standard-8 AMD was the fastest.

OpenSSL benchmark with settings of Algorithm: AES-128-GCM. c3-highcpu-8 SPR was the fastest.

OpenSSL benchmark with settings of Algorithm: AES-256-GCM. c3-highcpu-8 SPR was the fastest.

OpenSSL benchmark with settings of Algorithm: ChaCha20-Poly1305. t2d-standard-8 AMD was the fastest.

OpenSSL was commonly enjoying the best results with the EPYC Milan VMs over C3 Sapphire Rapids but for some algorithms tested the Sapphire Rapids performance was out in front.

10 Comments - Next Page

Page: 1 2 3 4 5 6 7 8 Next Page