Benchmarking The Performance Impact To AMD Inception Mitigations

Written by Michael Larabel in Software on 15 August 2023 at 10:30 AM EDT. Page 6 of 8. 35 Comments.
AMD Inception Ryzen

Over the past few days I also ran some benchmarks on an AMD Ryzen 9 7950X Zen 4 desktop. Here it was a comparison of Linux 6.4.10 stable using the default "safe RET no microcode" mitigation where simply moving to the new patched Linux kernel versions but where there isn't mitigated microcode yet available.

SQLite benchmark with settings of Threads / Copies: 1. off was the fastest.

Like with the EPYC Zen 3 server testing, on the desktop Zen 4 side it's also primarily a matter of seeing some typically small changes for workloads involving I/O.

3DMark Wild Life Extreme benchmark with settings of Resolution: 1920 x 1080. off was the fastest.
VKMark benchmark with settings of Resolution: 1920 x 1080, Present Mode: Mailbox. off was the fastest.

The good news for gamers is I hadn't spotted any changes in my graphics benchmarking so far.

Embree benchmark with settings of Binary: Pathtracer ISPC, Model: Crown. safe RET no microcode was the fastest.
SVT-AV1 benchmark with settings of Encoder Mode: Preset 8, Input: Bosphorus 4K. off was the fastest.
SVT-AV1 benchmark with settings of Encoder Mode: Preset 12, Input: Bosphorus 4K. off was the fastest.
SVT-HEVC benchmark with settings of Tuning: 7, Input: Bosphorus 4K. off was the fastest.
uvg266 benchmark with settings of Video Input: Bosphorus 4K, Video Preset: Ultra Fast. off was the fastest.
x265 benchmark with settings of Video Input: Bosphorus 4K. off was the fastest.

Video encoding and other workloads not involving significant I/O were typically not showing any performance changes with the Inception mitigation.

7-Zip Compression benchmark with settings of Test: Compression Rating. off was the fastest.
Timed FFmpeg Compilation benchmark with settings of Time To Compile. off was the fastest.
Timed Godot Game Engine Compilation benchmark with settings of Time To Compile. off was the fastest.
Timed Linux Kernel Compilation benchmark with settings of Build: defconfig. off was the fastest.
Timed LLVM Compilation benchmark with settings of Build System: Ninja. off was the fastest.

Like with the AMD EPYC 7763 server testing, the code compilation performance was coming in a little bit slower with the new mitigated kernel default.


Related Articles
Intel Core Ultra "Meteor Lake" Performance Improves With Linux 6.9
GCC 14 vs. LLVM Clang 18 Compiler Performance On Fedora 40
Intel Xeon Max Sees Some Performance Gains For OpenVINO & ONNX With Linux 6.9
Linux 6.9 Drives AMD 4th Gen EPYC Performance Even Higher For Some Workloads
Intel Core Ultra "Meteor Lake" Yields Faster Performance With Linux 6.9
Google Cloud's C3D Instances Provide Strong Performance Value For PingCAP's TiDB