AMD Ryzen 9 9900X3D Impact Of The 3D V-Cache Optimizer Linux Driver

Written by Michael Larabel in Software on 3 April 2025 at 12:30 PM EDT. Page 3 of 4. 10 Comments.

👁 Node.js V8 Web Tooling Benchmark benchmark with settings of . cache was the fastest.

👁 Stargate Digital Audio Workstation benchmark with settings of Sample Rate: 192000, Buffer Size: 1024. cache was the fastest.

👁 Stargate Digital Audio Workstation benchmark with settings of Sample Rate: 480000, Buffer Size: 1024. cache was the fastest.

👁 Stargate Digital Audio Workstation benchmark with settings of Sample Rate: 480000, Buffer Size: 512. cache was the fastest.

👁 ASKAP benchmark with settings of Test: tConvolve OpenMP, Gridding. cache was the fastest.

👁 PyTorch benchmark with settings of Device: CPU, Batch Size: 32, Model: ResNet-152. cache was the fastest.

With how easy it is to adjust the amd_x3d_mode when running on the Linux 6.13 kernel or newer at run-time, it certainly makes sense seeing what benefits or not you may find with your particular workloads from adjusting the "amd_x3d_mode" on your Ryzen X3D hardware.

👁 ClickHouse benchmark with settings of 100M Rows Hits Dataset, Second Run. cache was the fastest.

👁 MariaDB benchmark with settings of Test: oltp_read_write, Threads: 1. freq was the fastest.

👁 Llama.cpp benchmark with settings of Backend: CPU BLAS, Model: granite-3.0-3b-a800m-instruct-Q8_0, Test: Prompt Processing 512. freq was the fastest.

In some cases the differences are very slight but if you are using a Ryzen 9 9900X3D/9950X3D for a SOHO server, CI/CD box, or other always-on 24/7 operation type workloads, even the small differences can add up.

10 Comments - Next Page

Page: 1 2 3 4 Next Page

URL: https://www.phoronix.com/review/amd-9900x3d-3d-v-cache/3

⇱ AMD Ryzen 9 9900X3D Impact Of The 3D V-Cache Optimizer Linux Driver Review - Phoronix

AMD Ryzen 9 9900X3D Impact Of The 3D V-Cache Optimizer Linux Driver