Processors Linux Reviews & Articles

There have been 506 Linux hardware reviews and benchmark articles on Phoronix for processors. Separately, check out our news section for related product news.

Lisa Su's keynote just wrapped up at CES 2026 and in turn the embargo regarding AMD's first consumer product announcements for 2026. The AMD Ryzen AI 400 series and new Ryzen 7 9850X3D 3D V-Cache processors are what's in focus for CES this year.

As part of the various end-of-year annual benchmarking comparisons and the like on Phoronix, today is a look at how the Intel Core Ultra 7 155H "Meteor Lake" performance has evolved under Ubuntu Linux in the two years since launching. Plus with next-gen Intel Panther Lake laptops expected to be showcased next week at CES, it's a good time for revisiting the Meteor Lake performance to see the difference two years have made for Intel Meteor Lake laptops on Linux.

Since receiving the Gigabyte R284-A92-AAL1 a while back as a Xeon 6900 series 2U server platform to replace the failed Intel AvenueCity reference server, I have been getting caught-up in fresh Xeon 6980P Granite Rapids benchmarks with the latest software updates over the past year. I've provided fresh looks at the DDR5-6400 vs. MRDIMM-8800 performance, the AMX benefits for AI, SNC3 vs. HEX mode, Latency Optimized Mode, Cache Aware Scheduling, and more with the fresh Linux software stack and this production Gigabyte server platform. One of the areas I have been meaning to re-visit is a fresh head-to-head benchmark battle between 5th Gen AMD EPYC "Turin" and Intel Xeon 6 "Granite Rapids". In this article is a 128-core showdown between the Xeon 6980P and EPYC 9755 128-core processors with the latest open-source Linux software as of the end of 2025.

Over the past year Intel engineers have worked a lot on Cache Aware Scheduling for the Linux kernel. The yet-to-be-merged functionality allows for the Linux kernel to better aggregate tasks sharing data to the same last level cache (LLC) domain to reduce cache misses and cache bouncing. The Cache Aware Scheduling development was led by Intel but helps other CPU vendors too for processors with multiple cache domains. Back in October I showed some nice performance wins for AMD EPYC Turin with Cache Aware Scheduling while today's article are some benchmarks of the newest CAS code and looking at the performance benefit on Xeon 6 "Granite Rapids" processors.

AMD today announced their newest member of their expansive EPYC family: the EPYC Embedded 2005 series. The new AMD EPYC Embedded 2005 Series are intended primarily for networking, storage, and industrial devices while these BGA processors will likely see other interesting thin-server uses as well.

Nearly four years have passed since AMD launched their EPYC Milan-X processors with 3D V-Cache. When recently rearranging some servers in the lab and realizing the four year anniversary was coming up in March, curiosity got the best of me in wondering where the Linux performance and energy efficiency on Milan-X is now with the latest Linux software stack compared to the numbers when Milan-X launched back in March 2022.

It's been just over one year now since the launch of the Core Ultra 9 285K and other Arrow Lake desktop processors. For those that may be considering an Arrow Lake CPU this holiday season for a Linux desktop or just curious how the power and performance has evolved one year later, here are some leading-edge benchmarks of the Intel Core Ultra 9 285K compared to the launch-day performance last October.

This week marks two years since the debut of the Ryzen Threadripper 7000 series processors. Given the occasion, I decided to revisit the Linux performance of the Threadripper 7980X compared to original benchmarks from November 2023 to see how the latest Linux software stack performs for these Zen 4 HEDT processors.

Lenovo recently sent over their new ThinkPad P1 Gen 8 laptop for review under Linux. My Linux review on that ThinkPad P1 Gen 8 laptop will be coming up in the near future along with some other benchmarks from that premium mobile workstation. But with this being the first time I've had an Intel Core Ultra 7 255H "Arrow Lake H" device at Phoronix, here are some standalone benchmarks looking at the CPU performance of that 16-core mobile processor compared to various other Intel and AMD SoCs in different laptops while running Ubuntu Linux.

A new feature of Intel Xeon 6 "Birch Stream" platforms is the "Latency Optimized Mode" performance setting. The Intel Latency Optimized Mode will keep the uncore clock frequencies higher for more consistent performance but at the cost of increased power use. For those wondering about the performance and power impact, here are some comparison benchmarks of engaging this Latency Optimized Mode with Intel Xeon 6980P "Granite Rapids" server processors.

Details during the Clearwater Forest briefing at Intel Tech Tour Arizona were rather light... Especially as for what's known about the cores already from prior events like Hot Chips and other Intel disclosures around the Darkmont E-core. But we do now know the branding: Xeon 6+ for Clearwater Forest.

In addition to announcing Clearwater Forest as Xeon 6+, Intel also used their Tech Tour 2025 Arizona event for predominantly focusing on upcoming Panther Lake SoCs for laptops shipping in 2026.

Besides the support for MRDIMM-8800 memory, another distinct advantage of Intel Xeon 6 "Granite Rapids" processors is the continued presence of Advanced Matrix Extensions (AMX). Here are some fresh benchmarks looking at the impact of AMX on the Intel Xeon 6980P processors for AI inference workloads.

Next week marks one year since the launch of the Xeon 6900P series Granite Rapids server processors. Given the occasion and a new server in the lab, here is a look at how Intel's Granite Rapids top-end Xeon 6980P server processors are performing one year after the original introduction with a production-grade server platform as well as incorporating all of the Linux software improvements over the past year.

Since the launch of the AMD EPYC 9005 series nearly one year ago, I have performed hundreds of different benchmarks on these EPYC "Turin" processors across a wide range of workloads/disciplines to really terrific performance, power efficiency, and value. AMD EPYC 9005 performs exceptionally well compared to the competition from Intel and ARM CPU vendors. One area though I hadn't explored to this point was how well the AMD EPYC 9005 series performs for serving as the host CPU for GPU/AI servers. That changed as I recently wrapped up some benchmarks exploring that area using the AMD EPYC 9575F and it managed to accelerate past the available competition in proving capable of being the superior host processor for AI servers.

Back in May we provided an initial look at the Qualcomm Snapdragon X Elite laptop performance on Ubuntu Linux with the upstream support for the Qualcomm Snapdragon X1E maturing, more laptops becoming supported, and the Ubuntu X1E "Concept" ISOs enhancing the end-user experience. The performance was okay but short of expectations. Months later we are revisiting the Qualcomm Snapdragon X Elite Linux performance on the newest Ubuntu Concept ISOs and newer firmware that is providing a much better experience albeit still not as competitive as the newest AMD Ryzen AI 300 series and Intel Core Ultra laptops under Linux.

The newly-launched AMD Ryzen Threadripper 9000 series headlined by the 64-core Threadripper 9980X and 32-core Threadripper 9970X offer incredible performance and a wonderful addition to the Zen 5 family for the HEDT space. But there is also the Threadripper PRO 9000 series with the flagship Threadripper PRO 9995WX sporting 96 cores. In this article is a look at how that 96-core AMD Threadripper PRO 9995WX performs using a TRX50 platform with quad channel DDR5-6400 memory.

Last week alongside our Framework Desktop review with the AMD Ryzen AI Max+ 395 "Strix Halo" SoC I posted benchmarks of the Strix Halo performance compared to the Ryzen 9 9950X / 9950X3D socketed desktop processors. For those wondering similarly how the top-end Strix Halo SoC in the Framework Desktop competes with the Intel Core Ultra 9 285K "Arrow Lake" flagship in performance and power efficiency, here are those comparison benchmarks.

Recently we looked at the performance of the AMD EPYC 4545P that is a 16 core 65 Watt processor in the EPYC 4005 "Grado" series. This is quite an interesting processor for those after low-power servers, edge AI deployments, and other purposes with no similar Ryzen 9000 series processor or competition from Intel offering sixteen performance cores at around 65 Watts. Complementing all the performance and power data from that review article, here are some additional tests putting its performance and efficiency compared to the original AMD EPYC 7601 flagship processor that ushered in the EPYC family eight years ago.

In today's launch-day review of the Framework Desktop with AMD Ryzen AI Max "Strix Halo" were a number of benchmarks comparing the mini/SFF PC to Framework Laptops, the Strix Halo powered HP ZBook Ultra G1a laptops, and similar devices. With this being a desktop after all, for those wondering how the Ryzen AI Max+ 395 compares in a desktop form factor to the 16-core Ryzen 9 9950X series processors, this article has all those benchmark numbers.

Back in May when AMD launched the EPYC 4005 "Grado" processors for low-power, low-cost server processors we tested the EPYC 4565P and EPYC 4585PX. The EPYC 4565P is their standard 16-core offering while the EPYC 4585PX is the 3D V-Cache variant for these processors catering to web hosting, SOHO servers, edge computing, and other applications where not needing the performance of the flagship EPYC 9005 "Turin" processors. There is also another 16-core variant with the EPYC 4545P and what makes this SKU interesting is the 16-cores / 32-threads but with a 65 Watt TDP. In the Ryzen 9000 series so far AMD hasn't introduced any 16-core, 65-Watt part that makes the EPYC 4545P all the more interesting. Here are some benchmarks of the EPYC 4545P for those shopping for an affordable and very power efficient server platform that still sharply outperforms Intel's Xeon E / Xeon 6300 competition.

Ahead of the Threadripper 9000 series hitting store shelves tomorrow, today the review embargo lifts on these new high-end desktop/workstation Zen 5 processors. I have been testing out the Threadripper 9970X and 9980X this month and have been extremely excited about the generational uplift and all-around performance of these new AMD Ryzen Threadripper 9970X/9980X processors on Linux for delivering the best possible workstation performance in 2025.

Last week I published fresh benchmarks showing how AMD's EPYC 4005 series for budget servers can outperform the original EPYC 7601 flagship processor when EPYC first launched during the Zen 1 period. Even with lower core counts and fewer memory channels, the modern EPYC 4005 "Grado" processors were able to outpace that original EPYC "Naples" flagship processor from 2017. With carrying out the fresh re-testing of the AMD EPYC 7601 on a modern 2025 Linux software stack, in today's article is a look at how the EPYC 7601 Zen 1 performance compares to the EPYC 9005 "Turin" series with today's flagship EPYC 9755 and EPYC 9965 processors.

For those on very long server upgrade cycles, typically just running the hardware until failure or consider buying second-hand servers that are generations old for lower up-front cost, today's unique article is for you with quantifying a first-generation EPYC server compared to today's entry-level EPYC processors in performance and power efficiency. With the fascinating AMD EPYC 4005 "Grado" budget-friendly server processors I was curious how well they would stack up against AMD's original flagship EPYC processor, the AMD EPYC 7601 "Naples" processor from the Zen 1 era. Can an entry-level brand new Grado server processor with dual channel DDR5 memory outpace an original EPYC server with twice the core/thread counts and eight channel DDR4 server memory? Yes, with huge gains in performance and power efficiency.

The AMD EPYC 4005 "Grado"" processors launched by AMD in May for entry-level servers offer downright amazing value, performance, and power efficiency over the Intel Xeon 6300 / Xeon E-2400 series competition. Intel's top-of-stack Xeon 6300 (Xeon 6369P) / Xeon E processors fail to compete with even the mid-tier EPYC 4005 series processors in either performance, power, or cost effectiveness. Among the many advantages to these budget-friendly EPYC processors is having AVX-512 support with a full 512-bit data path compared to the Xeon 6300 series only having AVX2. For providing more insight into the AVX-512 performance impact with the AMD EPYC 4005 series, here are some enabled/disabled comparison benchmarks and how they are positioned relative to the Xeon 6369P server processor.

While the latest Intel Core Ultra processors have done away with Hyper Threading (HT), Intel Xeon CPUs continue supporting HT/SMT, including with their latest Xeon 6300 series budget server processors. As the new AMD EPYC 4005 "Grado" processors also support Simultaneous Multi-Threading (SMT) and can be found at the same core/thread count count as the flagship Xeon 6369P processor, it makes for an interesting look at comparing the SMT/HT performance impact and power efficiency. Here are some benchmarks showing the Xeon 6300 against the AMD EPYC 4005 in SMT performance.

Prior to the AMD Advancing AI 2025 event last week, AMD shared additional details on their forthcoming Ryzen Threadripper 9000 series processors.

Last month with the launch of the AMD EPYC 4005 "Grado" series for entry-level Zen 5 servers we ran benchmarks of the AMD EPYC 4565P and EPYC 4585PX processors as the top-tier 16-core CPUs. They delivered an excellent combination of performance, power efficiency, and most of all value for those looking to assemble an AM5-based budget-oriented server in 2025 and beyond. Those processors destroyed the Intel Xeon 6300 series competition's flagship, the Xeon 6369P that is simply 8 cores / 16 threads in 2025... Being curious about the core-for-core performance between the AMD EPYC 4005 series and Intel Xeon 6300 series, I got my hands on an AMD EPYC 4345P as the Grado 8-core processor to see how it performs against that Xeon E-2400 series replacement as well as how the performance compares to the prior generation 8-core EPYC 4344P.

For some very fun Linux benchmarking on this 21st anniversary of starting Phoronix is looking at the Ryzen AI Max (PRO) 390 Linux performance, the 12-core Strix Halo SoC with Radeon 8050S Graphics. While there have been various benchmarks of the AMD Ryzen AI Max+ (PRO) 395 in recent weeks on Phoronix and other publications, the other Ryzen AI Max "Strix Halo" SoCs haven't been as widely seen in the industry yet. The 12-core Ryzen AI Max PRO 390 was tested within another HP ZBook Ultra G1a for a very interesting look at the high-end/premium Linux laptop/workstation performance.

While Intel opted against implementing Hyper Threading for their latest Arrow Lake and Lunar Lake processors, Simultaneous Multi-Threading (SMT) still proves very effective on the AMD side. Even though the top-end AMD Ryzen AI MAX "Strix Halo" SoCs provide 16 Zen 5 cores, the presence of SMT for 32 threads still proves worthwhile from both a performance and power efficiency perspective. Here is an on/off comparison for SMT with the flagship AMD Ryzen AI MAX+ PRO 395 within the HP ZBook Ultra G1a.