惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

A
Arctic Wolf
博客园 - 聂微东
F
Fortinet All Blogs
云风的 BLOG
云风的 BLOG
小众软件
小众软件
V
Visual Studio Blog
博客园 - 三生石上(FineUI控件)
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
Apple Machine Learning Research
Apple Machine Learning Research
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
The Cloudflare Blog
H
Hackread – Cybersecurity News, Data Breaches, AI and More
The GitHub Blog
The GitHub Blog
Y
Y Combinator Blog
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
博客园_首页
L
LangChain Blog
A
About on SuperTechFans
阮一峰的网络日志
阮一峰的网络日志
I
Intezer
T
The Blog of Author Tim Ferriss
Security Latest
Security Latest
C
CXSECURITY Database RSS Feed - CXSecurity.com
Know Your Adversary
Know Your Adversary
Simon Willison's Weblog
Simon Willison's Weblog
cs.CL updates on arXiv.org
cs.CL updates on arXiv.org
P
Palo Alto Networks Blog
Scott Helme
Scott Helme
S
Secure Thoughts
Spread Privacy
Spread Privacy
T
Threat Research - Cisco Blogs
Attack and Defense Labs
Attack and Defense Labs
P
Privacy & Cybersecurity Law Blog
O
OpenAI News
H
Heimdal Security Blog
www.infosecurity-magazine.com
www.infosecurity-magazine.com
Help Net Security
Help Net Security
C
Cyber Attacks, Cyber Crime and Cyber Security
Blog — PlanetScale
Blog — PlanetScale
GbyAI
GbyAI
G
Google Developers Blog
博客园 - Franky
cs.AI updates on arXiv.org
cs.AI updates on arXiv.org
K
Kaspersky official blog
Recent Commits to openclaw:main
Recent Commits to openclaw:main
T
Tor Project blog
D
Darknet – Hacking Tools, Hacker News & Cyber Security
T
Tenable Blog
Google Online Security Blog
Google Online Security Blog
PCI Perspectives
PCI Perspectives

The Register - On-Prem: Systems

Qualcomm teases agentic CPUs and smartphones Fujitsu says quantum and AI will replace mainframes in 2035 ZTE & China's NCRC partner for smart interventional medicine Core Scientific accelerates crypto-to-AI pivot Meta to use millions of AWS Graviton cores AI now gobbling up power and management chips for servers Tesla stakes AI dreams on Intel's unfinished AI chip SK Hynix breaks ground on Indiana advanced packaging plant Datacenter boom keeps dirty coal plants alive in the US AMD's Ryzen 9 9950X3D2 Dual Edition tested World's blandest man steps down from CEO job to spend more time in tastefully appointed home World's blandest man steps down from CEO job Intel eases reliance on TSMC with 'Merica-made Core Series 3 processors Intel eases reliance on TSMC with Core Series 3 CPUs Guide to GPU virtualization: passthrough, vGPU, and MIG Guide to GPU virtualization: passthrough, vGPU, and MIG Orbital datacenter startup admits launch economics don't fly AI-powered mainframe exits are a bubble set to pop Cloud-smart strategy helps Interactive meet GenAI demands Oracle taps Bloom for fuel cells to support datacenter binge Oracle taps Bloom for fuel cells to support datacenter binge UK signs Rolls-Royce SMR design deal Japan going back to the future by reviving its chip industry Japan going back to the future by reviving its chip industry AWS ponders selling its home-grown chips by the rack-load Supply chain challenges risk delaying Nvidia's Rubin GPUs Supply chain challenges risk delaying Nvidia's Rubin GPUs Supermicro investigating alleged China chip smuggling Intel trapped in Elon's reality distortion field UALink delivers 2.0 spec before v. 1.0 silicon ships OpenInfra General Manager on sovereignty and kill switches Anthropic reveals $30bn run rate, plan to use new Google TPU Nvidia embraces optical scale-up as copper reaches limits Nvidia embraces optical scale-up as copper reaches limits IBM wants Arm software on its mainframes for AI support AI datacenters create heat islands around them, paper finds Arm says AI agents need a new CPU. Intel doesn't buy it Memory-makers' shares are down. Don't blame Google Memory-makers' shares are down. Don't blame Google US PC shipments to fall 13% as memory and storage crunch hits budget systems US PC shipments to fall 13% as memory costs surge ZTE showcases intelligent computing at CloudFest 2026 Rebellions eyes global expansion with rack-scale AI platform Rebellions eyes global expansion with rack-scale AI platform Enterprise infrastructure is entering an economic reset Apple's making more iPhone bits in US, but not the iPhone Three more charged with trying to smuggle GPUs to China Three more charged with trying to smuggle GPUs to China Dell slims Pro laptops, boosts battery and cooling Alibaba delivers RISC-V server chip optimized for Chinese AI Alibaba delivers RISC-V server chip optimized for Chinese AI AI-pilled Arm CEO teases mystery products for $1T TAM Arm rolls its own 136-core AGI CPU to chase AI hype train SoftBank builds AI mega-datacenter on nuke site SoftBank builds AI mega-datacenter on nuke site Chip tester shrugged off ransomware – then came the leak Explainer: AI-ready servers Elon Musk proposes 'Terafab' to level up chip production Australia to datacenter operators: BYO energy or stay home Australia to datacenter operators: BYO energy or stay home Supermicro co-founder charged over $2.5B GPU sales to China Blue Origin applies to launch 51,000 datacenter satellites Blue Origin applies to launch 51,000 datacenter satellites Alibaba has made 470,000 AI chips, admits they’re inferior Decoding Nvidia's Groq-powered LPX and the rest of its new rack systems Your next car might need 300 GB of RAM, and so will autonomous robots Your next car might need 300 GB of RAM, and so will robots It's not a binary choice: Boffin builds ternary CPU Nvidia H200 back on in China, production ramping: Huang Nvidia slaps $20B Groq tech into massive new LPX racks to speed AI response time AI Burning Man happens next week – what to expect at Nvidia GTC 2026 Meta reveals four Broadcom-built custom AI chips, claims some outperform commercial silicon Meta reveals custom AI chips it says beat Nvidia ZTE and Orange Morocco launch Livebox 7 for smart homes Ayar Labs taps Wiwynn to cram 1,024 GPUs into a photonic rack system Ayar Labs, Wiwynn to cram 1,024 GPUs into photonic system ZTE and Whale Cloud Showcase Digital Transformation at MWC AI datacenters may gulp NYC's daily water supply at peak Mystery outage behind JetBlue's request for grounding HPE tweaks T&Cs so it can change quotes as RAM prices rise Supermicro launches probe after staff charged with China export violations
AMD doubles up on V-Cache with 9950X3D2 Dual Edition
Tobias Mann Tobias Mann · 2026-03-27 · via The Register - On-Prem: Systems

Personal Tech

AMD's new desktop CPU oozes cache out of all 16 cores

Turns out massive caches are good for more than games. House of Zen boasts 5-13% perf boost over prior-gen part

AMD aims to extend its lead in desktop gaming with a new CPU, dubbed the Ryzen 9 9950X3D2 Dual Edition. This top-of-the-line part has 16 cores fed by an absolutely massive 208 MB pool of cache, with memory spread across both CCDs.

The hotly anticipated processor chip is essentially a modified version of the 9950X3D announced in 2025, only both of the chip's two compute dies are now equipped with a 64 MB SRAM tile, boosting the L3 cache from 128 MB to 192 MB.

Larger caches benefit data heavy workloads, in particular PC games, by keeping more of the working memory closer to the cores. Since the launch of the Ryzen 7 5800X3D in 2022, AMD has used advanced packing to expand its chips' L3 cache without needing to design a larger die. This technology helped AMD to overtake long-time rival Intel in gaming CPU performance. 

While 3D V-Cache's most obvious benefits accrue to gamers, the additional cache also benefits a lot of high-powered production workloads, like 3D rendering, code compilation, AI, and data science because frequently accessed data can stay resident on the CPU for longer. (This is one of the reasons why caches of server CPUs have increased so dramatically over the past few years.)

Processor Cores / Threads Base Clock Boost Clock L2 Cache L3 Cache TDP Launch MSRP
9950X3D216/324.3 GHz5.6 GHz16 MB192200 W?
9950X3D16/324.3 GHz5.7 GHz16 MB128170 W$699 USD
9950X16/324.3 GHz5.7 GHz16 MB64170 W$649 USD

According to AMD, customers can expect to see a between 5 and 13 percent boost in production workloads compared to the single V-Cache die equipped 9900X3D.

According to Jack Huynh, SVP of AMD's computing and graphics group, with the 9950X3D2, customers "no longer have to choose between a gaming or creator CPU."

However, this technology involves some compromises. Until now, only one of the two core complex dies (CCDs) on AMD's 12-and-16 core parts were ever equipped with an SRAM tile. Because of this, AMD implemented a core-parking feature where half of the chip's cores were essentially disabled during certain workloads to prevent them from being scheduled on the V-Cacheless dies.

According to AMD customers can expect a roughly 5-13 percent increase in performance from the 9950X3D2 versus the 9950X3D with a single V-Cache die.

According to AMD customers can expect a roughly 5-13 percent increase in performance from the 9950X3D2 versus the 9950X3D with a single V-Cache die.

Even with V-cache on both CCDs, we're told this core parking functionality is still necessary on the Ryzen 9 9950X3D2 in order to limit cross die communications which would otherwise hurt performance in applications like games.

Historically, one limitation to V-Cache-equipped CCDs is that they usually don't clock as high. This is for a variety of reasons, including thermal. AMD largely addressed this issue by moving the SRAM tile from the top of the chip to the bottom side in its 9000-series products, but the dies do still tend to clock lower.

In the case of the 9950X3D2, the base clock is 4.3 GHz while the max boost clock tops out at 5.6 GHz, a full 100 MHz lower than the 9950X3D with its single SRAM tile. Having said that, AMD often underestimates the actual cores clocks of its chips, so it wouldn't be surprising to see it hit 5.65 GHz or even 5.7 GHz depending on what you end up getting in the silicon lottery.

The 9950X3D2 is slated to hit store shelves on April 22. Pricing for the new part hasn't been released just yet, though with the 9950X3D currently retailing for north of $649, we don't expect it to be cheap.

This may make it tough to sell to gamers at a time when the memory, storage, and GPU prices are at an all-time high. AMD's decision to launch a new flagship in the current climate comes in stark contrast to Intel's newly-launched Core Ultra 200S Plus series processors, which we reviewed earlier this week, which promise 18 to 24 cores at a price ranging from $200-$300. 

While AMD's X3D chips still hold the advantage in gaming, Intel's latest parts may see wider adoption because they're cheap and also perform exceptionally well in production workloads. ®