AMD’s Ryzen 9950X3D2 chip features an incredible 208MB of on-chip cache
AMD just revealed the Ryzen 9950X3D2 Dual Edition desktop processor, which is a beastly follow-up to last year’s 9950X3D. This is the company’s first desktop processor where both chiplets have been equipped with AMD’s proprietary 3D V-Cache technology, which seems like a boon for gamers. Each chiplet includes 104MB of cache, offering an incredible 208MB total on-chip cache.
“208MB of cache means more game data, more assets and more working data sitting right next to the CPU cores,” AMD Senior VP Jack Huynh explained in an announcement video.
Just like last year’s release, the 9950X3D2 features a 16-core processor based on the Zen 5 architecture. This new release has increased to a 200W TDP, compared to the 170TDP of the original. This could indicate an increase in speed and performance, but with more heat output.
AMD says the chip will be great for both gaming and for creative workloads, like compiling game engines, running AI models and rendering 3D objects. The company says it can deliver a five to 10 percent performance boost when using applications like Unreal Engine, Chromium, Blender and DaVinci Resolve.
Last year’s 9950X3D chip was already an absolute powerhouse, so we are looking forward to putting this one through its paces. The Ryzen 9950X3D2 chip will be available on April 22, though we don’t have a price just yet. The standard 9950X3D currently costs around $675.
This article originally appeared on Engadget at https://www.engadget.com/computing/amds-ryzen-9950x3d2-chip-features-an-incredible-208mb-of-on-chip-cache-154137156.html?src=rss
AMD just revealed the Ryzen 9950X3D2 Dual Edition desktop processor, which is a beastly follow-up to last year’s 9950X3D. This is the company’s first desktop processor where both chiplets have been equipped with AMD’s proprietary 3D V-Cache technology, which seems like a boon for gamers. Each chiplet includes 104MB of…
Recent Posts
- TikTok bans Musk documentary account
- Microsoft’s Maia 300 swaps raw compute for a 2.5x memory bandwidth gain as it moves to make in-house silicon its main AI engine while claiming a 40% efficiency bump — could going the Google route be the pin that pops the Nvidia AI bubble?
- Android Auto can be used outside of your car: Here’s how
- Mercedes-AMG’s first ground-up SUV is a 1,150hp electric beast
- TDM Neo review: they twist and shout, but they don’t sound good
Archives
- October 2026
- September 2026
- August 2026
- July 2026
- June 2026
- May 2026
- April 2026
- March 2026
- February 2026
- January 2026
- December 2025
- November 2025
- October 2025
- September 2025
- August 2025
- July 2025
- June 2025
- May 2025
- April 2025
- March 2025
- February 2025
- January 2025
- December 2024
- November 2024
- October 2024
- September 2024
- August 2024
- July 2024
- June 2024
- May 2024
- April 2024
- March 2024
- February 2024
- January 2024
- December 2023
- November 2023
- October 2023