• We’re currently investigating an issue related to the forum theme and styling that is impacting page layout and visual formatting. The problem has been identified, and we are actively working on a resolution. There is no impact to user data or functionality, this is strictly a front-end display issue. We’ll post an update once the fix has been deployed. Thanks for your patience while we get this sorted.

Discussion Zen 5 Speculation (EPYC Turin and Strix Point/Granite Ridge - Ryzen 9000)

Page 304 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.
CAMM is a form factor. Why does it have numbered variants??

We didn't have SO-DIMM1, SO-DIMM2, SO-DIMM3 right?
CAMM is a proprietary standard developed by Dell.

CAMM2 is a JEDEC standard based on CAMM that anyone can implement.

Sort of like switching up from AMD/DICE's Mantle to the Khronos Vulkan API standard for low level graphics programming which was directly based on Mantle with input from the hardware and software industries.
 
Last edited:
CAMM is a proprietary standard developed by Dell.

CAMM2 is a JEDEC standard based on CAMM that anyone can implement - sort of like switching up from AMD/DICE's Mantle to the Khronos Vulkan API standard for low level graphics programming which was directly based on Mantle with input from the hardware and software industries.
3 minutes faster than I 🙂
 
Why is the added latency of LPDDR a problem for PC enthusiasts?

Apple Silicon Macs use LPDDR with no issue.

I suppose it has to do with the different design paradigms. Intel/AMD CPUs are designed to run at higher clock speeds, and are hence more latency sensitive.
 
Why is the added latency of LPDDR a problem for PC enthusiasts?

Apple Silicon Macs use LPDDR with no issue.

I suppose it has to do with the different design paradigms. Intel/AMD CPUs are designed to run at higher clock speeds, and are hence more latency sensitive.
Gaming... One of the reasons why X3D is so successful 🙂
 
Zen 2 is also quite small. If it provides enough CPU capability to exploit the GPU segment, then why change?
Imagine the size of it on N3. (not saying anything, just that the die would be super small.)

Yeah, that's the point.
You screw it in and a-ha! it works.
Not only that, but it could potentially go on the back side of the motherboard and that would save a ton of space. PCs gonna get smaller, yo!
 
the platform is fixed in place.
Nothing to see.

It still heats up and needs cooling. So no you don't.
It's just a smaller, neater form-factor for client memory.
(frankly, DIMMs kinda suck a fat one in general)
Case manufacturers are already accounting for this in new and future designs. Shoot. some manufacturers are already including extra space for backside power connectors.

I would dig up some links, but I am on mobile rn.
 
Case manufacturers are already accounting for this in new and future designs
Can't do that, you're ATX-limited.
some manufacturers are already including extra space for backside power connectors.
That's not dissipating any real heat.
It depends entirely on your use case.
The usecase for DIY DT PC is gaming.
LPDDR is sorta a mixed bag there; higher net (and I think effective) bandwidth but latency is measurably (very much so) worse.
 
Seems like a modern overhaul of overall PC system design is long overdue.
I prefer something like easy to plug rectangular modules. Everything covered with a plastic shroud to protect the internal electronics and having microchannel spaces in the plastic for airflow. Make it so easy that a five year old can assemble their own PC.
 
Back
Top