this post was submitted on 07 Nov 2024
42 points (100.0% liked)
Technology
37742 readers
505 users here now
A nice place to discuss rumors, happenings, innovations, and challenges in the technology sphere. We also welcome discussions on the intersections of technology and society. If it’s technological news or discussion of technology, it probably belongs here.
Remember the overriding ethos on Beehaw: Be(e) Nice. Each user you encounter here is a person, and should be treated with kindness (even if they’re wrong, or use a Linux distro you don’t like). Personal attacks will not be tolerated.
Subcommunities on Beehaw:
This community's icon was made by Aaron Schneider, under the CC-BY-NC-SA 4.0 license.
founded 2 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
wow! did they figure out why?
Because 9800 is 25.6% larger of a number than 7800.
no idea
Steve from GN and their team re-ran their tests multiple times and cross-verified with 2 other reviewers as they were also in disbelief/sketched out(I'm inferring their reactions here) by the results.
So at this point it's hard to say what's causing the significant performance uplift.
It could be due to something in the cpu like the relocation of 3D v-cache, the larger cache buffer but unless we see other reviewers provide test details with some differences it's difficult to say what exactly is causing this beneficial uplift.
like what was the tech that caused such a leap? They talk about how they switched up the x3D cache configuration - it used to be stacked above the main part of the chip with some sort of insulation in between, but they found a way to remove the insulation and put the 3D cache on the underside of the chip. I'm no expert and i watched the video yesterday, so sorry if that explanation isn't clear. Effectively, they found a way to bring the 3D cache "closer" to the cores, which shortens the time it takes for the cores to communicate with the cache.