Crucial T700 PCIe 5.0 NVMe SSD Review - 12GB/s
Sapphire Radeon RX 7600 PULSE review
Gainward GeForce RTX 4060 Ti GHOST review
Radeon RX 7600 review
ASUS GeForce RTX 4060 Ti TUF Gaming review
MSI GeForce RTX 4060 Ti Gaming X TRIO review
GeForce RTX 4060 Ti 8GB (FE) review
Corsair 2000D RGB Airflow Mini-ITX - PC chassis review
ASUS PG27AQDM Review - 240Hz 1440p OLED monitor
MSI MAG X670E Tomahawk WiFi review
Rumor: Massive Cache Size Increase for Intel Raptor Lake Processors
Intel's Raptor Lake-S desktop processor would contain up to 68 MB of "total cache" (L2 and L3 cache). In consonance with what AMD is doing with the pending Ryzen 7 5800X3D and 3D Vertical Cache technology.
The concept was posted on Twitter by PC enthusiast OneRaichu and illustrated by Olrak29. The "Raptor Lake-S" silicon is projected to comprise eight "Raptor Cove" P-core clusters and four "Gracemont" E-core clusters (each cluster amounts to four cores). Compared to the 1.25 MB dedicated L2 cache found in the "Golden Cove" P-core found in "Alder Lake-S," the "Raptor Cove" core is supposed to feature a dedicated L2 cache of 2 MB in "Raptor Cove." A "Gracemont" E-core cluster contains four CPU cores that share an L2 cache. With the introduction of "Alder Lake," Intel expects to quadruple the size of the L2 cache for E-core clusters from 2 MB per cluster to 4 MB per cluster. Compared to "Alder Lake-S" (C0 silicon), the shared L3 cache on "Raptor Lake-S" (C1 silicon) has increased from 30 megabytes to 36 megabytes. As a result, the total size of the L2 and L3 caches is 68 MB. Everybody's attention is now focused on "Zen 4," and whether or not AMD would expand the size of L2 caches from the 512 KB per-core size that AMD has maintained consistently since the first "Zen."
Rumor: Microsoft Xbox Series S refresh in 2022, using AMD 6nm SoC. - 09/09/2021 08:43 AM
Microsoft may be planning a refresh of the Xbox Series S in late 2022 with an updated 6 nm AMD APU. The refresh APU based on 6nm technology likely yields better allows Microsoft to enable all 24 Compu...
Rumor: Microsoft might share information on extremely critical vulnerability later today - 01/14/2020 03:53 PM
It's tagged as a rumor, but you can rest assured it'll become a fact. Keep an eye out on your Tuesday patches, and apply them. According to Krebs On Security, Microsoft is about to release an extre...
PrMinisterGR
Senior Member
Posts: 8103
Joined: 2014-09-27
Senior Member
Posts: 8103
Joined: 2014-09-27
#5983901 Posted on: 01/18/2022 06:48 AM
Seems to be really hard to grasp that the lower the power of the cores that your application is not using, the higher the power of the cores it is using.
The E-Cores have been thoroughly shown by multiple reputable sources as being worthless, or even a detriment, in anything outside of heavily multi-threaded workloads that aren't latency sensitive. In games they're complete trash. HUB demonstrated that it's the cache difference alone that makes the higher model Alder Lake processors perform better.
Seems to be really hard to grasp that the lower the power of the cores that your application is not using, the higher the power of the cores it is using.
Agent-A01
Senior Member
Posts: 11625
Joined: 2010-12-27
Senior Member
Posts: 11625
Joined: 2010-12-27
#5983910 Posted on: 01/18/2022 08:07 AM
It's simple. Don't use Ecores for gaming. Problem solved.
The E-Cores have been thoroughly shown by multiple reputable sources as being worthless, or even a detriment, in anything outside of heavily multi-threaded workloads that aren't latency sensitive. In games they're complete trash. HUB demonstrated that it's the cache difference alone that makes the higher model Alder Lake processors perform better.
It's simple. Don't use Ecores for gaming. Problem solved.
Neo Cyrus
Senior Member
Posts: 10558
Joined: 2006-02-14
Senior Member
Posts: 10558
Joined: 2006-02-14
#5983911 Posted on: 01/18/2022 08:08 AM
What makes you think anyone doesn't know that, or that it's always technically correct? It's irrelevant to what I said either way, what I said is correct regardless of how you want to spin it.
The problem is that it's a waste of silicon in a desktop environment, save for very niche cases. I'd hardly call that solved.
Seems to be really hard to grasp that the lower the power of the cores that your application is not using, the higher the power of the cores it is using.
What makes you think anyone doesn't know that, or that it's always technically correct? It's irrelevant to what I said either way, what I said is correct regardless of how you want to spin it.
It's simple. Don't use Ecores for gaming. Problem solved.
The problem is that it's a waste of silicon in a desktop environment, save for very niche cases. I'd hardly call that solved.
Agent-A01
Senior Member
Posts: 11625
Joined: 2010-12-27
Senior Member
Posts: 11625
Joined: 2010-12-27
#5983915 Posted on: 01/18/2022 08:26 AM
The problem is that it's a waste of silicon in a desktop environment, save for very niche cases. I'd hardly call that solved.
That's not true at all.
The desktop environment is not comprised of only gamers. In fact gamers are a small subset of desktop users.
Exactly how did you come to such a ridiculous conclusion?
The problem is that it's a waste of silicon in a desktop environment, save for very niche cases. I'd hardly call that solved.
That's not true at all.
The desktop environment is not comprised of only gamers. In fact gamers are a small subset of desktop users.
Exactly how did you come to such a ridiculous conclusion?
Click here to post a comment for this news story on the message forum.
Senior Member
Posts: 10558
Joined: 2006-02-14
The E-Cores have been thoroughly shown by multiple reputable sources as being worthless, or even a detriment, in anything outside of heavily multi-threaded workloads that aren't latency sensitive. In games they're complete trash. HUB demonstrated that it's the cache difference alone that makes the higher model Alder Lake processors perform better.