The AMD Zen and Ryzen 7 Review: A Deep Dive on 1800X, 1700X and 1700
by Ian Cutress on March 2, 2017 9:00 AM ESTThe Core Complex, Caches, and Fabric
Many core designs often start with an initial low-core-count building block that is repeated across a coherent fabric to generate a large number of cores and the large die. In this case, AMD is using a CPU Complex (CCX) as that building block which consists of four cores and the associated caches.
Each core will have direct access to its private L2 cache, and the 8 MB of L3 cache is, despite being split into blocks per core, accessible by every core on the CCX with ‘an average latency’ also L3 hits nearer to the core will have a lower latency due to the low-order address interleave method of address generation.
The L3 cache is actually a victim cache, taking data from L1 and L2 evictions rather than collecting data from prefetch/demand instructions. Victim caches tend to be less effective than inclusive caches, however Zen counters this by having a sufficiency large L2 to compensate. The use of a victim cache means that it does not have to hold L2 data inside, effectively increasing its potential capacity with less data redundancy.
It is worth noting that a single CCX has 8 MB of cache, and as a result the 8-core Zen being displayed by AMD at the current events involves two CPU Complexes. This affords a total of 16 MB of L3 cache, albeit in two distinct parts. This means that the true LLC for the entire chip is actually DRAM, although AMD states that the two CCXes can communicate with each other through the custom fabric which connects both the complexes, the memory controller, the IO, the PCIe lanes etc.
The cache representation shows L1 and L2 being local to each the core, followed by 8MB of L3 split over several cores. AMD states that the L1 and L2 bandwidth is nearly double that of Excavator, with L3 now up to 5x for bandwidth, and that this bandwidth will help drive the improvements made on the prefetch side. AMD also states that there are large queues in play for L1/L2 cache misses.
One interesting story is going to be how AMD’s coherent fabric works. For those that follow mobile phone SoCs, we know fabrics and interconnects such as CCI-400 or the CCN family are optimized to take advantage of core clusters along with the rest of the chip. A number of people have speculated that the fabric used in AMD’s new design is based on HyperTransport, however AMD has confirmed that they are using a superset HyperTransport here for Zen, and that the Infinity fabric design is meant to be high bandwidth, low latency, and be in both Zen and Vega as well as future products. Almost similar to the CPU/GPU roadmaps, the Fabric has its own as well.
Ultimately the new fabric involves a series of control and data passing structures, with the data passing enabling third-party IP in custom designs, a high-performance common bus for large multi-unit (CPU/GPU) structures, and socket to socket communication. The control elements are an extension of power management, enabling parts of the fabric to duty cycle when not in use, security by way of memory management and detection, and test/initialization for activities such as data prefetch.
Facebook
Twitter
RSS
574 Comments
View All Comments
zangheiv - Thursday, March 2, 2017 - link
Hard to believe how a company like intel that repeatedly and knowingly engaged in illegal acts and other tactics to monopolize the market and cheat the consumers into high-prices, can still have dumb happy consumers after Ryzenlmcd - Thursday, March 2, 2017 - link
Some people like 256-bit vector ops I guess :-/ who would've guessed?Ratman6161 - Thursday, March 2, 2017 - link
Have to agree. To me, the i7-7700K seems like the better bargain right now. Then again, I'm looking at a $329 I7-6700K motherboard and CPU bundle and the 7700K isn't really all that much of an upgrade from the 6700K. But in the final analysis, after all this reading, I'm still not seeing anything that makes me want to rush out and replace my trusty old i7-2600K.Meteor2 - Friday, March 3, 2017 - link
+1. Maybe, as Rarson says above, a 4C/8T Zen might clock fast enough to challenge the 7700K. But in the workloads run at home, the 1800X does not challenge the (cheaper) 7700K.HPC and data centre are completely different and here Zen looks like it has real promise.
Meteor2 - Friday, March 3, 2017 - link
...Sadly the R5s are clocked equally low.https://www.google.co.uk/amp/wccftech.com/amd-ryze...
Limited by process, I guess.
Cooe - Sunday, February 28, 2021 - link
Again. You're an absolute idiot for thinking that the only "workloads done at home" are 1080p gaming & browsing the web.... You are so out of touch with the desktop PC market, it's almost unbelievable. Here's hoping you were able to aquire some common sense over the past 4 years.cmdrdredd - Saturday, March 4, 2017 - link
" I'm still not seeing anything that makes me want to rush out and replace my trusty old i7-2600K."I agree with you. I have an overclocked 3570k and I don't see anything that makes me feel like it's too old. I'm mostly gaming on my system when I use it heavily, otherwise it's just general internet putzing around
Jimster480 - Thursday, March 2, 2017 - link
Sorry but this is not the case.This is competing against Intel's HEDT line and not against the 7700k.
2011v3 offers more PCI-E lanes only if you buy the top end CPU (which ofc isn't noted in most places) a cheaper chip like the 5820k for example only offers like 24 lanes TOTAL. Meaning that in price comparison there is no actual comparison.
Ratman6161 - Thursday, March 2, 2017 - link
Well, whomever is trying to compete against, I7-7700K is about the top of the price range I am willing to spend. So Intel's 2011V3 lineup isn't in the cards for me either. AMD really isn't offering anything much for the mid range or regular desktop user either. In web browsing, office tasks, etc, their $499 CPU is often beaten by an i3. Now, the i3 is just as good as an i7-6900K too and in at least one test the i3 7350K is top of the charts. Why does this matter? Well, where does AMD go from here? If the i3 out performs the 1800x for office tasks, what will happen when they cut it to 4 cores to make a cheaper variant? Seems like they are set up for very expensive CPU's and for CPU's they have to sell for next to nothing. Where will their mid range come from?silverblue - Thursday, March 2, 2017 - link
Something tells me that if I decide to work on something complicated in Excel, that i3 isn't going to come anywhere near an R7. Besides, the 4- and 6-core variants may end up clocked higher, we don't know for sure yet.