The High-Level Zen Overview

AMD is keen to stress that the Zen project had three main goals: core, cache and power. The power aspect of the design is one that was very aggressive – not in the sense of aiming for a mobile-first design, but efficiency at the higher performance levels was key in order to be competitive again. It is worth noting that AMD did not mention ‘die size’ in any of the three main goals, which is usually a requirement as well. Arguably you can make a massive core design to run at high performance and low latency, but it comes at the expense of die size which makes the cost of such a design from a product standpoint less economical (if AMD had to rely on 500mm2 die designs in consumer at 14nm, they would be priced way too high). Nevertheless, power was the main concern rather than pure performance or function, which have been typical AMD targets in the past. The shifting of the goal posts was part of the process to creating Zen.

This slide contains a number of features we will hit on later in this piece but covers a number of main topics which come under those main three goals of core, cache and power.

For the core, having bigger and wider everything was to be expected, however maintaining a low latency can be difficult. Features such as the micro-op cache help most instruction streams improve in performance and bypass parts of potentially long-cycle repetitive operations, but also the larger dispatch, larger retire, larger schedulers and better branch prediction means that higher throughput can be maintained longer and in the fastest order possible. Add in dual threads and the applicability of keeping the functional units occupied with full queues also improves multi-threaded performance.

For the caches, having a faster prefetch and better algorithms ensures the data is ready when each of the caches when a thread needs it. Aiming for faster caches was AMD’s target, and while they are not disclosing latencies or bandwidth at this time, we are being told that L1/L2 bandwidth is doubled with L3 up to 5x.

For the power, AMD has taken what it learned with Carrizo and moved it forward. This involves more aggressive monitoring of critical paths around the core, and better control of the frequency and power in various regions of the silicon. Zen will have more clock regions (it seems various parts of the back-end and front-end can be gated as needed) with features that help improve power efficiency, such as the micro-op cache, the Stack Engine (dedicated low power address manipulation unit) and Move elimination (low-power method for register adjustment - pointers to registers are adjusted rather than going through the high-power scheduler).

The Big Core Diagram

We saw this diagram last week, but now we get updates on some of the bigger features AMD wants to promote:

The improved branch predictor allows for 2 branches per Branch Target Buffer (BTB), but in the event of tagged instructions will filter through the micro-op cache. On the other side, the decoder can dispatch 4 instructions per cycle however some of those instructions can be fused into the micro-op queue. Fused instructions still come out of the queue as two micro-ops, but take up less buffer space as a result.

As mentioned earlier, the INT and FP pipes and schedulers are separated, but the INT rename space is 168 registers wide, which feeds into 6x14 scheduling queues. The FP employs as 160 entry register file, and both the FP and INT sections feed into a 192-entry retire queue. The retire queue can operate at 8 instructions per cycle, moving up from 4/cycle in previous AMD microarchitectures.

The load/store units are improved, supporting a 72 out-of-order loads, similar to Skylake. We’ll discuss this a bit later. On the FP side there are four pipes (compared to three in previous designs) which support combined 128-bit FMAC instructions. These cannot be combined for one 256-bit AVX2, but can be scheduled for AVX2 over two instructions.

AMD Zen Microarchiture Part 2 Fetch and Decode
POST A COMMENT

104 Comments

View All Comments

  • TristanSDX - Wednesday, August 24, 2016 - link

    Zen do not support transactional memory, big disadvantage comparing to Intel Reply
  • Senti - Wednesday, August 24, 2016 - link

    And how much does it matter? TSX is great thing no doubt there. But the adoption? What can you name of real software what uses and get significant benefit of it?

    I blame Intel stupid marketing for cutting TSX from too many versions and killing the adoption.
    Reply
  • coder111 - Wednesday, August 24, 2016 - link

    As far as I know, Azul JVMs do support transactional memory. So if you have a Java app, you can use it.

    Other than that, yes, I haven't seen TSX used much...
    Reply
  • 68k - Wednesday, August 24, 2016 - link

    Isn't the version of glibc in recent Linux-distributions using the lock elision feature of TSX?

    https://lwn.net/Articles/534758/
    https://01.org/blogs/tlcounts/2014/lock-elision-gl...

    If so, then essentially every single Linux program does make use of TSX when present.
    Reply
  • looncraz - Wednesday, August 24, 2016 - link

    One of the most important features of TSX are checkpoints. Zen supports checkpoints in its execution pipeline. Otherwise, I've not seen anything that said Zen did or did not support TSX, not that the tech is widely used at this time.

    From there, you just need tagging and a few other features to add support. It's something that could be included in Zen+ if Zen does not have it.
    Reply
  • silverblue - Wednesday, August 24, 2016 - link

    It looks like Zen was developed to accelerate the vast majority of software, and rely on core count for everything else. It might explain the lack of focus on AVX.

    If cache stats were any indication of performance, it would appear that Zen was destined to compete with Broadwell, but not quite match the Lake CPUs; Zen+ would perhaps close the gap albeit a bit late. Bulldozer was hamstrung by half-speed writes and horrific L3 latency - would it be remiss to assume that they've at least fixed those two issues?

    I'm not sure anybody can truly predict performance however, even with a Blender demonstration, and certainly not to work out prospective Cinebench or SuperPi performance. You could have a monster of an architecture, but if the software isn't optimised for it, it's not going to be representative of its true performance.
    Reply
  • wumpus - Wednesday, August 24, 2016 - link

    I'd still want the TSX instructions before even thinking about the server market. I guess they surrendered that before the overall architecture was finished. Although considering how badly it has worked for Intel (essentially turned off after errata was noted in the first generation), maybe it wasn't worth risk. Reply
  • Alexvrb - Sunday, August 28, 2016 - link

    Yeah they need to take their time. A faulty implementation would do more harm than good at this point. Reply
  • Xajel - Wednesday, August 24, 2016 - link

    I have a feeling that the Socket has more potential, there's a huge jump in pin counts that might hides something, I suspect AMD have specific HEDT version with higher TDP ( like 130-140 ) that might ship later in 2017 after the first wave. or maybe even triple channel that works only on higher-end HEDT motherboard while it will be still backward compatible with regular dual channels motherboards... Reply
  • none12345 - Wednesday, August 24, 2016 - link

    Nice article, thanks, and timely too.

    Cant wait for real zen benchmarks.

    I so badly want this to be another athlon64 x2 moment. But i dont think we will get that, and we don't need that. Consider the athlon 64 gave us multicore, and it stomped the pentium4 as well.

    Ill be completey happy with a phenom II moment. Which was note quite as fast as intel, but gave you more almost as fast cores for your money. As well as unlocking cores at a much lower price point, which gave you superior overclocking for your money.

    I will not at this point consider buying another quad core. Quad core is insufficient for my typical work load. I do not use 1 heavily multithreaded piece of software, i constantly use multiple pieces of moderately threaded software that currently mostly maxes out my processor.

    In my opinion the industry should have stopped selling dual cores a year ago. It should be quad core at the low end and 6 or 8 core should be the mainstream. For desktop that is, i can still see some moble things being dual core.

    Because i will NOT consider another quad core at this point. My only option today is the intel's enthusiast platform, which is far too expensive relative to the performance increase. So they are out.

    And this is why im hoping that zen does not disappoint. If they can give me 6 or 8 cores that are within 10% per core, for similar costs to the i5 or i7 line, then im a definite buy. If they give me 6 or 8 cores that are priced like intel's enthusiast platform, well then i guess im not upgrading, untill someone can offer me more cores for a reasonable price.

    If intel would offer more cores mainstream, then id absolutely consider a new chip from them. IE if i3 was 4 core, i5 was 6 core, and i7 was 8 core.
    Reply

Log in

Don't have an account? Sign up now