Slashdot Mirror


AMD Ryzen 7 Series Processor Reviews Go Live, Zen Looks Strong Vs Intel (hothardware.com)

MojoKid writes: AMD has finally lifted the veil on independent reviews of its new Ryzen series of desktop processors that bring the company's CPU architecture back more on competitive footing versus its rival, Intel's Core series. The initial family of Ryzen processors consists of three 8-core chips, the Ryzen 7 1800X at 3.6GHz with boost to 4.1GHz, the Ryzen 7 1700X at 3.4Ghz with boost to 3.8GHz, and the Ryzen 7 1700 at 3GHz with boost to 3.7GHz. Each has support for 2 threads per core, for a total of 16 threads with 16MB of L3 cache on-board, 512K of L2 and TDPs that range from 65 watts for the Ryzen 7 1700 at the low-end, on up to 95 watts for the 1700X and 1800X. In comparison to AMD's long-standing A-series APUs and FX-series processors, the new architecture is significantly more efficient and performant than any of AMD's previous desktop processor offerings. AMD designed the Zen microarchitecture at the heart of Ryzen with performance, throughput, and efficiency in mind. Initially, AMD had reported a 40% target for IPC (instructions per clock) improvement with Zen but actually realized about a 52% lift in overall performance. In the general compute workloads, rendering, and clock-for-clock comparisons, the Ryzen 7 1800X either outperformed or gives Intel's much more expensive Core i7-6900K a run for its money. The lower clock speeds of the Ryzen 7 1700X and 1700 obviously resulted in performance a notch behind the flagship 1800X, but those processors also performed quite well. Ryzen was especially strong in heavily threaded workloads like 3D rendering and Ray Tracing, but even in less strenuous tests like PCMark, the Ryzen 7 series competed favorably. It's not all good news, though. With some older code, audio encoding, lower-res gaming, and platform level tests, Ryzen trailed Intel -- sometimes by a wide margin. There's obviously still optimization work that needs to be done -- from both AMD and software developers.

175 comments

  1. strong til ... by arbiter1 · · Score: 0

    Then you start playing games then that strong hits a bit of a road block.

    1. Re:strong til ... by andydread · · Score: 4, Interesting

      some older games...and it still performed quite strong without optimization...and it's half the price of the $1000+ intel processor that it trailed by 20% but feel free to pay the extra $500 for 20% more performance for some older games.

    2. Re:strong til ... by Tough+Love · · Score: 5, Interesting

      Looking more like crappy game code than crappy processor. Reviews show Ryzen doing particularly well on high quality settings. Regardless of gaming, which really is all about the GPU especially with Vulkan games coming down the pipe, Ryzen by all appearances is a kickass workstation chip at a gimme price. Because of Ryzen, I expect to pay less for my next desktop than my next phone.

      --
      When all you have is a hammer, every problem starts to look like a thumb.
    3. Re:strong til ... by sexconker · · Score: 0, Troll

      $500 R7 1800X vs $340 i7 7700k.

      http://www.gamersnexus.net/hwr...

      The 1800X is a shitty choice for gaming. Perhaps drivers, coptimized software, and more mature motherboards/BIOSes will help over time. AMD's shit does tend to improve with age, but there's a huge delta there.

    4. Re:strong til ... by Tough+Love · · Score: 2, Informative

      Don't forget Vulkan, which effectively puts the CPU in the back seat. And there are lots of great Ryzen reviews out there, in contrast to the Intel dicksuck site you picked.

      --
      When all you have is a hammer, every problem starts to look like a thumb.
    5. Re:strong til ... by cfalcon · · Score: 4, Insightful

      > $500 R7 1800X vs $340 i7 7700k.

      The 1800X is like 8 cores to the 7700K's 4 cores. The 7700K, having half the cores, will presumably do better on single threaded tasks, such as the benchmarks in question. Future code, especially that which makes requests to the GPU in a multithreaded fashion, will perform better with more damned cores. For single threaded (or basically that), the 7700K also blows away Intel's 6950X, their top desktop CPU offering with 10 cores.

      A better comparison per price point would be the 1700X or 1700 to the 7700K. Again, you find that the 8 core chip blows away the 4 core chip on multiprocessing, with less amazing results from a single thread.

      There's a ton of applications that scale well with cores, and games will begin to do so more in the future. There will always be tasks that can't be parallelized, but the question is, when do they matter versus the ones that can? The question of cores versus speed per dollar is about as old as CPUs, and the answer is always "what is your use case".

    6. Re:strong til ... by Anonymous Coward · · Score: 0

      That's another way of saying "Ryzen performs better when the bottleneck is the GPU"

      Intel clearly retains the crown for single thread and high-end performance. - And single-thread performance is king for games and end-user applications. (Rendering and video encoding is not an end-user application)

      Ryzen's job is to push down the price of affordable mid and mid-high end gaming systems, which it's doing quite well it seems.

    7. Re:strong til ... by Anonymous Coward · · Score: 0

      You don't know what you're talking about.

    8. Re:strong til ... by Anonymous Coward · · Score: 0

      For gaming use you would be a fool to pay $500 for a cpu. There are much cheaper options. For video encoding however this CPU is quite good. It is close or faster to Intel offering for half the money. I also very curious how it would perform on compiling Android or linux kernel. Good performance would make is very useful in workstation.

    9. Re:strong til ... by Kjella · · Score: 4, Interesting

      Don't forget Vulkan, which effectively puts the CPU in the back seat. And there are lots of great Ryzen reviews out there, in contrast to the Intel dicksuck site you picked.

      1. Links to wccftech (the 4chan of tech sites)
      2. Uses the word "dicksuck"
      3. A poor CPU is still a poor CPU after Vulkan

      And I say that as someone planning to buy a Ryzen.. is it perfect? No. But it's close enough that AMD deserves a sale so Intel doesn't get to monopolize the high end again. Just deciding on whether I'll hold out for Vega or not...

      --
      Live today, because you never know what tomorrow brings
    10. Re:strong til ... by Anonymous Coward · · Score: 0

      wccftech is a well known amd 'dicksuck' site.. pot kettle...

    11. Re:strong til ... by barc0001 · · Score: 2

      Plus anyone with two brain cells to rub together knows you'll get better bang for the buck throwing that extra $500 at a good video card on the Ryzan box instead of dumping it into minor gains on the CPU side with Intel.

    12. Re:strong til ... by Anonymous Coward · · Score: 0

      The i7 7700k is a shitty choice for gaming too. That's way too much CPU if all you're going to waste it on are games.

    13. Re:strong til ... by hairyfeet · · Score: 4, Insightful

      The "bad" review? Was from hothardware....you ever went to that site without adblock? Last time I did the entire page was NOTHING but Intel ads.

      From what I've seen there is 4 sites you should never listen to, hothardware, Ars Technica, and the worst are Tom's Hardware (where their "expert" told a person asking what CPU to buy for GAMING that he should buy a Pentium dual core over a lower priced AMD X6 even though he admitted that most games the person wanted to play required a quad) and Anandtech who went so far as to drop several new triple A titles from their benchmark that so happened to play better on AMD hardware and replaced them with older titles that were expressly built with Nvidia Gameworks (which has been shown to have "cripple AMD" code baked in)...you wanna guess who their biggest advertiser is?

      Its sad that I have to even say this but you really have to do some digging before you can actually take any "news" as credible as we have had so many cozy deals with advertisers and companies affiliated with those they are reviewing that a good chunk of what you see and hear these days is just corporate propaganda or FUD.

      --
      ACs don't waste your time replying, your posts are never seen by me.
    14. Re:strong til ... by Anonymous Coward · · Score: 0

      These days, a lot of gamers run background processes like OBS to capture game footage. Extra cores will help keep the game's frame rate from dipping.

      They'll also be releasing six-core and hyperthreaded four-core in the i5 price range, so that should be a nice boost.

    15. Re:strong til ... by David_Hart · · Score: 5, Insightful

      The "bad" review? Was from hothardware....you ever went to that site without adblock? Last time I did the entire page was NOTHING but Intel ads.

      From what I've seen there is 4 sites you should never listen to, hothardware, Ars Technica, and the worst are Tom's Hardware (where their "expert" told a person asking what CPU to buy for GAMING that he should buy a Pentium dual core over a lower priced AMD X6 even though he admitted that most games the person wanted to play required a quad) and Anandtech who went so far as to drop several new triple A titles from their benchmark that so happened to play better on AMD hardware and replaced them with older titles that were expressly built with Nvidia Gameworks (which has been shown to have "cripple AMD" code baked in)...you wanna guess who their biggest advertiser is?

      Its sad that I have to even say this but you really have to do some digging before you can actually take any "news" as credible as we have had so many cozy deals with advertisers and companies affiliated with those they are reviewing that a good chunk of what you see and hear these days is just corporate propaganda or FUD.

      Toms Hardware is excellent, from my experience, for their hardware reviews. I've been building my own systems for a long time now and have used their reviews as primary source for selecting hardware components and have never had a problem with their findings. As for their "forum experts", I've had no experience with them. Saying that a whole site is horrible based on one bad experience is a tad on the extreme side, though.

      From a PC gaming perspective, until recently, very few games have taken full advantage of multi-core processors. Even if a game uses multi-core, they tend to be poorly optimized such that the load is not spread evenly across all cores. Your still better off getting the fastest CPU that you can buy even if it means getting a quad-core vs an octa-core.

    16. Re:strong til ... by Tough+Love · · Score: 4, Interesting

      single-thread performance is king for games

      It was, some time last decade. Apparently you have not heard about Vulkan. Applications are going that way too, and, well, everything.

      --
      When all you have is a hammer, every problem starts to look like a thumb.
    17. Re:strong til ... by Anonymous Coward · · Score: 2, Insightful

      Look at the delta from i7 7700k to R7 1800X to FX-8370. It's a reminder of how far AMD has come.

      And if the best thing that comes out of Ryzen is that Intel lowers its prices, then we all win anyway.

      I'll probably pick up an R7 1700 or the R5 later this year, because yes I'm an AMD fanboy.

    18. Re:strong til ... by Anonymous Coward · · Score: 0

      "Rendering and video encoding is not an end-user application"

      A heck of a lot of games do rendering. Streaming to the internet (twitch/youtube) and to another computer/tv, recording gameplay videos and video chatting involves video encoding.

    19. Re:strong til ... by r1348 · · Score: 2

      The 1800X seems to be extremely strong in compile benchmarks: https://www.phoronix.com/scan.php?page=article&item=ryzen-1800x-linux&num=1

    20. Re:strong til ... by Anonymous Coward · · Score: 1

      What he's talking about is obvious bias towards particular builds rather than empirical comparisons involving $ amounts as a divisor of performance numerals, rather than simply a small subset/collection of intentionally skewed benchmarks to make a case for something that in effect is an artifact of the analysis.

      If you want fanboyism you will find it in every flavor. Including integrated into specific benchmarking applications, intentionally. Do the reviewers know enough about the underlying use-cases to adequately vet their benchmarks and weight the results for the average use case? Of course they don't, that doesn't make them money from kickbacks.

    21. Re:strong til ... by epine · · Score: 1

      From what I've seen there is 4 sites you should never listen to

      I don't know what you're on about (or your ulterior motive), but I just read Peter Bright's summary on Ars, and it was just fine—yeoman's work—modulo 2017. BTW, "never" is a long time and a broad brush and also a brush that points in both directions.

      I miss Jon Stokes from way back something fierce, but that's not even true: I miss the era where the articles that Jon Stokes was writing could be written. AK-47[*], more than a billion transistors ago.

      [*] Uh, I meant 'aka'. Turns out Jon is an AR-15 nut (in one rant, he really carves the word "need" a new one), and all that stuff is not my speed, but then again, it's a free world.

      Way off topic, but here goes.

      What Jon wrote:

      By banning popular cosmetic features and specific models of semi-automatic long guns, the AWB succeeded in insulting, angering, and ultimately radicalizing gun owners while doing absolutely nothing about the drug-related handgun violence that accounts for the vast majority of gun homicides.

      The reality:
      Assault rifles are becoming mass shooters' weapon of choice

      Sorry, Jon, I loved you so much, but "drug-related handgun violence" is not a universal denominator in this debate.

      Separate problems, separate solutions.

    22. Re:strong til ... by Anonymous Coward · · Score: 1

      I would really like a Ryzen gaming system with top of the line Nvidia graphics. I'm going to ask my dad tomorrow to buy me one. He's in the hospital with something wrong with his kidney. The family wants me to get tested to see if I could donate a kidney. If he says no to me, I'm going tell him straight out, no gaming system, no kidney. He can go fuck him self. Fucking old bastard.

    23. Re:strong til ... by AmiMoJo · · Score: 1

      I wish they would offer more PCIe lanes though. Intel isn't any better. Top end Ryzen mobos give you one 16/8x8 slot for a GPU or two, a 4x slot and a few 1x slots. Apparently the combo of 16x GPU and 8x RAID card isn't catered for.

      --
      const int one = 65536; (Silvermoon, Texture.cs)
      SJW, n: "Someone I don't like, and by the way I'm a fuckwit" - AC
    24. Re:strong til ... by Anonymous Coward · · Score: 0

      That would immediately invalidate you. I am in the process of donating one myself, and it is quite explicit it should never be a sale (at least in my country).

    25. Re:strong til ... by Anonymous Coward · · Score: 0

      The crappy game code is technically correct, but really distorting the reality here. Especially in conjunction with the statement over Vulkan, it's borderline nonsense.
      On top of the fact that it's very difficult to switch takes performed by the CPU to a GPU, Vulkan does not fix the terrible multi-threading that many many games use. That is something the game developers have to do in the 'code' of the game. Something that does not appear to be trivial and costs money. Therefore most games that you can find will have the heaviest workloads on two or even a single thread, which then causes a bottleneck that slows everything else down.

      Before these things change and good multi-threading becomes widespread, Ryzen will not be the best choice for those who are mostly interested in gaming.

      Of course this doesn't mean that AMD didn't do impressive work with these CPUs. Finally Intel has something to worry about and that's good for all of us.

    26. Re:strong til ... by Anonymous Coward · · Score: 0

      Anandtech is good at rewriting press releases and pictures.

    27. Re: strong til ... by Anonymous Coward · · Score: 1

      No wonder I saw (and recognized) 3 of these 4 sites top of my first 'ryzen' search today! (Ars, Anand and Tom). I'm new to PC building and so I'm not aware who are the Intel shills. Thanks for the enlightenment!

    28. Re:strong til ... by Anonymous Coward · · Score: 0

      Why all the Vulkan nonsense here on Slashdot? I thought this community was a bit more tech savvy. Vulkan does not put the CPU in the back seat. It allows for lower CPU overhead and better multithreading, but that's still something each game has to implement itself. Meaning that if the programmers don't put effort in creating proper multithreading Vulkan will do very little. Doom does not run well on AMDs just because it uses Vulkan. It's mostly due to the work of the developers that created the id Tech 6 engine.
      On top of that CPUs and GPUs are for different task. A CPU is comprised of very few processors with relatively high individual computational power, while a GPU is comprised of a ton of processors that are individually very weak. GPUs excel at tasks that can be easily paralleled. Simply put, GPUs are great at doing the same thing to a huge amount of data (like post processing), while CPUs are great at doing a huge amount of things to the same piece of data.

      Hopefully there will be more engines like that in the future.

    29. Re:strong til ... by ravenshrike · · Score: 1

      Erm, no. Outside of gaming, Ryzen kicks Intel up and down the block outside of 2 or 3 real world applications. With gaming, once the BIOS, opcode, and MS drivers have had time to shake down and be updated it will trump everything but the 7700k. Which will probably be beaten by one of the Ry5 or Ry3 chips when they are released..

    30. Re:strong til ... by visualight · · Score: 1

      Show me a game that isn't bottlenecked by the GPU. Artificially creating a set up where the cpu becomes the bottleneck is like the OPPOSITE of real world testing. It's a stupid way judge (or buy) a CPU.

      --
      Samsung took back my unlocked bootloader because Google wants me to rent movies. They're both evil.
    31. Re:strong til ... by Anonymous Coward · · Score: 1

      Pfff. This is all garbage. A half decent CPU is all you need for gaming these days. The real grunt work is all done on the GPU - and it's getting more and more the case.

      CPUs these days are close to being irrelevant - and Intel knows it - even though they've done their best to convince people it's not the case. Monster processing tasks are all GPU based - and you shove in a mediocre CPU with multiple cores to coordinate things.

    32. Re:strong til ... by edxwelch · · Score: 1

      No, the answer is that single threaded is nearly always more important than multi-threaded, because you are doing single threaded tasks about 99% of the time.
      Even tasks that are multi-threaded benefit from having good single threaded performance.
      The best scenario is having a CPU that is good at both. (but it's not the only thing, memory and cache is also important)
      From what I read in the reviews is that AMD has improved their single threaded performance by 50%, which brings it close to Broadwell levels. That is a big improvement and means that they have something that's at least competitive.

    33. Re: strong til ... by Type44Q · · Score: 1

      Reviews show Ryzen doing particularly well on high quality settings.

      Those tend to be tests where the GPU - and not the CPU* - are bottlenecked. Did you only look at the graphs and not actually read the reviews?

      *Don't get me wrong; I'd still pick it over anything Intel for all but the priciest builds but I wouldn't mind seeing two more DDR4 channels and more PCI-E lanes added to the processor northbridge (as opposed to the motherboard chipset/southbridge)...

    34. Re:strong til ... by Anonymous Coward · · Score: 1

      You're kidding right? How are you supposed to test a CPU if the entire test is distorted by another component in the system? Do you also look at 720p benchmarks when the GPU is tested and would argue that 4k benchmarks are invalid because they're bottlenecking the GPU?

      The vast majority of games usually becomes bottlenecked by the GPU if you use a ton of post processes, high super sampling or huge resolutions. If you don't do that, the CPU is usually the limiting factor when it comes to minimal FPS. For a gamer, especially the ones that play competitive games this is one of the most valuable metrics when it comes to making a decision for hardware.

    35. Re:strong til ... by Gr8Apes · · Score: 1

      Who honestly uses a RAID card on a desktop system these days? Software RAID does everything you need, and just works with no noticeable performance hit for the most common desktop RAID0/1/10 configurations, with no expensive hardware needed. Servers with HA requirements I wouldn't run without them.

      --
      The cesspool just got a check and balance.
    36. Re:strong til ... by Gr8Apes · · Score: 1

      Single threaded performance is benchmark for how fast a single unit of work can be done. Multi-threaded is how many units you can do simultaneously. Games have notoriously been single threaded for ever, because it's a lot easier to program a linear algorithm and keep memory use clean. when you go parallel, there's all sorts of fun involved, especially if you're simultaneously doing multiple tasks on the same in memory data. Most developers have trouble with the linear algorithm already.

      --
      The cesspool just got a check and balance.
    37. Re:strong til ... by ChrisMaple · · Score: 1

      Outside of gaming, there is a wide swath of applications where the i7-7700k beats the Ryzen 1800X by 10% to 20%, and the Intel chip is 30% lower in price. I think it's unlikely that a Ryzen 3 or 5 can take enough advantage of lower heat generated by fewer cores to make up for that 10% to 20% deficit.

      I want to buy an AMD CPU; the disrespect Intel shows its customers by using an inferior thermal interface irks me. Alas, these AMD chips don't quite make the grade.

      --
      Contribute to civilization: ari.aynrand.org/donate
    38. Re:strong til ... by avandesande · · Score: 1

      People that do live streaming like 8 core machines since they are encoding and streaming on the fly.

      --
      love is just extroverted narcissism
    39. Re:strong til ... by cfalcon · · Score: 1

      > No, the answer is that single threaded is nearly always more important than multi-threaded, because you are doing single threaded tasks about 99% of the time.

      The answer is nowhere near that simple. If your single threaded task is any manner of I/O bound- disk, network, or memory, then you can't speed it up any further with a faster CPU, on clock or IPC. If PARTS of it are bound in those ways, then a faster processor will help, but not linearly.

      But in general, if you had a choice between a 4 GHz 8 core processor and an 8 GHz 4 core processor, you'd take the faster chip. But that has NEVER been the comparison, and that's why YOUR USE CASE matters, and why single threaded performance is not always the answer. In the top end desktop useage, you'll usually pick between something like the i7-6900K (Intel's 8 core desktop offering, stable up to 4.3 GHz, a Broadwell piece released middle of last year) and the i7-7700K (Intel's very latest 4 core desktop offering, some of which are stable up to 5 GHz, a Kabylake piece two generations advanced from Broadwell). And when these are benchmarked, you see that CPU bound tasks that are single threaded are in fact a bit faster on the Kabylake, which has both slightly improved instructions per clock over the broadwell piece, and a faster clock speed, but that anything that can make use of the cores is a LOT faster on the Broadwell chip.

      More relevantly, you get to make this tradeoff at many prices, and the reason you are normally going to recommend the higher singlethreaded performance is because the piece with the more core, while way hella better in multithreaded parts, usually costs more. Doubling cores doesn't double performance in multithreaded, but it isn't too far off in some cases. Meanwhile, a 20% increase in clock speed normally gets you almost 20% more performance on single threaded.

      AMD's chips are coming in at prices that are competitive with the 4 core desktop chip, while offering performance that competes with the 8 core desktop/enthusiast pieces. That's why this is important.

      And why your use case matters.

      And your use case is probably going to favor more cores, going forward. Only you know better for you, of course, but as a general recommendation it is worth pointing out.

    40. Re:strong til ... by Anonymous Coward · · Score: 0

      Probably a good idea to wait a bit before drawing conclusions.
      golem.de for example found that the original BIOS of the standard review sample mainboard AMD sent out there was a rather big bug causing the RAM to run at the wrong frequency.
      There is a good chance this motherboard/BIOS issues still. Especially if whatever article you read doesn't say that they tested with a different motherboard or updated the BIOS, you shouldn't take their numbers seriously for now.

    41. Re:strong til ... by cfalcon · · Score: 1

      > Games have notoriously been single threaded for ever, because it's a lot easier to program a linear algorithm and keep memory use clean.

      Some things games have to do are fundamentally single threaded, but you are correct: it's easier to program a single thread, and often the gain from another thread doesn't help much. 3D games are a little different, because much of the CPU tasking involves doing stuff so that data can be pushed to the graphics card. Those scale VERY well with extra cores, but only if coded that way.

      An example is the MMO Star Wars: The Old Republic. In any area where there is not many players, the CPU has almost nothing to do. It continuously funnels requests for frames to the graphics card, which goes totally bonkers rendering hundreds of frames per second, and spinning its fan like crazy (there's a vsync option, should you be looking for a solution to this issue, and also be running fullscreen). In an area where there's a ton of players, your frame rate drops below 60 fps, and sometimes even below 30 fps, and the graphics card fan is silent. Check out the processor status, and you see the CPU dance:

      https://www.youtube.com/watch?...

      And a bit of investigation reveals that the process is barely multithreaded at all.

      Meanwhile, other games don't have this issue: they divest that logic across the cores, and the graphics card can be fully tasked (ideally intelligently so), giving you a good framerate consistently, with your GPU fan starting up if the game is actually rendering something hard.

      But again, that requires those games be programmed that way. And more are being programmed that way today. Mostly, game developers have been happy to take the much simpler single threaded approach, which reduces development costs, and if you have to support a bunch of dual core chips because a decent chunk of your customers have those, why spend your time worrying about the extra cores most chips have? That's not necessarily how all future development will go, however, especially if, as is being made obvious, that adding more cores is a lot more reasonable than adding a little bit of IPC and clock.

    42. Re:strong til ... by Anonymous Coward · · Score: 0

      Maybe they don't use raid cards but there's something new to worry about. Fast M.2 SSDs (which use 4 PCIe 3.0 lanes) are becoming more popular. Having only PCIe 3.0 1x16 and 1x8 (AMD X370) becomes restricting restricting a bit faster than 1x16, 1x8 and 1x4 on Intel Z270 MoBos.
      Sure you can offset the issue by only using 8 lanes for your single graphics card, which will hardly impact the performance of our current age. But how long will that last? Maybe you want more of those M.2 SSDs in your machine, use them in a software RAID, would be probably overkill but may be a concern for some.

    43. Re:strong til ... by Anonymous Coward · · Score: 0

      or take the saving and buy a new game?

    44. Re: strong til ... by Anonymous Coward · · Score: 0

      "i7-7700k beats the Ryzen 1800X by 10% to 20%, and the Intel chip is 30% lower in price."

      Unmmmm no it is not. That's the whole point, the ryzen chips are way cheaper. You could get 20% more out of an intel chip, but you are going to pay 50% more for It. And that 20% is only on certain criteria. Ryzen is the better deal here and probably the better chip RIGHT now. But I'll wait until consumers get their hands on it. Right now it's all paid shills on both sides.

    45. Re:strong til ... by Anonymous Coward · · Score: 0

      Sounds more like a trade tbh

    46. Re:strong til ... by Gr8Apes · · Score: 1

      An example is the MMO Star Wars: The Old Republic. ...inter In an area where there's a ton of players, your frame rate drops below 60 fps, and sometimes even below 30 fps, and the graphics card fan is silent.

      That case is exactly where an asynchronous model would excel, keeping the framerate steady and offloading all object rendering to external pieces. It should be easy enough to do so, but the re-assembly is where it gets hard. However, that still doesn't get around the base issue that 100K+ things are being rendered for a frame when only a few hundred, at most, will ever be seen. Those particular game devs only know 1 way to solve a problem, which is the core problem.

      --
      The cesspool just got a check and balance.
    47. Re:strong til ... by Gr8Apes · · Score: 1

      Based on a quick review, the AMD X370 appears to have 2 X16 and 8 X2 which can be multiplexed together to support up to 4 M.2 SSDs, if you wanted to go that route.

      --
      The cesspool just got a check and balance.
    48. Re:strong til ... by Kitano123 · · Score: 1

      Vulkan/DX12 etc take a long time to become ubiquitous and were not at that point yet, most games are still on dx9-11 which is largely due to console architecture as developers usually don't go with the latest api just for porting over to PC.

      Single core performance is still the most valuable for gaming right now, but it will change. How quickly it will change is the important factor here.

      When building a new PC its certainly worth thinking about, but I generally find building for now is better than building for some potential need as its nearly impossible to predict exactly how the gaming PC landscape will change and when.

    49. Re:strong til ... by Anonymous Coward · · Score: 0

      Anandtech didn't do any game benchmarks in their Ryzen review. Hairyfeet, you are a liar.

      Source: http://www.anandtech.com/show/11170/the-amd-zen-and-ryzen-7-review-a-deep-dive-on-1800x-1700x-and-1700

      "Anandtech who went so far as to drop several new triple A titles from their benchmark that so happened to play better on AMD hardware and replaced them with older titles that were expressly built with Nvidia Gameworks" - hairyfeet

    50. Re: strong til ... by maorb · · Score: 2

      You didn't bother looking at the price of a 7700k did you...

      Last I checked $350 (i7-7700k) is less than $500 (Ryzen R7 1800x).

      The 7700k does better in most games due to it's better per-core performance (slightly better IPC, much higher clock), but tends to do worse in programs that can use all 8 cores/16 threads on Ryzen. We're hoping for the gap in single-core performance to be reduced slightly with bios updates, Windows updates, and software optimization, but we don't expect an 1800x to ever be better than an 7700k in that arena. On the otherhand the 1800x demolishes the 7700k in threaded apps when it's scaling well, we're hoping that the outliers where it doesn't scale well can be corrected with software updates.

    51. Re:strong til ... by Anonymous Coward · · Score: 0

      Sorry, that may have caused a bit of confusion. Let's compare two products from ASUS which in the same price range, this should remove ambiguous information:
      AMD X370: https://www.asus.com/us/Mother...
      Intel Z270: https://www.asus.com/us/Mother...

      If we scroll a bit down we see a picture of the boards and some features listed beside them, connected with red lines.
      On both we get 2x PCIe 3.0 x16, which is supposedly handled by the CPU. That's fine, both CPUs can run two graphicscards with 'full' lanes.
      But then the differences start.
      You can see that the AMD board offers 1x PCIe 2.0 x16 (PCH) and 3x PCIe 3.0 x1 (PCH). While the Intel board offers 1x PCIe 3.0 x16 (PCH) and 3x PCIe x1 (PCH). PCH, for those who are unfamiliar, is the platform controller hub, more generally speaking the chipset as in X370 and Z270. Here we can see that the AMD chipset is indeed a bit short on PCIe 3.0 lanes compared to the Intel one.

      On the right side we can also see their official M.2 Socket 3 Type M support (you need an adapter to jam those SSDs into regular PCIe slots). Where the AMD chipset offers 1x 2242~221100 (PCIe 3.0 x4). The Intel chipset offers the same but also adds 1x 2242~2280 (PCIe 3.0 x4).

    52. Re:strong til ... by Billly+Gates · · Score: 1

      To be honest Hairy I have not seen 1 positive review for games.

      Tomshardware did not totally bash it. It mentioned it as a big improvement and great workhorse CPU.

      The Joker did another video here and I made a comment after I noticed something? This was evident in the last game tested but I noticed in Tom Clancy's THe Division cpu utilization was higher on the Intel while lower on the 1st core for Ryzen

      "I think I figured out what Ryzen's issue is? Look at the CPU core usage? On the Ryzen the first core has a higher % used while the rest of the cores are less utilized? On the Intel the 1st core has less cpu usage but the rest of Intel;s core are higher utilized? From what I observed:
      1. The game is stuck trying to wait for synchronization on the Ryzen or
      2. The game has code expecting a previous cpu and over utilizing the threads expecting a slower core IPC and running it like a stream (how the PS3/4 are optimized) Netflix app.
      It could also mean AMD has inferior synchronization latency or optimizations too while the INtel doesn't slow down when trying to use it's cores. What do you all think?"

      So I think AMD is having a bug with synchronization or the game codes assume AMD sucks and overdoes it's threading and replication and lowers the priority of the main CPU core?

      It could also just mean it is still inferior to an Intel on per core performance even if much improved :-(

      Sorry Hairy, I own an RX 470 and used to be an AMD fan back in the day. Intel has a better CPU for most users and gamers. An i5 4660K from 2014 is much cheaper and so is a newer i5 7600K and performs better for a much cheaper price than AMD. It may make sense at your shop to switch to Intel as you can save money.

      If am paying $500 for a damn CPU you bet I expect it to be a 4 core in EVERY benchmark. I have not seen any games that beat Intel. Not one at 720P or 1080P which stress the CPU and not the GPU. I mean even Dues Ex du Mankind divided which is an AMD optimized title is .3% than a cheaper i7 7700K. I will wait back and see.

      Intel will not take this sitting down and you bet 8 core i7's will be here next year creaming AMD unless the next Ryzen finds out what is going on and fixes it. Also the ram not being able to past 2600 mhz, only 16 PCI Express lanes, as well as 30 second boots from UEFI show teething pains.

    53. Re:strong til ... by tepples · · Score: 1

      Show me a game that isn't bottlenecked by the GPU.

      Any Super FX or SA-1 game running in higan.

    54. Re:strong til ... by Tough+Love · · Score: 1

      Vulkan/DX12 etc take a long time to become ubiquitous and were not at that point yet, most games are still on dx9-11 which is largely due to console architecture as developers usually don't go with the latest api just for porting over to PC.

      That may be your theory, but it does not correspond to facts on the ground. Every major game engine already has a Vulkan port, and in many cases the results are jaw dropping. Within a year, all tier one publishers will be shipping Vulkan builds. Bottom line: gamers know about Vulkan and gamers know they want Vulkan.

      What this means if you are building a game box is simple: if your budget is limited, spend big on the GPU, not the processor.

      --
      When all you have is a hammer, every problem starts to look like a thumb.
    55. Re:strong til ... by hairyfeet · · Score: 1

      If all the latest review of the new Intel octocore were focused solely on DOS performance and kept harping on how its bad for DOS, would you consider that a fair and unbiased review? AMD has repeatedly said in every one of their tech talks The Ryzen 7 is designed to compete with the $1100 Intel chips....now do you see ANYBODY recommending $1100 Intel 16 thread chips for gaming? Have you ever seen a single article claiming the $1100 Intel chip is a gaming CPU? Can you find a single article saying this?

      Of course you can't because that is fucking stupid, the Intel chip is a gasp! shock! a WORKSTATION CPU and everyone knows this. Meanwhile what did you see the focus at the Ryzen 7 demos by AMD? Yep tools like Blender and Photoshop which is WORKSTATION LOADS. They also made it clear the gaming chips are the R3s and R5s being released later this year.

      So yeah sorry but these "reviews" focusing on a metric that a chip wasn't designed for is about as fair and unbalanced as Faux News. Again show me a single article when Intel released their $1100 chips that focused on their gaming performance, hell I bet you'd be hard pressed to find an article that even mentioned gaming because nobody would consider $1100 workstation CPUs as gaming chips.

      --
      ACs don't waste your time replying, your posts are never seen by me.
    56. Re:strong til ... by Gr8Apes · · Score: 1

      So you want to compare a multi-year out CPU socket with an initial release motherboard option for a CPU you can just recently purchase and complain about untweaked feature sets? OK, go ahead, I guess this will be the only chipset for this obsolete CPU that will ever be out there. Oh, and the much greater mesh bandwidth capable AMD CPUs will certainly never be taken advantage of, either.

      --
      The cesspool just got a check and balance.
  2. Freedom of choice by Anonymous Coward · · Score: 2, Interesting

    Ryzen isn't quite perfect but it's nice that AMD has burned their white flag of surrender and once again gotten fit to fight against chipzilla.

    1. Re:Freedom of choice by thejynxed · · Score: 1

      Unfortunately for AMD, it's a fight Intel is less and less interested in engaging in with them. Their focus has majority-shifted to keeping ahead of ARM-based CPUs, and they've already publicly stated that their only competitor is ARM (while at the same time offering small manufacturers the chance to have ARM-designed chips produced at their fabs, for a fee, of course).

      This all being said, Intel is already working on smaller fab processes and a new architecture that builds on what they achieved with all of the current "Lake" models. AMD's problem hasn't just been in attempting to come close to Intel in performance, but in fabrication processes and yields. They are always two steps behind, it seems.

      --
      @Mindless Drivel: 100% of Twitter posts ever Tweeted.
  3. Re:Nope by Anonymous Coward · · Score: 0

    "or running VMs" which is what I do. But I'm waiting for Naples, because I need enterprise server shi.

    verb

  4. Waiting To See Some Multi GPU Benchmarks by zenlessyank · · Score: 4, Informative

    I have a feeling feeding a multi GPU rig will show some of its muscles. STH has some nice benchmarks showing it holding its own against a lot of Xeons.

    1. Re:Waiting To See Some Multi GPU Benchmarks by Anonymous Coward · · Score: 0

      GPU makers are depreciating multi-gpu setups. Nvidia is clearly downplaying it in their marketing and they require and "activation code" to even enable more than 2 cards on the latest generation products.

      It's not a very good solution for most games - Drivers have to be loaded with hand-tuned profiles and game makers need to specifically optimize their games for specific multi-gpu setups. It's a lot of work for both developers and gpu makers and it's clear they don't really want to do it anymore.

      My experiences sure have been disappointing. If you play anything but the most mainstream AAA games you quickly become acquainted with disabling one of your video cards to get many games to even work. - And even then it's a crapshoot.

    2. Re:Waiting To See Some Multi GPU Benchmarks by Anonymous Coward · · Score: 0

      STH has some nice benchmarks showing it holding its own against a lot of Xeons.

      Have they announed an Opteron-ish version?

    3. Re:Waiting To See Some Multi GPU Benchmarks by zenlessyank · · Score: 4, Informative

      There are supposed to be up to 32 core Zen parts. Eventually.

    4. Re: Waiting To See Some Multi GPU Benchmarks by Anonymous Coward · · Score: 0

      I have to disagree about the need to disable one video card for anything. I've been running crossfire since AMD brought it out and never have I had the need to disable the secondary video card. Yes I have had an occasional issue with a driver where I have to go back one version. AMD video cards has always worked successfully with Windows and Linux based OSs for me and I haven't bought an Nvidia card in 10 years unless it was a customer with a specific need. I finally broke down and purchase an intel skylark cpu because I couldn't wait any longer for ryzen to come out. I have no doubt my next cpu will be back with AMD including laptops. I have 2 laptops with Intel and 2 with AMD based cpus including one with an A10-7300 which runs sweet.

    5. Re: Waiting To See Some Multi GPU Benchmarks by Anonymous Coward · · Score: 0

      Deprecating. Depreciate is what deprecated components oft do.

    6. Re:Waiting To See Some Multi GPU Benchmarks by aliquis · · Score: 1

      At-least for 8 vs 16 threads more games are limited by / core performance rather than the number of cores/threads so no, it won't.

    7. Re:Waiting To See Some Multi GPU Benchmarks by mrchaotica · · Score: 1

      The code name for server Zen is "Naples" and it's supposed to be out in the first half of 2017.

      --

      "[Regarding the 'cloud,'] ownership was what made America different than Russia." -- Woz

    8. Re:Waiting To See Some Multi GPU Benchmarks by zenlessyank · · Score: 1

      And it should be interesting to see how they matchup against the Xeon line. If these 'little' 8 core guys are any indication, Intel may be ordering up a few truckloads of adult diapers for all the pants-shitting that will be going on. I welcome the chaos.

  5. Are they on top of the software? by bill_mcgonigle · · Score: 4, Interesting

    After a while the virtualization code I was working with just stopped being maintained upstream for AMD because the value proposition was just so ludicrously bad vs. Intel and nobody was using them.

    Has AMD, perchance, contributed code to KVM or Xen to get a running start or are we going to be waiting until after Intel's next chip rev. before Zen stands a chance again in this arena (at which point, it's already lost its advantage)?

    --
    My God, it's Full of Source!
    OUTSIDE_IP=$(dig +short my.ip @outsideip.net)
    1. Re:Are they on top of the software? by BronsCon · · Score: 3

      Xen on Zen. 'nuf sed.

      --
      APK quotes people (including myself) without context and should not be trusted. Just thought you should know.
    2. Re: Are they on top of the software? by K.+S.+Kyosuke · · Score: 1

      How many yens will it cost?

      --
      Ezekiel 23:20
    3. Re: Are they on top of the software? by Anonymous Coward · · Score: 0

      At least ten.

    4. Re: Are they on top of the software? by Anonymous Coward · · Score: 1

      But when?

    5. Re:Are they on top of the software? by Anonymous Coward · · Score: 0

      Wait, are there any issues running KVM on AMD processors or are talking about performance optimization?

    6. Re: Are they on top of the software? by Anonymous Coward · · Score: 0

      when chicken fucks a hen

    7. Re:Are they on top of the software? by tender-matser · · Score: 1

      What problems has AMD with virtualization? -- this is not a rhetorical question, I'm using qemu+kvm and amd everyday, but apparently I'm too stupid to figure out how wretched I am. Has it anything to do with that piece of shit android emulator?

    8. Re:Are they on top of the software? by Anonymous Coward · · Score: 0

      AMD has this gargantuan problem where you don't have to pick your CPU carefully and pay a massive premium in order to both run your virtual machines as well as feel like an appropriately 1337 dick.

    9. Re: Are they on top of the software? by Anonymous Coward · · Score: 0

      And has a chick named Ben.

  6. Pronounce RYZEN like Wu Tang Klan's RZA ? by Anonymous Coward · · Score: 0, Interesting

    Everytime i see AMD Ryzen i can't help but view and pronounce it like Wu Tang Klan's famous Rza member.
    Anyone else with me?

    1. Re:Pronounce RYZEN like Wu Tang Klan's RZA ? by zenlessyank · · Score: 1

      No.

    2. Re:Pronounce RYZEN like Wu Tang Klan's RZA ? by Anonymous Coward · · Score: 0

      They couldn't trademark the name zen. They liked the word horizon so they removed the 'ho' and replace the 'zon' with 'zen' so the ry part should be pronounced the way you say horizon. They changed the ri to ry because they didn't want people mistaking its pronounciation with risen.

    3. Re:Pronounce RYZEN like Wu Tang Klan's RZA ? by basecastula+ · · Score: 1

      Same here.

  7. Re:Nope by Kjella · · Score: 5, Interesting

    In general, the reviews are negative. We knew Ryzen would be behind in single-threaded performance, and it is. But it's also behind in multi-threaded performance in a lot of benchmarks for some reason. It beats out Intel's offerings in certain workloads (primarily video encoding), but it gets its ass handed to it in games.

    On FP-heavy workloads it's toe-to-toe with Intel processors costing twice as much. On integer-heavy workloads Intel still has the better technology but on price/performance it's correctly priced between the i7-7700k and Intel's HEDT offering. On memory-heavy workloads the dual channel is no match for Intel's quad channel but the price/performance is still okay as far as I've seen.

    Where it does fall short is single/few-threaded games if you game at low resolution/high frequency but since hardly any gamer would spend $1000 on an 8C Intel processor it's no surprise games don't really take any advantage of the last four cores, even hyper-threading 4C/8T doesn't do much for gaming. But if you move to 1440p the difference is less, at 4K you're GPU limited anyway.

    Basically if you'll only be using it for gaming and have a Sandy Bridge or newer just save your money and use it for a 1080 Ti or Vega. I find the reviews are trying really trying to make games CPU bound when they're mostly not, at least the way I prefer to play them. Maybe the FPS addicts with 144Hz monitors see it differently, I prefer higher quality as long as frame rates are reasonably smooth.

    --
    Live today, because you never know what tomorrow brings
  8. from where i stand by KingBenny · · Score: 1

    all intel has to do is use the headstart money from the i-series whatever all the names were slash the price on i7, make i5 the new celeron even if selling it virtually no profit http://www.tomshardware.com/re... and bob's amd's uncle

    --
    Free speech was meant to be free for all... how can anyone grow up in a nanny state ?
    1. Re:from where i stand by Rockoon · · Score: 2

      Just what Intel needs, even more of its fabs not making any money for them, except this time its on purpose?

      --
      "His name was James Damore."
    2. Re:from where i stand by Anonymous Coward · · Score: 0

      From where I stand, that would be flat out illegal, and I'm sure Intel shareholders would be absolutely thrilled by the company starting to give away their products.

  9. Glad to see AMD having some success by Anonymous Coward · · Score: 2, Interesting

    Certainly good to see AMD come out with a real positive chip for a change. Still early yet, and Ryzen is more a chip for desktops and gamer's. But it's going to go up against Intel pretty well which has to be good for end users.

  10. Re: Nope by Anonymous Coward · · Score: 0

    "The 1800X is basically useless unless you need a lot of cores for specific workloads. The 1700X looks to be a better all around choice, but even the lower price of this model doesn't justify choosing it over a i7 7700K for gamers."

    This may come as a shock, so prepare yourself: Not everyone uses computers solely for gaming!
    It's true! They can be used for all manner of interesting things Other Than Gaming.

    So by God, you go right ahead with your windows box and your Intel i7 7700k. I'm gonna get me one of these basically useless 1800x doodads and it's gonna be glorious...

  11. What's an end-user application to you? by tepples · · Score: 5, Insightful

    Rendering and video encoding is not an end-user application

    Watch for "no true Scotsman" fallacies. How exactly do you define "an end-user application"? One focused on viewing works of authorship made by others rather than creating works?

    1. Re:What's an end-user application to you? by Black+LED · · Score: 1

      Most users do not do rendering or video encoding, but they probably do play video games.

    2. Re:What's an end-user application to you? by Anonymous Coward · · Score: 0

      Many users buying high performance chips (like the 6900K) do rendering and video encoding, in fact.

    3. Re:What's an end-user application to you? by serviscope_minor · · Score: 2

      Most users do not do rendering or video encoding, but they probably do play video games.

      On laptops? No I think most people are not gamers.

      --
      SJW n. One who posts facts.
    4. Re:What's an end-user application to you? by Anonymous Coward · · Score: 0

      Yeah, on phones, tablets and consoles. Joe Random is about ten times more likely to play Pokemon GO than own a PC with a discrete GPU.

    5. Re: What's an end-user application to you? by Anonymous Coward · · Score: 0

      Right. Gamers are the elite group of adult children losers. They play instead of work. They spread thier time wasting it instead of advancing.

      Gamers are as good as they will ever be. Help desk job at 25? Gamers will be there at 40 years old. Never advancing. Never learning anything new. Just playing play like the child. Hehe.

      Thank you gamers for not providing and competition in the real job market. Keep gaming all your selfish life. Hehe

    6. Re:What's an end-user application to you? by Anonymous Coward · · Score: 0

      actually with the advent of streaming everything, and instant replays of entire gaming sessions... most gamers, and they may not be aware of it ARE video encoding the entire time they are playing.

    7. Re:What's an end-user application to you? by Black+LED · · Score: 1

      I don't know how you inferred that I was talking about laptops specifically because I wasn't, but sure. Modern laptops are very capable gaming machines. My own gaming PC is in fact a laptop.

      Even if they are only playing Solitaire or web-based games, they are still gaming.

    8. Re:What's an end-user application to you? by Black+LED · · Score: 1

      If that's the case, then think about how few do things like video encoding or rendering. It would be a fraction of a fraction of users.

    9. Re:What's an end-user application to you? by Black+LED · · Score: 1

      But they might buy a much lower cost Ryzen expecting it to work as well as a 6900K for gaming due to the misleading video encoding and rendering benchmarks.

    10. Re:What's an end-user application to you? by maorb · · Score: 1

      If they are going to use it for gaming and rendering and they looked at the rendering benchmarks, why didn't they also look at the gaming benchmarks, it's not like they're hard to find.

    11. Re:What's an end-user application to you? by serviscope_minor · · Score: 1

      I was singling out PC's rather than mobile platforms. I would be skeptical about the claim that most PC owners use them for gaming.

      --
      SJW n. One who posts facts.
    12. Re:What's an end-user application to you? by Anonymous Coward · · Score: 0

      My point isn't the small numerator but the not-anymore-so-enormous denominator. Few people need multicore performance, but also few people need single core performance. Or PC at all for that matter.

  12. Re:Ayy by Anonymous Coward · · Score: 0, Flamebait

    Too bad Ryzen only supports Windows 10 or I might have bought a few.

  13. AMD Ryzen 7 1800X Linux Benchmarks by tepples · · Score: 5, Informative

    Too bad Ryzen only supports Windows 10

    Source? My sources say GNU/Linux runs on it.

    1. Re:AMD Ryzen 7 1800X Linux Benchmarks by partiallynothing · · Score: 4, Insightful

      The only operating systems I run are Ubuntu Linux and Gentoo Linux and 80% of my gameplay occurs on Ubuntu Linux, as well. Ok, "only Linux" was an exaggeration because for the other 20% of games I care about that don't have Linux ports, I have a small partition for Windows 10, which I use exclusively for those games. But, 98% of the time I'm booted into a Linux OS. Sure, I'm a programmer, so it makes sense that I run Linux, but the OS is more than capable, hugely customizable, and nowadays easy enough for anyone to use. Moreover, today software exists to accomplish almost any required task, and even more, you will likely be able to look and fix any bugs you may encounter, instead of simply relaying a bug to a closed source programming team that will get around to it "when it is high enough priority for them to care". And if you can't dig into the code yourself like I can, the open source community will help resolve your bug immediately. It may not be right for everyone, but calling Linux "a completely worthless desktop OS" is simply wrong.

      --
      Regards, Rob
    2. Re:AMD Ryzen 7 1800X Linux Benchmarks by FalcDot · · Score: 4, Informative

      I believe he refers to the fact that it will not run Windows 7: http://www.pcgamer.com/amd-con...

    3. Re:AMD Ryzen 7 1800X Linux Benchmarks by Anonymous Coward · · Score: 0

      Strange, my mother, retired office worker with no background in CS/IT, uses Ubuntu Linux exclusively since 2009.

      She "inherited" my old computer twice, I do system upgrades between LTS versions for her, the last time I did unscheduled "support call" was when Chrome for Linux stopped supporting i386 systems and auto-upgrade started to show errors.

      Since switch to Linux I actually get less support calls. My mother uses a lot of sport streaming (tennis and snooker), back in Windows days she used to catch a virus from a fake streaming page every month or two.

    4. Re:AMD Ryzen 7 1800X Linux Benchmarks by Anonymous Coward · · Score: 0

      there is no difference in difficulty between changing the desktop resolution on linux or windows. my mother uses linux, she cant change the resolution, but its not like she can do that under windows either... thatd require reading or listening

    5. Re:AMD Ryzen 7 1800X Linux Benchmarks by Anonymous Coward · · Score: 0

      The troll is unimaginative and uninspired. Execution lacks any passion. Elicits at best a "what a dumb ass" remark with little to no anger.

      1 out of 10.

    6. Re:AMD Ryzen 7 1800X Linux Benchmarks by Gr8Apes · · Score: 3, Insightful

      Sure, I'm a programmer

      And therein lies the problem. Linux is a technical OS, for technical people who can solve technical problems.

      And therein lies the problem, people that think Linux is a technical OS only for technical people, and those that perpetuate that vision.

      The real elephant in the room problem are those people that use the latest version of Office whose documents have interoperability issues with pretty much everything else. That takes some minor finagling to fix most of the common errors that put people off (unsupported fonts) and for 99% of regular people that will address everything they need.

      --
      The cesspool just got a check and balance.
    7. Re:AMD Ryzen 7 1800X Linux Benchmarks by Anonymous Coward · · Score: 0

      Either you have to support Windows 7 AND Windows 10, or you migrate to Windows 10. The effect is what Microsoft want, at the cost of customer resentment.

      If these companies weren't such fucking babies maybe they could also, oh I don't know, stop supporting other companies like Microsoft who fuck them over with devious bullshit all the time.

    8. Re:AMD Ryzen 7 1800X Linux Benchmarks by mrchaotica · · Score: 2

      Why the everlasting fuck does a CPU require a driver in order to "support" an operating system anyway?! It's not as if it's not x86, after all. The damn thing should run DOS if I try hard enough!

      --

      "[Regarding the 'cloud,'] ownership was what made America different than Russia." -- Woz

    9. Re:AMD Ryzen 7 1800X Linux Benchmarks by Anonymous Coward · · Score: 0

      I have a counter anecdote to offer. I recently experimented with Debian in a VM, and in just days discovered a usability bug that I would consider a SHOWSTOPPER for an average user, but the open source developers have ignored for years. This is a simple enough issue. Installed Debian with XFCE. Wanted to play around with the audio. Watched some videos in Youtube to verify the sound is working. Found the ALSA Audio Mixer in the XFCE pre-populated utility menus. Clicked Master Mute. Ok, sound is off. Clicked again to restore sound. Sound doesn't come back. WTF. Clicked/reclicked mute on the other 'output' controls I see in ALSA. Doesn't help. Tried rebooting the VM. Nope, sound is still gone. For a non-technical user, they might decide at this point that the system is unusable and resort to reinstalling Debian. If it happens again they might just give up. Of course I'm a technical user so I did some searching (and this means I also had the knowledge to know what search terms to use, that a non-technical user may have no hope of knowing). Turns out this is a known issue. It's been known since 2013. It's an interaction problem between ALSA and Pulseaudio. You can recover from it with a command line fix, or (as I found on my own), you can reconfigure the ALSA Mixer to show all the controls it doesn't by default, and start unmuting -all- of them until the sound comes back.

      Here's the kicker. In the bug tracker where I eventually found the known issue, a developer just noted 'pulseaudio doesn't have a way for us to deal with this', and demoted the bug to WISHLIST. In effect saying 'this is too hard for us to deal with, and the customer can workaround, so meh'. To me that is SHITTY support and -not- better than what closed source software provides in any way. And this is something I run into over and over again in the open source world. "We don't HAVE to make it properly usable because nobody is paying us. We just have to provide -some- hack or workaround that a savvy user (like us) can use to get around the problem." Fix this attitude issue and open source will become much more successful.

    10. Re:AMD Ryzen 7 1800X Linux Benchmarks by Anonymous Coward · · Score: 0

      I'd say you reported it to the wrong place. The ALSA mixer shouldn't be there if you use pulseaudio. And the solution should be for the ALSA mixer to refuse muting when pulseaudio is used.
      But it's not like Windows has no issues. We have a projection system at work that works via HDMI, including sound.
      Yet, every time some plugs it in in their Windows 7 laptops they end up with no sound (neither HDMI nor speakers) and you have to click all over to make it work.
      (and ignoring that if user-friendly is the top-criteria, XFCE probably isn't the right choice, and if it's for a really weak system, pulseaudio absolutely is the wrong choice, and Debian is kind of meant for those who know what stuff to install and not to install - though I admit I have no idea if XUbuntu fares better here)

    11. Re:AMD Ryzen 7 1800X Linux Benchmarks by Anonymous Coward · · Score: 0

      It quite possibly does. The thing is, any class of devices that wasn't supported by BIOS in 1995 won't work without some sort of drivers so you are stuck with a single core, ide disk and a handful of vesa modes.

    12. Re:AMD Ryzen 7 1800X Linux Benchmarks by Anonymous Coward · · Score: 1

      When my mother can use it without me walking her through changing her monitor resolution, it will be on par with windows as far as usability goes.

      And therein lacks the problem in the first place. Linux has better support for detecting the resolution and picking the right one. The fact that you even suspect you would need to change the resolution shows you haven't really been using Linux lately. That's a problem Windows users have.

      Basically all you said was "I can't fix the problem that I have on Windows when I use Linux"... because it doesn't *have* the problem to begin with. Next you'll tell me you don't know how to defrag your Linux filesystem so Linux sucks. (Google that topic if you don't understand the point I'm making there)

    13. Re: AMD Ryzen 7 1800X Linux Benchmarks by Anonymous Coward · · Score: 0

      Someone dreams of working in the help desk? Hehe. Losers.

    14. Re: AMD Ryzen 7 1800X Linux Benchmarks by Anonymous Coward · · Score: 0

      HDMI carries audio. Ill just guess. Sound. Default output device. Built in speakers or hdmi. Hmmmm ok. Fixed. But I did have to click all over to realize how to get the sound to my tv the first time. And vice versa.

    15. Re:AMD Ryzen 7 1800X Linux Benchmarks by tender-matser · · Score: 1

      When my mother can use it without me walking her through changing her monitor resolution,

      I don't use windows and I don't know your mother, but I know dozens of windows users who bitterly complain about not being able to use their 21" or 23" monitors because the fonts are too small, and not a single one of them was able to figure out by themselves (or even google it) how to change that horrible 96dpi default. In windows it's something like 3 clicks away (and they don't need to change the "resolution"; that would be stupid). The same operation on my father's xfce (linux) desktop is probably 4 or 5 clicks away -- do you think THAT makes any difference?

      With the demise or CRTs, usability means a) automatically using the monitor's natural resolution, and b) NOT forcing some 96dpi default just because some moron webdesigners weren't able to design things that scale. Both current windows and linux distros get the first right and fuck up the second (in linux because the xorg guys intentionally crippled the x11 server to make it "windows-compatible")

    16. Re:AMD Ryzen 7 1800X Linux Benchmarks by sjames · · Score: 1

      It doesn't. This is nothing more than the latest from MS's department of dirty tricks. And old OS may not take advantage of new capabilities, but it should run just fine.

    17. Re:AMD Ryzen 7 1800X Linux Benchmarks by laffer1 · · Score: 1

      If you're just talking CPU, power management comes to mind. Consider how the SMT and amd's turbo equivalent work. Power management is another reason.

      Even in open source systems, cpu frequency/power management, scheduling decisions in the kernel and obviously chipset support for new SATA/PCI controllers are all needed.

      AMD hasn't had hyper-threading before so how would windows 7 know that? It would need to schedule processes on real cores when possible to minimize performance loss.

      Then there's SATA controllers and PCIe disks.. hvme. A lot has changed since 2009 when windows 7 came out.

    18. Re:AMD Ryzen 7 1800X Linux Benchmarks by sjames · · Score: 2

      My Mom uses Linux regularly. She is certainly not a programmer or even a "power user". She browses the web and emails. Occasional light word processing. Nothing hard about any of that. My experience as the "computer guy" is that Windows users don't know how to change their screen resolution either, even though it is nearly as simple as doing it in Linux.

    19. Re:AMD Ryzen 7 1800X Linux Benchmarks by Kartu · · Score: 1

      Remember how we got to 64 bit CPUs?
      AMD did AMD64 thing.
      Microsoft said "no way I'd support to 64 bit versions" and Intel went with x86-64.

      Now, x86-64 and AMD64 were nearly the same, but there still were differences in certain commands, of interest only to operating systems.

      Another reason for OS to know exact version of CPU is scheduling tasks effectively. E.g. Ryzen 8 cores are internally 4+4 cores, each 4 with their own L3. Taking that into account can increase performance quite a bit.

      At the end of the day, it's no big deal to add support for new CPUs, surely, but Microsoft has decided to use the opportunity and push Win 10 like that.
      Neither Ryzen nor Kaby Lake CPU get official support from Microsoft.

      But Windows 7 still boots, to my knowledge:
      http://www.pcgamer.com/amd-con...

    20. Re:AMD Ryzen 7 1800X Linux Benchmarks by tepples · · Score: 1

      It was a crap move by Microsoft to sneakily renege on their advertised support schedule for Windows 7. "Yes, sure we support Windows 7 over the agreed lifecycle, but don't dare buy a new PC".

      I at first understood it to mean that Microsoft includes new support for brand new PC hardware during the "mainstream support" phase, which for Windows 7 ended in January 2015 (source). The rest is extended support, which is mostly security updates and updates to the means of delivering security updates. But then I saw that Windows 8.1 is not getting hardware enablement while still in its mainstream support phase.

    21. Re:AMD Ryzen 7 1800X Linux Benchmarks by thegarbz · · Score: 1

      A driver for a CPU... what an interesting and utterly frigging pointless idea.

      Windows 7 will run just fine on Ryzen. I'll bet you a mars bar so will Windows XP.

    22. Re: AMD Ryzen 7 1800X Linux Benchmarks by Anonymous Coward · · Score: 0

      How the fuck can it be simpler? The audio icon is in the task bar to double click, and then one button press to set output device.
      With Realtek chipset, it often prompts you to confirm that the auto detected connections are correct, which I find they are.
      If this is too much for you, don't ever think about linux, their audio stuff is years behind and fucked.

    23. Re: AMD Ryzen 7 1800X Linux Benchmarks by Anonymous Coward · · Score: 0

      No, they didn't reneg. Mainstream Windows 7 Support ended over 2 years ago. They are in security support phase, not new features/development. Those developers have moved on to other things.

      Don't be so obtuse.

  14. This just in... by Anonymous Coward · · Score: 3, Insightful

    Intel releases the 8-core i7-7900K for $499 which blows all the Ryzen 7 1800X away in every performance metric...
    This is not probably too far off, and based on single threaded performance of the i7-7700K which is already 18% faster than the 1800X, an 8-core i7-7900K (if the price was right) would push AMD's best back to being #2...

    However, the good news will be Ryzen will be a strong enough competitor to force chipzilla into a pricing war, and that'll make every buyer happier, no matter which horse you back.

    1. Re:This just in... by Joe_Dragon · · Score: 1, Troll

      still need to up the pci-e lanes. 16 + DMI is to low. and give the Skylake-X cpus 44 in ALL cpus.

    2. Re:This just in... by Anonymous Coward · · Score: 1

      "which blows all the Ryzen 7 1800X away in every performance metric..." - WRONG.

    3. Re:This just in... by Melkman · · Score: 2

      The i7-7700k runs at a turbo frequency of 4.5GHz. Thats 10% faster than the maximum frequency of the X1800. The rest of the performance gain is better IPC. However the i7700K also has a TDP of 91W which is almost the same as the 95W TDP of the X1800. If intel doubles that chip it will melt down unless they scale back the clock speed. And you wind up with something that performs less than the i7-9600 which performs at about the same level as the X1800. So nope, not going to happen any time soon. What I'm wondering is what will happen with the release of the 4 core Ryzen processors. Will the reduced power requirement allow AMD to up the clockspeed to a level where they beat the i7-7700K ?

    4. Re:This just in... by Anonymous Coward · · Score: 1

      AMD's TDP != Intel's TDP

      Or, maybe TDP does, power consumption definitely does not.
      65W 1700 ends up using a bit more power than 91W 7700K.
      95W 1700x/1800x are using power roughly in the same range as 140W 6900K.

    5. Re:This just in... by Anonymous Coward · · Score: 0

      Source? How do you work this out?

    6. Re:This just in... by edxwelch · · Score: 1

      Yeah, but that won't happen til next year... by which time AMD have Zen2

    7. Re:This just in... by Anonymous Coward · · Score: 0

      He lied, or got things backwards. It's AMD CPUs which rarely if ever reaches their rated TDP, while Intel's cited numbers are notoriously... optimistic.

    8. Re:This just in... by ChrisMaple · · Score: 1

      All Intel has to do to accommodate more power is replace their crappy thermal interface material with something better, or use solder like AMD does. Die temperature under heavy load drops from 95 C to 65 C in some cases.

      --
      Contribute to civilization: ari.aynrand.org/donate
    9. Re:This just in... by Anubis+IV · · Score: 1

      You're saying his hypothetical headline for a fake chip is wrong? Really? What next, point out that Huckleberry Finn is a work of fiction?

  15. Horses, held by Anonymous Coward · · Score: 2, Funny

    "AMD multithread optimized games" is right up there with "Year of Linux desktop".

    1. Re:Horses, held by Anonymous Coward · · Score: 0

      Yeah, because nobody is writing for Vulkan, right. /sarcasm

  16. same die? by Anonymous Coward · · Score: 0

    the cores and on-board caches is the same.. so just a hunch, here's just one actual chip being made and it's being binned according to quality off the line? so going cheap will probably not give you a part that will OC to the levels of the more expensive SKUs? going to wait a bit before taking the plunge to see what earlier adopters can do with that $329 part.

  17. Ryzen makes my dick hard by Anonymous Coward · · Score: 0

    Ryzen make it stiff.

    Heat sinks? I make my own thermal paste.

  18. There may only be so much they can optimize by Sycraft-fu · · Score: 2

    Not all tasks can simply be split out in parallel. I mean you can see that with physical tasks, just like computer tasks: Some things just have to be done in sequence, you can't speed them up by doing them at the same time.

    Well with some kinds of games it may well be there's only so much you can spin off to run in parallel and you are still going to have one or two threads that hit the hardest, so they'll be the limiting factor.

    Now that said, it looks like this processor is still plenty fast enough for gaming these days. Most new high end games need a good CPU, but are more GPU bound and it looks like the new AMD processor does fine. You do find some outliers but it is things like Ashes of the Singularity which is not only a notoriously power hungry game, but a bit on an anomaly engine-wise so its performance isn't that relevant to other titles.

    1. Re:There may only be so much they can optimize by Anonymous Coward · · Score: 0

      Some things just have to be done in sequence, you can't speed them up by doing them at the same time.

      Very few things have insurmountably long dependency chains. The main issues are that a) existing software has chosen to use a sequential algorithm and b) a parallel algorithm might have more overhead than you have cores.

      When the typical core count goes way up, both of these things change.

    2. Re:There may only be so much they can optimize by Anonymous Coward · · Score: 0

      Every object in a game can be spooled off in to its own thread in a scheduler(which is essentially a in game kernel) and rejoin the results at the end of the render loop. Games are an embarrassingly parallel application if written using modern techniques.

  19. Re: Ayy by tigersha · · Score: 1

    Same thing I said wh n the 486 came out.

    32 bits!!!! 1mb of ram!!!

    --
    The dangers of excessive individualism are nothing compared to the oppressiveness of excessive collectivism
  20. x86 by DrYak · · Score: 2

    It's a CPU running x86 instruction.
    It basically works.

    The rest is just drivers for the various parts (for the northbridge that's inside the CPU package, or for the chipset on the motherboard).
    And drivers can be provided by the motherboard manufacturer.

    So basically there's no reason why a Ryzen won't run on your Windows 8.1 or 7 (once you loaded the appropriate chipset drivers), nor why it won't run on older versions of Ubuntu (kernel 4.4, predates Ryzen, doesn't have any Ryzen specific code, will output a few oopses in code, but otherwise reported to run).

    --
    "Sufficiently advanced satire is indistinguishable from reality." - [Tips: 1DrYakQDKCQ6y52z6QbnkxHXAocMZJE61o ]
  21. Vulkan and threads by DrYak · · Score: 1

    Regardless of gaming, which really is all about the GPU especially with Vulkan games coming down the pipe, ...

    Vulkan has even another reason: it supports better multithreading, and Ryzen seems to shine under those circumstances.

    (That's also why older, more single-thread-oriented games don't work better)

    --
    "Sufficiently advanced satire is indistinguishable from reality." - [Tips: 1DrYakQDKCQ6y52z6QbnkxHXAocMZJE61o ]
  22. End-user application by DrYak · · Score: 2

    Rendering and video encoding is not an end-user application

    No, indeed. Spending time online on Facebook/Whatsapp/instagram/etc. is the more typically end-user application.
    And that has been already solved for quite some time.
    Including by CPUs that run into your pocket.

    Now please, can we go back to what modern CPUs have to offer ?

    Intel clearly retains the crown for single thread and high-end performance. - And single-thread performance is king for games and end-user applications.

    Was.
    Multithreading is slowly entering other fields.
    Games start to make better use of multiple cores.
    That was one of the main argument for Vulkan : better multithreading support.

    --
    "Sufficiently advanced satire is indistinguishable from reality." - [Tips: 1DrYakQDKCQ6y52z6QbnkxHXAocMZJE61o ]
    1. Re:End-user application by Anonymous Coward · · Score: 0

      They key word and pivotal point when it comes to Vulkan is "support". It won't magically fix the badly optimized code, that's still something the software developer has to do intentionally by investing time and therefore additional money. My projection is that the current generation of CPUs will be outdated anyway when the developers finally catch up with the trend. I mean they've been 'doing it' since for over a decade. Don't expect it to happen over night, just because of Vulkan and the new Doom.

  23. Re:Ayy by l20502 · · Score: 2

    Strange, I just looked at a random x370 motherboard and there were drivers for win7,8,10

  24. Comment removed by account_deleted · · Score: 4, Interesting

    Comment removed based on user account deletion

  25. For the sake of competition by Anonymous Coward · · Score: 0

    I'm going to buy from AMD, probably a motherboard with RAM installed, just to help preserve competition in the processor market. No matter what I get, it's going to be a major upgrade from my current system.
    Even if you ultimately choose an Intel processor, you're going to get a better deal thanks to AMD. Having some competition is obviously the major motivation for Intel to reduce prices on similar products. It's fun to compare the price/performance metrics, but keeping AMD viable is good for everyone.

  26. Re:Nope by supercell · · Score: 1

    I agree. Most games, for serious gamers, that are going to buy the 1800x are GPU bound anyway, not CPU. The 1800x will perform just as well as the Intel high end desktop CPU's at 4k or on multi-monitor setups. This is a clear home run for AMD, considering performance/$ across the board. If you play games at low resolution and that's it, why would you buy a $500 CPU in the first place? The reviews have been overly negative in this light, IMO.

  27. Ryzen a prelude to a juggernaut server CPU ? by supercell · · Score: 1

    Going through the benchmarks, it appears that AMD has really developed an architecture that was built with the datacenter/server/virtualization/HPC world in mind. It crushes Intel 6900k on some of the intensive Floating Point and computational processes that utilize all the cores efficiently. While on the desktop this may not be as crucial, in the server/hpc/virtualization world this huge. The new 'Naples' server chip, if it performs as well as the Ryzen, will be a major competitor to Intel in the HPC, cloud computing and server arena. The virtualization market alone is huge, which demands large numbers of highly efficient cores, which Ryzen has demonstrated it is capable of delivering. Unless AMD stumbles, the server CPU market is about to get a breath of fresh air later this year, with a much better performance/$ product in all likelihood.

  28. Workaround by Anonymous Coward · · Score: 0

    For the single power user, if you install Linux, then use kvm and VGA-Passthrough, the chipset drivers will look like the ones the VM creates and Windows 7 should be fine as long as you don't set "-cpu host".

    Further, I would wager that Red Hat could make some interesting ripples if they can have qemu emulate the new processor options without making Win7 unhappy (like using kvm=off to workaround nVidia's driver shenanigans).

  29. Re:Ayy by thegarbz · · Score: 2

    Don't smoke weed before posting on Slashdot please.

  30. Ryzem Worthy by BrendaEM · · Score: 1

    I have an aging Sandybridge Quad. From the the benchmarks I've ready, the Ryzen will be a slight upgrade for me in gaming.

    Obviously, when I edit and compress video, as I often do when starting a youtube channel: https://www.youtube.com/channel/UCALWDnHfbhcpdPco0cXIeOQ/videos?sort=dd&view=0&shelf_id=0

    ...and raytrace images from Rhino 3D, compress music, it will quite an upgrade.

    I am glad AMD is competitive again because I like competition in the marketplace.

    --
    https://www.youtube.com/c/BrendaEM
  31. English, motherfucker. Do you speak it? by Anonymous Coward · · Score: 0

    If that's what he meant, then it's a real shame he said something so utterly, completely different.

    Dude1: "Too bad I only like the taste of chocolate, and raspberry tastes terrible."

    Dude2: "What's wrong with the taste of raspberry?"

    Dude3: "He was referring to the fact that he doesn't like his new car." WTF?

  32. Public performance crackdowns by tepples · · Score: 1

    actually with the advent of streaming everything, and instant replays of entire gaming sessions

    How long will this remain true once video game publishers crack down on infringement of the publisher's exclusive right to perform a video game or audiovisual work publicly?

    1. Re:Public performance crackdowns by maorb · · Score: 1

      Since publisher's already DID do that (most publishers have a specific set of terms available covering streaming for all their games) and most decided to grant permission to do it... how is that still a problem?

      iirc we still don't know whether it's fair use for non-commercialized streaming, but publishers do describe what you can stream for financial gain and it's usually fairly permissive.

    2. Re:Public performance crackdowns by tepples · · Score: 1

      Since publisher's already DID do that (most publishers have a specific set of terms available covering streaming for all their games) and most decided to grant permission to do it... how is that still a problem?

      Because the grants aren't permanent; the publisher can revoke them at any time for any reason. In addition, the fact that you wrote "most decided" rather than "all decided" is telling.

      publishers do describe what you can stream for financial gain and it's usually fairly permissive

      Until they change the description without notice.

  33. Xfce: Start > Settings > Display by tepples · · Score: 2

    When my mother can use it without me walking her through changing her monitor resolution

    In Xubuntu, it's Start > Settings > Display. But because modern monitors have fixed pixels, you usually want to keep it at the highest supported resolution and change the scaling. That's in Start > Settings > Appearance > Fonts. And in either case, I'd have to do the same amount of "walking her through" under Windows.

  34. Would DEFPOTEC give a better experience? by tepples · · Score: 1

    NOT forcing some 96dpi default just because some moron webdesigners weren't able to design things that scale

    Then what should be the default? A 1080p panel with a (1920^2+1080^2)^.5/96 = 23 inch diagonal visible image size does indeed display 96 dpi. Should a user instead be shown an eye chart when logging in for the first time in order to set the display's virtual density?

    1. Re:Would DEFPOTEC give a better experience? by tender-matser · · Score: 1

      No, because the monitor reports its own size and resolution via EDID. The default should be the real DPI. All OSs support that since 20 years or so.


      $ xrandr | grep VGA
      VGA-0 connected 1920x1080+0+0 (normal left inverted right x axis y axis) 477mm x 268mm
      $ echo '1920 / 477 * 25.4' | bc
      101.6

  35. Hangouts and Skype by tepples · · Score: 1

    think about how few do things like video encoding

    Hangouts, Skype, and other video chat applications encode video in real time during a call. Or do you claim that most use only the text and audio features of those applications?

  36. Multi-monitor and TV use cases by tepples · · Score: 1

    If a window spans two screens that have different DPI values, how should the window system behave?

    If a PC is connected to a physically large monitor, such as an HDTV, the user is likely to be sitting significantly farther away than arm's length. If the virtual DPI is then set equal to the physical DPI, body text drawn under the assumption that the display is at least 72 dpi is unlikely to be readable.

    1. Re:Multi-monitor and TV use cases by tender-matser · · Score: 1

      If a window spans two screens that have different DPI values, how should the window system behave?

      Use the DPI that matches at least one of them? I don't see how using some absurd "middle-ground" (which will make both look ugly) is better than that.

      If a PC is connected to a physically large monitor, such as an HDTV, the user is likely to be sitting significantly farther away than arm's length.

      An application could easily query the monitor's size via xrandr and adapt. A usage case where someone is tiling an image across screens with different sizes and resolutions is not a very common case -- no need to ruin the experience of 99.99% of users just because of that.

  37. Re:Ayy by sixsixtysix · · Score: 1

    they also support the last bristol ridge am4 apus released last year.

    --
    ...
  38. Re: Nope by sexconker · · Score: 1

    Hey, dumbass. I don't have a 7700k. I do have Windows (7), and an old i7-2600k.
    And if you had read my post, you'd realize that I fucking mentioned other workloads. I call out the 7700k and gaming performance specifically because that's the worst situation for Ryzen. I also point out the best situation for Ryzen.