Slashdot Mirror


Intel Launches 9th Generation Core Processors; Core i9-9900K Benchmarked (hothardware.com)

MojoKid writes: Intel lifted the embargo veil today on performance results for its new Core i9-9900K 9th Gen 8-core processor. Intel claims the chip is "the best CPU for gaming" due to its high clock speeds and monolithic 8-core/16-thread design that has beefier cache memory (now 16MB). The chip also has 16-lanes of on-chip PCIe connectivity, official support for dual-channel memory up to DDR4-2666, and a 95 watt TDP. Intel also introduced two other 9th Gen chips today. Intel's Core i7-9700K is also an 8-core processor, but lacks HyperThreading, is clocked slightly lower, and has 4MB of smart cache disabled (12MB total). The Core i5-9600K takes things down to 6 cores / 6 threads, with a higher base clock, but lower boost clock and only 9MB of smart cache. In benchmark testing, the high-end Core i9-9900K's combination of Intel's latest microarchitecture and boost frequencies of up to 5GHz resulted in the best single-threaded performance seen from a desktop processor to date. The chip's 8-cores and 16-threads, larger cache, and higher clocks also resulted in some excellent multi-threaded scores that came close to catching some of Intel's many-core Core X HEDT processors in a few tests. The Core i9-9900K is a very fast processor, but it is also priced as such at $488 in 1KU quantities. That makes it about $185 to $225 pricier than AMD's Ryzen 7 2700X, which is currently selling for about $304 and performs within 3% to 12% of Intel's 8-core chip, depending on workload type.

130 comments

  1. What security? by sinij · · Score: 5, Interesting

    which is currently selling for about $304 and performs within 3% to 12% of Intel's 8-core chip, depending on workload type.

    Is it really going to be any faster after inevitable microcode and OS patching to address gross security flaws?

    1. Re:What security? by Anonymous Coward · · Score: 0

      If you are buying for gaming which this is aimed at you really don't care about the security flaws.

    2. Re: What security? by Anonymous Coward · · Score: 0

      But Windows may shove the patches down your throat anyway.

    3. Re: What security? by Anonymous Coward · · Score: 1

      windows and linux both provide mechanisms to disable the patch for instances where you value performance more than security, there are plenty of circumstances where this is critical on both platforms so this isn't changing anytime soon.

    4. Re:What security? by Tough+Love · · Score: 4, Insightful

      If you are buying for gaming which this is aimed at you really don't care about the security flaws.

      What rubbish. If you are buying for gaming you are online for sure, in a swamp of script kiddies that know your IP and have a vested interest in learning your passwords. If you are gaming online then you are more at risk than the general population. And of course there is the usual swarm of professional hackers. Sometimes I take a moment to watch them hitting my firewall, it's like a cloud of bugs hitting your windshield at sunset. It is that bad, take a look for yourself. I would not advise any gamer to buy an Intel rig as of today for security alone, never mind the value factors.

      --
      When all you have is a hammer, every problem starts to look like a thumb.
    5. Re:What security? by GerryGilmore · · Score: 1

      If by "gross security flaws" you mean the techniques that require that you are already infected by malware in order to function, then - no, probably not. If, OTOH, you maintain clean systems and do not install said microcode and OS patches, then rock and roll!!
      I, for one, think that the whole Meltdown/Spectre nonsense is a hyper over-reaction to a most obscure vulnerability that - again!! - requires that your machine already be infected. The whole JS scripting shit is nonsense also, BTW.

    6. Re:What security? by Anonymous Coward · · Score: 0

      The whole JS scripting shit is nonsense also, BTW.

      It's quite real. Side channels have been demonstrated on real computers within real browsers.

    7. Re:What security? by Anonymous Coward · · Score: 0

      In order for someone to even exploit the flaw, they would already have to have remote access to the system. Meltdown and Spectre only pose a threat on multiuser systems and even then, it's very unlikely that a user exploiting the flaw will glean any useful data.

      So you're wrong. A single-user (or family) gaming PC isn't vulnerable.

    8. Re:What security? by Tough+Love · · Score: 2

      In order for someone to even exploit the flaw, they would already have to have remote access to the system.

      Completely wrong. Please stop spreading dangerous disinformation. Meltdown can be exploited by Javascript, meaning that any website you visit can end up owning any private data you have on your Intel machine. Meltdown is not just a problem for web host operators, but anyone running a browser with Javascript enabled.

      --
      When all you have is a hammer, every problem starts to look like a thumb.
    9. Re:What security? by thegarbz · · Score: 1, Troll

      Oh noes, shared data. Whoop de fucking do. Without knowing what that shared data is you're targeting precisely nothing. Also this has been patched against by all browsers.

      Get a helmet!

    10. Re:What security? by thegarbz · · Score: 2

      If you are buying for gaming you are online for sure, in a swamp of script kiddies that know your IP and have a vested interest in learning your passwords.

      Calm yourself. If a script kiddie is able to get your passwords using Spectre/Meltdown then you have really ballsed up your own security big time. These aren't fly by vulnerabilities that are exploited like a shitty PDF bug or I/E vulnerabilities. Spectre / Meltdown have not left the lab for very good reasons. They are highly targetted attacks that require knowledge and existing access to the machines.

      If you're worried about the NSA getting access to your kiddy porn, patch.
      If you're worried about giving shared access to your VMs in your cloud service, patch.

      If you're worried about script kiddies as a result of not patching, may I recommend a big dose of perspective.

    11. Re:What security? by Tough+Love · · Score: 0

      I hope you don't work in any responsible position.

      --
      When all you have is a hammer, every problem starts to look like a thumb.
    12. Re:What security? by Jamu · · Score: 1

      Which games require lots of cores and high clock speeds. The older games benefit from clock speed, but these are older games that don't need 5GHz. The newer games (should) benefit more from more cores. Why not get something with more cores and a reasonable clock speed? It'll be cheaper, and you can put the excess towards the GPU. Hey, maybe someone will release a game that uses RTX.

      --
      Who ordered that?
    13. Re:What security? by Anonymous Coward · · Score: 0

      How would a script kiddie know my IP? Games are normally client-server, despite some notable exceptions that use some peer-to-peer, such as Diablo III, Starcraft II and World of Warcraft.

    14. Re:What security? by Anonymous Coward · · Score: 0

      Meltdown can be exploited by Javascript

      Nope. Wrong. Incorrect.

      I've seen that "article" linked many times, however nobody seems to be able to point me to the actual JavaScript that magically does this. If it actually works, I'm giving you the opportunity to use it to hack into my computer. I'll wait...

      meaning that any website you visit can end up owning any private data you have on your Intel machine

      Wrong. It is a fact that the attacker needs to have access to the system beforehand and then it takes a long time just to produce a few bytes worth of data that 99.99% of the time won't be anything sensitive like passwords or banking details. You are clueless. Stop spreading FUD.

      Meltdown is not just a problem for web host operators, but anyone running a browser with Javascript enabled.

      You sure repeat yourself a lot. As if you don't actually know what you are talking about, nor have you actually seen these so-called "JavaScript exploits" and you are now trying to convince yourself that what you are saying is true by saying it over and over. You're an American, aren't you?

      Well, once again, you're wrong and you don't know what you are talking about, kid.

    15. Re:What security? by Anonymous Coward · · Score: 0

      What a cop-out response. Especially coming from one with such a demonstrated lack of technical knowledge.

      You may think that your position as a McDonald's assistant manager is a great responsibility, but it's not. Just relax and let us big boys handle all of the real work keeping the world running.

    16. Re:What security? by Anonymous Coward · · Score: 0

      Not a single person has ever demonstrated a live, remote, browser-only exploit of Meltdown or Spectre on a system where they don't already have access.

    17. Re:What security? by Anonymous Coward · · Score: 0

      You may not have noticed, but 1998 is long gone.

    18. Re:What security? by Anonymous Coward · · Score: 0

      Pretty much none of them. The 8700k is not much slower than the 9900k in games, and the 9900k gains most of its additional performance from higher boost clocks and more L3 cache.

    19. Re:What security? by epine · · Score: 1

      Slashdot: where the four stages of grief are buried under a think coat of foamy, wanker creme.

      Despite their reputation, geeks are usually well informed about the world, including worldly matters we learned about at age 19 instead of age 14. Within those parameters, there's also a sub-tribe of geeks who rapidly become unmoored from reality when reality disrupts their innate sense of law and Lego order, who never outgrow the eternal adolescence of plastic bricks.

    20. Re: What security? by Anonymous Coward · · Score: 0

      Turning game mode on, on a ryzen sets it to 4 cores, on average it'll lose about 10%, and that average is mostly propped up by AoS where they run ai in multiple threads, which is so rare that many benchmarking considers AoS to be synthetic .

      If adding 50% more cores gives you 9%, you're well into diminishing returns. Once you reach around 6 cores, there's very few games where larger numbers of slower cores provides a benefit over faster cores. Games are not perfectly parallel. The slowest thread limits performance, increasing the speed of the slowest thread is better than allowing more threads.

    21. Re:What security? by DamnOregonian · · Score: 1

      Hey, maybe someone will release a game that uses RTX.

      Huh? Is there some AMD equivalent of Fox News around here somewhere that prevents you guys from getting access to facts or something?

    22. Re:What security? by thegarbz · · Score: 1

      I do. I work in a position so responsible that I conduct actual risk assessments rather than freaking out about news articles.

    23. Re: What security? by thegarbz · · Score: 1

      Does the position of Intel Shill come with any responsibility?

      Shill? Who is shilling for Intel? We are simply discussing security. Shills exist to promote products in which case let me help you: Buy AMD, the price performance offer is far better in every way.

      Signed: An apparent Intel Shill and happy Ryzen 2700X user.

    24. Re:What security? by Anonymous Coward · · Score: 0

      Guess you're a fan of Battlefield V? Metro Exodus? No? That just leaves Shadow of the Tomb Raider then, and a handful of minor games few people will know.

    25. Re: What security? by Anonymous Coward · · Score: 0

      Not many people care about the diminishing returns on the number of cores. They care about the diminishing returns on the dollars they spend. And spending $200 on cores instead of clock speed - for a new computer - means that they'll get better performance on games in the future. Unless the games developed are somehow optimized for clock speed instead of cores. Which would be bad as new processors will be getting more cores, and not much more clock speed. Although that doesn't rule out Intel pushing clock speed onto developers.

  2. Wow, no hyperthreading? by UnknownSoldier · · Score: 1

    Wow, for a flagship chip, with the i7-9700K lacking HyperThreading Intel must *finally* be starting to be concerned about security. Guess performance isn't everything when you can get p0wned. =P

    1. Re:Wow, no hyperthreading? by Tough+Love · · Score: 4, Informative

      i7 is the new 85. I9 is the new i7. Pretty cynical of Intel. BTW, hyperthreading only speeds up Meltdown, but Meltdown still will get your passwords even without hyperthreading, it just takes a bit longer. This is because of the way cache is shared between processor cores.

      --
      When all you have is a hammer, every problem starts to look like a thumb.
    2. Re:Wow, no hyperthreading? by DamnOregonian · · Score: 1

      Meltdown is as much a risk for the average joe as death by meteorite.
      The side-channel has abysmal transfer rates, can in no way be executed in a way that doesn't impact the performance of the machine, and can be easily mitigated when used in vectors that are going to affect the average person.
      Assuming worst case, where it's allowed to run while someone doesn't notice it, a program's virtual address space is *huge*.
      These attacks are real, but their real-world applicability is highly hypothetical.
      I think you're part of the crowd trying to amplify their impact to sell your particular sports team's processor vendor, and your posting history makes this pretty apparent.

  3. Too soon by Snotnose · · Score: 5, Insightful

    They haven't had time to fix Spectre and Meltdown, I think I'll pass.

    1. Re:Too soon by iggymanz · · Score: 5, Informative

      the list of different things going into the "Spectre" bucket keep growning

    2. Re:Too soon by Tough+Love · · Score: 1

      Right. There are supposedly some mitigations in this Coffee Lake release but I seriously doubt that they are real hardware mitigations, probably just microcode hacks that cost performance. I am highly skeptical that Intel had enough time to develop and qualify the fundamental cache circuitry changes they need to fix Meltdown properly, let alone changing all the masks.

      --
      When all you have is a hammer, every problem starts to look like a thumb.
    3. Re:Too soon by thegarbz · · Score: 1

      They haven't had time to fix Spectre and Meltdown, I think I'll pass.

      Incidentally there are not some 6 different Speculative Execution attacks on processors. According to the test script my brand new AMD is vulnerable to 5 of them. When I got news of this the first thing I did... disable the work arounds in Windows. Screw performance hits. My enemies are the script kiddies, and trojan makers of the internet, not the NSA or other well funded organisations that actually *may* have the capability to do something *useful* with these exploits.

    4. Re:Too soon by Anonymous Coward · · Score: 0

      Better start looking REALLY FUCKING HARD at your GPU because we've got very similar attacks that work on those, too, and don't require root access.

      And yet you're worried about the much slower CPU being the attack vector. LMFAO.

      We've got the next APK here, folks.

    5. Re:Too soon by Anonymous Coward · · Score: 0

      Meltdown is the issue, because that's the one who's patches hit performance the hardest. It's often lumped together with the less-serious but more-complicated Spectre as a result of Intel's marketing efforts to dilute the attention on its Meltdown disaster.

      Meltdown is a fairly trivial exploit to an Intel-patented technique to slightly speed up speculative execution by disabling memory protection on the speculative branch that's less likely to be executed according to heuristics. All you need to do is rig the heuristically unlikely condition to be the one that is satisfied and your process can read the gigabyte or so of shared kernel memory that gets mapped into application space whenever you want.

      Intel had an awkward situation in that the offending aspect of memory protection is hardwired rather than part of updatable firmware, so they can't just fix it. Instead the best solution anyone could come up with was to work around the problem by moving anything sensitive out of the kernel's shared (but privileged) address space and into its dedicated address space, which slows everything down quite a lot because the system is now forced to wait for a bunch of context switches that used to be unnecessary.

      Sorry if I'm explaining something you already know, but the reason I'm replying to you is to say that they have had plenty of time to fix Meltdown. Whether they actually fixed it is another story, but they've certainly had enough time. The proper fix was very simple - there was just no way to apply the fix to existing product lines. Since this is a new generation it's entirely possible that Intel made it immune to Meltdown out of the box and therefore not need the performance-killing OS patches.

    6. Re:Too soon by Anonymous Coward · · Score: 0

      I r8 0/8. Not the gr8est b8, m8

    7. Re: Too soon by Anonymous Coward · · Score: 0

      They have hardware mitigations against some of them. No x86 cpu has full hardware mitigation against all of them, even AMD.

    8. Re: Too soon by Anonymous Coward · · Score: 0

      They are real hardware fixes.

    9. Re: Too soon by Tough+Love · · Score: 1

      Tweaks, maybe. They just did not have time to do anything major. I just don't have a whole lot of confidence they closed up Meltdown definitively. Intel will need at least a few more months to do the job properly and copy AMD in time for the Cannon Lake ramp.

      --
      When all you have is a hammer, every problem starts to look like a thumb.
    10. Re:Too soon by Anonymous Coward · · Score: 0

      Current GPUs are vulnerable to Rowhammer.

      In 2015 a Linux rootkit exploited GPUs.

      You're a fucking moron, forever.

  4. PCIe by darkain · · Score: 4, Interesting

    "The chip also has 16-lanes of on-chip PCIe connectivity" - this actually sounds EXTREMELY low. And here I am, on a CPU with 40 lanes, and a chipset that provides another 5... in a system that is several years old. This sounds like a massive downgrade. Though, most people I guess only populate 1 slot for the GPU nowadays, and nothing else. Consumer 10gbe isn't quite there yet. Add-on sound cards have gone to the wayside (onboard audio is still shit quality in comparison, but since people only listen to low bit rate streaming MP3s anyways, I guess it doesnt matter!?) The only thing I question is the NVMe craze right now, and how this chip will be able to keep up with that, since most recent ones are usually PCIe (though some are DIMM socket now as well)

    1. Re:PCIe by Anonymous Coward · · Score: 0, Interesting

      This is standard for Intel CPUs.

      16 PCIe lanes on-chip is standard for Intel and any other PCIe lanes are multiplexed off the 4x DMI Interface.

    2. Re:PCIe by pjrc · · Score: 1

      Any chip that's old by "several years" would have at best pcie2, at roughly half the bandwidth per lane of pcie3.

      Your 40 pcie2 lanes could still be considered better than only 16 pcie3 lanes, but really not by very much, certainly not enough to call the I/O capability of these newer chips "EXTREMELY low".

    3. Re: PCIe by Anonymous Coward · · Score: 0

      Ok, but isn't 16 lanes still anemic with today's I/O? Personally, I think Intel is segmenting the market here (like ECC) to force I/O power users into multi socketed Xeon platforms

    4. Re:PCIe by WaffleMonster · · Score: 1

      This is standard for Intel CPUs.

      16 PCIe lanes on-chip is standard for Intel and any other PCIe lanes are multiplexed off the 4x DMI Interface.

      AMD no doubt fully supports this standard for "Intel" CPUs.

    5. Re:PCIe by WaffleMonster · · Score: 4, Informative

      Any chip that's old by "several years" would have at best pcie2, at roughly half the bandwidth per lane of pcie3.

      Nonsense, CPUs with 16x 3.0 lanes were available more than 5 years ago.

      https://ark.intel.com/products...

      There is no excuse for 16 lanes in 2018.

    6. Re:PCIe by _merlin · · Score: 1

      My 2014 Xeon has a lot more lanes than that, and they're PCIe 3rd-generation. The chipset splits some up into PCIe 2nd-generation slots though. I currently have two Quadros in 16x 3rd-gen slots, a 2x40Gbps Ethernet NIC in an 8x 3rd-gen slot, and a SAS controller in a 4x 2nd-gen slot. The SAS controller could use an 8x 3rd-gen slot but I don't have one spare.

    7. Re:PCIe by David_Hart · · Score: 1

      "The chip also has 16-lanes of on-chip PCIe connectivity" - this actually sounds EXTREMELY low. And here I am, on a CPU with 40 lanes, and a chipset that provides another 5... in a system that is several years old. This sounds like a massive downgrade. Though, most people I guess only populate 1 slot for the GPU nowadays, and nothing else. Consumer 10gbe isn't quite there yet. Add-on sound cards have gone to the wayside (onboard audio is still shit quality in comparison, but since people only listen to low bit rate streaming MP3s anyways, I guess it doesnt matter!?) The only thing I question is the NVMe craze right now, and how this chip will be able to keep up with that, since most recent ones are usually PCIe (though some are DIMM socket now as well)

      Actually, as I understand it, the i9 has 40 platform PCIe lanes (16 CPU + 24 PCH). 16 lanes are dedicated to devices needing fast access to the CPU like 16x/8x graphics card slots. 24 chipset lanes handle other connectivity, like M.2 slot, network interface, SATA, and other PCIe slots, etc.. How the lanes are allocated are based on the motherboard design.

      The Nvidia 2080 is the first graphics card that can max out 8x PCIe 3.0 lanes, and just barely. There is only a 1% to 2% improvement when running with 16x PCIe 3.0 lanes. Of course, your graphics card slot should only be running at 8x if you are using SLI or if you have another fast card in the second 16x PCIe slot, otherwise it should be at 16x.

      I'm not defending Intel in the decision to stick with 16x dedicated CPU lanes. More would definitely be better and would give breathing room for even more powerful graphics cards in the future. All I'm saying is that the reality is that most of us won't max it out, even in a higher end gaming system.

      As for 10Gbps Ethernet, you need M.2 drives or a RAID array to get even close to 10Gbps speeds when transferring data. I recently implemented a 10Gbps lab where they were transferring 500GB datasets. Standard SATA III IDE drives were capping out at about 1.5Gbps, SATA III SSD at 3 Gbps, and a RAM drive at 6 Gbps. The RAM drive was to simulate what a NVME M.2 drive performance would be like. Fast storage was required on both sides of the connection. 10Gbps would be nice to have but you're not going to get much benefit out of it in a home or home/office environment without designing for it.

    8. Re:PCIe by darkain · · Score: 2

      My several year old system is indeed 40x PCIe3 straight from the CPU, with the additional 5x lanes from the north bridge being PCIe2. Nice assumption though!

    9. Re:PCIe by darkain · · Score: 2

      For reference, 10gbe is ~1GB/sec. That is sustainable on burst reading on a 8x SATA drive array. I'm currently running over 20 drives in a home server with 10gbe link back to the networking core, and my desktop with a 10gbe link to that core as well. It is trivially easy to saturate a 10gbe link nowadays.

    10. Re:PCIe by thegarbz · · Score: 1

      Any chip that's old by "several years" would have at best pcie2, at roughly half the bandwidth per lane of pcie3.

      PCIe 3.0 is over 8 years old. Dual GPU systems would consume all 16 lanes available which is precisely why AMD has upped the lanes to 20 for even their lower entry Ryzen chips. Gotta leave enough for storage.

    11. Re:PCIe by thegarbz · · Score: 1

      24 chipset lanes handle other connectivity, like M.2 slot

      And that along with Spectre/Meltdown is why you shouldn't go Intel for systems which require fast storage I/O. You'll note that Ryzens also only dedicate 16 PCIe lanes to graphics, but have an additional 4 dedicated to NVMe.

    12. Re:PCIe by Anonymous Coward · · Score: 0

      "Any chip that's old by "several years" would have at best pcie2"

      WRRRRRRRROOOOOOOONNNNNNNNNNG.

      Oh, and once that 16X is taken by the GPU, what am I to do with my USB 3.0 expansion card, 2 NVMe drives, and 1x PCI-E sound card? I need at LEAST another 12 lanes, and the shit coming off the DMI ain't going to cut it.

      16 lanes is pure and simple gimped. Expansion lanes from the chipset side is nonsense because you've still got to address the CPU (which means a performance hit.)

      And this is why I go AMD. I can actually USE all of my peripherals, at a lower cost, with very similar performance.

    13. Re:PCIe by samwichse · · Score: 1

      The Ryzen 2700X has 20 lanes. 1x16 and 1x4.

      My Epyc system has 64 lanes per processor and dual processors (although I understand the single processor systems get 128 lanes because they don't use 64 of them them for inter processor communications.

    14. Re:PCIe by Anonymous Coward · · Score: 0

      The shit coming out of the DMI cuts it. Plus your peripherals under there might DMA stuff between them !?!

      Do you know AMD exactly is the same, but with four more lanes on the CPU? and these lanes aren't doubled to support two M.2 4x drives. So it's still weak for two NVMe drives.

    15. Re:PCIe by Anonymous Coward · · Score: 0

      Skylake doubled the DMI link between CPU and chipset to PCIe 4x 3.0 instead of PCIe 4x 2.0 on Haswell. A small but important distinction.
      If the DMI link on next-gen is based on PCIe 4.0 that'll be another better round of good enough.

    16. Re:PCIe by drinkypoo · · Score: 1

      Though, most people I guess only populate 1 slot for the GPU nowadays, and nothing else.

      16 lanes for GPU. If you have a second GPU, which some do, that's 32 lanes already. NVMe storage is 4 lanes, and the GbE gets at least 1 lane and possibly 4 lanes. 16 lanes is a bad joke.

      --
      "You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
    17. Re:PCIe by David_Hart · · Score: 1

      Though, most people I guess only populate 1 slot for the GPU nowadays, and nothing else.

      16 lanes for GPU. If you have a second GPU, which some do, that's 32 lanes already. NVMe storage is 4 lanes, and the GbE gets at least 1 lane and possibly 4 lanes. 16 lanes is a bad joke.

      No, that's not how it works. If you put the two GPUs in the two 16x slots they both downgrade to 8x and 8x. Only the newly released 2080 can saturate an 8x PCIe 3.0 slot. Tests show that a 2080 will perform 1% to 2% faster with a PCIe 3.0 slot at 16x vs 8x. So, while having 32x lanes would give you a bit of graphics boost, it's not that much. NVMe usually gets it's lanes from the 24x PCH lanes. But it depends on the motherboard design.

    18. Re:PCIe by David_Hart · · Score: 1

      For reference, 10gbe is ~1GB/sec. That is sustainable on burst reading on a 8x SATA drive array. I'm currently running over 20 drives in a home server with 10gbe link back to the networking core, and my desktop with a 10gbe link to that core as well. It is trivially easy to saturate a 10gbe link nowadays.

      If you have a RAID array and the device(s) on the other side have fast storage to handle it, then yes, you can saturate a 10gbe link. But again, you have the necessary components to make use of it. Most people who talk about wanting 10Gbps on a consumer motherboard have no idea.

      Also, would you really rely on a 10Gbps chipset built-in to the motherboard vs a dedicated PCIe card that can handle the network offloading? Most consumer motherboards use the CPU for network processing. Server motherboards are a different class all together...

    19. Re: PCIe by Anonymous Coward · · Score: 0

      You don't get 12 extra lanes with AMD unless you go threadripper. You only get an extra 4 for 1 nvme drive. Everything else is shared down a x4 link to the chipset, just like intel. Except intel give you pcie3 at the chipset, amd gives you pcie2 at the chipset. That 2nd nvme drive will never give you full speed on amd, even if there's no congestion.

  5. Thank god for AMD by Ecuador · · Score: 1

    Thank god for AMD. Intel faces stiff competition once again and still charges 50% more for a 10% faster CPU. Remember the days before good competition? The P66 was introduced at $1000 in 1k quantities back in '94, which is about $1800 now. I mean even the terrible P4s were being sold at a premium (ok using dubious means, but still).

    --
    Violence is the last refuge of the incompetent. Polar Scope Align for iOS
    1. Re:Thank god for AMD by Tough+Love · · Score: 2

      Actually, i9-9900K is 90% more expensive than Ryzen 2700X. And Intel had to fiddle the gaming benchmarks to make it look faster than it really is. These are on Intel's 14nm process, they were hoping to be on 10nm by now but that isn't happening until some time next year. Meanwhile Ryzen 2 on 7nm will be out while Coffee Lake is still shipping, oops. Ryzen 2 will probably probably put AMD even in IPC and ahead in GHz. Intel's last remaining bragging points gone. And Intel isn't going to catch up any time soon, by the time they finally have 10nm online TSMC will already be sampling its next gen EUV process.

      This is easy: go Ryzen and put that 90% Intel markup in your pocket, ready to spend on 7nm Ryzen 2 next year.

      --
      When all you have is a hammer, every problem starts to look like a thumb.
    2. Re:Thank god for AMD by PixetaledPikachu · · Score: 1

      Actually, i9-9900K is 90% more expensive than Ryzen 2700X. And Intel had to fiddle the gaming benchmarks to make it look faster than it really is. These are on Intel's 14nm process, they were hoping to be on 10nm by now but that isn't happening until some time next year. Meanwhile Ryzen 2 on 7nm will be out while Coffee Lake is still shipping, oops. .

      Ryzen 2 (2xxx) series is based on 12nm process, which are already in the market. You are referring to Zen 2 architecture (Probably will be released as Ryzen 3 series)

    3. Re:Thank god for AMD by Tough+Love · · Score: 1

      Zen+ is Ryzen 2000 series, Zen 2 will be Ryzen 3000. It's a bit confusing. Ryzen+ means Zen+ mainstream desktop. I think AMD intended Ryzen 2 to mean Zen 2, not Zen+, but there's so much confusion about that now that it's better to stick to the thousands terminology.

      --
      When all you have is a hammer, every problem starts to look like a thumb.
    4. Re:Thank god for AMD by DamnOregonian · · Score: 1
      Intel Core i9-9900K 9th Gen CPU Review: Fastest Gaming Processor Ever

      Then again, if money is no object and you have the need for speed, Core i9-9900K is the CPU to buy.

      Also, out of curiosity, from where are you getting this 90% more expensive from?
      The 9900K has an MSRP of $488, the 2700X has an MSRP of $329.
      Now, I'm no mathematician, but $488 != $625.

    5. Re:Thank god for AMD by PixetaledPikachu · · Score: 1

      Zen+ is Ryzen 2000 series, Zen 2 will be Ryzen 3000. It's a bit confusing. Ryzen+ means Zen+ mainstream desktop. I think AMD intended Ryzen 2 to mean Zen 2, not Zen+, but there's so much confusion about that now that it's better to stick to the thousands terminology.

      Yes, perhaps you should do that, I already did (2xxx). What is clear is that the 7nm process is named Zen 2, while the product using the architecture is yet to be named

    6. Re:Thank god for AMD by Tough+Love · · Score: 1

      Yes, perhaps you should do that, I already did (2xxx).

      I'm just going to have to go ahead and point out that your retort qualifies as kind of snippy, considering that you actually said "Ryzen 2 (2xxx)" which is wrong, or at best adds to the confusion.

      --
      When all you have is a hammer, every problem starts to look like a thumb.
    7. Re:Thank god for AMD by PixetaledPikachu · · Score: 1

      Yes, perhaps you should do that, I already did (2xxx).

      I'm just going to have to go ahead and point out that your retort qualifies as kind of snippy, considering that you actually said "Ryzen 2 (2xxx)" which is wrong, or at best adds to the confusion.

      Well, I do kind of already using the thousand terminology that you have pointed out above and AMD website refers to the series as 2nd Generation Ryzen Processors, while many publications have dubbed them as either Ryzen 2nd Gen, Ryzen+, or Ryzen 2. Asking me to use the thousand terminology without addressing your own use of "Ryzen 2 on 7nm" is well.. not fair. What exist today is Zen 2 architecture on 7nm, and whatever product that uses it is not yet named

    8. Re:Thank god for AMD by Anonymous Coward · · Score: 0

      Where can I buy 9900K for $488? There's one in newegg (https://www.newegg.com/Product/Product.aspx?Item=N82E16819117957), it's $580, but out of stock. There's also one in amazon for the same price.

      Meanwhile you can buy 2700X for just $305 (https://www.newegg.com/Product/Product.aspx?Item=N82E16819113499).

    9. Re:Thank god for AMD by Tough+Love · · Score: 1

      What exist today is Zen 2 architecture on 7nm, and whatever product that uses it is not yet named

      Pretty safe bet they will call it Ryzen 3, a change from their original plan which was on the dumb side. Confusion is not helpful. BTW there already is a 5nm Zen 3 on the roadmap, I bet that gets the damnatio memoriae treatment too, they will reimagine it as Ryzen 5 (skipping Ryzen 4 as originally planned because 4 rhymes with "dead" in Chinese)

      --
      When all you have is a hammer, every problem starts to look like a thumb.
    10. Re:Thank god for AMD by Tough+Love · · Score: 1

      Oh, and another source of confusion: what is a Ryzen 3? Is that zen-3-formerly-known-as-zen-2 or is it the cheap budget PC bin?

      --
      When all you have is a hammer, every problem starts to look like a thumb.
    11. Re:Thank god for AMD by Tough+Love · · Score: 1

      Of course, I meant to write "they will reimagine it as Zen 5 skipping Zen 4", there's that confusion at work. To make that seem somewhat legit, they can go with "5nm means Zen 5, right?" Then just grin and go with Zen 6 for the 3nm generation.

      --
      When all you have is a hammer, every problem starts to look like a thumb.
    12. Re:Thank god for AMD by PixetaledPikachu · · Score: 1

      Oh, and another source of confusion: what is a Ryzen 3? Is that zen-3-formerly-known-as-zen-2 or is it the cheap budget PC bin?

      I think that is actually why they formally use the over complicated "2nd Generation Ryzen" instead of Ryzen 2 or Ryzen+. Intel do this as well. To make things worse the first gen mobile and APU parts were based on the 14nm Zen instead of 12nm Zen+ and name 2xxxH and 2xxxG respectively

      Of course, I meant to write "they will reimagine it as Zen 5 skipping Zen 4", there's that confusion at work. To make that seem somewhat legit, they can go with "5nm means Zen 5, right?" Then just grin and go with Zen 6 for the 3nm generation.

      Or introduce yet another code name.

    13. Re:Thank god for AMD by Tough+Love · · Score: 1

      the first gen mobile and APU parts were based on the 14nm Zen instead of 12nm Zen+

      The 12nm node name surely counts as one of the most egregious terminology abuses in the process wars so far. It uses all the same dimensions as 14nm but tweaks some details for better clocks and power efficiency. It really really should be called 14nm+, but maybe they just felt a compelling need to distinguish it from Intel's unrelated 14nm. And 12nm is better than 14nm, right? And 12nm must be better than 14nm+, so that settles that. What we need to be clear on is, nm no longer means "nanometer", it means "node marketing"

      --
      When all you have is a hammer, every problem starts to look like a thumb.
    14. Re:Thank god for AMD by DamnOregonian · · Score: 1

      Pre-orders started at $488 (or so sites that track such things claim)
      Prices then flew up once limited supply was apparent. Such is the way of things. You're definitely right that you can't get one for MSRP right now, but you will be able to eventually.

  6. Hey Intel 16 lanes is NOT enough by Anonymous Coward · · Score: 2, Insightful

    Currently I have:

    1 x 16 lane graphics card
    1 x 4 lane USB3 controller (four independent USB controllers)
    1 x 1 lane USB3 controller

    As a result GPU currently only able to use 8 of 16 lanes on my circa 2013 i7. Here it is 5+ years later and NOTHING has changed.

    No way will I be spending money on a new CPU with only 16 lanes.
    No way will I be spending money on a new CPU without ECC memory.
    No way will I be spending money on a new CPU without security bugs fixed.
    No way will I be spending money on a new CPU that does not officially support my operating system.

    1. Re:Hey Intel 16 lanes is NOT enough by Anonymous Coward · · Score: 0

      Please learn about the fact that Ivy Bridge series processors from Intel, such as the i7 3770, had PCIe3 in Q2 of 2012.
      Learn also that not all desktop CPUs are created by Intel. Their competition is offering more than 16 direct PCIe lanes on Desktop CPUs *right now*.
      Learn also that some people have different use cases than you or I do. We don't know that the GP doesn't need ECC for their workload or wouldn't find benefit in a Quadro series graphics card.

    2. Re:Hey Intel 16 lanes is NOT enough by Anonymous Coward · · Score: 2, Informative

      Please learn about the difference between PCIe3 and PCIe2

      I have a 1080ti GPU that runs PCIe 3.0 @ 8x rather than 3.0 @ 16x due to the additional PCIe cards. Remove the cards and it runs 16x.

      and the fact your motherboard chipset will give you more PCIe lanes.

      Sure you could add a manifold to a 1" water pipe and get 4 1" pipes. It doesn't allow you to move 4x the water.

      All desktop CPUs have had 16 lanes direct to the CPU since your generation CPU.

      All desktop *Intel* CPUs that is. AMD processors have no such limit.

      And you don't need ECC memory.

      There is no basis to for you to conclude anything about me or my needs. You don't even know who I am. I demand ECC memory. My next system WILL have ECC no matter what.

      Had to rerun jobs that spin all cores for months at a time due to subtle errors from bad ram not to mention wasting days of my time troubleshooting what turned out to be a hardware problem. Of course memtest never finds a problem even after 24hrs. I refuse to waste my time with this BS ever again.

      Are you also going to fork over money for a Quadro graphics card with an ECC framebuffer?

      No. I only use GPU for VR / goofing off playing video games. Don't much care if it glitches.

    3. Re:Hey Intel 16 lanes is NOT enough by Anonymous Coward · · Score: 0

      I'm curious, has anyone benchmarked how not having direct pcie lanes to the cpu is affecting performance?

      I could see a base gaming system ideally needing 16 for the graphics card and at least another 4 for everything else for no contention. If this is being used for some kind of number crunching, then wanting full bandwidth may matter.

      I'm guessing dual video cards don't necessarily need double the pcie channels to the cpu, since it probably makes more sense to talk to each other directly for a lot of stuff. They might need more to be optimum though.

      Does anyone have actual numbers?

    4. Re:Hey Intel 16 lanes is NOT enough by Anonymous Coward · · Score: 0

      You have demanding needs and you're rich enough to pay for VR, so get ECC if you need ECC. Intel has been selling Xeon versions of i7 for a decade and you know what they're priced the same or nearly the same (Xeon E3, now Xeon E-2100, don't know how the Xeon version of i9-9900, i7-9700 will be called).
      You will still get graphics card @8x instead of @16x, unless your cards go on 1x slots. On AMD, your graphics card will also run at 8x for the same reason (unless maybe it's a lower end chipset and secondary PCIe 16x@4x slot is connected to the chipset not the CPU). It is what it is but that's much faster than a graphics card used on an iMac Pro.

    5. Re: Hey Intel 16 lanes is NOT enough by Anonymous Coward · · Score: 0

      Google worked on a study involving DRAM errors. Long story short, with an increase in densities along with tighter timings, the error rate has been going up.

      ECC should be mandatory for all consumer devices. That is, if you value system stability and the integrity of the results of your data (meaning you don't want corruption).

      https://storage.googleapis.com/pub-tools-public-publication-data/pdf/35162.pdf

    6. Re:Hey Intel 16 lanes is NOT enough by DamnOregonian · · Score: 1

      Weird. My GPU is using all 16 lanes of my CPU PCIe bus.
      Everything else is on my chipset.

      Wait, yours are too. Sucks being stupid, doesn't it?

    7. Re: Hey Intel 16 lanes is NOT enough by Anonymous Coward · · Score: 0

      Amd has a 20 lane limit, only 1 nvme drive more than intel. Sounds like you're running into motherboard design issues.

  7. Beastly Xeon W-3175X by Tough+Love · · Score: 3, Interesting

    Beastly 28 core Xeon W-3175X, obviously targeted at AMD's 32 core Threadripper 2990WX, which you can buy right now on Amazon for $1,720. I'd like to know Intel's price, I guess it's not remotely close.

    Note that with these top heavy core counts you always get lower clock frequency because of bus contention. Not a stopper by any means, if you have the use case. But personally I'm a lot more interested in the higher clocked 16 core AMD parts, specifically the 2950X, $900. Slightly higher cost per core but clocked about 10% higher. Boost frequency 4.4 GHz, the technical term for that is awesome.

    --
    When all you have is a hammer, every problem starts to look like a thumb.
    1. Re:Beastly Xeon W-3175X by Anonymous Coward · · Score: 0

      You get lower clock frequencies because of power budget. It would be all too easy to reach and exceed 500 watts with an 28 or 32 core or less cores than that. Overclock some and you've got a full kilowatt.

    2. Re:Beastly Xeon W-3175X by Anonymous Coward · · Score: 0

      PS : you're very right to say it's because of the bus, too. The bus gets awesomely power hungry. Anandtech I think has measurement graphs on bus and cores power use and does an Intel vs AMD kind off.
      AMD has this "Russian dolls" bus as comms are inside a CCX, between CCXes, between dies, between two sockets. It is awesome they got this working. Their cores really are more power efficient than Intels. What actually happens is on 32 core Epyc, more power is spent on the bus than on cores!
      Also, 32 core Threadripper 2 saves power over the Epyc due to the disabled memory controllers and PCIe controllers on two of the four dies. Quite a lot of power, which goes to higher clock speeds. There's this benefit, not just going into desktop motherboards. It gets shitty performance on Windows most of the times due to the lacking NUMA support from the OS so the W2990X turns out to be a shitty choice for a Windows workstation (unless a future Windows upgrade fixes this), 2950X better.

  8. What a ridiculous comparison by Anonymous Coward · · Score: 4, Informative

    That's $304 per SINGLE AMD processor, $488 per if you buy a thousand units of the Intel. Unless you're building a thousand computers this makes no sense to compare, and even then, the cost of the AMD processor goes down at those volumes too. This reveals a stupid level of bias in this article.

    1. Re:What a ridiculous comparison by Anonymous Coward · · Score: 0

      Not only that these motherboards and chips are basically an *oh crap, we fell behind* and are basically chips meant for xeon systems... so the motherboards aren't going to be cheap either.

    2. Re:What a ridiculous comparison by Tough+Love · · Score: 1

      these motherboards and chips are basically an *oh crap, we fell behind*

      I would say so... i9-9900K is currently "out of stock" on Amazon. Invites the question, is Intel really producing these in volume or is this just a delay tactic hoping some folks will drop their 2700x plans? I'm thinking, Intel had to dust off their 14nm fabs to produce these, do they really have the capacity? If they don't, we're going to be seeing a whole lot of "out of stock" and asking prices will probably spike above MSRP like they did for first gen Epyc. A little voice whispers to me, they don't.

      Anyway, you can build a 12 core Threadripper box for about the same bottom line as the i9-9900K and that's clearly superior in core count, PCI lanes and memory channels. Not sure Intel really has a point here.

      --
      When all you have is a hammer, every problem starts to look like a thumb.
    3. Re:What a ridiculous comparison by Tough+Love · · Score: 1

      Right, i9-9900K currently available (maybe) from ebay scalpers for $650 - $1100.

      --
      When all you have is a hammer, every problem starts to look like a thumb.
    4. Re:What a ridiculous comparison by Anonymous Coward · · Score: 0

      Nope you're talking shit

    5. Re:What a ridiculous comparison by Anonymous Coward · · Score: 0

      Intel has a general shortage hitting all Coffee Lake, I've had a check and seeing the lowly i5 8400 out of stock, completely outrageous prices for i7-8700K and 8700, i5-8600K, even Pentium out of stock.

      Two reasons I can have in mind (thanks to attention paid on nerdy sites and me remembering this pointless stuff...)
      - They have lost an entire 10nm generation. This is one of the big Intel fiascos, though they rode through it very well till now.
      - Priority is on server and laptop CPU production. Huge demand, shortages of parts unacceptable, utter domination of Intel on these markets (AMD Epyc will take a share but is barely out of "first-gen hardware v1.0" phase). If they fail to deliver here I think we might see articles on how Intel shortages are a drag on the world economy.

      The plan for 10nm was lowest power laptops first, servers second, desktops third. Now there's nothing at all until second gen 10nm, they're stuck with an unusable first gen 10nm production line.

    6. Re:What a ridiculous comparison by Tough+Love · · Score: 1

      Judging from the elongated production schedule and complete nonavailability of Cannon Lake, Intel must have bulldozed the first gen 10nm production line. Then they had to deal with the question of expanding 14nm production to fill the gap. That one must have been really tough, they needed to add the absolute minimum capacity at that already obsolete node. So Coffee Lake shortages would be because of trying to build less capacity, and also competing for resources with their own Kaby Lake and maybe even Skylake production.

      --
      When all you have is a hammer, every problem starts to look like a thumb.
  9. I'd buy a one, but... by edibobb · · Score: 0

    I'd buy one, but it won't run Windows 7.

    1. Re:I'd buy a one, but... by Anonymous Coward · · Score: 0

      Well, yes. It won't run your 'retard spec' computer.

    2. Re:I'd buy a one, but... by Anonymous Coward · · Score: 0

      Windows 7 was the high water mark for M$ OSs. It's all downhill from here.

    3. Re:I'd buy a one, but... by Anonymous Coward · · Score: 0

      You'd be right if you had said Windows 2000. But I guess you weren't borne then. It's been one massive failure after another ever since, getting worse and worse over time.

      It started relatively gently with the ugly and unprofessional Fisher-Price interface in XP, then we got the Vista piece of shit with it's brilliant interface which actually led you in circles, followed by the ribbon disaster, etc, etc. And for every generation the cancer goes deeper, until the latest instance where they actually had to pull the Windows 10 update since it could delete your files.

      It's like everyone who actually knew what they were doing have been fired or quit.

  10. Honestly they mostly just hit the firewall by rsilvergun · · Score: 2

    and don't get any further. To make good use of the micro code bugs you usually need root/admin. And if somebody's got that you're already boned.

    Spectre/Meltdown are a problem because they enable a bunch of exploits that let you get out of a hypervisor and into the host OS. If you're in a data center that's a huge deal. If you're a gamer it's, well, not.

    You'll notice that there's been no gaming apocalypse. No massive class action lawsuits because of lost performance. And no big exploits. No big wins from AMD tied to better security. Spectre/Meltdown turned out to be a nothing burger for desktop users. Enterprise is a different kettle of fish, but the i9 is desktop chip.

    That said, if money is at all an object during a build the Ryzen 2700 is the chip to go with. You can get one, with a board and cooler for $350 bucks on newegg right now as I type this. Worst case It's about 17-24% slower than the i9 but it's literally half the price. I'll keep my $350 bucks and spend it on a better GPU.

    --
    Hi! I make Firefox Plug-ins. Check 'em out @ https://addons.mozilla.org/en-US/firefox/addon/youtube-mp3-podcaster/
    1. Re:Honestly they mostly just hit the firewall by Tough+Love · · Score: 2, Insightful

      To make good use of the micro code bugs you usually need root/admin. And if somebody's got that you're already boned.

      And you are boned for being stupid.

      Spectre/Meltdown are a problem because they enable a bunch of exploits that let you get out of a hypervisor and into the host OS. If you're in a data center that's a huge deal. If you're a gamer it's, well, not.

      The boneheadedness is strong in this one. I hope that nobody ever listens to you about anything.

      --
      When all you have is a hammer, every problem starts to look like a thumb.
    2. Re:Honestly they mostly just hit the firewall by Anonymous Coward · · Score: 0

      by Lucian Armasu January 4, 2018 at 9:10 AM

      Uhh, got anything more recent to refer to or just long outdated, incorrect information?

      Show me a live, working JavaScript that I can visit with my browser right now. I want to see it magically collect all of my data.

      If you can't produce a link to such a site, then shut up and stop spreading FUD. You don't know what you are talking about, kid.

  11. Also: Only 16 PCIe lanes?? by Anonymous Coward · · Score: 1

    Is that a joke, or are they serious?

    So one single decent GPU can't even be fully fed, if you would also like any other type of IO??

    The Ryzen at least has 24. And Threadripper a whopping 64!!

    If that does not outweigh their single core performance in practical applications, I'll eat my hat^WIntel CEO.

    Oh, and any reason single core performance matters more in gaming, is solely due to developers optimizing for the low-thread-count consoles, and do shitty lazy ports later. As soon as commonly used consoles start having that many threads, that problem will quickly vanish. No developer will waste a core, given how low-end consoles generally are.

    1. Re:Also: Only 16 PCIe lanes?? by Anonymous Coward · · Score: 0

      Low thread-count consoles? Since when?

      PS4 and Xbone have 8c/8t CPUs.

    2. Re: Also: Only 16 PCIe lanes?? by Anonymous Coward · · Score: 0

      Number of errors.

      x16 is fine for a single gpu,no consumer gpu needs more than that. And really there's very little difference between x16 and x8 in the way a gpu performs.

      Ryzen only has 20 not 24, 4 are reserved for the chipset and act like Intel's DMI link.

    3. Re:Also: Only 16 PCIe lanes?? by Anonymous Coward · · Score: 0

      Oh, and any reason single core performance matters more in gaming, is solely due to developers optimizing for the low-thread-count consoles, and do shitty lazy ports later. As soon as commonly used consoles start having that many threads, that problem will quickly vanish. No developer will waste a core, given how low-end consoles generally are.

      aren't the current xbox and playstation 8-core machines?

  12. +4x for the NVMe! by Anonymous Coward · · Score: 0

    Don't forget NVMe.

    And I wonder if SATA, SuperIO, the onboard sound and the other PCIe slots are supposed the share a single lane?

    This is supposed to be for high-end gaming rigs, they tell us. So 2 GPUs and NVMe and USB3 should be supported at the very least.

    16 lanes ... There is a Risitas video about that: https://youtu.be/ozcEel1rNKM

    1. Re:+4x for the NVMe! by Anonymous Coward · · Score: 0

      I find it decent on Intel since two NVMe 4x slots are part of the base package, though that's multiplexed on the chipset along with USB3 and SATA and other base I/O.
      High end gaming rig also means single user system running Winblows 10.

  13. AMD 2800X released in... by Anonymous Coward · · Score: 0

    ...3...2...1...

  14. Psst, Intel... by LordHighExecutioner · · Score: 1

    While you are so busy developing top speed CPUs for gaming, could you remember once in a while to release something new for the few of us who still have to spend their life *working* ?!? Thank you...

    1. Re:Psst, Intel... by drinkypoo · · Score: 1

      While you are so busy developing top speed CPUs for gaming, could you remember once in a while to release something new for the few of us who still have to spend their life *working* ?!? Thank you...

      Don't worry, AMD has got you covered with loads of PCIe lanes, and encrypted ECC RAM.

      --
      "You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
    2. Re:Psst, Intel... by Anonymous Coward · · Score: 0

      Intel has their "Refresh" bullshit on the bigger LGA2066 socket as well. The highlight of this is all lanes are enabled on the lower end 6-core and 8-core ones, no more 28 lanes enabled out of 44. But it's still i7 with ECC disabled.
      I think working on 2D/3D/video i.e. content creation without ECC is not too bad. You might do a memtest86 scan before/after unavoidable Windows 10 upgrades, if you're in that case. (Linux is not that great either, who's still running Ubuntu 14.04 or 12.04 or debian squeeze on their workstation?)
      Unacceptable for high 24/7 or months long HPC, not unworkable otherwise.

      A bad case would be : someone has ECC on their workstation, but doesn't know to read the logged memory failure events or doesn't get warned about them, and this person doesn't have backup hygiene so they still lose three full years of work for unrelated reasons.

    3. Re: Psst, Intel... by Anonymous Coward · · Score: 0

      Did you miss the e and w series releases.

  15. People will pay up, just like with Apple by Anonymous Coward · · Score: 0

    those extra 3% makes all the difference when you run the benchmark.. and that's what matters. The fact that you're paying $200 to get scalped and won't notice anything in day-to-day usage means little. People basically just wrag about how they paid the highest price for whatever they're getting.

  16. What compiler options ? by Alain+Williams · · Score: 1

    I'm not a gamer, but I suspect that games are sold and will work on both Intel & AMD CPUs but are generic binaries. This means that the vendors will have used compiler options so that they work on both, but that means that they might work faster on one. I have seen instructions generated that test which CPU & run these instructions or those ones. How much does that favour one CPU type over another ?

  17. Meanwhile at AMD... by Anonymous Coward · · Score: 1

    Threadripper offers 128 PCIe lanes and support for ECC memory.

    1. Re:Meanwhile at AMD... by Anonymous Coward · · Score: 0

      Actually EPYC has 128 lanes. Threadripper has just 64. Sorry about that. There's still ECC support on both.

  18. This is Intel's brilliance at its best by Anonymous Coward · · Score: 0

    So again can't really raise the bar in performance any other way these days but slap a few more cores on. This is pretty much why PC sales are flat. Nobody see's much in the way of real speed improvements. Its all about reducing chip size, lowering power consumption in mobile's or adding more cores to spread out same old speed limitations.

  19. Help me understand the point of this by jon3k · · Score: 1

    I'm not a gamer, so I'm prepared to be flogged for my ignorant question. This is advertised as "the best gaming CPU". But at any resolution over 1080p every modern title is GPU bound. Every benchmark I've seen at 1440p or higher shows absolutely no difference in frame rate between this CPU and one that costs 1/2 as much.

    So my question is: who spends $580, on the CPU alone, to build a gaming PC that only plays at 1080p? I understand that 1080p is the most common gaming resolution, but for people spending that much on a CPU I'm going to guess it is most certainly not.

    So what is the point? Why would this ever be the choice for a gaming CPU? Why wouldn't you spend $200 less on a CPU and put that money into a better GPU or monitor, if you really wanted "the best gaming" PC?

    1. Re:Help me understand the point of this by Anonymous Coward · · Score: 0

      You're right. But if I could afford this shit, I would go for 1920x1080 at 144Hz monitor - it's even available with VA panel technology which has the deepest blacks for an LCD (but lesser angles of vision than IPS)
      I gamed at 100Hz and 120Hz back in 2001 on 17" CRT ("Diamondtron"), and 75Hz and 85Hz on a 14" CRT that was mine, while not being particularly rich at all. I can appreciate the quickness but also remember when 1024x768 was high res.

      There are also supersampling options these days, even playing games that don't offer advanced AA methods at 4K resolution or other and have the result downsampled in real time to 1080p with a better method than simple bilinear/box filter. So, GPU power won't be so wasted from only having a 1080p monitor on old and undemanding games. BUT I doubt this works under Linux, or I have no idea.

      Over $500 for the CPU still is stupid. There are price increases over the board still, as Intel has shortages. Buying an i7 8700K on launch day would have been a better deal than getting hardware now. Best ones right now are AMD 2600 and 2600X.

  20. i9 = i7 = i5 by CptLoRes · · Score: 1

    So the i7 is now what used to be the i5 series but with i7 prices, and the new i9 is i7 at a new higher price range?

    1. Re:i9 = i7 = i5 by Anonymous Coward · · Score: 0

      Given that a couple years ago the i7's were 4 cores and now i5's are 6 cores it's really not that simple. I don't think Intel was trying to scam us with these, and really they had to drop prices to compete with Ryzen.

      Still, I don't think they should have called a 16-lane 2-channel cpu an i9, it really distracts from the feature set that they have on the x299 platform.

  21. The subject of your sentence is "the list". by Anonymous Coward · · Score: 0

    The subject is not "things"; it, being "the list", is what keeps growing.

    1. Re:The subject of your sentence is "the list". by iggymanz · · Score: 1

      no one gives a shit

      into the spectre bucket with you too, AC

  22. Lego porn: it's a thing by epine · · Score: 1

    One of the reasons I write on social media is that the subconscious mind doesn't convey its knowledge in straight lines.

    Maybe some people don't know this, but the five stages of grief model (formally Kübler-Ross) was basically a brilliant conversation starter. Constructive ways to talk about loss, grief, and death are relatively thin on the ground. Its half-century zeitgeist tenure was well deserved.

    But the model itself is far from a physical constant of the universe, so I wasn't surprised that I got a memo from my subconscious mind right after pressing submit "you know, most people think this is a five stage model; it could even be that the only response your post gets is correcting four to five, and nobody even notices the central point."

    Me to my subconscious: tell me about it.

    I'm generally a stickler for precision when there's something to be precise about, but the "five" in five stages of grief functions as what linguists call a "bound lexeme". We've gotten into the habit, like the five senses (which are still the five main exo-senses, even though we've now added things like proprioception as interior senses; the bigger argument with "five" senses ought to involve its total exclusion of the entire category of wufullness—e.g. telepathy, premonition, and private messages from God about your true path in life, transmediated via the as-yet unidentified theochlorians, smack dab in the middle of the colour green, within a spectrum formed from a whole new photonic vibratory node physicists have yet to discover, though there's a flagrant clue in one of the 10^500 string theory universes, if we would just sit down and do the work).

    My lexical mind still knows the difference between four/five stages of grief, but my semantic mind departed from this niggle long ago.

    Then you see articles in major publications with headlines blaring: "The 12 reasons we should abandon the 5 stages". And suddenly the light dawns: Lego porn: it's a thing.

    Oh, how that little number up front tickles our desire to stack conformable plastic bricks.

    We used to think that young human males were particular prone to falling down antisocial rabbit holes, such as video gaming.

    That was before we discovered social media. Now we know that young women fall down antisocial rabbit holes every bit as easily. As ever, men and women are mirror images, though often with the battery reversed.

    In my first post, I pinned Lego porn onto a geek sub-tribe, implicitly male. My bad.

    * The Five Love Languages
    * 5 Ways Your Relationship Changes After Someone Cheats
    etc.

    All this appeals to a specific sub-tribe of cultural stereotype 'stress kitten'.

    So some publication writes up a study of how psychopathic personality types are discovered to be very good as passing themselves off as thoughtful, introverted wallflowers on eharmony.

    And of course this immediately triggers the stress kitten version of the 4.5 stages of grief, covered over by a think foam topping of wankette creme: "oh, but this isn't the boy I'm chatting with, because I don't go into those dark corners (because my desktop computer never runs porous security containers chock to the brim with malignant JavaScript downloaded from hither and yon)".

    Yeah, right, sweetie pie. I guess that works for you.

  23. YAY! Now Windows can be even more bloated! by walterbyrd · · Score: 1

    I can hardly wait.

  24. NSA Inside! by Anonymous Coward · · Score: 0

    Fuck Intel.

    They lied to us for 15 years about their collusion with the NSA to usurp freedom worldwide. They lied for 10+ years about the security and speed of their processors.

    Intel owes us money.
    Intel should be disencorporated.

    Fuck the NSA. Fuck Intel.

  25. Re: NSA dll in win2000 by Anonymous Coward · · Score: 0

    You consider the NSA's dll backdoor in windows2000 a win for us???

    Eat shit NSA employer!

  26. Patched by rsilvergun · · Score: 1

    see here.

    There's still some theoretical exploits. They require incredibly precise timing and are unlikely to ever be used. Maybe if I was in a high security environment I'd worry about it. I'm playing video games. If the KGB or the CIA decides they want access to my Street Fighter V profile I'm pretty sure they'll find a way to get it with or without spectre/meltdown. Jokes on them, I suck.

    --
    Hi! I make Firefox Plug-ins. Check 'em out @ https://addons.mozilla.org/en-US/firefox/addon/youtube-mp3-podcaster/