Search results

  1. P

    Confirmed - i9 9900k will have soldered IHS, no more toothpaste TIM

    The physical problems are the same, this is just an engineering/accounting tradeoff between RMA rates and performance. Now that AMD provides effective competition again, delivering optimal performance for the top mainstream SKUs has become a higher priority than minimizing RMA rates, because...
  2. P

    Undecided between i7 7820X & i7 8700K

    If you want to use low buffer depths (64 or 128 samples), stay away from Ryzen/Threadripper. They handle low-latency DAW processing very badly. See the TechReport reviews here and here, as well as the articles from ScanProAudio here and here. If you are using higher buffer depths, the AMD...
  3. P

    This is interesting. Kaby lake and Sandy bridge comparison. By [H].

    There really wasn't an option to keeping core counts stable, as long as AMD refused to compete. AMDs CPUs have been so noncompetitive, if Intel had increased core counts at fixed price points for their mainstream SKUs, AMDs CPU sales would have pretty much stopped. If Intel had done that with...
  4. P

    New Zen microarchitecture details

    For 14nm, the wafer cycle time alone is around 90 days; then the wafers need to be shipped to the packaging plant where they are cut into dies, tested/binned and packaged. Then the CPUs are shipped to the distributors, which then ship to retailers. So that's probably closer to 4 months between...
  5. P

    First ever look at core IPC and Blender benchmark

    No, that sounds right. SIMD=Single Instruction Multiple Data, i.e. a single instruction will perform several arithmetic operations at once, in contrast to scalar code, where one instruction performs a single arithmetic operation. Thus SIMD code needs fewer instructions to perform the same number...
  6. P

    New Zen microarchitecture details

    The discussion about the number of ALUs misses an important point: ALUs don't matter if you can't keep them fed. For that you need a sufficient number of Load/Store Units. Zen will retain the two LSUs from the Bulldozer family. This will probably pose a pretty hard limit on the performance of...
  7. P

    New Zen microarchitecture details

    That will be IBMs SOI-based 14nm FinFET, which GF only acquired in 2014 together with IBMs foundry business, far too late to be used in Zens design. GF may also be contractually obliged to not offer this process to other customers, or only offer it well after POWER9 launches. IBM has been using...
  8. P

    Zen hasn't taped out yet

    Kumar didn't say it "will take" 12-14 months, but that it "can take" 12-14 months. And that's easily possible; depends on bugs detected during silicon validation and any possible respins necessary to get parametric yields to acceptable levels. Remember that Broadwell production silicon was on...
  9. P

    Intel Broadwell Thread

    Cost shouldn't be much of an issue in this case. The smallest BDW-EP die is probably 10c (smallest HSW-EP die is 8c). With the 14nm shrink, the BDW 10c should be quite a bit smaller than HSW 8c. Most sales will be for 6c/8c, so Intel won't need too many fully functional 10c dies. Even with the...
  10. P

    AMD Wants To Stop Being Known As The “Cheaper Solution”

    Where did AMD talk about performance? AFAIK they only talked about IPC (which is completely meaningless without a frequency/performance target). Personally, I think +40% IPC @"we're not telling" GHz is completely believable.
  11. P

    How to best upgrade my entry level Haswell system...

    The problem is not disk or CPU, the load values are far too low for that. Modern HDs will deliver ~100 MiB/s, and DAWs will pre-buffer during playback, so you won't get I/O problems until you're playing back many many more channels. And you're not even fully using one CPU core in this case, so...
  12. P

    Proccessor vs Microprocessor

    http://www.instructables.com/id/How-to-Build-an-8-Bit-Computer/
  13. P

    WCCFAMD Zen Architecture Could Feature in APUs in 2016, ASUS a Key Player

    AMDs market share in 2Q14 was: x86 overall, counting consoles: 16.3% x86 overall, without consoles: 11.2%. x86 segments: console=100%, DT=15.0%, mobile=9.6%, server=2.2%. I doubt they managed to double their DT market share in the last quarter with their anemic offerings, so there's no way for...
  14. P

    Do you have HPET enabled or disabled?

    The 15ms (actually 15.625ms) resolution is not really a problem of the underlying timer hardware, but of Windows kernels. At least up to Win7, the "master tick" of the kernel runs at this speed of 1/64s. Many of the timer functions in Windows run off this master clock. You can check out the...
  15. P

    Broadwell TDP, partially DDR4?

    True for lower-end consumer boards but not for server/HEDT and probably the higher-end Skylake DT boards. It will be possible to use several DDR4 LRDIMMs on one channel. These Load Reduced DIMMs use active buffering so that they have bus load characteristics of a single DIMM even when multiple...
  16. P

    [Softpedia] 2014-Bound Intel Broadwell-K CPUs Get 80% Graphics Boost from Iris Pro

    This is isn't only about the GPU part - I expect proper successors to the Iris Pro SKUs with beefier GPUs than for the Broadwell K models. It's also about the 128MiB L4 cache. Crystalwell isn't a dedicated GPU cache, it's a general purpose Last Level Cache which works for both GPU and CPU loads...
  17. P

    kaveri bf4 good performance?

    He's right as far as the costs on Intels side are concerned. Crystallwell is 80% of the die size of Bay Trail -> lowest Bay Trail list price $37 -> Crystalwell adds some $30 actual list price if calculated with Bay Trail margins. OEM costs will be lower. However, Intel can't currently price...
  18. P

    AMD 2014 Desktop roadmap

    I was thinking about general-purpose cores which scale from client to server across a wide range of workloads, sorry, should have made that clearer. Even so, only Silvermont and Quark don't have SMT. Quark is obvious, and Silvermont couldn't benefit much from SMT as long as the out-of-order...
  19. P

    AMD 2014 Desktop roadmap

    Useless comparison. All CMT CPUs suck. Some SMT/HTT CPUs sucked - before SMT was added and after (P4). Some SMT CPUs are class leaders across a wide range of performance and performance/W targets - before and after SMT was added (Core2->Nehalem-->Haswell). SMT -> design choice which doesn't...
  20. P

    AMD 2014 Desktop roadmap

    If AMD wants to keep up with Intels Core series, they'll have to increase performance. Frequency scaling seems to be dead, as Kaveris clocks are going down, not up. This leaves IPC increases, and this will require wider cores. And widening the core is a rather far-reaching change. You can't just...
  21. P

    AMD 2014 Desktop roadmap

    You really think that AMD, who have trouble mastering 28nm CPU design, should target a new process for a drastically changed architecture? That's something even Intel doesn't dare to do anymore; this was one of the fundamental reasons for the introduction of the tick-tock cycle, you improve...
  22. P

    6 or 8 core Steamroller based AMD CPU likely?

    This article is about ISSCC in February 2014, by which time we should have final Kaveri silicon tested by reviewers. Hotchips was back in August, I think AMD only presented some details of the console APUs this year.
  23. P

    AMD on track for launch of Kaveri in February 2014

    Come to think of it, with ongoing process optimizations, production costs may drop slightly. That wasn't what I was talking about, though. Try reading the second sentence in my post.
  24. P

    Kaveri Steamroller vs BulldozerPiledriver

    I'm sure they are using the HPP from GFLs 28nm processes. But the 28nm SHP which appeared on roadmaps isn't listed for GFLs current processes; maybe AMD was supposed to pay for development, couldn't, and now has to make do with a process which is suboptimal for their purposes. This is one thing...
  25. P

    AMD on track for launch of Kaveri in February 2014

    Here.
  26. P

    AMD on track for launch of Kaveri in February 2014

    i5-4570R @ $288. And Crystalwell currently is on the N0 process - next year it moves to N-1, which changes the economics considerably. This will be a nice dumping place for "excess" 22nm capacity.
  27. P

    Been reading anandtech for a while... new to the forum - Anyone got information on...

    For CPU microarchitecture, start with the Wikipedia article. Follow the links. After that you should have a basic grasp of the concepts. If you want to delve deeper into the topic, be aware that it will be a long journey; modern CPUs are extremely complex beasts, understanding them is not easy...
  28. P

    Intel to Manufacture ARM CPUs for Altera

    Unlike Seronx' stuff, this is quite believable if you look at the retail prices for top FPGAs. This Altera Stratix V GT model @mouser.com shows at 26,508 €. So the production prices are probably far higher than $1000, otherwise there'd be a 3500% markup between production and retail...
  29. P

    Kaveri Steamroller vs BulldozerPiledriver

    Underperforming in what metrics? If the process gives great parametric yields for LP designs <= 2GHz at low wafer costs, then it could turn out be an excellent process for GFL. If AMD would have chosen the wrong designs for the process, that would be AMDs problem, not GFLs. "Process quality" has...
  30. P

    Kaveri Steamroller vs BulldozerPiledriver

    It can make sense if you have a fixed transistor budget and want to optimize your design for certain performance target points. It's well known that the SR FPU will be reduced from 4 pipelines to 3 - that's been on every SR block diagram AMD ever published. It seems they used the transistor...
  31. P

    is i5 750 (Jun/2009) worth upgrading to i5 4670k?

    As regards SC2, hardware.fr has benched it on a range of CPUs in their Haswell i3 test: 30% improvement from Sandy Bridge to Haswell; compared to Lynnfield, that will be 40-50%. So, at least for SC2, going Haswell will certainly pay off.
  32. P

    AMD A4-1200 and its product wins.

    Are you sure the system works as it's supposed to (turbo enabled, not throttling)? The i5-3317U has a turbo of 2.6 GHz, it will be about 2x faster than any Kabini for lightly threaded workloads.
  33. P

    AMD Q313 Results

    If Intel had the same business strategy as the classic RISC vendors had in the 90s (concentrate solely on high-profit big iron), ARM could have a valid attack vector. But Intel already adjusted its server strategy to fend off attacks in the low-end segment; the very first Silvermont Atoms...
  34. P

    AMD Q313 Results

    Samsung has started doing custom ARM designs: http://english.etnews.com/device/2806178_1304.html. Nvidia as well. I think all big players are going to custom designs. It certainly won't be easy to compete in that market.
  35. P

    Intel 14 nm delayed.

    You need to look at the historical timeline of Tick-Tock releases. Each tick or tock has taken an average of 13.8 months between Conroe and Haswell. If you extrapolate from that historical data, you get release dates of 2014-07 for Broadwell and 2015-09 for Skylake. If BRW is delayed to 2014-09...
  36. P

    Geekbench 3 Sandy Bridge v.s. Apple Cyclone IPC comparison

    Yup, you never worked retail and got a chance to look at the buying prices of your store compared to the selling prices. Read this and then look at the gross margins here. Taking 36% gross margins, average computer/software markup is ~56%. Which leaves plenty room for a ~20% discount while...
  37. P

    New type of CPU...

    Certainly. While you could manipulate the vendor ID with a Via Nano and Agner Fogs CPUID manipulation program, the vendor ID as returned by CPUID function 0 has a maximum length of 12 bytes, which obviously is too short for storing the 25 characters of "AllYourBaseAreBelongToCPU".
  38. P

    [FUDZILLA] No Broadwell for Desktop

    Well, after the Baytrail-T previews, this shouldn't come as a surprise. It's all about fab capacity management. Silvermont already is a highly competitive architecture and Atoms will now begin to sell in volume. When Airmont comes out next year, it should be a performance leader across a wide...
  39. P

    Haswell-E with DDR4 showed.

    Probably several factors: aggressive turbo for the workstation SKUs, more PCIe lanes, 1.5x the L3 cache/core, QPI link for 2P, higher supported memory speed (1866 vs. 1600 for DT CPUs). I'd also guess that the RDRAND implementation would be much stronger than in the DT models. And the server...
  40. P

    [OCA]4670K vs 3570K Gaming performance

    Hardware.fr has a test of various Haswell SKUs versus their IVB/SNB predecessors. No performance regressions, although the improvements aren't breathtaking either. But it's enough to see that the ocaholic benches seem to be useless.
COMPANY
RESOURCES
FOLLOW
Top Bottom
sale-70-410-exam    | Exam-200-125-pdf    | we-sale-70-410-exam    | hot-sale-70-410-exam    | Latest-exam-700-603-Dumps    | Dumps-98-363-exams-date    | Certs-200-125-date    | Dumps-300-075-exams-date    | hot-sale-book-C8010-726-book    | Hot-Sale-200-310-Exam    | Exam-Description-200-310-dumps?    | hot-sale-book-200-125-book    | Latest-Updated-300-209-Exam    | Dumps-210-260-exams-date    | Download-200-125-Exam-PDF    | Exam-Description-300-101-dumps    | Certs-300-101-date    | Hot-Sale-300-075-Exam    | Latest-exam-200-125-Dumps    | Exam-Description-200-125-dumps    | Latest-Updated-300-075-Exam    | hot-sale-book-210-260-book    | Dumps-200-901-exams-date    | Certs-200-901-date    | Latest-exam-1Z0-062-Dumps    | Hot-Sale-1Z0-062-Exam    | Certs-CSSLP-date    | 100%-Pass-70-383-Exams    | Latest-JN0-360-real-exam-questions    | 100%-Pass-4A0-100-Real-Exam-Questions    | Dumps-300-135-exams-date    | Passed-200-105-Tech-Exams    | Latest-Updated-200-310-Exam    | Download-300-070-Exam-PDF    | Hot-Sale-JN0-360-Exam    | 100%-Pass-JN0-360-Exams    | 100%-Pass-JN0-360-Real-Exam-Questions    | Dumps-JN0-360-exams-date    | Exam-Description-1Z0-876-dumps    | Latest-exam-1Z0-876-Dumps    | Dumps-HPE0-Y53-exams-date    | 2017-Latest-HPE0-Y53-Exam    | 100%-Pass-HPE0-Y53-Real-Exam-Questions    | Pass-4A0-100-Exam    | Latest-4A0-100-Questions    | Dumps-98-365-exams-date    | 2017-Latest-98-365-Exam    | 100%-Pass-VCS-254-Exams    | 2017-Latest-VCS-273-Exam    | Dumps-200-355-exams-date    | 2017-Latest-300-320-Exam    | Pass-300-101-Exam    | 100%-Pass-300-115-Exams    |
http://www.portvapes.co.uk/    | http://www.portvapes.co.uk/    |