• RELEVANCY SCORE 4.22

    DB:4.22:/Qparallel Uses Only 2 Cores On An 8 Core Machine zp





    Hi there,

    my colleague is on a construction site installing one of his programs on the clients machine.

    The clients machine has8 Cores. His program is being compiled with the /Qparallel option, but the program uses only 2 Coreswith 100%.

    So my question is, does the /Qparallel option "only" optimizes for 2 Cores? Would an OMP approach do better?

    I dont know what the clients machine really is (Intel or AMD), but I asked my colleague. Because he cannot go online very often I havent got an answer yet. He usesVisual Studio 2008 9.0.21022.8 RTM andIntel Fortan Compiler 10.1.4159.2008 (seems likethe integration version).

    Thanks in advance,
    Markus

    DB:4.22:/Qparallel Uses Only 2 Cores On An 8 Core Machine zp


    By default, the maximum number of threads is taken from the number the processor is capable of (including Hyperthreading). It's possible that the problem size is not large enough to split across 8 cores.

  • RELEVANCY SCORE 2.93

    DB:2.93:Strange Problem With Openmp s1





    Hi,

    I have a strange problem with OpenMP.
    My computer has one processor with four cores. Sometimes OMP_GET_MAX_THREADS() returns 4 and sometimes it only returns 1. The behavior seems to be totally random.

    Any idea on what is going on?

    Compiler settings:
    /nologo /Qparallel /Qopenmp /Qopenmp-report1 /warn:declarations /real_size:64 /fpconstant /module:"x64\Release\" /object:"x64\Release\" /libs:static /threads /c

    Is it the combination /Qparallel /Qopenmp that is the problem?

    I am using the latest version of Intel Visual Fortran.

    Thanks,
    Henrik

    DB:2.93:Strange Problem With Openmp s1


    I haven't verified if omp_get_num_procs()...

    returns the number of hardware threads the system has

    or

    returns the number of hardware threads the application is restricted to run on.

    For the latter, on Windows you can call GetProcessAffinityMask.

    Note, an application may be restricted to run on specific hardware threads which may total less than the total of all physical threads. When tuning number of threads the total number of hardware threads available to the application (GetProcessAffinityMask) may be more important than the number of hardware threads available on the system.

    Jim Dempsey

  • RELEVANCY SCORE 2.91

    DB:2.91:Logic Pro X Works Only On 2 Cpu Cores! Why? They Have To Fix That! Fast! p9




    I have a 8 Core MacPro, but Logic Pro X uses only 2 or sometimes 4 cores. But this very extensiv. So the playback always stopps! I was thinking they fixed this problem in Logic Pro X, because i still had it in Logic 9. THEY HAVE TO FIX THAT A.S.A.P.

    DB:2.91:Logic Pro X Works Only On 2 Cpu Cores! Why? They Have To Fix That! Fast! p9

    No, it doesn't work in Logic Pro X! I know this article. And by the way, he program has to do this sh** automatically! I have to focus on my work, not on my CPU! Every other DAW does it, only in Logic i have this problem.

  • RELEVANCY SCORE 2.84

    DB:2.84:4+ Cores On Linux 18



    Currently Im using a 2 core Athlon 64 x2 6000+ 2x3GHz, but most of the programs uses only one cpu core. For example openmovieeditor used only one core, but avidemux used both when I was converting a video. I know that there are some programs, which can use more cores with proper config or arguments (for example make -j2 I think), but even the kioslave at a file copy only uses one cpu core.My question is: Do I really need more than 2 cpu cores on a desktop computer? If the cores are slower it can be even slower sometimes. Or its just my lameness in configuration? Can it be better wth a custom kernel?

    DB:2.84:4+ Cores On Linux 18


    This is not windows, you do not have to reinstall for something so trivial.

    And what is wrong with reiserfs on multi core? Never had a problem and have run it on multi core systems for years...

  • RELEVANCY SCORE 2.75

    DB:2.75:# Of Cores Enabled? a7



    I was running a benchmark test on my CPU using PC Wizard and noticed under the information for my processor (i7 920) that the number of cores enabled was only 2.Are the number of cores enabled at any one time dependant on how much activity or how many programs are being ran? It did say thatthe number of cores was 4 and the number of threads was 8 which is as it should be. I just didn't understand why the number enabled was only 2. I also noticed that the processor speed was about 100MHZ faster than the product standard of 2.67GHZ, benchmarking at 2794MHZ. Is that possibly due to turbo and the fact that only 2 cores are running?

    As always any help is greatly appreciated by this PC Wizard in training.

    Lawrence

    DB:2.75:# Of Cores Enabled? a7


    The # of cores parked is a power saving scheme. The extra cores kick in automatically when needed. If you run a CPU benchmark program then you can observe the action bu having Task Manager - Performance viewable when running the benchmark.

    I ran the CPU only benchmark from PC Wizzard and all eight threads (4 cores and 4 hyperthreads) were at 100%.

  • RELEVANCY SCORE 2.73

    DB:2.73:Labview Multicore Support 8k


    Dear Sir,

    I have a problem with Labview 8.5. When I use a vi for more than 4 cores (Suach as on my Dell Precision T7400
    which have 8 cores in two quad CPUs), the vi core crshed.
    I wonder does Labview support more than 4 cores?

    Also, when I use two cores, I found the time increase almost 2 time in a VI code with two parallelism (on my 8 core computer); But for more than 3parallelism, the speed does not improve (again on my 8 core computer); Does this means that labview only fully support a computer with 2 cores? For more than a computer with 2 cores, the speed is equal to that of two cores, sinec the limitation of labview?

    Thanks.

    Mark-Ren.

    DB:2.73:Labview Multicore Support 8k

    Hi, GerdW,

    The VI code you just emailed me can acheive 30% gain on my dual-core computer (the same result with yours), and it acheives
    45% again on my 8-core Dell T7400 desktop computer. The gain is not so much compared with the 2-core computer, since your code
    is not total parallesm.

    In my VI codes (that is perfect parallelism), I have 8 parallel structures, and eachstructure is manually assigned to different core. To verify the gain for multi-cores, you can modify my VI code. Case 1: you only keep the sctructure 1 (you need to delete other structures), and then run the code. Now you have core 1 available, I got 10 secondof runing timeon my computer (by look my watch). Case 2: you keep 2 structures and run the code. Then you have two cores (cores 1 and 2) available. Then I got nearly 10 second of running time. The two cores is 2 times fast than the one core, since the code working load is twice (2 structure); Case 3: you keep3 structures, and run the code again, the running time is 20 seconds; Case 4: you heep 4 structures and the running time is 30 seconds and so on. And then each time you add a structure, you add a 10-second running time, indicating thatno any improvementforcases that have morethan 2 cores. Therefore, I conclude that Labview is only optimised for a computer that has the core number less than 3-core computer. To verify this, you need have a computer that has at least 4 cores.

    Again, all the examples that I can find on NI website are for 2 cores. I have not yet find an example from NI for 3 more different cores. I have attached my code again.

    Thanks.

    Mark-ren
    ----------------

    Hi Mark-Ren,beside the 8-core problem of crashing (which I cannot confirm on a DualCore) your code seems pretty senseless:How do you want to measure performance increase when you stick each timed sequence to a single core?Both measurements (in each timed sequence) will give nearly the same result with pipelined version even being a bit slower due to simultanous memory access and "parallel" execution. You will only measure better performance when you allow more than one core to process each timed sequence!(Overall performance will be better on 8-core as all timed sequences can run in parallel...)The attached (stripped down) version of your vi gives a performance increase of ~30% on my DualCore, which changes to ~-8% when using a timed sequence put around that code...
    Message Edited by GerdW on 04-15-2008 09:15 PM

    Best regards,GerdW









    Attachments:






    MultiCoreTest1.vi ‏1451 KB

  • RELEVANCY SCORE 2.62

    DB:2.62:Cpu-Cores + Ram Per Core km



    Hello,

    On what way the amount of CPU-cores and the amount of RAM is optimal?

    For example; do I need an minimum of RAM per CPU-core (so 2 Quad-Core CPU's = 8 cores; 2GB per core is 32GB)

    Oz!

    DB:2.62:Cpu-Cores + Ram Per Core km


    I would have to say it all depends on what type of load that you are going to be putting on the system and what type of env your in.

    What i have come to learn is it is better to be a bit frugal with your system resources and go back and add more if needed, that way you are not giving away resources.

    Currently i have a dual quad core with 16 GB running in a dev environment with about 20-25 VM's Running and i am only using about 8 GB of my memory.

    If you plan on running exchange, SQL or other intensive applications you will need to accommodate for that in your planing

  • RELEVANCY SCORE 2.62

    DB:2.62:Best Practice For Choosing # Of Processor Cores? mk



    Is there a best practice when choosing the number of processor cores to assign to a VM?

    Previously on my old MacBook Pro I only had to consider 2 cores (Intel Core 2 Duo). Now with my new i7 MacBook Pro and it's 4 cores, I'm wondering what the best practice is.

    For example, I noticed that assigning 2/4 cores to a Windows XP SP2 VM causes those 2 cores to max out at 100% usage, while the remaining 2 cores are barely being utilized by the host OS (Mac OS X 10.6.3). I'm wondering if I should allow the VM to take advantage of all 4 cores so that potentially none of the cores get maxed out at 100% utilization. On the other hand, if the host OS has to share all of core with the VM, Mac OS X will probably run slower?

    DB:2.62:Best Practice For Choosing # Of Processor Cores? mk

    If you have a single Core 2 Duo, only give the VM 1 Virtual CPU. On the new i7's, you might get away with 2, but test it. Giving too many virtual CPU's will starve the host for cycles.

    Windows XP is notoriously bad at using more than 1 CPU anyway.

  • RELEVANCY SCORE 2.61

    DB:2.61:Simulate Less Cores sd


    We have a test machine with 8 Cores. When using Parallel.ForEach, what is the easiest way to simulate a machine with only 1, 2 or 4 Cores?
    We tried to use the /NUMPROC windows startup parameter, but weirdly it doesn't seem to have any significant impact on the total running time.

    DB:2.61:Simulate Less Cores sd

    You can limit a process in Windows to only run on certain cores, so that's one approach, albeit quite heavy-handed (and also more specific than you're asking for since this will not only limit the DOP but will also constrain how that DOP may be applied).
    By default all work from Parallel Extensions runs on the .NET ThreadPool, so you can use the ThreadPool's SetMaxThreads method to limit how much work occurs concurrently. That's also heavy-handed, won't work for less than Environment.ProcessorCount,
    and can lead to deadlock if work items queued to the ThreadPool have dependencies on other items queued to the ThreadPool.
    You can alsocreate a custom TaskScheduler that enforces the DOP (several of the
    sample TaskSchedulers in ParallelExtensionsExtras do this). Then you can pass an instance of that scheduler into every place you want to limit the DOP. Additionally, unless
    a TaskScheduler is overriden by explicitly passing one in, Tasks automatically pick up the current scheduler rather than the default scheduler when they're scheduled, so for a tree of work if you create the root task on a scheduler, all descendents will be
    scheduled to the same place.
    Beyond that, no, there's no more global way to do this, and that was an explicit design choice.

  • RELEVANCY SCORE 2.61

    DB:2.61:Trying To Use More Cores On An Proliant Dl385g7 W/ Amd jj



    I have a server with 2 Processors x 12 cores = 24 cores.

    32G RAM

    I have ESXi5 free version. I am trying to figure out if I have to upgrade to Enterprise Plus to get more cores assigned to a machine

    I only have 2 hosts assigned to the box. One host does a lot of processing.

    VShpere client will only allow me to get to 8 cores per host. This seems to be a licensing issue. My problem is that I cannot seem to assign a second machine other cores that are not being used,etc. I see 8 cores running very high. (around 75% all day), and 16 cores doing nothing.

    Am I stuck with basically 2/3 of my processing power doing nothing at all times unless I upgrade to Enterprise Plus.

    Basically, Enterprise Plus costs as almost much as a new server. So, I suppose I made a mistake buying a server with weak, but many cores in the AMD brand ?

    Any advanced settings I can tweak ?

    Thanks so much in advance for any information.

    DB:2.61:Trying To Use More Cores On An Proliant Dl385g7 W/ Amd jj


    I think something else is going on because there is no cap on the number of PHYSICAL cores you can use with the Free License per http://www.vmware.com/files/pdf/vsphere_pricing.pdf - Also remember a vCPU runs in physical core at a time - so if you have only the single VM running it will only use 8 cores -

  • RELEVANCY SCORE 2.59

    DB:2.59:Managing Cores 81



    Trying to switch to VMWARE the most painless way didn't work. Didn't have a chance to start up ESXi3.5 or ESX 4 on our servers 3*Intel SR1500ALSAS with an active backplane. So we decided to go for Win 2003+VmWare Server 2.0. And after the decision i came up across a post mentioning that only 2 CPU cores per VM are allowed. As there won't be too many CPU hungry applications (WSUS, AV, MSSQL, local ERP, some Informix and some nix stuff) that won't be such a problem (i hope). But how does Server 2 balance all the cores itself? We have 2xeon on each machine, so that makes it 8 cores per place. Will it put vm1 on cores 12, vm2 on cores 34 e.t.c?

    DB:2.59:Managing Cores 81


    The hypervisor will schedule the virtual CPUs (vCPUs) across all available physical cores. With ESX/ESXi, the hypervisor has a great deal of control over this scheduling activity and will try to optimize cache hits and "near" memory utilization. In the hosted products (like VMware Server), the host operating system is ultimately responsible for scheduling processes on the physical cores. So...the vCPUs will (mostly) "stick" to the same pCores; however, it is possible that they will "migrate" from core to core.

    The great thing about this virtualization stuff is that you really don't need to worry too much about how it works at the scheduling level - just know that it works and that, if the resources are available on the host, they will be granted to the guest as needed. Obviously, if you seriously overcommit your host resources, your guests can become resource starved.

    Ken Cline

    VMware vExpert 2009

    VMware Communities User Moderator

    Blogging at: http://KensVirtualReality.wordpress.com/

  • RELEVANCY SCORE 2.59

    DB:2.59:Corei7 Fedora10 Only Picks Up 2 Cpu Cores 8z



    I get the following in the vm web access summary;

    Processors: Intel(R) Core(TM) i7 CPU 920 @ 2.67GHz

    1 CPU x 2 Cores

    So, the core i7 is obviously a quad core unit. I've switched HT off, and the os can see the four CPU cores. The way I see it, its either an i7 issue, a fedora 10 issue, or a combination of both... but I have no idea... Help?

    UPDATE: Well it seems to accept all 4 when I switch on HT... but that's going to drop performance right? Whats the best config with this setup?

    DB:2.59:Corei7 Fedora10 Only Picks Up 2 Cpu Cores 8z


    I think this was actually just VMware server seeing an i7 and halving the cores, I had hyperthreading switched off.

  • RELEVANCY SCORE 2.59

    DB:2.59:All Cpu Cores To 1 Vcpu 38



    Hello,

    We are trying to improve performance of AutoCAD. It almost does not use multithreading so it uses only 1 kernel of CPU provided. So I have an idea to install it on VM and provide vCPU that would be emulated by all cores of CPU. Is it possible in ESXi or other VMWare products?

    Thanks

    DB:2.59:All Cpu Cores To 1 Vcpu 38


    As written by Andr, is not possible.

    CPU is virtualized (the VM "see" the physical cores) and there is no way to "aggregate" them with this kind of solutions.

    Andre

  • RELEVANCY SCORE 2.58

    DB:2.58:Problem With /Qparallel And /Qopenmp? p7



    If a program is compiled with /Qparallel without /Qopenmp, the 11.0 compiler will link libguide40 to the application. But if both switches are used together, libiomp5md is linked. While this is satisfactory for stand-alone applications, this will cause problems when multiple DLLs are built into a single application. If some of the DLL's are built with only /Qparallel they will have a dependency on libguide40 while if others are linked with both switches they will have a libiomp5md dependency. This will cause the application to fail to load due to the multiple OpenMP libraries.

    I realize that forcing linkage of the library will solve the problem, but shouldn't libiomp5md be linked in all cases?

    DB:2.58:Problem With /Qparallel And /Qopenmp? p7


    The problem with /Qparallel brings old openmp runtime lib is fixed in the 1st update. You can download it from our eval center or the registration center.

    Thanks,
    Jennifer

  • RELEVANCY SCORE 2.58

    DB:2.58:Mental Ray Satellite Processor Cores k7


    Is it possible to set mental ray satellite to exploit only 2 or 3 cores?!

    DB:2.58:Mental Ray Satellite Processor Cores k7

    Is it possible to set mental ray satellite to exploit only 2 or 3 cores?!

  • RELEVANCY SCORE 2.57

    DB:2.57:Ipo - Libguide40.Dll f3



    I am using IVF 9.1 on a command line under Windows XP.

    I compile/link an old file and the results show a different

    behavior, probably due to an additional compiler option /Qparallel.

    When I ran nMake, the monitor showed

    iFort e:srcppbS.f90 /nologo /c /fast /Qparallel /Ie:srcinc /module:e:IVFmod /Ie:IVFmod

    /noD /error-limit:10 /object:e:IVFobjppbS.obj

    and a lot of message such as

    IPO: performing multi-fie optimizations

    e:srcppbS.f90(1344) : (col. 6) remark: LOOP WAS

    AUTO-PARALLELIZED.

    e:srcppbS.f90(1257) : (col. 8) remark: LOOP WAS VECTORIZED.

    e:srcppbS.f90(3052) : (col. 16) remark: PARTIAL LOOP WAS VECTORIZED.

    The problem is that the resulting executable could be run

    only on the DOS windows that I have run IA32inifortvars.bat.

    When I ran that executable on a DOS window before I ran

    ifortvars.bat, an error message of Unable to Locate Component:

    This application has failed to start because libguide40.dll

    was not found. Re-installing the application may fix this problem.

    I have libguide40.dll in

    C:Program FilesIntelCompilerFortran9.1IA32Bin

    which is in the PATH of the DOS window after ifortvars.bat

    is run but not in DOS windows without running ifortvars.bat.

    How could I run that executable in a PC

    without IVF?

    Wen

  • RELEVANCY SCORE 2.56

    DB:2.56:Intel Quad Core, Only Two Cores Found Please Help zm


    i just upgraded from windows vista and all 4 of my cores where working. now on windows 7 ultimate 32bit i only have to cores? i tried going into msconfig to try and sort things out but there is NO detect HAL option and only 2 cores avalible.

    Please Help

    DB:2.56:Intel Quad Core, Only Two Cores Found Please Help zm

    In Device Manager, uninstall the CPU and then reboot. Windows should reinstall on the restart. Let's hope it manages to find all four cores.

  • RELEVANCY SCORE 2.54

    DB:2.54:Db 11g On Min2k3 Take 100% Of One Core 2 To 4 Minutes After Startup x1


    I have a Windows 2003 VirtualBox instance, to which I assigned 3 out of 4 cores my laptop has.
    This is a demonstration environment for an Oracle vertical product. I got it from my colleagues.
    The OS boots without starting the DB services - I did this deliberatley while trying to figure out what is happening.
    About 2 and half to 3 and a half minutes after the service is started the oracle.exe "latches onto a core and does not let go" (as best as I can describe what I see). With 3 cores I see 33%-34% cprocessor use in the task manager with oracle.exe doing all the using. Nothing else is started. There is no process of which I am aware which actually uses the DB.
    I only start the TNS listener and the database service.

    Once I start it, the demonstration software uses the database extensively for complex queries. With one of the 3 cores 100% used by the oracle.exe I am running short on CPU at times, which makes the demonstratin seem slaggish, and queries take longer than is really acceptable (not surprising seeing oracle.exe is very busy doing I know not what).

    Can somebody, please, suggest what I can do to try to diagnose and remedy this?

    Thanks in advance

    DB:2.54:Db 11g On Min2k3 Take 100% Of One Core 2 To 4 Minutes After Startup x1

    I cannot speak for a Windows guest, but on Linux I have seen the VKTM process take excessive resources in a VirtualBox environment. See this,orcl select ksppstvl from x$ksppi join x$ksppcv using (indx)
    2 where ksppinm='_high_priority_processes';

    KSPPSTVL
    -------------------------------------------------------------------
    ----------
    LMS*|VKTMif you get the same result, do thisalter system set "_high_priority_processes"='' scope=spfile; and re-start. Of course, one would never do this on a production system, but this has fixed the problem of a CPU being maxed out for me a couple of times.

  • RELEVANCY SCORE 2.54

    DB:2.54:32 Vs 64 Differences On Core I7 jk


    We just bought a Core i7 computer. I was doing some benchmarks and in order to get reproducible numbers, I usually disable hyperthreading. Suprise this Dell XPS 730 does not have any BIOS option to disable Hyperthreading.
    After tweaking I realised that by restricting Vista32 to 4 cores, it actually took the "real" 4 cores, effectively disabling hyperthreading.
    Unfortunately, Vista64 does not do this because it numbers the cores differently than Vista32. So when restricted to 4 cores, you end up with only 2 "real" cores hyperthreaded. Not at all efficient, and certainly not what I want.

    I looked and couldn't find any KB article or update related to that. Anyone know of such an update?

    DB:2.54:32 Vs 64 Differences On Core I7 jk

    Hardware related??? What do you make of Vista 32 bit doing the right thing on the same hardware? The problem is Vista 64 related, not hardware related. I'm not looking for a BIOS solution here, but a way to make Vista 64number the cores the samewayVista
    32 does, or at least be intelligent and privilige "real" cores when the number of cores to use is limited at boot time.

    Unless you mean to say that Vista 64 has to run on hardware, then yes I guess it is hardware related. But then again, what's the alternative!

  • RELEVANCY SCORE 2.54

    DB:2.54:Why Hyper-V Uses Only 4 Vcpus And Not More? Does This Affect Performance Over Vmwares 8 Vcpu? zf


    We have a server with 2 physical processors with 6 cores, so a total of 12 vCPUs
    when setting up the hyper-v guest, we can only select up to 4 vCPUs.We are only going to be running 2 guest machines which would give us a total of 8 vCPU's, so are we wasting the other cores?
    How does this affect performance compared to how vmware uses vCPUs?Brad Nelson MCSE/DCSE/A/Network/WCSP

    DB:2.54:Why Hyper-V Uses Only 4 Vcpus And Not More? Does This Affect Performance Over Vmwares 8 Vcpu? zf

    .........Sort of :) You can run more than 4 cpu's by doing this:
    http://social.technet.microsoft.com/Forums/en-US/virtualmachingmgrhyperv/thread/cf17b31f-3ef9-49c8-93a0-a6d6b83b2bbe

    And as far as our testing goes it seems to use all phyiscal cpu's by way of the perfmons in hyper-v.

  • RELEVANCY SCORE 2.54

    DB:2.54:Running On 800 Mhz, Even Though 2 Cores Are On 100% fa



    Running on ondemand cpufreq governor with 800 Mhz, even though 2 cores are on 100% load. What could be the problem?/proc/cpuinfo shows 1000 Mhz for 2 cores (out of 4) and cpupower somehow shows only 800 Mhz for all of them.

    Last edited by ernetas (2012-12-08 14:41:38)

    DB:2.54:Running On 800 Mhz, Even Though 2 Cores Are On 100% fa


    Well as it turns out ACPI is used.
    [user@archbox:~]% sudo lsmod |grep cpufreq
    [sudo] password for user:
    acpi_cpufreq 6854 1
    mperf 2124 1 acpi_cpufreq
    processor 27916 1 acpi_cpufreq

  • RELEVANCY SCORE 2.54

    DB:2.54:Low Performance 1f



    Hi,

    I have a maya plugin which uses cgal and ublas. I compiled it with Intel C++ Complier using VS2005 ide on xp. The plugin run time was 1:45 seconds, while with visual studio compilers it took only 50 seconds. I am quite disappointed, and I was wondring if I did anything wrong to cause such a performance degradation.

    I compiled the app with /O3 /MD (I tried also various switches such as /Qparallel /O2 interproc...), disabled default libraries, and added:

    OpenMayafx.lib OpenMayarender.lib OpenMayaAnim.lib openmayaui.lib foundation.lib openmaya.lib libmx.lib libeng.lib libiomp5md.lib libmmd.lib libircmt.lib oldnames.lib OpenMayaFX.lib libboost_serialization-iw-mt-1_47.lib libboost_thread-iw-mt-1_47.lib Opengl32.lib glu32.lib msvcrt.lib msvcprt.lib libgmp-10.lib CGAL-iw-mt.lib blas.lib lapack.lib libf2c.lib libumfpack.lib libamd.lib lemon.lib

    Thanks

    DB:2.54:Low Performance 1f

    Okay, after three very long days of digging inside your compiler, trying

    every switch and technique, building all my additional libraries

    (boost, cgal ....) from scratch, creating new test cases (simple one

    didn't fail), I found the problem: God damn /EHa!

    People, what's wrong with you?! Put it in sticky, burn all your

    documentation and instead distribute one doc with a single bold line:

    DON'T USE /EHa switch with intel compiler, performance degradation is insured!

  • RELEVANCY SCORE 2.53

    DB:2.53:About Hyper Threading 9c



    We have enabled Hyperthreading on one of the host. Which has 2 processors sockets and each socket has 10 cores.

    10*2=20 Physical cores with HT active it should be 40(logical) cores, but in the screenshot(attached) its showing 20 cores only.

    DB:2.53:About Hyper Threading 9c


    Thats because ESXi understands the difference between a physical core and a logical (HT core).

  • RELEVANCY SCORE 2.53

    DB:2.53:Are All 4 A10-6700 Cores Enabled? zk



    I purchased a 700-210 in August 2014 with an A10-6700 APU. The A10 and Envy 700-210 description identifies the A10 APU as having 4 cores, but the Windows Task Manager showsonly 2 cores supporting 4 logical processors. I expected to see 4 cores enabled and 4 logical processors, but maybe 2x4=8 logical processors is possible. What I can not determine is how to enable the additional 2 cores on the A10 using the UEFI/BIOS interface. Can you tell me 1)if the other cores can be enabled and 2) the BIOS page to make that change?

    DB:2.53:Are All 4 A10-6700 Cores Enabled? zk


    Hello,

    Thanks for your followup.

    First, no, I have not made modifications to my PC in terms of the bios. I have upgraded thepower supply,added a graphics card, and hard drives to the system.

    I did contact HP support but the technician only referred me to AMD and offered little else.

    AMD tech support did respond to my inquiryand stated that the A10-6700 "is not a true "quad-core" CPU owing to the fact it has four integer cores and two floating point cores. Windows 8 reads that as it having four hardware threads and two cores, whereas previously Windows 7 would report it as having "4" cores."

    So it appears the discrepancy, if it can be called that, is just how Windows 8.1 classifies the threads with only 2 FPUs available.

    Thanks for your interest and getting back with me.

  • RELEVANCY SCORE 2.53

    DB:2.53:Why Mental Ray In 3ds Max 7 Uses Ony 2 Cores? I Have 8 Cores. 97


    Hi,unfortunately I have to use old max 7 with old mental ray, I wonder whymental usues ony two cores during render - I see only 2 buckets, but I have 8 cores.In mental ray log window i see: CPU: 8, Threads: 2I am using 3ds max 7 on Windows 7 64bit.I tried with vray 1.46 and it usues correct 8 cores.Do You have any ideas?Thanks in advance...

    DB:2.53:Why Mental Ray In 3ds Max 7 Uses Ony 2 Cores? I Have 8 Cores. 97

    Hi,unfortunately I have to use old max 7 with old mental ray, I wonder whymental usues ony two cores during render - I see only 2 buckets, but I have 8 cores.In mental ray log window i see: CPU: 8, Threads: 2I am using 3ds max 7 on Windows 7 64bit.I tried with vray 1.46 and it usues correct 8 cores.Do You have any ideas?Thanks in advance...

  • RELEVANCY SCORE 2.53

    DB:2.53:Qmaster Not Using All Cores For Compressor px


    I have an 8-core Intel MacPro with a virtual cluster set through Qmaster to use 4 cores for Compressor processing. However, when I submit a Compressor batch, Qmaster only uses one core. Changing the settings from 1 core to 8 produces the same results. Anyone know what's going on here?

    DB:2.53:Qmaster Not Using All Cores For Compressor px

    Strangely, I had to check off the "Managed" box next to "Shared" on the Qmaster main screen in order to get things to work, but now it works!

  • RELEVANCY SCORE 2.53

    DB:2.53:Converter 4.X - Multiple Cores Per Cpu md



    I seem to be having a problem converting a VM. The VM is an XP x64 machine with 2 vCPUs and 2 cores per CPU (total of 4 cores). When I try to run converter on it I am receiving an error which states (essentially) that the target/guest OS only supports 2 physical CPUs. Which I obviously know (XP can only run 2 pCPUs). It seems that Converter (and Workstation) are viewing the additional cores as separate and distinct pCPUs...thus thinking there are 4 total pCPUs.

    Is there any way to fix/get around this so that a machine I convert ends up with 2 pCPUs of 2 cores each?

    Thanks!

    DB:2.53:Converter 4.X - Multiple Cores Per Cpu md


    Once edited though you can export from ESXi through the vSphere Client to an OVA

  • RELEVANCY SCORE 2.52

    DB:2.52:2008 R2 Rds Allocates Little Memory Per Session - Apps Slow mp


    I have an RDS server physical on Dell PowerEdge T410, 16 cores, 32Gb RAM.
    With 8-10 RDP sessions connected only 5Gb of physical RAMis used out of the 32Gb available. The apps (Dynamics ERP) are performing sluggishly - at least 50% slower thanin native Windowsclient server on an average desktop. The desktops utilize
    2-4Gb each, so I am having hard time understanding how 8 concurrent sessions only uses 5Gb. These session should be faster than on desktops. LAN/WAN bandwidthis not in the picture, because the same slow speed happens on the console.
    Note: in addition to RDS, this server also has IIS Role.
    Maybe the server is not tuned for RDS?

    DB:2.52:2008 R2 Rds Allocates Little Memory Per Session - Apps Slow mp

    Hi,

    How is issue going on? Can you let us know the present situation?

    Thanks.Dharmesh Solanki

  • RELEVANCY SCORE 2.52

    DB:2.52:Xeon E5620 Vs I5-2300 sf



    Hello,
    first of all excuse me please for my English.

    I am develop some graphics processing application and one of parts of this application it is compressing images by JPEG codec.
    I try to use uic JPEG codec from latest IPP 7.0.5 and obtain very good results on my middle entry desktop PC with Intel i5-2300 CPU.
    Testing JPEG compression performance on 1920x1080 RGB24 source image show next results:
    using 1 compression threads - approx. 55 fps
    using 2 compression threads - approx. 95 fps
    using 3 compression threads - approx. 95 fps
    using 4 compression threads - approx. 91 fps

    This results shown very good compression performance and also they shown that it is useless to make compression with more that 2 threads (but in all cases Task Manager shown that CPU cores was uploaded to 100% so in case 3 and 4 threads, they do useless work :-)).

    But problem begins when I make tests on target server with dual Xeon E5620 CPUs.
    Same testing program which run with same source image shown next results (if all threads run on 1 of CPU):
    using 1 compression threads - approx. 37 fps

    using 2 compression threads - approx. 46 fps

    using 3 compression threads - approx. 50 fps

    using 4 compression threads - approx. 51 fps
    using more that 4 thread shown continuous slowly down results from 50 to 35-40 fps...
    Also, if even one threads run on another CPU then results become more badly (slowdown approx. 10 fps).

    Turning off HyperThreading in BIOS slightly improve results, they grow up on approx. 10 fps, but they still 2 times badly that on consumer i5 CPU... :-(

    So, my question is, are this results expected and normal, or I make something wrong?

    I am expected, that 2.5 times more expensive Xeon CPU will show best results that regular i5...
    I am can understand performance slowdown when working threads run on different physical CPUs (memory acces issues and so on), but when I make test in same conditions on only one of Xeon CPU (using SetProcessAffinityMask) why they 2 times more slowly that i5?
    E5620 has 12Mb cache and source 1920x1080 image only 6Mb, so whole image can be simply placed in cache...

    Thank you in advance.

    Best regards,
    Vladimir.

    PS: I compile uic JPEG codec with latest Intel C++ Compiler XE for applications running on IA-32, Version 12.1.1.258 Build 20111011 with /Ox /QaxSSE4.1 /QxSSE4.1 /Qparallel /Qopenmp switches.
    My desktop PC run under Windows 7 professional 32 bit.
    My server run under Windows Server 2008 R1 32 bit.
    I use ippSetNumThreads() function to set number of processing threads.

    DB:2.52:Xeon E5620 Vs I5-2300 sf


    Hi Vladimir,

    ...using more that 4 thread shown continuous slowly down results from 50 to 35-40 fps...

    In the 2nd case '...if all threads run on 1 of CPU...' there are more context switches onthat CPU.

    ...if even one threads run on another CPU then results become more badly
    (slowdown approx. 10 fps)...

    vTune applicationallows tomonitor athreading performance of an applicationand it allows to
    see how many context switches are donebetween threads, etc.

    ...I use ippSetNumThreads() function to set number of processing threads...

    How many? Also, since you compiled the project with OpenMP support it also creates some number
    of threads, right?

    I would try to get numbers for how many threads are actually created in both cases.

    Best regards,
    Sergey

  • RELEVANCY SCORE 2.52

    DB:2.52:Fortran Cpu Performance And Core Affinity 3k



    Dear All,

    I have two problems that I have been struggling to get around with unfortunately no result. I would really appreciate your help on this.

    I have a fortran code regarding some MDS simulations. The code was happily running on each core (not assigned any core to it but when I manually started 4 instances of the exe file each of them was running exclusively on each of the 4 cores of my PC hence having a 100% processor utilisation and 4 different simulations running on my machine). I have a windows XP 32bit machine with intel quad core processor.

    When I passed the same exe file to some colleagues running windows 7 with an i5 670 processor, even when trying to run 1 instance of the code (1 exe file) their machine ran at a low single and multiple core utilisation. When we increased the number of instances on the same windows 7 machine the core utilisation remained the same (only around 10-25% of the total cpu performance was utilised while windows was starting to park some of the cores of the machine instead of having every core active and running at full performance - like my XP machine). So this is one of the problems emerging.

    Further development of the code required a user input prior starting the simulations (unlike the previous version for which the code was taking all of its inputs via a txt file). The weird thing now is that after implementing the user input routine and having the code running the simulations -as before-, even on my XP machine the core utilisation is at 25% however the amount of instances I run. Even more strangely, when I increase the number of instances running to more than one - as I did with the previous version to have more cores working on different instances of the code- the core utilisation for each instance of the code running is divided so that the total overall processor utilisation remains at most at 25%. Leaving the simulation to run for some time, the processor utilisation drops to nearly zero activity.

    I have really run out of ideas on how to tackle this problem. Even tried fiddling with the affinity options on windows task manager but it doesn't really do anything. I have Qparallel installed and attempted setting the affinity manually but unfortunately with no success - things were quite complicated to understand as my background is not on computing or software development.

    I would love to hear your opinions and ideas on this.

    Many Thanks

    Antonis

    DB:2.52:Fortran Cpu Performance And Core Affinity 3k


    /Qparallel links against the OpenMP dynamic library (libiomp5) by default, so it normally depends on your compiler environment being set to find it.

    If you wanted to choose specific cores to run with libiomp5, you could list them out:

    set KMP_AFFINITY="proclist=[0,1,2,3],explicit"

    You could choose a single core for a single thread. While I doubt this was an intended usage for this environment variable, it may be worth an experiment, given the limited choice of similar options in Windows. If you use this method to run multiple applications together, you must run each in a different shell window, with a different core chosen, as you are attempting to over-ride the effort of Windows to schedule efficiently.

    The usual reason for affinity setting is to improve thread cache locality, for the case where you take responsibility for not causing other applications to compete on the same cores.

    Windows 7 has improved over XP in certain scheduling situations, but (depending on your application) there may be significant advantages in helping it out with affinity settings.

  • RELEVANCY SCORE 2.52

    DB:2.52:Sockets z8



    Hello,

    I'm a bit confused about the Socket, cores in ESXi.

    I'm running SBS2008 on HP ML150 with dual socket quad core cpu.

    In total I have 8 cores but my SBS sees only 4.

    I want to configure 2 sockets each has 4 cores.

    How can I do it in ESXi 4.1

    Cheers,

    Yuri

    DB:2.52:Sockets z8


    Thanks guys,

    Will do that.

    yuri

  • RELEVANCY SCORE 2.52

    DB:2.52:Create A Vm With Maximum Cores Esxi Has? x3



    I have been told by someone that VMware does not support creating a VM with more than 50% of the available cores your host has. For instance I have an ESXi host with 2 cpus each with 8 cores. So I have 16 cores on my host. I would only be able to create a VM with 8 cores to be supported. Even though I am able to create a VM with 16 cores? Is this person crazy who told me?

    DB:2.52:Create A Vm With Maximum Cores Esxi Has? x3


    Just as I thought. I do not know why this person is adamant. I know one less source to rely on information now

  • RELEVANCY SCORE 2.52

    DB:2.52:Macbook Pro - How Many Cores To Designate To Fusion (Vista Ultimate) 9z



    I have a full version of Vista Ultimate which I haven't even opened yet... and a MacBook Pro with an Intel Core Duo (the first intel macbook pro)... and have been using Xp on Boot Camp partition...

    Should I be apply only 1 of the 2 cores to Vista.. or can I apply both...

    Thanks

    DB:2.52:Macbook Pro - How Many Cores To Designate To Fusion (Vista Ultimate) 9z


    I see it now... as far as where number of CPU's are listed...

    Virtual Machine Settings System Hardware Processors...

    and I have only 1 core... and though I haven't run any programs yet.. except for Word Pad.. with only 512RAM and 1 core.. it isn't all that bad having this run on in a window in OSX... I like it better than Xp already.. I was so sick of that blue they had... with its flatness/clunkness... just awful... Royale' theme was a little better but still kind of aggravating... Vista is a little more orderly in its layout than Xp with Xp's popup All Programs submenu's et.. I've seen Vista in machines at stores... and played around with it... and I think it runs more elegantly on the mac in a vm... than on some of the clunky hardware out there... can only get better as things move along... the underdog will be the poor guy who has to run Vista natively on non-mac hardware...

    I mean once upon time the 'best' pc was IBM... and the rest were inferior clones... and now Apple makes the best 'PC'.. and thats only a subset of what the Mac can do.. and what the Mac can do is only a subset of what the company (Apple Inc) is currently doing... Times have really changed... not bad for a company that was on death's doormat a few years ago... and me?.. I get to finally perform any and all kinds of work on the laptop of my choice.. I'm really lucky Apple chose Intel... cause otherwise.. I'd be back to the same dilemma.. and I'm not sure I'd be able to get anywhere in life meaningful, longterm ... I'd be the has-been that never was... at least now.. I have a chance...

  • RELEVANCY SCORE 2.51

    DB:2.51:Strange Lizard Problem zc


    I have a cluster with only two node. The head node is quadcore while the compute node is using dual core( headnode also acts as compute node).
    1. However, when i choose P = 2 and Q= 2 in lizard, it uses all the 4 cores in head node instead of 2 in each nodes. How can I configure it so that headnode is running with 2 cores and compute node also running with 2 nodes?
    2. Btw, when i choose P = 2 and Q = 3, it runs on all 6 cores but the speed drops sharply. The network i use is fast ethernet, does the speed limited by fast ethernet?
    Here's the rough result i get:
    2x2 ~~~~ 22 GFLOPS (it uses only headnode as i can see there is no usage of the network in task manager)
    2x3 ~~~~ 10 GLOPS

    DB:2.51:Strange Lizard Problem zc

    Lizard works on heterogeneous clusters, so I suggest you to run it first on your compute node, in order to compute the best values for Linpack on a single node.
    I don't think you can thru lizard specify only 2 cores on the HN and 2 cores on the compute node.
    HTH
    Xavier

  • RELEVANCY SCORE 2.50

    DB:2.50:Which Esx 5.5 License Allows For 16 Vsmp as



    hi experts

    I have an ESX 5.5 server, with two 8-core CPUs. I have the following license:

    VMware vSphere 5 Hypervisor Licensed for 2 physical CPUs (unlimited cores per CPU). This means I would have 16 cores available to my VM

    But my sole virtual machine only sees 8 CPU cores instead of the 16 that I am expecting.

    EDIT:

    a quick test on creating a vm shows that I can create a vm with 16 cores, but i get an error when i tried to power it on.

    "Feature vsmp not licensed, requires 16 have 8".

    So i guess I have a license issue. what kind of license would get me 16 vsmp?

    END EDIT

    Any help you can provide would be greatly appreciated.

    thanks guys

    davy

    DB:2.50:Which Esx 5.5 License Allows For 16 Vsmp as


    Yes it did. But you didn't have the standard license. The standard license is paid one. You had the free hypervisor license

  • RELEVANCY SCORE 2.49

    DB:2.49:Pardiso Solver On More Than 8 Cores 93



    Hello sir,
    please tell me whether pardiso solver can run on more than one 8 cores machine
    or it uses only 8 cores what ever number of cores present in the machine.
    any processor where pardiso isefficient?
    Is there any other solver faster than pardiso?

    DB:2.49:Pardiso Solver On More Than 8 Cores 93


    quote "processor where pardiso isefficient?".

    Internally PARDISO is based on BLAS3 and LAPACK routines

    which are highly optimized for the all latest IA architectures( see the list of

    all supported processors into Release notes)

    --Gennady

  • RELEVANCY SCORE 2.49

    DB:2.49:Vm Does Not See 4 Cores In Task Manager kf



    Hi, I have installed test SCCM 2012 R2 and SCOM 2012 R2 virtual servers running Windows Server 2012 R2 - vSphere 5 infrastructure. I set these two to have 1 socket with 4 cores. However in task manager I can not see those 4 cores, only one is displayed (picture in attachment) although there is an info that machine has 1 socket and 4 virtual processors . On other test server running Windows Server 2008 R2 I set up it to have 1 socket with 2 cores and both cores are displayed in Task Manager.

    DB:2.49:Vm Does Not See 4 Cores In Task Manager kf


    Thank you Porto, I have forgotten this, on win 2k8r2 it is default setting.

  • RELEVANCY SCORE 2.49

    DB:2.49:Use Of Only 25% Of Cpu With Auto-Parallelization 9z



    Hi,

    I'm using Intel Visual Fortran Compiler Pro 11.1 to compile my code on an Intel core i5 architecture.

    Because I would like to parallelize the exectution of the programm i use the "-c /Qparallel" option at the compilation step, and the "/Qpar-report" option outputs that almost all the loops have been parrallelized.

    But when i execute my programm, only 25% of the total CPU ressource is allocated to the reffering process, enven if all the proccessors seem to work simultaneously. I've tried to set the priority of the process at "/high" when i execute the programm, with no effects, and the affinity is set by default on all the 4 processors.

    I don't know what is going wrong, thanks in advance for any help.

    JB

    DB:2.49:Use Of Only 25% Of Cpu With Auto-Parallelization 9z


    You indicate your version of ifort Ver 11.1. I have found a significant improvement in /Qparallel changeing to Composer XE 2011, which has been superceeded by Ver 2012 and possibly Ver 2013.
    I would recommend you upgrade from Ver 11.1, as I found problems with that version.

    John

  • RELEVANCY SCORE 2.49

    DB:2.49:Virtual Center 1.4.1 See Only 2 Cores Insted Of 4 77



    Hi,

    I have one VMware Server 1.4, installed onto Debian Etch host, the machine is Dual CPU, each CPU is an Intel Dual-Core Intel Xeon processor 7120M 3.0 GHz, so the whole system is 2 CPU, 4 Cores.

    I am evaluating the VMware Virtual Center 1.4.1 and have noticed that in the summay my sistem is described as 2 CPU, 2 Core - see attachment for details. Why is that so? Does my VMware Server actualy see only 2 Cores and can not take advantage of all of the four cores? The operating system (Debian Etch) see all 4 cores and is hyper-threading enabled - so all 8 logical processor are available and active (see the other attachment wich is the output of the "top" command).

    Does the fact, that VMware migh see only 2 cores affect performance, considernig that Operating system still see all cores (and the operating system is the one that schedules the processes)? Further more, are there any paramteres for the Server configuration file (/etc/vmware/config) that operates with those core-specific settings? I do not have the Web management console installed on my server so I can not check, if via the Web console those settings are available or not.

    Kind regards, Marko.

    DB:2.49:Virtual Center 1.4.1 See Only 2 Cores Insted Of 4 77


    Hi,

    So, nobody is having similar issues? I just want to know if this is an cosmetic issue of the VirtualCenter 1.4.1 or it is actualy an problem with VMware Server and as such causing possible performance draw-backs... I also installed VMware Server Web Management Console but there no such informations/settings are available.

    Kind regards, Marko.

  • RELEVANCY SCORE 2.48

    DB:2.48: Qosmio X500 Uses Only Two Cores When Hyperthreading Is Turned Off aj


    Hello,

    I'm running Windows Server 2008 R2 as I'd like to use the machine as a workstation (not for gaming). Using Hyper-V role was not successfull with hyperthreading turned on, lot of crashes (BSOD) appeared.

    I have turned hyperthreading off in BIOS but since then I can only see two cores instead of 4 cores (using Device Manager or Task Manager). i720 CPU is natively 4 core processor so it can't show just 2 cores if everything is ok. Also the notebook is noticably slower.

    I've checked the BIOS and also found strange thing. It has an option "Enable Intel Dynamic Accelleration" but that technology relates to Core Duo CPUs, not to latest quad core CPUs (like i720).

    Toshiba, I want all my 4 cores, not just 2 cores. Someone should try and prove I'm right.

    Qosmio BIOS story is definitely not finished yet.

    Radek

    DB:2.48: Qosmio X500 Uses Only Two Cores When Hyperthreading Is Turned Off aj

    i have a Qosmio X500/02G

    Part Number - PQX33A-02G00J

    I am having problems with playing games on it, i was told to disable hyper threading so when i rebooted i disabled multi core and reset and nothing, didnt help what so ever accept to slow down the computer alot, the laptop is fairly new and i was told it is the ultimate for gaming, however it has been the ultimate pain in the bottom and i feel as if i got ripped off,

    can anyone advice if disabling hyper threading is infact the correct thing to do or should i take it back to the place i bought it and put my foot down on them and get a desktop that actually works with games with out freezing or massive lag during call of duty modern warfare 2, and i was playing in single player....

    Any help would be appreciated, you can contact me on Email: a.marsters@hotmail.com as well if you have any extra info. Thanks.

    Line:

    Qosmio X500/02G

    Part Number - PQX33A-02G00J

    General

    CPU Intel® Core™ i7 processor 720QM (1.6GHz/2.8GHz, 1333MHz FSB, 6MB L2 Cache)

    Operating System Genuine Windows® 7 Home Premium (64bit)

    Screen Size 18.4” Widescreen Full HD TruBrite® Display (1920 x 1080)

    Memory 4GB DDR3 (2GB + 2GB) (1066MHz) expandable to 8GB

    Storage 1000GB (500GB + 500GB) (5400rpm) SATA

    Graphics NVIDIA® GeForce® GTS 250M (2298MB Total: 1GB DDR5 discrete memory + 1274MB shared memory)

    Optical Disc Drive Blu-Ray RW/DVD SuperMulti Double/Dual Layer Drive

    Speakers Premium harman/kardon® speakers

    Sound Harman/Kardon Speakers

    Security 3D Hard Drive Shock Sensor, Fingerprint Reader, Kensington® cable lock slot for optional theft protection devices

  • RELEVANCY SCORE 2.48

    DB:2.48:Quad Core Cpu Only Showing 2 Cores 33



    I recently got a New HP decktop, aP6-2378, and it came with an AMDQuad-Core A8-5600K processor. When I look at the task manager under Performance: CPU it says "cores: 2"

    Does this not reflect the quad core processor in the task manager?

    Thanks,

    DB:2.48:Quad Core Cpu Only Showing 2 Cores 33


    Hi,

    The "parked" CPU marking is a Windows 7 nomenclature.I haven't seen this with Windows 8 on my quad core. It might be because I am using a "high performance" power plan instead of the "power saver" plan.

  • RELEVANCY SCORE 2.48

    DB:2.48:Hyperthreading Turned Off In Bios, But Hpc Still Using It....How Do I Stop It? zc


    I have hyperthreading turned off in the bios on my servers. There are 2 dual core processors in each of them. When I tell HPC to use 8 nodes, or 16 sockets HPC reports to me that it is using 16 cores on each machine, or 128 cores. How can
    I stop HPC from using hyperthreading?? Note that when I open the task manager on the servers and check out the performance graphs it is only showing me 8 cores.
    Is this just an error in HPC telling me it is using 16 cores, or is something else going on here I am unaware of?
    Craig

    DB:2.48:Hyperthreading Turned Off In Bios, But Hpc Still Using It....How Do I Stop It? zc

    I think I found the issue. I needed to reset the servers. When we ran the monthly upgrade and rebooted the servers all was well.
    I also found thishttp://scorpiotek.com/blog/?tag=hpc which I plan to try in the future should this problem arise again.

  • RELEVANCY SCORE 2.48

    DB:2.48:How To Limit Number Of Mr Threads On One Machine? sx


    hello,how do I limit the number of threads/cores that xsi gui uses on my workstation? I have 8 cores but only want mental ray to use 6 so that I can run other apps while test rendering.is there an environment variable in the setenv.bat?thanks in advance,mike

  • RELEVANCY SCORE 2.48

    DB:2.48:Single Cpu With Multi-Core In Sql Server 2008 R2 Express am


    I have two servers, both with single CPU, multi-core XEONs (an E5506 and an E31270). SQL Server 2008 R2 Express on the E5506 server uses all its four cores. But on the E31270 it only uses one of the cores.
    Server 1
    Xeon E6605, 8GB RAM, Windows 2008 R2 Standard 64 bit, SQL 2008 R2 Expresswith Advanced Services
    Server 2
    Xeon E31270, 16GB RAM, Windows 2008 R2 Standard 64 bit, SQL 2008 R2 Expresswith Advanced Services
    I've checked across the web and generally the consensus is that, whilst neither will use multi-CPU,both should be able to use multi cores (so the E5506 server is doing things correctly).
    Automatically Set Processor Affinity is on and I'm not after Parallelism, just lots of queries coming in from different sources being ran at the same time on different cores (like Server 1 already does).
    Any ideas on why this better more recent server only uses the one core whilst the older server uses all of them?
    Could it be that the CPU is reporting itself slightly differently so SQL thinks it's a multi CPU rather than a multi-core?

    DB:2.48:Single Cpu With Multi-Core In Sql Server 2008 R2 Express am

    New week, any new ideas? This is still not working right. :-/

  • RELEVANCY SCORE 2.48

    DB:2.48:Missing 2 Cores 1k


    Issue resolved - I figured it out. Unchecked box for cores in msconfig

    CPU-Z shows my windows 7 to only have 2 cores and 4 threads. - Its supposed to have 4 cores and 8 threads (i7 2600k) Also, my computer's performance has dropped. The cause of problem = **** brother who thinks its funny to underclock / disable cores on my pc.
    (Hes disabled multicore on my laptop before which made it really fen slow) Bios shows that All cores are enabled with hyper thread support. Msconfig shows all 4 cores enabled on start up. Hardware Manager shows all 8 threads

    DB:2.48:Missing 2 Cores 1k

    Hi,

    Good to know you were able to find the actual problem with the computer.

  • RELEVANCY SCORE 2.48

    DB:2.48:Vmware Server 2.0.1 Only Recognizing One Physical Cpu? f7


    My vmware 2.0.1 server host (CentOS 5.3 x64) has 2 x 2 cores. vmware server, when I log into the :8333 interface, only recongizes 1 x 2 cores. I am pretty sure all CPU's are being used. The total Mhz under 'Usage' can go much higher than the total Mhz of two cores. Any ideas what is going on?

    Anyone else see this?

    - henrik

    DB:2.48:Vmware Server 2.0.1 Only Recognizing One Physical Cpu? f7


    OK, I will partially answer my own question, but I think there is a bug in 2.0.1 that needs to be addressed.

    I had turned off hyperthreading on the CPU's. As soon as I turned it back on, vmware 2.0.1 report 2 x 2 CPU's. I am speculating now.... it is almost as if vmware sees that the CPU are capable of hypertheading and it then halves the number of CPU to take into account hyperthreading. It seems it does this even when hyperthreading is turned off, giving a wrong CPU count.

    - Henrik

  • RELEVANCY SCORE 2.47

    DB:2.47:Operation Of New Xe Inspector 2011 When Memory Resources Are Low p7



    I have an intermittent issue that occurs when running the mentioned tools.

    Myapplication runs fine with any of the IDE package, however randomly looks like the new XE Inspector 2011 Beta acts as it is hunging.

    The application has been extensively optimized and tested with the Current Parallel Studio tools (not Beta) and it had to issuesreported

    After fewattempts I was able to run with the Task Manager on, which reports that I had 99-100% utilization across all 8 cores and memory was used as 2.96GB (Application was compiled for large memory usage 3GB iLARGEADDRESSAWARE)

    I believe thatduring this run the memory resource werereduced to basically nothing, producing the mentionedissue.

    My Question is:

    How shouldthetool be operating? Shoud some sort of message popping out somewhere or what ?

    In the past VTuneand the Thread Checker were able to recover by purging (I believe) the oldest events or something of that affect

    As I said, is not very repeatable, but when it happens I am forced to restart the machine.
    I am running on a Dell Precision R5200 (Dual-Quad Xeon) a 32 bits application, in a 64 Bits Win 7 environment

    I thought that I was over utilizing the CPU cores (since I am running with the Intel compiler and I had the Properties C/C++ \\ Optimization \\ Enabled . See \\Qparallel)

    Turning this off it helped for few runs. Now the issue has resurfaced

    Thanks for any clarification you can supply that would help me to stop this issue

    DB:2.47:Operation Of New Xe Inspector 2011 When Memory Resources Are Low p7


    Hi Peter,

    The machine uses 4 Gig.
    Thanks for the hints.

    I was trying the capability of the Memory Leak detector new features and the New Thread Inspection tool. Looking for a memory block leak of 260k (I later discovered that it was created with a"new" statement - I hope this can be of help)

    The tool did not found it, though it was obviously there - Microsoft VS2005 reported it at closing
    The tool insteadreported some minor resources leaks that I did not know about and I cannot repair since part of some 3rd party library

    Eventually I did find and repair the leakwith some good old manual code Inspection
    Thanks for everything

    Sal

  • RELEVANCY SCORE 2.47

    DB:2.47:How To Use 2+ Core Cpu? zj


    Hi, In running a Load Test how do I get it to use all the CPU cores on my computer? How do I get an Agent to use all the cores? Right now it uses only 1 of out 2 cores and maxes out at 50% _TOTAL. Thanks, Kevin

    DB:2.47:How To Use 2+ Core Cpu? zj

    Hello Kevin,Rig should be the right choice for you.For more detailed information about rig, you can refer to the following article:http://msdn.microsoft.com/en-us/library/ms182634.aspx

    Please remember to mark the replies as answers if they help and unmark them if they provide no help. Send us any feedback you have about the help from MSFT at fbmsdn@microsoft.com.

  • RELEVANCY SCORE 2.47

    DB:2.47:Problem With Openmp Hello World! fd



    Dear all,

    I have some problems in compiling the following prototype. I execute the attached simple program using multiple cores. Problem is that I am all the time getting just one instead of multiple 'Hello World's.I have used -openmp -Qparallel -fpp settings.

    Thanks in advance.

    DB:2.47:Problem With Openmp Hello World! fd


    Dear Lorri,

    Special thank for your usefull comment. Problem solved!

    thanks everyone :)

  • RELEVANCY SCORE 2.47

    DB:2.47:Win7 Hangs After Unlocking Cores zx




    Ive unlocked the cores of a Phenom X2 550 on a 785GTM-E45. It shows up as an X4 in the bios after unlocking the cores. However Windows 7 Ultimate hangs at the splash screen. If I set it back to using only 2 cores it boots fine. I double checked and I do have the latest version of the bios that is available to the automatice update utility.

    Ive tried reinstalling and the same thing happens - hang during splash screen after first reboot of install.

    Ive booted into safe mode and after loading the initial drivers I get a STOP 0x1a.

    Id greatly appreciate hearing any ideas as to how to fix this please!!

    Thanks!

    DB:2.47:Win7 Hangs After Unlocking Cores zx


    Great. Care to let us know how high have you tried?
    The spec states somewhere around 1.4, ahh not sure, just curious...

    A 3core for awesome enough!

    PS: maybe next time you see grayed out options, you can try the old fashioned page up/page down first.

  • RELEVANCY SCORE 2.47

    DB:2.47:Replication Performance x7


    I have questions about Timesten replication performance.
    After I configured the Timesten as active/standby (return receipt) pair from standalone server, the throughput is reduced to 1/3.
    Then application updates an AWT cachegroup and a in-memeory table.
    The active timesten machine has 16 Cores (Intel Xeon 3.4 GHZ).
    And the standby timesten machine also has 16 cores (Intel Xeon 2.9GHZ).
    And I observed that when testing, in the standby timesten machine, only 2 cores are working.

    what is the best practise for configuring replication scheme? How about the performance lose after configuring replication?
    thanks

    Edited by: ramon_lmj on May 9, 2010 12:38 AM

    DB:2.47:Replication Performance x7

    As you say, the intuitive expectation is that Return Receipt will perform better than Return Twosafe. Under very specific conditions that is true (legacy replication, transmit non-durable mode) but in most situations, and always for active/standby pair replication, return twosafe has significantly better performance than return receipt. This is because in most cases Return Receipt includes a synchronous disk write as part of the transmission of each batch of replicated transactions (in order to ensure full recoverability in all failure scenarios). For Return Twosafe, this disk write is not needed and so is not done and hence the performance is better.

    Your observation about the limitations of the single threaded replication model are correct; this has been the case in TimesTen for a very long time. The good news is that we are now addressing this; the 11.2.1.6.0 release includes fully parallel replication for legacy asynchronous replication (for workloads that have the required characteristics) and it is planned to expand this support to active/standby pair and return receipt/twosafe in a future major release of TimesTen.

    In order to be sure that everything is fully optimised you should ensure that all tuning parameters are set for optimal replication performance. For example, you should ensure that LogBufMB is set much higher than the default 64MB and that LogFileSize is increased so that it is equal to LogBufMB. You need to be sure that the value in SYS.MONITOR.LOG_FS_READS is not increasing as you run your workload.

    Once everything is fully optimised, if the performance is still not adequate then the only solution is to split the datastore into multiple datastores and partition the data across these stores as this will then increase the number of threas used overall for replication (1 per datastore).

    Chris

  • RELEVANCY SCORE 2.47

    DB:2.47:Http://Ark.Intel.Com/Products/65509/ Has 4 Cores, Windows 8 Detects And Seemingly Uses 2 Cores, How Do I Enable The Other Cores? c1


    Hello TechNet users
    I find myself in a bit of a concern, I have searched the various support forums of many sites and have come to a conclusion that this is an OS problem. I have Microsoft Windows 8 (6.2) 64-bit (Build 9200) and it seems that for some odd
    reason, the OS only uses 2 cores instead of 4.
    CPUZ and Core Temp displays 2 cores and 2 threads

    DB:2.47:Http://Ark.Intel.Com/Products/65509/ Has 4 Cores, Windows 8 Detects And Seemingly Uses 2 Cores, How Do I Enable The Other Cores? c1

    Run msconfig.exe, go to boot and uncheck the option to limit the usable processors.

    A programmer is just a tool which converts caffeine into code

  • RELEVANCY SCORE 2.46

    DB:2.46:Any Tools To Measure Cpu Speed ak


    My notebook uses following processor, by default setting, there are4 Threads with 2 Cores,when I disable the multi-processing core within BIOS, there is only 1 thread available, but I assume there should be 2 threads available, because there are 2 physical
    cores for this CPU. Does anyone know why there is only 1 thread instead of 2 threads?

    Furthermore, I assume that Hyper-thread technology is disable, each each thread of core should be double in performance, and I would like to measure the CPU speed difference with multi-processing core enable / disable.

    Does anyone have any suggestions on any tools to measure CPU speed?

    Thanks in advance for any suggestions :

    Intel® Core™ i5-2467M Processor

    DB:2.46:Any Tools To Measure Cpu Speed ak

    Sounds like you're looking for benchmark software then -
    http://www.cpubenchmark.net/

    Regards,

    Patrick

  • RELEVANCY SCORE 2.46

    DB:2.46:Windows Task Manager And Cpu Usage p9


    Recently started overclocking using Intel's Extreme Tuning Utility which reports numbers of cores being used, etc. Just to see how my video editor was utilizing cores, I open Intel XTU and Windows Task Manager at the same time.

    Win 8.1 Pro with Media Center 64bit with latest updates.

    When I turn on hardware acceleration in my video editor, Intel XTU reports only one core used. This mode uses the GPU to render certain effects.
    When I turn off hardware acceleration, Intel XTU reports all four cores used.

    Windows Task Manager shows all 8 virtual cores in use both times. So why does Task manager report that all 8 'virtual cores' are being used when Intel XTU reports only One core being used?

    The answer may be over my head, but hopefully there is an explanation. Just curious because it doesn't make much sense.

    DB:2.46:Windows Task Manager And Cpu Usage p9

    Hi,
    Could you please share us an screenshot of the compare result?
    What is the result when we view the core information for other programs or precesses?
    In addititon to the two tools, have you test this via other tools? What is the result?Yolanda Zhu
    TechNet Community Support

  • RELEVANCY SCORE 2.46

    DB:2.46:Upgrade From Core2duo To Quad Core Only Shows 2 Cores In Task Manager m8


    I recently upgraded my Vista64 Ultimate from an E8600 CPU to a Q9550 CPU.

    In the task manager, it only shows 2 cores.

    Device Manager shows all 4 CPU's.
    Bios shows all 4 CPU's.
    My Computer Properties shows Intel(R) Core(TM)2 Quad CPU Q9550 @ 2.83 GHz 2.83 Ghz

    Any ideas on how to correct this?

    Reinstalling the OS is not an answer it's an excuse for not solving the issue.

    DB:2.46:Upgrade From Core2duo To Quad Core Only Shows 2 Cores In Task Manager m8

    Hello Halima,

    I ran sfc.

    Microsoft Windows [Version 6.0.6002]
    Copyright (c) 2006 Microsoft Corporation. All rights reserved.
    C:\Windows\system32sfc /scannow
    Beginning system scan. This process will take some time.
    Beginning verification phase of system scan.
    Verification 100% complete.
    Windows Resource Protection did not find any integrity violations.

    By making it just one graph for all cpu's, am I just hidding the fact that is not seeing all 4 processors?

    Thanks

  • RELEVANCY SCORE 2.46

    DB:2.46:Single Vs Multithreaded Performance When No Spare Cores Are Available 89


    I've been running some multi threaded operations on an unsorted int array such as finding highest number by searching the array using 2 threads on a 2 core laptop. I get nearly a 2X speed up using 2 threads, but lets say that 1 of the cores was used up by another thread running another task. Does it make any sense to still use 2 threads on the array rather then 1 if only 1 core is available to use. Would it be better to have the method check how many cores are free and then assign the correct number of threads for the operation to match the number of free cores at that point in time; rather than just giving the OS thread scheduler more threads to juggle between a single free core?

    Is this type of thinking used with concurrent operations on Java collections better than simply hard coding the number of threads to use for each operation regardless of the number of cores actually available when the operation is being run?

    If the other task using the other core is a high priority task and the array search operation uses 2 threads when only 1 core is available will it impact the other tasks performance?

    DB:2.46:Single Vs Multithreaded Performance When No Spare Cores Are Available 89

    fireandspike wrote:
    Yea, I often used the idea of use as many threads as there are cores on your system for parallel operations, but if you use that mantra on each of the many algorithms in a program that do parallel operations on collections, then it all adds up and you can end up with many, sometimes 100 times as many threads wanting to run as cores available because there are likely to be many unrelated methods running at the same time each doing parallel operations on collections.So have them share a single ExecutorService.

    With kind regards
    Ben

  • RELEVANCY SCORE 2.46

    DB:2.46:Will Sql Server Express 2005 Support Multiple Cores On A Single Cpu How Do I Set It So That It Recognizes Multiple Cores 1j


    I have SQL Server Express 2005 installed but it only uses 1 core of a dual core processor. How do I change this?

    select *
    from sys.dm_os_sys_info

    Produces 1 CPU_COUNT and 1 Hyperthread_ratio even if we have 2 dual core processors on our server that is on VM.

    Thanks,
    Ryan

  • RELEVANCY SCORE 2.46

    DB:2.46:Backend Signals Error With Multi-Processor Compilation 7a



    A very strange error has started to show up recently when using Intel C++ included with Intel Parallel Studio 2011 in Visual Studio 2010. Searching for this error in the forums suggests that it may be caused by using options like /Qipo and /Qparallel together, but this project has none of those options set. Even more, the error only shows up when I use many threads for Multi-processor Compilation. If I keep this number low (1 or 2), the error does not pop up. The whole process takes longer, though.My PC has a Core i7 with 4 cores and HT, but setting the number of simultaneous files to compile to 4 or 8 triggers this problem somewhere during the build process. I thought the problem could be caused by lack of RAM (3GB XP limit), but it does not seem to be the case. Now I am using Windows 7 64 bits with 8GB of RAM, and the problem still pops up.The strange thing is that this problem just decided to show up out of nowhere, and it does not seem to be linked to any specific file. As mentioned before, with 1 or 2 files at a time it does not occur.Do you have any ideas as to what may be happening?

    DB:2.46:Backend Signals Error With Multi-Processor Compilation 7a


    I would love to send you a file in order for you to see what is going on, but the error is highly inconsistent. As a matter of fact, yesterday I made some changes, and now it compiles with 8 threads just fine. If I can find a consistent way to reproduce it, and blame it on a specific file, I will do what I can to help you find the culprit.Thanks.

  • RELEVANCY SCORE 2.46

    DB:2.46:Cores Vs Threads In Vmware 17



    I have done a few searches but didn't find the answer to this. How does VMWare handle Cores vs Threads. An example would be a Core i7 CPU that has 4 Cores with 2 threads each. The host os registers this as 8.

    If in VMware I select 4 cores, is that taking all of the cores (yikes) or just 4 threads?

    If I select 2 cores, my guest os does not report 2x2 it only reports 2.

    Thanks!

    DB:2.46:Cores Vs Threads In Vmware 17


    I have done a few searches but didn't find the answer to this. How does VMWare handle Cores vs Threads. An example would be a Core i7 CPU that has 4 Cores with 2 threads each. The host os registers this as 8.

    If in VMware I select 4 cores, is that taking all of the cores (yikes) or just 4 threads?

    If I select 2 cores, my guest os does not report 2x2 it only reports 2.

    Thanks!

  • RELEVANCY SCORE 2.45

    DB:2.45:Windows Xpx64 On Esx 3 xf


    I have a physical machine with Windows XP x64. That physical machine works with 2 quad-core processors and recognizes 8 cores. When creating a virtual machine on ESX recognizes only 2 cores. What do I need to make the virtual machine can see a total of 8 cores?. I am working on a Sun Fire X4600. Thank you

    DB:2.45:Windows Xpx64 On Esx 3 xf


    Windows XP x64 is limited to 2 CPU sockets, thus will use 8 cores on a physical box because it can see that the box has 2 CPU sockets. In a VM, ESX does not present the physical CPU or socket count up to the VM so XP x64 is only able to use two virtual CPUs (which ESX will then schedule to run on two free CPU cores). ESX is currently limited to 4 virtual CPU VMs so the most any VM could use today is 4 CPU cores.

  • RELEVANCY SCORE 2.45

    DB:2.45:Core Generator: Regenerate Virtex-2 Cores mj



    I have an existing design that is implemented on a Virtex-2 device.

    I am currently porting this design to a Spartan-3A DSP device.

    Do I have to regenerate my cores (FIFOs, Dual Port Rams, etc)?

    Thanks

    DB:2.45:Core Generator: Regenerate Virtex-2 Cores mj


    Some clarification.

    If I try to regenerate a RAM block There is NO option to Regenerate (under current project settings)

    If I try to regenerate a FIFO block There is an option to Regenerate (under current project settings)

  • RELEVANCY SCORE 2.45

    DB:2.45:Question On Sockets Vs Cores d9



    Is there any technical/performance difference when allocating additonal cores per socket vs more sockets?

    An example would be:

    1 socket with 2 cores VS 2 sockets with one core

    I'm just trying to understand the difference and if there is really any considerations for this other than licensing on the guest end. Thanks!

    DB:2.45:Question On Sockets Vs Cores d9


    It will be more clear when we will see some comparison. A multicore CPU combines multiple independent cores on a single physical CPU.Most virtualization software vendors sell licenses by the socket and not by the number of cores that the socket has, so multicore processors are fantastic for virtualization

    An insight into dual core and quad core CPUs.

    quad-core:-

    The first is that most virtualization software is licensed by the number of sockets in a server and not the number of cores you have,and having more cores in a host server gives the hypervisor CPU scheduler more flexibility when trying to schedule CPU requests that are made by VMs.Having more cores available makes a CPU scheduler's job easier and improves VMs' performance on a host.

    dual core:-

    if you plan on assigning VMs a single virtual processor, dual-core processors can be a better option, because single vCPU VMs are easier for the hypervisor to schedule than multiple vCPU VMs.

    PS: A dual-core CPU is roughly 50% faster than a single-core CPU (not 100%, as you might expect), and a quad-core CPU is only about 25% faster than a dual-core CPU.

    HTH

  • RELEVANCY SCORE 2.45

    DB:2.45:6-Cores Limitation With More Cores Hw jc


    Hi everybody,

    does anybody know what happens if I replace an existing "2 Prozessor with 6-Cores" Host with vSphere Enterprise License (Limit to 6 Cores per Processor) with new HW with more Cores? The new G7 from HP has at least 8 Cores, so can I use my existing License with a limitation to 6 Cores (only 6 Cores per Prozessor used) or is it a must to Upgrade to Enterprise plus? I just want to know if it works with Enterprise Licenses or not?

    Thank you

    Sigurd

    VCP

    DB:2.45:6-Cores Limitation With More Cores Hw jc


    my guess is, and this is pure speculation, is that it will work, but is based on the honor system. I don't see how anything beyond 6 cores can be masked by your feature set (licensing information). However, since I've never tried it may be the case were if you are licensed for 6 cores per, then the remaining get masked somehow.

  • RELEVANCY SCORE 2.45

    DB:2.45:Devenv.Exe Only Uses One Core? xm


     
    Whenever i switch from code view to design view one of the cores (on Core 2 6600) max out for 10-30 seconds. The second core of the CPU is not utilized at all. During that time Visual Studio does not respond. Can something be changed to allow devenv.exe to utilize all cores available so this wait time can be decreased?
     
    This is running on a Core 2 6600 with 2 GIG ram.

    DB:2.45:Devenv.Exe Only Uses One Core? xm

    Moving this thread to a more appropriate forum. This forum is for questions pertiaining to using the visual studio debugger.

  • RELEVANCY SCORE 2.45

    DB:2.45:Sql Server Performance Impact By Physical Processor Sockets. s8



    I know that SQL Server licensing is only concerned with physical processor sockets, not physical cores, or logical cores.
    What is the Impact on SQL Server Performance?
    If I configure SQL Server with 1 physical processor socket with 8 physical cores instead of 2 physical processor sockets with 8 physical cores.
    Thanks Regards
    Malatesh KakadeMalatesh Kakade

    DB:2.45:Sql Server Performance Impact By Physical Processor Sockets. s8


    Hello,

    Two physical processors of 4 cores each providing 8 cores in total are faster (provide better performance) than 1 processor of 8 cores, assuming similar speed on processors.

    Hope this helps.
    Regards,

    Alberto Morillo
    SQLCoffee.com

  • RELEVANCY SCORE 2.45

    DB:2.45:Web Logic Licensing For Multi-Core Processor Machine To Host Adf Applicatio zd


    Hi Experts,

    I have a VM with 2 CPU each having 2 cores i.e. 2 Physical CPUs and total 2*2 = 4 CPU Cores. I would like to get Web Logic Standard Edition Licensing to build an ADF Application (using 11.1.1.5.0) on this VM.

    Since I have only 2 CPUs (with 2 Cores each), how many processor based license should I go for? 2 or 4?
    Please share your thoughts.

    Thanks in advance,
    Rathnam

    Edited by: rathnam on Nov 2, 2012 3:33 PM

    DB:2.45:Web Logic Licensing For Multi-Core Processor Machine To Host Adf Applicatio zd

    As far as I know you will pay per core, so 4 cores in your case.
    But like Joonas Linkola said, check Oracle Sales to be 100% sure.

  • RELEVANCY SCORE 2.44

    DB:2.44:Premiere Elements 8 Only Uses One Core zx



    Heya everyone

    On my computer here, I did install Premiere Elements 8. However it runs really slow despite the 8GB ram and an i7 processor. Then I noticed, that of the eight processor cores, it only uses one! And this for 100%!

    I have no clue what's wrong with Premiere Elements, All other programs run without a problem and use all cores.

    In the Task Manager, Premiere Elements is allowed to use all cores.

    Anyone may know what could be wrong?

    I did find some entries here with similar problems but they didn't get an answer or the answer got deleted :/

    Thanks in advance

    DB:2.44:Premiere Elements 8 Only Uses One Core zx


    We're all just users here. It's probably best for you to take this one up with Adobe Technical Support direct. The product definitely does use all cores when necessary (I posted a screen dump at one point showing all four cores on my PC at 100% during a render). It could always be that your machine (massively specified by comparison to mine) doesn't need more than the one core.

    Cheers,-- NealeInsanity is hereditary, you get it from your children

  • RELEVANCY SCORE 2.44

    DB:2.44:How Does Adobe Assign Cores With Htt? m7



    Hi guys,

    I will soon be purchasing a computer and I am pretty set on an i7 3770 vs an 8 core Xeon based off of everything I've read. My only thing is, I know that the OS will recognize the i7 as 8 cores due to HTT when I put multiprocessing on in AE. My question is: is there a way to make JUST the logical cores reserved for other programs or background processes? I know Adobe likes physical cores over virtual ones so if I reserve 2 of the 8 cores to other programs would it take one physcal core and one logical core or two logical cores? because I would prefer that it takes 2 logical cores and leaves all 4 physical. If not then are there any programs/configurations to make it that way? I really just dont see a benefit to jumping up to an 8 core Xeon to get more physical cores even tho I am using heavy effects, filters, and coloring. Thank you for your help!

    DB:2.44:How Does Adobe Assign Cores With Htt? m7


    You could just turn of HT in your BIOS/ motherboard power managent driver.

    Mylenium

  • RELEVANCY SCORE 2.44

    DB:2.44:Vmware Server 2.0 Does Not See 8 Cores On Intel I7, Only 4 p9


    I have a new system that Im building with an EVGA X58 SLI MB, Intel Core i7-920. I have opensuse 11.1 x86_64 installed with VMware-server-2.0.0-122956 installed.

    All 4 cores are enabled as well as hyperthreading. Catting /proc/cpuinfo shows all 8 processors. When I reboot into the XEN kernel, it also recognizes and can use all 8 cores. However VMware Server only shows 4 cores in the administration console. I am wondering why I'm not seeing all 8 cores?

    DB:2.44:Vmware Server 2.0 Does Not See 8 Cores On Intel I7, Only 4 p9


    Thx for the reply.

    I've always been a semi-fan of vmware server cuz of it's simplicity, as well as the biggest reason being that it's free.

    Our IT budget's not that big so can't afford the full blown licensed versions, hence our use of vmware server.

    Biggest thing is though, our hardware config is made so it's expandable

    Supports: 2x xeons

    12x4gb = 48gb ram

    running on raid 6 with 3ware 8650SE 8 port (7 on raid 6 + 1 on hot-spare)

    Though if it won't be able to fully utilize my cpu's that's the biggest beef that I'll have

  • RELEVANCY SCORE 2.44

    DB:2.44:Qparallel Does Not Work cx



    I am using Intel Fortran 10, and trying to learn parallelization with the compiler. I am using a sample of codes from Intel website as follows: PROGRAM TEST PARAMETER (N=10000000) REAL A, C(N) DO I = 1, N A = 2 * I - 1 C(I) = SQRT(A) ENDDO PRINT*, N, C(1), C(N) END PROGRAM TEST I turned on Qparalle and Qpar_report and expected the compiler can parallelize the codes and give some messages, However, no messages that are generated after compiling to show the codes have been parallelized. Furthermore with or without parallelization, the executable still uses one core thought my machine is due-core.

    DB:2.44:Qparallel Does Not Work cx


    I suppose /Od would be the prime suspect in suppressing auto-parallelization. /iface:cvf should be used only if necessary (e.g. in an attempt to make a combined build with CVF compatible objects, when you can't do a complete rebuild including allowing C or C++ to use the default C_DECL interface).

  • RELEVANCY SCORE 2.44

    DB:2.44:How To Change Number Of Processors / Cores m9



    I have virtual machines that I have to move periodically between 3 main host computers I use:

    1. Intel Core2 Quad CPU with Windows 7 Home Premium 64-bit - 1 processor with 4 cores

    2. Intel Core i7-2630QM CPU with Windows 7 Home Premium 64bit - 1 processor with 4 cores

    3. Intel Core2 Duo T7700 CPU VT with Windows XP 64 bit - 1 processor with 2 cores

    The host computers run VMWare workstation 7.

    Most of my virtual machines use XP 32 bit, and were originally created for my platform 3.

    When I move my machines between computers I find that the Virtual Machine Settings for my processor change in (to me)an unpredictable way. Sometimes it shows 1 processor and gives me a choice of up to 4 cores,in other cases (still on a 4 core platform) only 1 processor with 1 core, in other cases 2 processors with 1 core.

    In most of the cases my freedom of choice is limited, because the selection of number of cores is greyed out.

    When I try to make changes by editing the vmx file I find them ineffective (no change).

    The other problem I am finding is that my VMs have been running VERY SLOWLY on my i7 platform with 8GB!I have no idea if this is related to the improper setting of the number of processores / cores (I am not able to set them to 1-processor 4-cores and am running with settingsd 1,1 instead).

    Could someone please help me to understand how to:

    1. Control / change the number of processors / threads on an existing VM.

    2. How to properly set those up for an i7 processor

    Thanks in advance,

    Andrew

    DB:2.44:How To Change Number Of Processors / Cores m9


    I'm trying to understand your suggestions. I have a hex core AMD processor - would it be optimal to assign 6 cores to the VM (if I suppose you were only running one VM at a time). What about assigning 2 virtual processors? I haven't tried the latter - will the guest OS detect 2 processors if there is one one "real" one? For exlample lusing the System control panel app? If so how would hyp er-threading in the VM work out?

  • RELEVANCY SCORE 2.43

    DB:2.43:New Cpu - No More Parallelism 7s



    Hi there,

    Im still using the 11.0.075 compiler. We moved from XP to Windows7 and got new hardware. Now I call a Intel Core i5-2540M Processor my own, before that Ihadsome Core2 Duo CPU.

    But now our programs run only on 1 CPU (25% with 4 cores), I changed nearly every compiler setting, but it wont use all 4 cores as it did with the 2 cores of my old machine.

    My command line is (and so it was on the old machine):
    /nologo /O3 /Og /QaxSSE2 /QxHost /Qparallel /Qipo /D_Release /Qopenmp /warn:none /Qfp-stack-check /module:"Release\\\\" /object:"Release\\\\" /check:none /libs:qwin /c

    Do I really have to buy the new compiler to get parallelism back?

    Markus

    DB:2.43:New Cpu - No More Parallelism 7s


    Quoting TimP (Intel)

    I'm concerned about whether /QxHost is useful on a CPU model which wasn't tested during development of your compiler.

    I would not be concerned about that. The /QxHost feature will query the CPUID capability bits if the CPU type is not recognized.

  • RELEVANCY SCORE 2.43

    DB:2.43:Couldn't Get Openmp To Work 3k



    Next step to "hello world" program on learning OpenMP, I started making the following code, such that I can implement on the bigger code which I work on. Unfortunately, I couldn't see any difference across normal, /Qopenmp and /Qparallel options. All uses only one processor out of 4, for any value of n. Of course, beyond certain value of n, virtual memory error is thrown.

    Compilation was done in command line with following options using Fortran Compiler 12.1.5.344 in Intel i5-3320M processor (Win 7, 32-bit).

    ifort test.f90

    ifort /Qopenmp test.f90 (i see from report that, the do loop was parallelized)

    ifort /Qparallel test.f90

    Can someone help on, what am I missing?

    module mod1
       
        contains
       
        subroutine sub1(a,b,c)
           
            implicit none
            real*4, intent(in) :: a,b
            real*4, intent(out):: c
           
            c=a*b
        end subroutine sub1
    end module mod1
     
     
    program test
       
        use omp_lib
        use mod1
       
        implicit none
        real*4, allocatable :: a(:), b(:), c(:)
        integer  :: i,n
       
        read(*,*) n
       
        allocate(a(n),b(n),c(n))
       
        do i=1,n
        call random_number(a(i))
        call random_number(b(i))
        end do
       
        !$omp do
        do i=1,n
        call sub1(a(i),b(i),c(i))
        end do
        !$omp end do
       
        write(*,*) a(1),b(1),c(1)
    end program test

    DB:2.43:Couldn't Get Openmp To Work 3k


    Thank you Jim and John. !$omp parallel was the miss, and by including it, I see all 4 processors involved in my test code.

    John - your example helped me to understand many things (allocation, calculation, what and what not to parallelize) about using OpenMP in one go. Special Thanks to you!!!

    Just before completion EXE got crased due to insufficient virtual memory error (#41). May I request a suggestion to fix it?

  • RELEVANCY SCORE 2.43

    DB:2.43:Problem With Licences 8m



    Hi,

    I have a server with 4 physical CPU. I want to install on it an ESX Server.

    This server is being used with another one like a cluster HA and DSR.

    However, i only have 1 license of HADSR (2 CPU cores).

    Will I be able to use this server (with 4 physical CPU) without any problem ?.

    Will i need to purchase another license (2 CPU) or will it work with only 2 CPU cores?

    Regards.

    DB:2.43:Problem With Licences 8m


    Hi,

    I have a server with 4 physical CPU. I want to install on it an ESX Server.

    This server is being used with another one like a cluster HA and DSR.

    However, i only have 1 license of HADSR (2 CPU cores).

    Will I be able to use this server (with 4 physical CPU) without any problem ?.

    Will i need to purchase another license (2 CPU) or will it work with only 2 CPU cores?

    Regards.

  • RELEVANCY SCORE 2.42

    DB:2.42:Essentials 4 Vcpu License Limit W/ 8 Core Host mp



    I have a (2) quad-core Intel based VM Host server, w/ the basic Paid version Eseentials License. It only allows for a 4 vCPU max VM. I know about setting the cpuid.coresPerSocket option to present the number of CPU's/cores differently to the Guest OS. Doing 4vCPU with a setting of 4 cores, the guest OS sees a single quad core processor. Doing 4vCPU with a setting of 2 cores, the guest OS sees (2) dual core processors.

    So am I correct in saying with a 4 vCPU license, there is no way to assign 8 cores to a guest OS? I first thought doing a 4 vCPU VM with 2 cores per socket would allow me to use 8 cores on the host processor, but based on my tests, its still only 4 cores. I guess I need to upgrade my license to a 8 vCPU license?

    Thanks.

    DB:2.42:Essentials 4 Vcpu License Limit W/ 8 Core Host mp


    If you have a workload that requires 8 cores you may not have a good candidate for virtualization. Even if you you were able to provide all 8 cores to a VM you would have issues with resources for additional VMs.

  • RELEVANCY SCORE 2.42

    DB:2.42:Using Both Cores? 1z


    i have an early 2008 MBP, obviously they have 1 processor and 2 cores, what program can i get that shows that an application is using both cores? or do they always use all cores? and just (if i had multiple processors) only use the amount of processors they were designed to use?

    thanks for reading

  • RELEVANCY SCORE 2.42

    DB:2.42:Coherence Licensing For Hyperthreaded Cores? cc


    Since Coherence nowadays is licensed only per code (and not per CPU as was possible back in the Tangosol days) an interesting question is how is hyperthreading Cores (on Intel HW) threated are handled?

    HT cores only adds a fraction of the capacity of real cores so if they are licensed like a normal core the HT feature must be disabled in order to get good value for money...

    /Magnus

    DB:2.42:Coherence Licensing For Hyperthreaded Cores? cc

    Thanks - that is how I was reading the rules as well but I wanted to get it confirmed since we are planning our deployment and, of course, want to get it as cost efficient as possible!

    /Magnus

  • RELEVANCY SCORE 2.42

    DB:2.42:Esxi 4 With Amd Phenom X3 720 And M3a78-Em Motherboard (Minor Problem) z9



    Hello,

    I am fairly new to the vmware world. I have successfully used this whitebox combo for around 6 months. In order to have a succesful install, I had to upgrade my bios to ver 2003 and use intel nic pcie cards. After a successful install, I looked inside the host and it recognized the CPU X3 720 with all 3 cpu cores. It also allowed me to assign all 3 cores to a windows 7 media box I setup as an image on the host. The question and problem I have is: In the new windows 7 x64 image, it doesn't show 3 cores, it only shows 2 cores. The detail information inside Windows 7 say's it is an AMD phenom X3 2.81Gz processor with 2 processors, not 3. In the task manager, the cpu usage window only displays 2 windows instead of 3.

    Two processors are plenty for what this image is going to be doing but it would be nice to use all 3 processors, if possible.

    No matter what I try, I cannot get windows 7 to recognize all 3 cores. Even after I try all the tricks online, including re-installing, there isn't even a hint of success.

    I have concluded that the vmware bios used for images, doesn't properly recognize the CPU with 3 cores. Am I correct on my assumption?

    Thanks

    DB:2.42:Esxi 4 With Amd Phenom X3 720 And M3a78-Em Motherboard (Minor Problem) z9


    Thank you, your a genious. I tried your second suggestion and it worked! I see all 3 cores in windows 7 OS. All 3 show up in the device manager and under the CPU performance monitor.

  • RELEVANCY SCORE 2.42

    DB:2.42:5110p Usage Questions. ps



    Hi,
    I have  a dumb question on the Phi co-coprocessor. I've been passed the marketing material by our central business infrastructure team (who are looking to cut costs as usual).

    We have a single threaded C++ process that perform double precision floating point calculations. Several of these run in parallel on a multi-core server and pick jobs form a queue. We run a fixed number of these processes per core on the server. Currently we're running out of cores and may need to buy more servers.

    The Phi card has multiple cores. So a very naive interpretation of the marketing material is that a server with the card in will have extra cores to the server.  So we could run more single thread processes with the load spread across the cores on the server and the Phi card.

    I don't believe that this is the case for a variety of reasons such as:
    1. The work has to be offloaded to the co-porcessor programmatic. This does not just happen by magic.
    2. The co-processor would not have access to the 100GB memory of the server, only it's own 8GB local memory. So if one process uses 4GB the card's memory could only support two processes rather than 30 or 40.

    Hence my believe is that this card cannot be used to add additional cores to an existing servers. Though with some code changes it may be possible to use offload work to the co processor and run it in parallel. This is much easier to achieve using a phi rather than an GPU style api.

    It would be very helpful if someone would confirm this is the case.
    For my on interest I have two other questions:
    1) is it possible to run multiple cards in one servers
    2) If, for our sins, we are using Microsoft Visual Studio 2010 (for C++) does this have any implications using Phi cards.

    Thanks in advance!
    D

    DB:2.42:5110p Usage Questions. ps


    The memory size of Intel(C) Xeon Phi(tm) is definitely a limit on the number of processes, even when running a single job on MPI.  It's usually necessary to run each job threaded parallel and vectorized, e.g. OpenMP or Cilk+, to get value for the platform, even when running multiple processes.

    Typical server platforms designed for the purpose accommodate up to 4 coprocessor cards.  Several products are likely to support more than that.

    You must recompile using an Intel compiler, which supports a high degree of interoperability with Microsoft compilers.  Windows host support has not yet been released.

  • RELEVANCY SCORE 2.42

    DB:2.42:P55-Gd65 Limited To 2 Cores zz




    I have a P55-GD65 running a Core i7 860. HT is working fine but the system only finds 2 cores/4 threads rather then 4 cores/8 threads.

    In the bios it is limited to run on 1 core, 2 cores or auto. I have it on auto but none the less, it should be 4 cores.

    I hear alot of reference to the pins on this board...should i take the cpu and cooler out and check the pins? I have a foxconn socket.

    DB:2.42:P55-Gd65 Limited To 2 Cores zz


    I dont recall the bios version number but i did try to flash to the latest version in hopes of fixing this. Will clear cmos and see what happens.

    CMOS/Defaults didnt work, guess ill have to check the seating. :(

    I checked the seating, didnt see anything wrong, reseated it and tried again, still only 2 cores.

    EDIT2: Tried reseating again, still no luck.

    ~! EDIT3:Ok I tried google before coming here, but i was including the mobo in the search. No luck. After I searched Core i7 2 cores I found an answer on the Dell forums. I had manually adjusted the boot to run off 4 cores, once i disabled that and rebooted I now have all 4 cores running!

  • RELEVANCY SCORE 2.42

    DB:2.42:Two Cores Shown In Profiler, Should Be Four mf


    I recently noticed in TechTool Pro that it was only showing two cores working, it had been showing four. I went to "About This Mac" an under Hardware is shows "Total Number of Cores 2" and that's wrong. I have a late 2010 MacBook Pro i7 2.66 GHz. Which I presume is no different than the currently shipping i7 MBP - and the Apple Store shows in their specs as having four cores. Any suggestions as to the "lost cores"?Thanks for any input.Tom

    DB:2.42:Two Cores Shown In Profiler, Should Be Four mf

    I guess the old saying about "having the latest and greatest" applies here; one can never keep up with the evolution of technology.TomIf you can buy it in a box from a store, there is always something better within the next year. Deciding when to buy is always a balance between need / want / production refresh cycles.

  • RELEVANCY SCORE 2.42

    DB:2.42:Only Two Cpus Working For Vmware Server On Intel I7 Q720 (4 Cores) Windows 7 System? p3



    when i installed the vmware server, the resource monitor showed me two cores was parked, and only two core was working.

    after installation, on vmware infrastructure web access only shows 2 cores at summary-general-processors.

    when i installed solaris 10 on vmware server, i saw only two core working it.

    could anybody tell me how to let vmware server knows this computer has 4 cores, even though some cpus parked?

    (windows 7 doesn't have disable cpu parking function).

    DB:2.42:Only Two Cpus Working For Vmware Server On Intel I7 Q720 (4 Cores) Windows 7 System? p3


    Hi,

    you welcome

    Please, remember to mark the answer as correct. This is the way to award vmware communities users that helps others.

    Regards/Saludos,

    Pablo

    Please consider awarding any helpful or corrrect answer. Thanks!! - Por favor considera premiar cualquier respuesta til o correcta. Muchas gracias!!

    Virtually noob blog

  • RELEVANCY SCORE 2.42

    DB:2.42:Correct Allocation Of Cpu Resources To Vm With Hyperthreading Vcpu Esxi 5.5 3d



    HI,

    I have been reading various articles about trying to size the CPU allocation for VMs and performance issues with overcommitting but still can't seem to find a definitive answer with hyper threading involved for this particular setup and was hoping someone could clarify it for me.

    Example 1 - Exchange 2010 Server

    1 x 6 Core Processor (12 logical with hyper threading)

    Currently this has 1 socket and 6 cores assigned to it out of a possible 12.

    There is only 1 virtual machine running on the server. Would I benefit from increasing the number of cores from either of the following:

    1 socket, 12 cores

    6 sockets, 1 core

    12 sockets, 1 core

    any other configuration?

    Example 2 - Server has 2 x 6 Core Processors with Hyper threading enabled. (12 Cores, 24 Logical)

    I want to assign 2 physical cores to VM1, 4 physical cores to VM2 and 6 physical cores to VM3

    Which would I do out of the following:

    VM1 - 1 socket, 2 cores VM2 - 1 socket, 4 cores VM3 - 1 socket 6 cores

    VM1 - 1 socket, 4 cores VM2 - 1 socket, 8 cores VM3 - 1 socket 12 cores

    VM1 - 2 sockets, 1 core VM2 - 2 sockets, 4 cores VM3 2 sockets, 6 cores

    VM1 - 2 sockets, 2 cores VM2 - 2 sockets, 8 cores VM3 - 2 sockets, 12 cores

    VM1 - 2 sockets, 1 core VM2 - 4 sockets, 1 core VM3 - 6 sockets, 1 core

    VM1 - 4 sockets, 1 core VM2 - 8 sockets, 1 core VM3 - 12 sockets, 1 core

    any other configuration?

    DB:2.42:Correct Allocation Of Cpu Resources To Vm With Hyperthreading Vcpu Esxi 5.5 3d


    No you can allocate more vCPU than you have. what you have stated there is fine. I usually go for a 6 to 1 ratio. for example with 12 cores we could have up to 72 vCPUS (this is all relative to workload type and VM size through)

    I was saying you never allocate a single VM more than the physical cores as the guest OS on the VM thinks it has full cores to play with not hyper threaded cores..

    But hyper threading can give use better ability to over commit the CPU resources as it intelligently uses the additional threads when performance will not be impacted. as long as all those VMs are not going to be running at 100% then you could add a number more with no real impact. If those 3 VMs you have listed were to use 100% each you would be using 100% of the host CPU not 50%. never use logical cores when it comes to capacity calculations only physical cores

    Cheers

  • RELEVANCY SCORE 2.42

    DB:2.42:Compressor Only Uses 50% Cpu xs


    Whenever I use compressor it only ever uses 50% CPU across all cores. I'm using a MacPro with Dual Quad Core Xeons. There are no other apps running on the box and would like to get my compressing done faster, is there any way?

    DB:2.42:Compressor Only Uses 50% Cpu xs

    It has been pointed out that the amount of installed RAM makes all the difference. How much RAM is in your dual quad?

  • RELEVANCY SCORE 2.42

    DB:2.42:Compiling With Two Cpu Cores 3f


    Is it possible to compile with two or more CPU cores or just with one?

    As it seems, javac uses only one core when I compile with the Ant tasc "javac".

    DB:2.42:Compiling With Two Cpu Cores 3f

    I don't know of a way to do this, but I've never seen a need to do this either, since java compilation is never too slow for me (even for huge projects).

    If you seriously need faster compilation, you could switch to a faster compiler (jikes is seriously fast, ecj (the eclipse compiler) is even faster, sometimes).

    You might also try compiling seperate (independent) parts of your sourcecode with explicit parallel constructs in ant ('though I don't know if it's worth the overhead).

  • RELEVANCY SCORE 2.41

    DB:2.41:Mkl Parallel Execution Confusion cp



    I have some confusion regarding how MKL execute in parallel.  The problem I have is that after making some changes to a program, calls to DGBTRS, DGETRS, DGETRF and DGBTRF are no longer executed in parallel by MKL even though I am using the complier option /Qmkl:parallel.

    Let me explain a little more.  I have the following code structure for solving a medium size set of ODES (~5000 differential equations).

    PROGRAM

    -Allocates space, etc

    CALL ODE_SOLVER

    -save, cleanup , etc

    END PROGRAM
    SUBROUTINE ODE_SOLVER

    CALL USER_ODES

    ...

    CALL DGBTRF

    CALL DGBTRS

    CALL DGETRF

    CALL DGETRS

    ...

    RETURN

    END SUBROUTINE ODE_SOLVER
    SUBROUTINE USER_ODES

    -this is where I made some changes, in particular larger vector/matrix multiplications

    -Note, however, ODE system size has not changed, so ODE_SOLVER sees the same system size

    that is no change has occur that ODE_SOLVER sees.

    END SUBROUTINE USER_ODES

    For the initial version of the program, the above LAPACK calls made within ODE_SOLVER were executed in parallel by MKL, and I got very good execution time speedup (across 8 cores).  I made some changes to USER_ODES, but I did not change the size of the ODE system, so ODE_SOLVER was effectively solving the same problem.  However, USER_ODES did allocate larger matrices to compute the ODES.

    The problem is, after making changes to USER_ODES, calls to the LAPACK routines stopped executing in parallel (only get serial execution).  If I use the Intel fortran compilier option /Qparallel, all cores become busy, but performance is terrible.

    Sorry this is not much to go on.  My guess is that USER_ODES is generating multiple threads now, and this prevents MKL for producing parallel threads for the LAPACK calls.  Any suggestions?

    Thanks

    -joe

    DB:2.41:Mkl Parallel Execution Confusion cp


    Hi Chao,

    Thanks for your comment.  I was crudely checking thread creation by just following core activity.  As I noted above, MKL was generating threads as expected, it just that my modified code, which has a lot of serial execution, was taking much longer than I had anticipated.  At first appearance, I thought MKL was also executing in serial, but that was incorrect.  MKL did execute code in parallel, it just did it so quickly that I missed it at first.

    cheers,

    -joe

  • RELEVANCY SCORE 2.41

    DB:2.41:Quad Core Processor Running On 2 Cores cp


    Hello, my quad core processor is running on 2 cores despite that it was running on 4 cores previously. I tried msconfig and easy bootcd but it did'nt work. Msconfig showed only 2 cores in the chekbox. I noticed in easybcd that after I click save sittings
    the checkbox goes empty again. I'm running Windows 7 64 bit and the processor model is Intel core 2 extreme qx6700.

    DB:2.41:Quad Core Processor Running On 2 Cores cp

    Hi,

    Glad to know that issue has been resolved, I really appreciate your patience and time and thank you for sharing the information with us.

    In future if you have any questions feel free to contact Microsoft Answers.

  • RELEVANCY SCORE 2.41

    DB:2.41:Forcing Number Of Cores Used By Esp 38


    Hi,Is it possible to restrict the number of cores that ESP uses on a multi-core box?For example. I would like to use ESP on only 3 cores of a quad core box, so I can use the other core for running a separate flight model in C#.Thanks, Kenjiwww.mihpc.net Kenji

  • RELEVANCY SCORE 2.41

    DB:2.41:Cpu's Cores And Overprovisioning ap



    I know this question has been asked before in one form or another however I am looking for answers from those who administrate and use servers running ESXi not a document of best practices.

    If I have a server with a single CPU that has 8 cores, best practices says that I can have eight virtual machines configured with one single core each, or four using two cores each, or some variant that uses all eight cores but no more.

    What happens if I have four virtual machines configured with two cores each and I had another virtual machine configured with two more cores? I know its next to impossible to say how this will affect performance as different apps use CPU differently and depending on the workload of the server, number of users the VM's are serving etc.

    In my scenario I have a single server with an 8 core CPU running vm's of Exchange 2010, Terminal server (2008R2), an application server (2008R2) all of these configured with 2 cores, then two vm's that are domain controllers each configured with a single core each. This is all serving a company of 50 or so people.

    I am going to need to add to more VM's in the near future, one running Microsoft SQL and the other an application server, I suspect each of these will require two cores each. I do have a second server with a single quad core processor that I can move two VM's using two cores each to which I am likely going to do.

    I just wanted to know what others are doing out there with their VM's and cores and how they are managing it and what if any performance degradation they are seeing in real world use.

    DB:2.41:Cpu's Cores And Overprovisioning ap


    ESXi's resource scheduler is pretty smart in terms of spreading the CPU workload. See these resources available not as individual CPU cores, but rather as their total frequency combined - this is what the ESXi host has in pool for all your currently running VMs. The hypervisor gives them just enough frequency they actually need. This is also what you get in the Summary page of your ESXi host - the total frequency your CPU has.

    The multi-CPU core count comes into play when a VM requests them. VMs using more than 1 vCPU must be provisioned with the same amount of the physical cores for that operation. So for a machine with 4vCPUs, 4 physical cores must always be free at one point of time to process the instruction. Also, VMs' vCPUs migrate all voer physical CPU cores in realtime depending on their physical contention. Literature tells that depending on the workload, you can serve give or take 3 vCPUs per one physical core.

    Of course it all depends on the workload and CPU peak times. Observe long-term CPU usage of your ESXi host (especially the Ready value) once you build the new VMs - you can always migrate them off if they cause problems.

    The bottom line: If RAM is not a constraint and you are not facing any CPU peak usage yet, then go ahead and build the servers on your already running host

  • RELEVANCY SCORE 2.41

    DB:2.41:Creating A Vm---Virtual Sockets Vs Virtual Cores fc



    I am not sure where to post this.

    I am a bit confused on when creating a VM you now get an option to choose number of sockets or number of cores. Ie 4 socket 1 core, or 2 socket 2 cores.

    I have heard different reasons from different vmware trainers

    From it is only for licensing it doesn't matter. To it must match your numa configuration or you will have performance issues.

    To me I always thought it was just 4 cores for vm--no matter how it got there.

    Could someone explain this to me please.

    DB:2.41:Creating A Vm---Virtual Sockets Vs Virtual Cores fc


    Another consideration is that if you use CPU hot add, you cannot change the number of cores, only number of sockets (while the VM is running). And if you change sockets, it will be another vCPU with the same number of cores as the first.

    For example, if I had a single processor 6 core VM and I hot-add a second socket, I am going to end up with Two 6 core processors. That's a big jump.

    If I had 3 dual core CPU and I hot add a fourth socket, I end up with 4 dual core processors. Or I could do 5 or 6 or 8 dual cores, etc. It gives me a bit more flexibility when I keep the core count lower.

  • RELEVANCY SCORE 2.41

    DB:2.41:I7 Ideapad U510 Only Using 2 Cores :/ xz


    Here is the screenshot. This is a i7 laptop which I just bought.. It is suppose to have 4 cores and 8 threads.. but it is only showing only half of them.. Even when i try to use my 3Ds Max it still uses only 2 cores and 4 threads..Can someone help me with it? How to fix this?Thanks..Here is another screenshot from task manager..

    DB:2.41:I7 Ideapad U510 Only Using 2 Cores :/ xz

    Yup, you got the 2 core version. Not all hope is lost to do 3D work though, do you have a video card?



    ___________________________________________-Lenovo IBM T60 Intel Core Duo T2300 1.66GHz 4.0 GB Dual-Channel DDR2 Intel 945 Express Graphics. Win 7 Pro. 7 years and running-Lenovo Y580 Intel Core i7 2.40GHz Ivy Bridge 22nm Technology 16.00 GB Dual-Channel DDR3 @ 798MHz Cosair Vengence NVIDIA GeForce GTX 660M

  • RELEVANCY SCORE 2.41

    DB:2.41:X305-Q708 Bios 1.60 Disables One Core Only Instead Of Two Cores pm



    When I had BIOS 1.50, setting the BIOS to disable the 2nd core disables two cores on my laptop with the quad-core qx9300 cpu, which is the correct behavour.

    After I updated to BIOS 1.60, the same setting disables just 1 core out of the four, leaving 3 cores running in Vista Ultimate 64 bit.

    Is thisa bug? can it be fixed please. I don't like having an odd number of cores running for some reason.

    DB:2.41:X305-Q708 Bios 1.60 Disables One Core Only Instead Of Two Cores pm


    For the best solutionhighly recommendto contact a Service Center or www.toshiba.com to ensure that the BIOS configuration you relate is within normal parameters. Thus, you avoid conflicts later on.

  • RELEVANCY SCORE 2.41

    DB:2.41:I7 Imac And 8 Threads? 91


    I believe i7 in the 27 inch iMac is the intel i7-860 part. As such, it's four

    cores of course and hyper-threaded so 2 threads per core.

    Can anyone who purchased an i7 confirm that in fact Snow Leopard not only sees all

    four cores but 2 threads per CPU core effectively making it appear as 8 cores?

    Thanks.

    DB:2.41:I7 Imac And 8 Threads? 91

    You will always get issues here on this forum as it is a help forum, few people come he to post that they have no problems. I for one am very happy with the current i7. It supports the 64bit kernel is amazingly fast and the screen is stunning, no problems at all..

    Chris

  • RELEVANCY SCORE 2.41

    DB:2.41:Esxi 2 Vm's Both With 2 Vcpus And 3 Vcores 17



    Hi,

    First off i'm using ESXi 5.1 and the hardware wise i'm using are 2x Hexcore X5650 2.67GHz, 48GB RAM and RAID 1 600GB SAS 15k drives

    I've come across an issue where i've purchased a higher spec server to go along with our others at our dedicated hosting company, however, i've gone from dual quad core to dual hexcore processors which now puts me over my 8 core limit on ESXi.

    So my question is, as i can only use a max of 8 cores per virtual machine and i have 12 physical cores available, would 2 vms with 2vCPUs and 3 vCores utilise all 12 physical cores, or would it still be limited to only using 8 of these cores?

    Also, would it be a good (load balanced) idea to use 2 VM's with 2vCPUs and 4 vCores?

    All advise and guidance welcome.

    Regards

    Liam

    DB:2.41:Esxi 2 Vm's Both With 2 Vcpus And 3 Vcores 17


    Hahaha! and you'd deserve it mate!

    That's great advice, far beyond what i'd expected to receive for my starting thread :-) (you sure you're not already paid?? ;-))

    I'll keep all in mind and come back to this when i get a chance later this year (when work has died down a bit, failing that i'll just put off a work load and make time!)

    Thanks again for your support :-)

    Regards

    Liam

  • RELEVANCY SCORE 2.41

    DB:2.41:Does Logic 8 On Leopard Use All 8 Cores ? 8z


    I want to upgrade my mac pro to a new mac pro with 8 cores. Does logic really use all 8 cores EFFICIENTLY or are the stories true that it still really only uses 1?

    DB:2.41:Does Logic 8 On Leopard Use All 8 Cores ? 8z

    As I mentioned in another thread... I have just finished upgrading from a G5 2x2 to the 2.8G 8 core MacPro. I mentioned there, that the power increase is astounding!!! Brilliant.
    I am running an RME Fireface800 at 64 samples with Logic8, LIVE, Melodyne Studio, ProToolsLE, NativeInstruments Komplete 2,3,4 5, GarritanPO, Waves GOLD and a pile of 3rd party plugs.

    I have not had a single crash since getting it all going over a week ago. i am still waiting for my extra ram to arrive from OWC, but nothing has been slow and it is working so well. Giddy Up!

    Regards,
    Matt

  • RELEVANCY SCORE 2.41

    DB:2.41:Release Configuration Flags - Need For Additional Dlls ck



    I have three questions:

    1) The executable in release configuration says that some DLLs are not found when used in machines that do not have ifort installed. Here are the options that I am using for compilation:

    ifort /nologo /debug:full /Qparallel /assume:buffered_io /Qipo /fpp /gen-interfaces /stand:f03 /warn:all /fp:precise /Qfp-speculation=off /module:quotRelease\\" /object:quotRelease\\" /traceback /check:all /libs:static /threads /c /QaxTPNS /Qvc9 /Qlocation,link,C:Program FilesMicrosoft Visual Studio 9.0VCbin"

    When I turn off /Qparallel and /Qipo and run in debug the executable runs. The DLL 'libiomp5md.dll' is not found on some machines. Are there any special flags to make the parallelization /IPO work without additional DLLs?

    2) Why am I getting the following warning?

    ifort: command line warning #10212: /fp:precise evaluates in source precision with Fortran.

    I thought /fp:precise floating point model is compatible with /Qfp-speculation=off. I want to compile such that the results can be repeated (reproduced) on multiple hardware / platforms with the same double precision accuracy in the code.

    integer, parameter, public :: dp_k = selected_real_kind(2*precision(1.0_sp_k))

    3) There used to an Intel page and discussion about multiple CPU displatch flags (/QaxTPNS). I can not find it now. Is the above flag still good to make sure that the execulatble is optimized for all common CPU configurations? Whats the suggestion for the current version 11.1.054?

    Your help is appreciated.

    DB:2.41:Release Configuration Flags - Need For Additional Dlls ck


    1) openmp-link:static links the static library in place of libiomp5md.

    There shouldn't be any direct relationship between /Qipo and the libraries used.

    3) Current Core 2 CPUs (but not early ones) would take advantage of the SSE4.1 option, and it will be fairly good for Core I as well. Any deviation from Steve's recommendation would apply only in specific circumstances. If your application depends strongly on complex arithmetic and performance on older SSE3-capable CPUs were important, you might want to include /arch:SSE3 in the options, but it seems that would prevent running on CPUs which don't support SSE3.

    If you want to take advantage of SSE4.1 but also run on 32-bit CPUs which don't support SSE2, it seems you require /QaxSSE4.1 /arch:IA32

  • RELEVANCY SCORE 2.41

    DB:2.41:Sql Server With A License For 2 Cores On Cpu With 8 Cores 3m


    hi guys, how are you doing
    i have a question for the msdn experts
    can we run an sql server 2012 with a license for 2 cores on a cpu of 8 cores (from a technical point and legal )
    maybe by limiting the number of cores used by sql server
    it will run on the latest windows server
    i'm looking for your answers
    thanks

    DB:2.41:Sql Server With A License For 2 Cores On Cpu With 8 Cores 3m

    To license a physical server properly, you must license all the cores in the server with a minimum of 4 core licenses required for each physical processor in the server
    Check below if it helps
    http://www.brentozar.com/archive/2014/01/whats-the-smallest-sql-server-you-should-build/
    http://blogs.technet.com/b/uspartner_ts2team/archive/2011/11/30/a-concise-sql-server-2012-licensing-overview.aspxPlease click the Mark as answer button and vote as helpful if this reply solves your problem

  • RELEVANCY SCORE 2.41

    DB:2.41:Single Core Cpu Only Uses 50 Of Its Power cz


    I have a single core Atom N270 processor, but XP "sees" it as 2 cores as shown in the Task Manager. When I use eg. a chess program, it only uses one of the 2 virtual cores and therefore uses only 50% of the processor.

    Is there a way to force XP to treat the cpu as the single core that it is?

    DB:2.41:Single Core Cpu Only Uses 50 Of Its Power cz

    Thanks for your replies Palcouk and thomas. It is an N270 for sure.

    Here's the answer: the N270 is an Atom processor and is hyperthreaded. XP "sees" this as 2 cpu's and if you run a single thread process, it "uses" one of those 2 virtual cores, and ~50% is idle. My logic was, "If I turn off hyperthreading thereby turning the
    processor into a single core and regaining the 50% idle capacity, my single thread programs will run close to 2x as fast." I tried it, and XP indeed saw the processor as a single core and regained the 50% idle capacity. It now ran 100% cpu usage on single
    thread apps.

    So, did my apps now run 2x faster? NO. No measurable difference, except some were even slower. Click! Turned back on hyperthreading because when needed, running 2 parallel threads is ~50%
    faster.

    You would think the netbook maker or Intel would know this, wouldn't you? I did ask both during long exchanges for days before asking here and causing Tom a headache. ;)

  • RELEVANCY SCORE 2.41

    DB:2.41:8 Cores Configured But 4 Cores Displayed mj



    Hello,

    I installed 2 virtual machines each with 8 cores (I have two Intel Xeon X5650). On the VM Linux, I configured 8 cores and 8 cores are displayed. But in VM Windows, I configured 8 cores but only 4 are displayed in the task manager but 8 in the device manager:

    http://himages.tk/uploads/1308701113.png

    How can I do to activate the other 4 cores ?

    Thanks

    DB:2.41:8 Cores Configured But 4 Cores Displayed mj


    that's the limitation of windows standard, try on windows enterprise ...

  • RELEVANCY SCORE 2.41

    DB:2.41:How /Qparallel Works? 9j



    I used /Qparallel compiler option, and observed some parallel execution. My code is intended to process lot of data. It was interesting to see that, when I use small data size, then I see higher degree of parallelism (from CPU usage) than if I use large amount of data. My understanding is, /Qparallel option parallelize the code only during compilation, and not during the execution. If not, please let me know, whether is there any dynamic memory limit which decides the extent of parallelization.

    Also, can someone help me with the coding methods which could enable high degree of parallelism in /Qparallel?

    DB:2.41:How /Qparallel Works? 9j


    I usually start the investigation of CPU performance by using Process Explorer to measure CPU load in CPU clock cycles which are charged to specific process.Task manager uses Interrupt clock to sample the CPU load and IP so it is not as accurate as PE.

  • RELEVANCY SCORE 2.40

    DB:2.40:Forcing Paralelization On Same Phisical Processor mj



    Hi

    We have a scenario where an aplication runs in a single thread in serial mode (no paralelization at all). In a Xeon 2 x quad processors we have 8 of this applications running simultaneously, one in each core. now, as this Xeon processors have hyperthreading we would like to see if we can improve speed by paralelizing this application in 2 threads (either by using compiler automatic loop paralelization or openmp) and take advantage of the 8 "hyperthreaded" remaining cores. The problem is that we would like to ensure that each application uses only the two virtual processors of the same phisical core and does not use other phisical cores. We are using Debian runnin kernel 2.6.30-1-amd64 SMP and applications are attached to cores using sched_setaffinity

    Is that something that can only be handled at OS level or can be forced someway while compiling ?

    DB:2.40:Forcing Paralelization On Same Phisical Processor mj


    That looks like a loaded question. If PGO doesn't help you, you needn't use it. There are many reasons why parallelization might not help, not limited to insufficient parallel work, inadvisable affinity or lack of, race conditions which you may be hoping to deal with by affinity, ....

  • RELEVANCY SCORE 2.40

    DB:2.40:Mental Ray : License Question xd


    Dear Community,Currently mental ray's Distributed Bucket Rendering (DBR) system works only for 16 cores. If you want more CPU power, you have to buy mr Standalone licenses.If we purchase 1 license of mr Standalone and install on a new workstation with 8 cores, can we use these cores in addition to our existing 16 free cores? That means a total of 24 cores. (if we bought 2 licenses that would be 16 free cores+8+8=32 cores)Thank you.

    DB:2.40:Mental Ray : License Question xd

    Dear Community,Thank you for your replies.Each of our workstations has 8 cores (dual Xeon quadcore CPU). During DBR, the base workstation with Max license uses 100% CPU, others use 50%. We have 3 of these machines, so our DBR power is limited to 16 cores.The question is: If we buy 1 mr Standalone license, will we get to keep these 16 cores (for which we only paid 1 Max license), and still be able to render with 8 additional cores on a fourth workstation?Thank you.PS: I found DBR very useful for scenes with high tracing settings (30+). I am currently doing a scene with a lot of glass, and without DBR, it would never end.