Search Results

Search found 156 results on 7 pages for 'multicore'.

facebook twitter digg google delicious technorati stumbleupon myspace wordpress linkedin gmail igoogle windows live tumblr viadeo yahoo buzz yahoo mail yahoo bookmarks favorites email print

Page 4/7 | < Previous Page | 1 2 3 4 5 6 7  | Next Page >

  • Fast inter-process (inter-threaded) communications IPC on large multi-cpu system.

    - by IPC
    What would be the fastest portable bi-directional communication mechanism for inter-process communication where threads from one application need to communicate to multiple threads in another application on the same computer, and the communicating threads can be on different physical CPUs). I assume that it would involve a shared memory and a circular buffer and shared synchronization mechanisms. But shared mutexes are very expensive (and there are limited number of them too) to synchronize when threads are running on different physical CPUs.

    Read the article

  • c# STILL returning wrong number of cores

    - by Justin
    Ok, so I posted in In C# GetEnvironmentVariable("NUMBER_OF_PROCESSORS") returns the wrong number asking about how to get the correct number of cores in C#. Some helpful people directed me to a couple of questions where similar questions were asked but I have already tried those solutions. My question was then closed as being the same as another question, which is true, it is, but the solution given there didn't work. So I'm opening another one hoping that someone may be able to help realising that the other solutions DID NOT work. That question was How to find the Number of CPU Cores via .NET/C#? which used WMI to try to get the correct number of cores. Well, here's the output from the code given there: Number Of Cores: 32 Number Of Logical Processors: 32 Number Of Physical Processors: 4 As per my last question, the machine is a 64 core AMD Opteron 6276 (4x16 cores) running Windows Server 2008 R2 HPC edition. Regardless of what I do Windows always seems to return 32 cores even though 64 are available. I have confirmed the machine is only using 32 and if I hardcode 64 cores, then the machine uses all of them. I'm wondering if there might be an issue with the way the AMD CPUs are detected. FYI, in case you haven't read the last question, if I type echo %NUMBER_OF_PROCESSORS" at the command line, it returns 64. It just won't do it in a programming environment. Thanks, Justin UPDATE: Outputting PROCESSOR_ARCHITECTURE returns AMD64 from the command line, but x86 from the program. The program is 32-bit running on 64-bit hardware. I was asked to compile it to 64-bit but it still shows 32 cores.

    Read the article

  • What factors could cause the scalability issue on a 10-core CPU?

    - by JackWM
    I am tuning the performance of parallel Java programs. And want to check the impacts from the Architecture. I'm look into the Intel 10-core CPU, Intel(R) Xeon(R) CPU E7-L8867. I found my program only scales up to 5 cores. What could be the causes? I'm considering the Architecture effects. e.g. memory contention? More specifically, Are the 10 cores symmetric to each other? How many memory controllers does it have?

    Read the article

  • Solve a maze using multicores?

    - by acidzombie24
    This question is messy, i dont need a working solution, i need some psuedo code. How would i solve this maze? This is a homework question. I have to get from point green to red. At every fork i need to 'spawn a thread' and go that direction. I need to figure out how to get to red but i am unsure how to avoid paths i already have taken (finishing with any path is ok, i am just not allowed to go in circles). Heres an example of my problem, i start by moving down and i see a fork so one goes right and one goes down (or this thread can take it, it doesnt matter). Now lets ignore the rest of the forks and say the one going right hits the wall, goes down, hits the wall and goes left, then goes up. The other thread goes down, hits the wall then goes all the way right. The bottom path has been taken twice, by starting at different sides. How do i mark this path has been taken? Do i need a lock? Is this the only way? Is there a lockless solution? Implementation wise i was thinking i could have the maze something like this. I dont like the solution because there is a LOT of locking (assuming i lock before each read and write of the haveTraverse member). I dont need to use the MazeSegment class below, i just wrote it up as an example. I am allowed to construct the maze however i want. I was thinking maybe the solution requires no connecting paths and thats hassling me. Maybe i could split the map up instead of using the format below (which is easy to read and understand). But if i knew how to split it up i would know how to walk it thus the problem. How do i walk this maze efficiently? The only hint i receive was dont try to conserve memory by reusing it, make copies. However that was related to a problem with ordering a list and i dont think the hint was a hint for this. class MazeSegment { enum Direction { up, down, left, right} List<Pair<Direction, MazeSegment*>> ConnectingPaths; int line_length; bool haveTraverse; } MazeSegment root; class MazeSegment { enum Direction { up, down, left, right} List<Pair<Direction, MazeSegment*>> ConnectingPaths; bool haveTraverse; } void WalkPath(MazeSegment segment) { if(segment.haveTraverse) return; segment.haveTraverse = true; foreach(var v in segment) { if(v.haveTraverse == false) spawn_thread(v); } } WalkPath(root);

    Read the article

  • Threading and cores

    - by Matt
    If I have X cores on my machine and I start X threads. Let's assume for the sake of argument that each thread is completely separated in terms of the memory, hdd, etc it uses. Is the OS going to know to send each thread to a core or do more time slicing on one core for multiple threads. What the question boils down to, is if I have X cores and my program must do independent calculations, should I start X threads, will they each get piped to a core, or is the presumption that because I have X cores I can start X threads completely wrong? I'm thinking it is. This is with C# --

    Read the article

  • How to achieve a specific fraction(say 80%) of the cpus and balanced over them

    - by swellfr
    Hi, I was wondering if it would be possible to run app not at 100% of the cpu but at a specific amount of the cpus. I see different usage of this , we can better balance concurrent application ( we may want to have balance app 50% to have fair apps/agent/... ) i was also wondering if the power consumption would not be better if the cpus doesnt run at full throttle but at some lower level( say 80% ) What are your thoughts Thx examples are welcomed :)

    Read the article

  • What Use are Threads Outside of Parallel Problems on MultiCore Systesm?

    - by Robert S. Barnes
    Threads make the design, implementation and debugging of a program significantly more difficult. Yet many people seem to think that every task in a program that can be threaded should be threaded, even on a single core system. I can understand threading something like an MPEG2 decoder that's going to run on a multicore cpu ( which I've done ), but what can justify the significant development costs threading entails when you're talking about a single core system or even a multicore system if your task doesn't gain significant performance from a parallel implementation? Or more succinctly, what kinds of non-performance related problems justify threading? Edit Well I just ran across one instance that's not CPU limited but threads make a big difference: TCP, HTTP and the Multi-Threading Sweet Spot Multiple threads are pretty useful when trying to max out your bandwidth to another peer over a high latency network connection. Non-blocking I/O would use significantly less local CPU resources, but would be much more difficult to design and implement.

    Read the article

  • How do I fix this installation problem with multicore Solr on Ubuntu 10.04?

    - by coleifer
    Following instructions from the two sites below, I've installed Tomcat 6 and Solr 1.4. http://gist.github.com/204638 https://wiki.fourkitchens.com/display/TECH/Solr+1.4+on+Ubuntu+9.10+and+CentOS+5 I have successfully got it up and running on a server running 9.04 with multicore support, but on the 10.04 I can't seem to get it to work. I am able to reach localhost:xxxx/solr/ on the 10.04 box and see a single link to the Solr Admin, but following the link takes me to a 404 page with the following output: /solr/admin/ HTTP Status 404 - missing core name in path The requested resource (missing core name in path) is not available I am also unable to access /solr/site1/ as I would except - it similarly returns a 404. <!-- from /var/solr/solr.xml, site dirs exist --> <cores adminPath="/admin/cores"> <core name="site1" instanceDir="site1" /> <core name="site2" instanceDir="site2" /> </cores> <!-- from /etc/tomcat6/Catalina/localhost/solr.xml --> <Context docBase="/var/solr/solr.war" debug="0" privileged="true" allowLinking="true" crossContext="true"> <Environment name="solr/home" type="java.lang.String" value="/var/solr" override="true" /> </Context>

    Read the article

  • No dual cpu support for VirtualBox with a CPU that doesn't support multicore?

    - by djangofan
    With VMWare it works fine and I can run multiple cores on a VMWare image. With Sun VirtualBox I can only run 1 cpu on a image. Its annoying. Why does Sun Virtualbox not work the same as VMWare in this respect?? My CPU is: XEON 3.00GHz Intel 90nm 2MBCache QUAD CPU x14 Socket 604 mPGA Family 15 Model 4(04) Stepping 3 Revision 05 MMX SSE3 XD SIV.exe tells me: No virtual machine extensions x86 with 64-bit support NO IA64 support MPS but with NO MCP 2 physical processors, 2 cores, 4 logical processors

    Read the article

  • links for 2010-05-04

    - by Bob Rhubart
    IdMapper: A Java Application for ID Mapping across Multiple Cross-Referencing Providers H/T to Geertjan for posting a link to this paper on a Netbeans-based project. (tags: java netbeans) Mastering Your Multicore System - Oracle Solaris Video How Sun Studio compilers and tools can simplify these challenges and enable you to fully unlock the potential in multicore architecture. Don Kretsch presents at Tech Days, Brazil, 2009. (tags: oracle sun sunstudio multicore video) Allison Dixon: COLLABORATE: OAUG Staff #c10 ORACLENERD guest blogger Allison Dixon offers a peek behind the curtain and a tip of the hat to the people behind Collaborate 10. (tags: oracle oaug ioug collaborate2010) @myfear: Java EE 5 or 6 - which to choose today Author, software architect, and Oracle ACE Director Markus Eisele shares his insight into the choice between Java EE versions. (tags: oracle otn java oracleace glassfish) @blueadept61: Architecture and Agility #entarch In yet another great, succinct post, Oracle ACE Director Mike Van Alst offers more quotable wisdom than I can share here. Read the whole thing. (tags: oracle otn entarch enterprisearchitecture agile) @blueadept61: Governance Causes SOA Projects to Fail? Oracle ACE Director Mike Van Alst's short but thought-provoking post raises issues of language and perception in dealing with the cultural hurdles to SOA Governance. (tags: oracle otn soa soagovernance communication) Anthony Shorten: List of available whitepapers as of 04 May 2010 Anthony Shorten shares a list of whitepapers available from My Oracle Support covering Oracle Utilities Application Framework based products. (tags: oracle otn whitepapers frameworks documentation) @processautomate: SOA Governance is Not a Documentation Exercise Leonardo Consulting SOA specialist Mervin Chiang proposes that simply considering and applying basic SOA governance -- service management -- can go a long way. (tags: otn oracle soa soagovernance) Article: Cloud Computing Capability Reference Model This Cloud Computing Capability Reference Model provides a functional view of the layers in a typical cloud stack to help Enterprise Architects identify the components necessary to implement Cloud solutions. (tags: oracle otn cloud entarch soa virtualization)

    Read the article

  • A Method for Reducing Contention and Overhead in Worker Queues for Multithreaded Java Applications

    - by Janice J. Heiss
    A java.net article, rich in practical resources, by IBM India Labs’ Sathiskumar Palaniappan, Kavitha Varadarajan, and Jayashree Viswanathan, explores the challenge of writing code in a way that that effectively makes use of the resources of modern multicore processors and multiprocessor servers.As the article states: “Many server applications, such as Web servers, application servers, database servers, file servers, and mail servers, maintain worker queues and thread pools to handle large numbers of short tasks that arrive from remote sources. In general, a ‘worker queue’ holds all the short tasks that need to be executed, and the threads in the thread pool retrieve the tasks from the worker queue and complete the tasks. Since multiple threads act on the worker queue, adding tasks to and deleting tasks from the worker queue needs to be synchronized, which introduces contention in the worker queue.” The article goes on to explain ways that developers can reduce contention by maintaining one queue per thread. It also demonstrates a work-stealing technique that helps in effectively utilizing the CPU in multicore systems. Read the rest of the article here.

    Read the article

  • Catching Up with Lisp

    Support for multicore and Big Data are among the upcoming features of Franz's Lisp-based tools Lisp - Programming - Languages - FAQs Help and Tutorials - Compilers and Interpreters

    Read the article

  • Performance affects of compressing Program Files on Windows / NTFS

    - by SRobertJames
    What are the performance affects of compressing Program Files on Windows NTFS? On a fast, multicore machine, the overhead of decompression is minimal. Machines are generally disk bound, and if you can reduce the disk load by compression, you often speed things up. (Microsoft says that the built in compression of Windows Search indexes actually improves speed for this reason.) On the other hand, Windows' virtual memory is complicated. Perhaps if files are compressed, they can't be paged out simply. And there may be other issues. In short: On a fast, multicore machine with a relatively slow disk, what performance affects will compressing Program Files have?

    Read the article

  • The Cloud is STILL too slow!

    - by harry.foxwell(at)oracle.com
    If you've been in the computing industry sufficiently long enough to remember dialup modems and other "ancient" technologies, you might be tempted to marvel at today's wonderfully powerful multicore PCs, ginormous disks, and blazingly fast networks.  Wow, you're in Internet Nirvana, right!  Well, no, not by a long shot.Considering the exponentially growing expectations of what the Web, that is, "the Cloud", is supposed to provide, today's Web/Cloud services are still way too slow.Already we are seeing cloud-enabled consumer devices that are stressing even the most advanced public network services.  Like the iPad and its competitors, ever more powerful smart-phones, and an imminent hoard of special purpose gadgets such as the proposed "cloud camera" (see http://gdgt.com/discuss/it-time-cloud-camera-found-out-cnr/ ).And at the same time that the number and type of cloud services are growing, user tolerance for even the slightest of download delays is rapidly decreasing.  Ten years ago Web developers followed the "8-Second Rule", (average time a typical Web user would tolerate for a page to download and render).  Not anymore; now it's less than 3 seconds, and only a bit longer for mobile devices (see http://www.technologyreview.com/files/54902/GoogleSpeed_charts.pdf).  How spoiled we've become!Google, among others, recognizes this problem and is working to encourage the development of a faster Web (see http://www.technologyreview.com/web/32338/). They, along with their competitors and ISPs, will have to encourage and support significantly better Web performance in order to provide the types of services envisioned for the Cloud.  How will they do this? Through the development of faster components, better use of caching technologies, and the really tough one - exploiting parallelism. Not that parallel technologies like multicore processors are hard to build...we already have them.  It's just that we're not that good yet at using them effectively.  And if we don't get better, users will abandon cloud-based services...in less than 3 seconds.

    Read the article

  • What is the best way to exploit multicores when making multithread games?

    - by Keeper
    Many people suggest to write a program, and then start optimizing it. But I think that when it's coming to multithreading with multicore, a little think ahead is required. I've read about using threads, and experienced it myself during some courses at the university (still a student). The big question is simple, but a bit abstract: What thread related steps in game design do I need to take, before implementation? Now trying to be more specific. Let's say, as an example, that I'm making a small board game (like Monopoly) that I want to be multithreaded. My goal Is that this multithreaded game will exploit the best of the multicore system, lets say 4-6 cores (like in i7 processors). My answer to this question at the moment is, one thread for each of these four basic components: GUI User Input / Output AI (computer rival) Other game related calculations (like shortest path from A to B, or level up status change) I'm not an expert (yet!), and I'm sure there are better answers out there. Any suggestion, answer, different approach will be helpful. Some thoughts: Maybe splitting the main database is a good way.. (or total disaster.. )

    Read the article

facebook twitter digg google delicious technorati stumbleupon myspace wordpress linkedin gmail igoogle windows live tumblr viadeo yahoo buzz yahoo mail yahoo bookmarks favorites email print

< Previous Page | 1 2 3 4 5 6 7  | Next Page >