Search Results

Search found 740 results on 30 pages for 'processors'.

Page 5/30 | < Previous Page | 1 2 3 4 5 6 7 8 9 10 11 12  | Next Page >

  • SQL Server Process Queue Race Condition

    - by William Edmondson
    I have an order queue that is accessed by multiple order processors through a stored procedure. Each processor passes in a unique ID which is used to lock the next 20 orders for its own use. The stored procedure then returns these records to the order processor to be acted upon. There are cases where multiple processors are able to retrieve the same 'OrderTable' record at which point they try to simultaneously operate on it. This ultimately results in errors being thrown later in the process. My next course of action is to allow each processor grab all available orders and just round robin the processors but I was hoping to simply make this section of code thread safe and allow the processors to grab records whenever they like. So Explicitly - Any idea why I am experiencing this race condition and how I can solve the problem. BEGIN TRAN UPDATE OrderTable WITH ( ROWLOCK ) SET ProcessorID = @PROCID WHERE OrderID IN ( SELECT TOP ( 20 ) OrderID FROM OrderTable WITH ( ROWLOCK ) WHERE ProcessorID = 0) COMMIT TRAN SELECT OrderID, ProcessorID, etc... FROM OrderTable WHERE ProcessorID = @PROCID

    Read the article

  • "Work stealing" vs. "Work shrugging"?

    - by John
    Why is it that I can find lots of information on "work stealing" and nothing on "work shrugging" as a dynamic load-balancing strategy? By "work-shrugging" I mean busy processors pushing excessive work towards less loaded neighbours rather than idle processors pulling work from busy neighbours ("work-stealing"). I think the general scalability should be the same for both strategies. However I believe that it is much more efficient for busy processors to wake idle processors if and when there is definitely work for them to do than having idle processors spinning or waking periodically to speculatively poll all neighbours for possible work. Anyway a quick google didn't show up anything under the heading of "Work Shrugging" or similar so any pointers to prior-art and the jargon for this strategy would be welcome. Clarification/Confession In more detail:- By "Work Shrugging" I actually envisage the work submitting processor (which may or may not be the target processor) being responsible for looking around the immediate locality of the preferred target processor (based on data/code locality) to decide if a near neighbour should be given the new work instead because they don't have as much work to do. I am talking about an atomic read of the immediate (typically 2 to 4) neighbours' estimated q length here. I do not think this is any more coupling than implied by the thieves polling & stealing from their neighbours - just much less often - or rather - only when it makes economic sense to do so. (I am assuming "lock-free, almost wait-free" queue structures in both strategies). Thanks.

    Read the article

  • Django-imagekit: how to reduce image quality with a preprocessor_spec ?

    - by pierre-guillaume-degans
    Hi, please excuse me for my ugly english :p I've created this simple model class, with a Preprocessor to reduce my photos'quality (the photos'extension is .JPG): from django.db import models from imagekit.models import ImageModel from imagekit.specs import ImageSpec from imagekit import processors class Preprocessor(ImageSpec): quality = 50 processors = [processors.Format] class Picture(ImageModel): image = models.ImageField(upload_to='pictures') class IKOptions: preprocessor_spec = Preprocessor The problem : pictures'quality are not reduced. :( Any idea to fix it ? Thank you very much ;)

    Read the article

  • Oracle’s Sun Server X4-8 with Built-in Elastic Computing

    - by kgee
    We are excited to announce the release of Oracle's new 8-socket server, Sun Server X4-8. It’s the most flexible 8-socket x86 server Oracle has ever designed, and also the most powerful. Not only does it use the fastest Intel® Xeon® E7 v2 processors, but also its memory, I/O and storage subsystems are all designed for maximum performance and throughput. Like its predecessor, the Sun Server X4-8 uses a “glueless” design that allows for maximum performance for Oracle Database, while also reducing power consumption and improving reliability. The specs are pretty impressive. Sun Server X4-8 supports 120 cores (or 240 threads), 6 TB memory, 9.6 TB HDD capacity or 3.2 TB SSD capacity, contains 16 PCIe Gen 3 I/O expansion slots, and allows for up to 6.4 TB Sun Flash Accelerator F80 PCIe Cards. The Sun Server X4-8 is also the most dense x86 server with its 5U chassis, allowing 60% higher rack-level core and DIMM slot density than the competition.  There has been a lot of innovation in Oracle’s x86 product line, but the latest and most significant is a capability called elastic computing. This new capability is built into each Sun Server X4-8.   Elastic computing starts with the Intel processor. While Intel provides a wide range of processors each with a fixed combination of core count, operational frequency, and power consumption, customers have been forced to make tradeoffs when they select a particular processor. They have had to make educated guesses on which particular processor (core count/frequency/cache size) will be best suited for the workload they intend to execute on the server.Oracle and Intel worked jointly to define a new processor, the Intel Xeon E7-8895 v2 for the Sun Server X4-8, that has unique characteristics and effectively combines the capabilities of three different Xeon processors into a single processor. Oracle system design engineers worked closely with Oracle’s operating system development teams to achieve the ability to vary the core count and operating frequency of the Xeon E7-8895 v2 processor with time without the need for a system level reboot.  Along with the new processor, enhancements have been made to the system BIOS, Oracle Solaris, and Oracle Linux, which allow the processors in the system to dynamically clock up to faster speeds as cores are disabled and to reach higher maximum turbo frequencies for the remaining active cores. One customer, a stock market trading company, will take advantage of the elastic computing capability of Sun Server X4-8 by repurposing servers between daytime stock trading activity and nighttime stock portfolio processing, daily, to achieve maximum performance of each workload.To learn more about Sun Server X4-8, you can find more details including the data sheet and white papers here.Josh Rosen is a Principal Product Manager for Oracle’s x86 servers, focusing on Oracle’s operating systems and software. He previously spent more than a decade as a developer and architect of system management software. Josh has worked on system management for many of Oracle's hardware products ranging from the earliest blade systems to the latest Oracle x86 servers.

    Read the article

  • HP ProLiant DL980-Oracle TPC-C Benchmark spat

    - by jchang
    The Register reported a spat between HP and Oracle on the TPC-C benchmark. Per above, HP submitted a TPC-C result of 3,388,535 tpm-C for their ProLiant DL980 G7 (8 Xeon X7560 processors), with a cost of $0.63 per tpm-C. Oracle has refused permission to publish. Late last year (2010) Oracle published a result of 30M tpm-C for a 108 processors (sockets) SPARC cluster ($30M complete system cost). Oracle is now comparing this to the HP Superdome result from 2007 of 4M tpm-C at $2.93 per tpm-C, calling...(read more)

    Read the article

  • Windows 7 BSOD with Service Exception Error and Randomly Reboots

    - by Jason Shultz
    I've got a windows 7 laptop that BSOD with a Service Exception Error when I connect to a wireless network. It also does it when it's just sitting still doing nothing. I ran bluescreenview and here are the last four BSOD's from today: ================================================== Dump File : 051210-18642-01.dmp Crash Time : 5/12/2010 8:36:14 AM Bug Check String : SYSTEM_SERVICE_EXCEPTION Bug Check Code : 0x0000003b Parameter 1 : 00000000`c000001d Parameter 2 : fffff880`00000000 Parameter 3 : fffff880`06fda160 Parameter 4 : 00000000`00000000 Caused By Driver : Ntfs.sys Caused By Address : Ntfs.sys+7f030 File Description : Product Name : Company : File Version : Processor : x64 Computer Name : Full Path : C:\Windows\Minidump\051210-18642-01.dmp Processors Count : 2 Major Version : 15 Minor Version : 7600 ================================================== ================================================== Dump File : 051210-16551-01.dmp Crash Time : 5/12/2010 8:41:04 AM Bug Check String : SYSTEM_SERVICE_EXCEPTION Bug Check Code : 0x0000003b Parameter 1 : 00000000`c000001d Parameter 2 : fffff880`00000000 Parameter 3 : fffff880`06f40160 Parameter 4 : 00000000`00000000 Caused By Driver : ntoskrnl.exe Caused By Address : ntoskrnl.exe+70600 File Description : NT Kernel & System Product Name : Microsoft® Windows® Operating System Company : Microsoft Corporation File Version : 6.1.7600.16539 (win7_gdr.100226-1909) Processor : x64 Computer Name : Full Path : C:\Windows\Minidump\051210-16551-01.dmp Processors Count : 2 Major Version : 15 Minor Version : 7600 ================================================== ================================================== Dump File : 051210-17269-01.dmp Crash Time : 5/12/2010 8:45:51 AM Bug Check String : SYSTEM_SERVICE_EXCEPTION Bug Check Code : 0x0000003b Parameter 1 : 00000000`c000001d Parameter 2 : fffff880`00000000 Parameter 3 : fffff880`07db1160 Parameter 4 : 00000000`00000000 Caused By Driver : Ntfs.sys Caused By Address : Ntfs.sys+7f030 File Description : Product Name : Company : File Version : Processor : x64 Computer Name : Full Path : C:\Windows\Minidump\051210-17269-01.dmp Processors Count : 2 Major Version : 15 Minor Version : 7600 ================================================== ================================================== Dump File : 051210-19453-01.dmp Crash Time : 5/12/2010 5:46:25 PM Bug Check String : SYSTEM_SERVICE_EXCEPTION Bug Check Code : 0x0000003b Parameter 1 : 00000000`c000001d Parameter 2 : fffff880`00000000 Parameter 3 : fffff880`02625160 Parameter 4 : 00000000`00000000 Caused By Driver : win32k.sys Caused By Address : win32k.sys+2d4201 File Description : Product Name : Company : File Version : Processor : x64 Computer Name : Full Path : C:\Windows\Minidump\051210-19453-01.dmp Processors Count : 2 Major Version : 15 Minor Version : 7600 ==================================================  

    Read the article

  • Making your WCF Web Apis to speak in multiple languages

    - by cibrax
    One of the key aspects of how the web works today is content negotiation. The idea of content negotiation is based on the fact that a single resource can have multiple representations, so user agents (or clients) and servers can work together to chose one of them. The http specification defines several “Accept” headers that a client can use to negotiate content with a server, and among all those, there is one for restricting the set of natural languages that are preferred as a response to a request, “Accept-Language”. For example, a client can specify “es” in this header for specifying that he prefers to receive the content in spanish or “en” in english. However, there are certain scenarios where the “Accept-Language” header is just not enough, and you might want to have a way to pass the “accepted” language as part of the resource url as an extension. For example, http://localhost/ProductCatalog/Products/1.es” returns all the descriptions for the product with id “1” in spanish. This is useful for scenarios in which you want to embed the link somewhere, such a document, an email or a page.  Supporting both scenarios, the header and the url extension, is really simple in the new WCF programming model. You only need to provide a processor implementation for any of them. Let’s say I have a resource implementation as part of a product catalog I want to expose with the WCF web apis. [ServiceContract][Export]public class ProductResource{ IProductRepository repository;  [ImportingConstructor] public ProductResource(IProductRepository repository) { this.repository = repository; }  [WebGet(UriTemplate = "{id}")] public Product Get(string id, HttpResponseMessage response) { var product = repository.GetById(int.Parse(id)); if (product == null) { response.StatusCode = HttpStatusCode.NotFound; response.Content = new StringContent(Messages.OrderNotFound); }  return product; }} The Get method implementation in this resource assumes the desired culture will be attached to the current thread (Thread.CurrentThread.Culture). Another option is to pass the desired culture as an additional argument in the method, so my processor implementation will handle both options. This method is also using an auto-generated class for handling string resources, Messages, which is available in the different cultures that the service implementation supports. For example, Messages.resx contains “OrderNotFound”: “Order Not Found” Messages.es.resx contains “OrderNotFound”: “No se encontro orden” The processor implementation bellow tackles the first scenario, in which the desired language is passed as part of the “Accept-Language” header. public class CultureProcessor : Processor<HttpRequestMessage, CultureInfo>{ string defaultLanguage = null;  public CultureProcessor(string defaultLanguage = "en") { this.defaultLanguage = defaultLanguage; this.InArguments[0].Name = HttpPipelineFormatter.ArgumentHttpRequestMessage; this.OutArguments[0].Name = "culture"; }  public override ProcessorResult<CultureInfo> OnExecute(HttpRequestMessage request) { CultureInfo culture = null; if (request.Headers.AcceptLanguage.Count > 0) { var language = request.Headers.AcceptLanguage.First().Value; culture = new CultureInfo(language); } else { culture = new CultureInfo(defaultLanguage); }  Thread.CurrentThread.CurrentCulture = culture; Messages.Culture = culture;  return new ProcessorResult<CultureInfo> { Output = culture }; }}   As you can see, the processor initializes a new CultureInfo instance with the value provided in the “Accept-Language” header, and set that instance to the current thread and the auto-generated resource class with all the messages. In addition, the CultureInfo instance is returned as an output argument called “culture”, making possible to receive that argument in any method implementation   The following code shows the implementation of the processor for handling languages as url extensions.   public class CultureExtensionProcessor : Processor<HttpRequestMessage, Uri>{ public CultureExtensionProcessor() { this.OutArguments[0].Name = HttpPipelineFormatter.ArgumentUri; }  public override ProcessorResult<Uri> OnExecute(HttpRequestMessage httpRequestMessage) { var requestUri = httpRequestMessage.RequestUri.OriginalString;  var extensionPosition = requestUri.LastIndexOf(".");  if (extensionPosition > -1) { var extension = requestUri.Substring(extensionPosition + 1);  var query = httpRequestMessage.RequestUri.Query;  requestUri = string.Format("{0}?{1}", requestUri.Substring(0, extensionPosition), query); ;  var uri = new Uri(requestUri);  httpRequestMessage.Headers.AcceptLanguage.Clear();  httpRequestMessage.Headers.AcceptLanguage.Add(new StringWithQualityHeaderValue(extension));  var result = new ProcessorResult<Uri>();  result.Output = uri;  return result; }  return new ProcessorResult<Uri>(); }} The last step is to inject both processors as part of the service configuration as it is shown bellow, public void RegisterRequestProcessorsForOperation(HttpOperationDescription operation, IList<Processor> processors, MediaTypeProcessorMode mode){ processors.Insert(0, new CultureExtensionProcessor()); processors.Add(new CultureProcessor());} Once you configured the two processors in the pipeline, your service will start speaking different languages :). Note: Url extensions don’t seem to be working in the current bits when you are using Url extensions in a base address. As far as I could see, ASP.NET intercepts the request first and tries to route the request to a registered ASP.NET Http Handler with that extension. For example, “http://localhost/ProductCatalog/products.es” does not work, but “http://localhost/ProductCatalog/products/1.es” does.

    Read the article

  • Oracle Linux Delivers Top CPU Benchmark Results on Sun Blades

    - by sergio.leunissen
    From the Performance and Best Practices blog: Fresh SPEC CPU2006 results for Sun Blade X6275 M2 Server Modules running Oracle Linux 5.5. The highlights: The dual-node Sun Blade X6275 M2 server module, equipped with two Intel Xeon X5670 2.93 GHz processors per node and running the Oracle Enterprise Linux 5.5 operating system delivered the best SPECint_rate2006 and SPECfp_rate2006 benchmark results for all systems with Intel Xeon processor 5000 sequence. With a SPECint_rate2006 benchmark result of 679, the Sun Blade X6275 M2 server module, with two compute nodes per blade, delivers maximum performance for space constrained environments. Comparing Oracle's dual-node blade to HP's dual-node blade server, based on their single node performance, the Sun Blade X6275 M2 server module SPECfp_rate2006 score of 241 outperforms the best published HP ProLiant BL2X220c G5 server score by 3.2x. A single node of a Sun Blade X6275 M2 server module using 2.93 GHz Intel Xeon X5670 processors delivered 37% improvement in SPECint_rate2006 benchmark results and 22% improvement in SPECfp_rate2006 benchmark results compared to the previous generation Sun Blade X6275 server module. Both nodes of a Sun Blade X6275 M2 server module using 2.93 GHz Intel Xeon X5670 processors delivered 59% improvement on the SPECint_rate2006 benchmark and 40% improvement on the SPECfp_rate2006 benchmark compared to the previous generation Sun Blade X6275 server module.

    Read the article

  • SPARC64 VII+ Processor Core License Factor Reduced by 33%

    - by john.shell
    The Oracle processor core license factor has been a popular topic the last few months.  For those partners new to Oracle software licensing, the processor core license factor determines the number licensed CPUs that are required when running Oracle software (those charged on a per-CPU basis) on multi-core processors.My last entry talked about the core factor reduction for our T3 processor.  The core license factor for our newly announced SPARC64 VII+ processor is 0.5, which is a 33% reduction from the 0.75 rate used with our SPARC64 VI and VII processors.What does this mean for our partners?  Increased opportunity.  This change, similar to our T3-based systems, means that our hardware is the preferred platform for Oracle software. Still a little dizzy on the breadth of Oracle's software offering?  Do a simple scan of Oracle's software price lists. Consider this your target market.This change allows you to focus on total solution price or price/performance, not server prices or per core performance (a standard IBM sales tactic). That's the offensive side of the game.  Don't forget your defense.  One of the biggest customer benefits around the M-Series is investment protection.  The combination of a simple processor/board upgrade, along with a reduction in processor core license factor, makes upgrading one of the best financial moves for our customers.    One reminder.  The update to the processor core license factor only applies to the new VII+ processor - NOT the SPARC64 VI or VII processors.  You can find the official table here.

    Read the article

  • Is it possible to use a dual processor computer as your desktop?

    - by Ivo
    I've seen some people suggesting to get a motherboard that supports two processors and stick two Xeon Nehalem processors in it. Could you use this system as a desktop PC or is this useless or even impossible? It's more hypothetical question if Windows 7 would support such a set-up. I know you could just take an i7, but wouldn't two of those processors be a whole lot more awesome? Like the previous generation Skulltrails? The idea would be to have a motherboard like this ASUS Z8NA-D6C Dual LGA 1366 Intel 5500 ATX and two Xeons (since I don't think i7's could be used) Intel Xeon E5405 Harpertown to run something like Windows 7 Ultimate.

    Read the article

  • 912 stream processor available in OpenCL

    - by tugrul büyükisik
    I am thinking of assembling this system: AMD CPU (A8-3870 APU which has Radeon HD 6550D inside: 400 stream processors:xxx GFLOPS) nearly 110$ AMD Graphics card: HD 7750 (512 stream processors:819 GFLOPS peak performance) nearly 170$ Appropriate ram (1600MHz bus) Mainboard What GFLOPS level can I reach as a stable mode with using OpenCL and similar programs? Can I use all 912 stream processors at the same time? I am not trying to do a VS question. I need to know what could be better for scientific computing (%75 of the time) and gaming (%25 of the time) because I have a low budget. With "scientific calculations" I mean fluid dynamics/solid state physics simulating; with games I mean those that need openCL and PhysX.

    Read the article

  • Videos: Getting Started with Java Embedded

    - by Tori Wieldt
    Are you a Java developer? That means you can write applications for embedded processors! There are new six new videos up on the YouTube/Java channel that you can watch to get more information. To get an overview, watch James Allen of Oracle Global Business Development give OTN a tour of the Oracle booth at ARM Techcon. He also explains the huge opportunity for Java in the embedded space. These videos from Oracle Engineering show you how to leverage your knowledge to seamlessly develop in a space that is really taking off. Java SE Embedded Development Made Easy, Part 1 This video demonstrates how developers already familiar with the Java SE development paradigm can leverage their knowledge to seamlessly develop on very capable embedded processors. Part one of a two-part series. Java SE Embedded Development Made Easy, Part 2 This video demonstrates how developers already familiar with the Java SE development paradigm can leverage their knowledge to seamlessly develop on very capable embedded processors. Part two of a two-part series. Mobile Database Synchronization - Healthcare Demonstration This video demonstrates how a good portion of Oracle's embedded technologies (Java SE-Embedded, Berkeley DB, Database Mobile Server) can be applied to a medical application. Tomcat Micro Cluster See how multiple embedded devices installed with Java Standard Edition HotSpot for Armv5/Linux and Apache Tomcat can be configured as a micro cluster. Java Embedded Partnerships Kevin Smith of Oracle Technical Business Development explains what's new for partners and Java developers in the embedded space. Learn how you can start prototyping for Qualcomm's new Orion board before it's available. (Sorry about the video quality, the booth lights were weird.)   Visit the YouTube/Java channel for other great Java videos. <fade to black>

    Read the article

  • What hardware makes a good MongoDB Server ? Where to get it ?

    - by João Pinto Jerónimo
    Suppose you're on dell.com right now and you're buying a server to run your MongoDB database for your small startup. You will have to handle literally tens of thousands of writes and reads per minute (but small objects). Would you go for 2 processors ? Invest more on RAM ? I've heard (correct me if I'm wrong) MongoDB handles the most it can on the RAM and then flushes everything to the disk, in that case I should invest on a CPU with a large L2 cache, probably 40GB of RAM and a solid state drive.. right ? Would I be better off with a high end (~$11,309, 2 expensive processors, 96GB of RAM) server or 2x(~$6,419, 2 expensive processors, 12GB of RAM) servers ? Is Dell ok or do you have better sugestions ? (I'm outside the US, on Portugal)

    Read the article

  • whats the name of this pattern?

    - by Wes
    I see this a lot in frameworks. You have a master class which other classes register with. The master class then decides which of the registered classes to delegate the request to. An example based passed in class may be something this. public interface Processor { public boolean canHandle(Object objectToHandle); public void handle(Object objectToHandle); } public class EvenNumberProcessor extends Processor { public boolean canHandle(Object objectToHandle) { if (!isNumeric(objectToHandle)){ return false } return isEven(objectToHandle); } public void handle(objectToHandle) { //Optionally call canHandleAgain to ensure the calling class is fufilling its contract doSomething(); } } public class OddNumberProcessor extends Processor { public boolean canHandle(Object objectToHandle) { if (!isNumeric(objectToHandle)){ return false } return isOdd(objectToHandle); } public void handle(objectToHandle) { //Optionally call canHandleAgain to ensure the calling class is fufilling its contract doSomething(); } } //Can optionally implement processor interface public class processorDelegator { private List processors; public void addProcessor(Processor processor) { processors.add(processor); } public void process(Object objectToProcess) { //Lookup relevant processor either by keeping a list of what they can process //Or query each one to see if it can process the object. chosenProcessor=chooseProcessor(objectToProcess); chosenProcessor.handle(objectToProcess); } } Note there are a few variations I see on this. In one variation the sub classes provide a list of things they can process which the ProcessorDelegator understands. The other variation which is listed above in fake code is where each is queried in turn. This is similar to chain of command but I don't think its the same as chain of command means that the processor needs to pass to other processors. The other variation is where the ProcessorDelegator itself implements the interface which means you can get trees of ProcessorDelegators which specialise further. In the above example you could have a numeric processor delegator which delegates to an even/odd processor and a string processordelegator which delegates to different strings. My question is does this pattern have a name.

    Read the article

  • Is it possible to use a dual processor computer as your desktop?

    - by Ivo Flipse
    I've seen some people suggesting to get a motherboard that supports two processors and stick two Xeon Nehalem processors in it. Could you use this system as a desktop PC or is this useless or even impossible? It's more hypothetical question if Windows 7 would support such a set-up. I know you could just take an i7, but wouldn't two of those processors be a whole lot more awesome? Like the previous generation Skulltrails? The idea would be to have a motherboard like this ASUS Z8NA-D6C Dual LGA 1366 Intel 5500 ATX and two Xeons (since I don't think i7's could be used) Intel Xeon E5405 Harpertown to run something like Windows 7 Ultimate.

    Read the article

  • recommendation for configuration for a multi-core guestOS

    - by reidLinden
    Hi there, I've just received an upgraded Host machine, and am looking to push some of those advances to my workstations Guest OS(s). In particular, I used to have a single processor, with 2 cores, so my guestOS only had 1/1. Now, I've got a single processor with 8 cores, so I'm curious about what would be recommended for my GuestOS now? 1 processor/4 cores? 2 processors/2Cores? 4 processors/1 core? My instinct says to stick with the number of physical processors (or less), but, is that based on reality? I spent a good while looking for an answer to this, but perhaps my google-karma isn't in my favor today. Suggestions?

    Read the article

  • Critical Threads Optimization

    - by Rafael Vanoni
    Background One of the more common issues we've been seeing in the field is the growing difficulty in optimizing performance of multi-threaded applications. A good portion of this difficulty is due to the increasing complexity of modern processors that present various degrees of sharing relationships between hardware components. Take any current CMT processor and you'll find any number of CPUs sharing execution pipelines, floating point units, caches, etc. Consequently, applying the traditional recipe of one software thread for each CPU will have varying degrees of success, according to the layout of the underlying hardware. On top of this increasing complexity we've also seen processors with features that aim at dynamically resourcing software threads according to their utilization. Intel's Turbo Boost allows processors to increase their operating frequency if there is enough thermal headroom available and the processor isn't fully utilized. More recently, the SPARC T4 processor introduced dynamic threading, allowing each core to dynamically allocate more resources to its active CPUs. Both cases are in essence recognizing that current processors will be running a wide mix of workloads, some will be designed for throughput, others for low latency. The hardware is providing mechanisms to dynamically resource threads according to their runtime behavior. We're very aware of these challenges in Solaris, and have been working to provide the best out of box performance while providing mechanisms to further optimize applications when necessary. The Critical Threads Optimzation was introduced in Solaris 10 8/11 and Solaris 11 as one such mechanism that allows customers to both address issues caused by contention over shared hardware resources and explicitly take advantage of features such as T4's dynamic threading. What it is The basic idea is to allow performance critical threads to execute with more exclusive access to hardware resources. For example, when deploying an application that implements a producer/consumer model, it'll likely be advantageous to give the producer more exclusive access to the hardware instead of having it competing for resources with all the consumers. In the case of a T4 based system, we may want to have a producer running by itself on a single core and create one consumer for each of the remaining CPUs. With the Critical Threads Optimization we're extending the semantics of scheduling priorities (which thread should run first) to include priority over shared resources (which thread should have more "space"). Now the scheduler will not only run higher priority threads first: it will also provide them with more exclusive access to hardware resources if they are available. How does it work ? Using the previous example in Solaris 11, all you'd have to do would be to place the producer in the Fixed Priority (FX) scheduling class at priority 60, or in the Real Time (RT) class at any priority and Solaris will try to give it more "hardware space". On both Solaris 10 8/11 and Solaris 11 this can be achieved through the existing priocntl(1,2) and priocntlset(2) interfaces. If your application already assigns these priorities to performance critical threads, there's no additional step you need to take. One important aspect of this optimization is that it requires some level of idleness in the system, either as a result of sizing the application before hand or through periods of transient idleness during runtime. If the system is fully committed, the scheduler will put all the available CPUs to work.Best practices If you're an application developer, we encourage you to look into assigning the right priorities for the different threads in your application. Solaris provides different scheduling classes (Time Share, Interactive, Fair Share, Fixed Priority and Real Time) that offer different policies and behaviors. It is not always simple to figure out which set of threads are critical to the performance of a workload, and it may not always be feasible to take advantage of this optimization, but we believe that this can be correctly (and safely) done during development. Overall, the out of box performance in Solaris should meet your workload's requirements. If you are looking into that extra bit of performance, then the Critical Threads Optimization may be what you're looking for.

    Read the article

  • Is there a CPU that can be described as "Celeron D 4xx model"?

    - by romkyns
    The "D" letter after Celeron appears to only be used for processors numbered with 3xx. Celerons of the 4xx series do not seem to have the "D". And yet I am looking at a motherboard described as supporting these processors: Intel Celeron D 3xx and 4xx models Intel Pentium 4 5xx and 6xx models Intel Pentium D 8xx and 9xx models Intel Core 2 Duo models with LGA775 Is this compatible with a Celeron 450, sSpec SLAFZ, despite not having a "D" in its name?

    Read the article

  • Some Memory Slots Not Working on MSI FM2-A85XA-G65 Motherboard

    - by Mike Ciaraldi
    Short version of question: Does anyone have an MSI FM2-A85XA-G65 motherboard, who can confirm that all four memory slots work? Long version: Several months ago I bought an MSI FM2-A85XA-G65 motherboard at Newegg. At that point I installed an AMD A8-5500 processor and two sticks of Corsair Vengeance 8 GB DDR3-1866 memory, and put it into my file server. I installed the RAM in slots 1 and 3, as directed in the manual, to enable dual-channel memory access. It seemed to work fine, so I bought a second identical mobo (which arrived dead, but was quickly replaced by Newegg) and set of RAM, installed an A10-5800K, and put that into my production Linux machine. Again, it seemed to work well. Eventually I happened to notice that on the server only 8 GB of RAM appeared in the BIOS. I tried each of the slots and memory modules individually and in various combinations. I even swapped processors with the production machine. The result was that putting memory in slots 1 and 2 worked (showing a total of 16 GB), but any memory in slots 3 or 4 was not recognized. However, all four memory slots in the production machine worked, and I confirmed this with both processors. I contacted MSI and arranged to ship the defective mobo back to them for replacement under warranty. I did not want my file server to be down in the interim, and I had another machine I wanted to upgrade, so I bought a third identical mobo to use. That one had the same problem -- only memory slots 1 and 2 worked. I tested it thoroughly with multiple processors and memory sticks. I sent the defective mobo back to MSI and they sent me a new one. This has the same memory slot problem. So I sent it back. The replacement arrived the other day and shows the same problem. I contacted MSI yet again and they said that nobody else has reported memory slot problems on this board and it must be my processor. So my score so far is, out of six boards of this model, I have: One where all four slots work. One which was dead on arrival. Four where only memory slots 1 and 2 work. Before I tear my other machines apart and start swapping processors again I thought I would ask if anyone else has this exact model motherboard and could confirm that all four memory slots either do or do not work. According to MSI you should be able to just plug a single memory module into any of the slots and it will work (and it does on the one mobo I have which works correctly). If you have not yet used all four slots, this is a good time to test them so you know if you can expand your memory in the future. Thanks in advance to anyone who can help.

    Read the article

  • Duplication of Architecture State means physically extra?

    - by Doopy Doo
    Hyper-Threading Technology makes a single physical processor appear as two logical processors; the physical execution resources are shared and the architecture state is duplicated for the two logical processors. So, this means that there are two sets of basic registers such as Next Instruction Pointer, processor registers like AX, BX, CX etc physically embedded in the micro-processor chip, OR they(arch. state) are made to look two sets by some low level duplication by software/OS.

    Read the article

  • Difference between Content Protection and DRM

    - by BlueGene
    In this recent post about criticism regarding built-in DRM in Intels SandyBridge processors, Intel denies that there's any DRM in Sandybridge processors but goes on to say that Intel created Intel insider, an extra layer of content protection. Think of it as an armoured truck carrying the movie from the Internet to your display, it keeps the data safe from pirates, but still lets you enjoy your legally acquired movie in the best possible quality I'm confused now. So far I was thinking DRM is content protection. Can someone shed light on this?

    Read the article

  • RemoteFX Hardware For Home Use

    - by The Woo
    I would like to setup Windows Server 2008 R2 using RemoteFX at home, for a couple of users to all use the server (instead of buying each user a seperate computer). I have been trying to find what processors (Intel based) that support the SLAT that is apparently needed to run RemoteFX. I currently have a computer that has an i3 processor, but after testing it shows that it will not support it. Does anyone know which processors from Intel do support this?

    Read the article

  • Is Stopwatch really broken?

    - by Jakub Šturc
    At MSDN page for Stopwatch class I discovered link to interesting article which makes following statement about Stopwatch: However there are some serious issues: This can be unreliable on a PC with multiple processors. Due to a bug in the BIOS, Start() and Stop() must be executed on the same processor to get a correct result. This is unreliable on processors that do not have a constant clock speed (most processors can reduce the clock speed to conserve energy). This is explained in detail here. I am little confused. I've seen tons of examples of using Stopwatch and nobody mention this drawbacks. How serious is this? Should I avoid using Stopwatch?

    Read the article

  • Which parallel sorting algorithm has the best average case performance?

    - by Craig P. Motlin
    Sorting takes O(n log n) in the serial case. If we have O(n) processors we would hope for a linear speedup. O(log n) parallel algorithms exist but they have a very high constant. They also aren't applicable on commodity hardware which doesn't have anywhere near O(n) processors. With p processors, reasonable algorithms should take O(n/p log n/p) time. In the serial case, quick sort has the best runtime complexity on average. A parallel quick sort algorithm is easy to implement (see here and here). However it doesn't perform well since the very first step is to partition the whole collection on a single core. I have found information on many parallel sort algorithms but so far I have not seen anything pointing to a clear winner. I'm looking to sort lists of 1 million to 100 million elements in a JVM language running on 8 to 32 cores.

    Read the article

< Previous Page | 1 2 3 4 5 6 7 8 9 10 11 12  | Next Page >