Search Results

Search found 14643 results on 586 pages for 'performance comparison'.

Page 281/586 | < Previous Page | 277 278 279 280 281 282 283 284 285 286 287 288  | Next Page >

  • Expectations + Rewards = Innovation

    - by D'Arcy Lussier
    “Innovation” is a heavy word. We regard those that embrace it as “Innovators”. We describe organizations as being “Innovative”. We hold those associated with the word in high regard, even though its dictionary definition is very simple: Introducing something new. What our culture has done is wrapped Innovation in white robes and a gold crown. Innovation is rarely just introducing something new. Innovations and innovators are typically associated with other terms: groundbreaking, genius, industry-changing, creative, leading. Being a true innovator and creating innovations are a big deal, and something companies try to strive for…or at least say they strive for. There’s huge value in being recognized as an innovator in an industry, since the idea is that innovation equates to increased profitability. IBM ran an ad a few years back that showed what their view of innovation is: “The point of innovation is to make actual money.” If the money aspect makes you feel uneasy, consider it another way: the point of innovation is to <insert payoff here>. Companies that innovate will be more successful. Non-profits that innovate can better serve their target clients. Governments that innovate can better provide services to their citizens. True innovation is not easy to come by though. As with anything in business, how well an organization will innovate is reliant on the employees it retains, the expectations placed on those employees, and the rewards available to them. In a previous blog post I talked about one formula: Right Employees + Happy Employees = Productive Employees I want to introduce a new one, that builds upon the previous one: Expectations + Rewards = Innovation  The level of innovation your organization will realize is directly associated with the expectations you place on your staff and the rewards you make available to them. Expectations We may feel uncomfortable with the idea of placing expectations on our staff, mainly because expectation has somewhat of a negative or cold connotation to it: “I expect you to act this way or else!” The problem is in the or-else part…we focus on the negative aspects of failing to meet expectations instead of looking at the positive side. “I expect you to act this way because it will produce <insert benefit here>”. Expectations should not be set to punish but instead be set to ensure quality. At a recent conference I spoke with some Microsoft employees who told me that you have five years from starting with the company to reach a “Senior” level. If you don’t, then you’re let go. The expectation Microsoft placed on their staff is that they should be working towards improving themselves, taking more responsibility, and thus ensure that there is a constant level of quality in the workforce. Rewards Let me be clear: a paycheck is not a reward. A paycheck is simply the employer’s responsibility in the employee/employer relationship. A paycheck will never be the key motivator to drive innovation. Offering employees something over and above their required compensation can spur them to greater performance and achievement. Working in the food service industry, this tactic was used again and again: whoever has the highest sales over lunch will receive a free lunch/gift certificate/entry into a draw/etc. There was something to strive for, to try beyond the baseline of what our serving jobs were. It was through this that innovative sales techniques would be tried and honed, with key servers being top sellers time and time again. At a code camp I spoke at, I was amazed to see that all the employees from one company receive $100 Visa gift cards as a thank you for taking time to speak. Again, offering something over and above that can give that extra push for employees. Rewards work. But what about the fairness angle? In the restaurant example I gave, there were servers that would never win the competition. They just weren’t good enough at selling and never seemed to get better. So should those that did work at performing better and produce more sales for the restaurant not get rewarded because those who weren’t working at performing better might get upset? Of course not! Organizations succeed because of their top performers and those that strive to join their ranks. The Expectation/Reward Graph While the Expectations + Rewards = Innovation formula may seem like a simple mathematics formula, there’s much more going under the hood. In fact there are three different outcomes that could occur based on what you put in as values for Expectations and Rewards. Consider the graph below and the descriptions that follow: Disgruntled – High Expectation, Low Reward I worked at a company where the mantra was “Company First, Because We Pay You”. Even today I still hear stories of how this sentiment continues to be perpetuated: They provide you a paycheck and a means to live, therefore you should always put them as your top priority. Of course, this is a huge imbalance in the expectation/reward equation. Why would anyone willingly meet high expectations of availability, workload, deadlines, etc. when there is no reward other than a paycheck to show for it? Remember: paychecks are not rewards! Instead, you see employees be disgruntled which not only affects the level of production but also the level of quality within an organization. It also means that you see higher turnover. Complacent – Low Expectation, Low Reward Complacency is a systemic problem that typically exists throughout all levels of an organization. With no real expectations or rewards, nobody needs to excel. In fact, those that do try to innovate, improve, or introduce new things into the organization might be shunned or pushed out by the rest of the staff who are just doing things the same way they’ve always done it. The bigger issue for the organization with low/low values is that at best they’ll never grow beyond their current size (and may shrink actually), and at worst will cease to exist. Entitled – Low Expectation, High Reward It’s one thing to say you have the best people and reward them as such, but its another thing to actually have the best people and reward them as such. Organizations with Entitled employees are the former: their organization provides them with all types of comforts, benefits, and perks. But there’s no requirement before the rewards are dolled out, and there’s no short-list of who receives the rewards. Everyone in the company is treated the same and is given equal share of the spoils. Entitlement is actually almost identical with Complacency with one notable difference: just try to introduce higher expectations into an entitled organization! Entitled employees have been spoiled for so long that they can’t fathom having rewards taken from them, or having to achieve specific levels of performance before attaining them. Those running the organization also buy in to the Entitled sentiment, feeling that they must persist the same level of comforts to appease their staff…even though the quality of the employee pool may be suspect. Innovative – High Expectation, High Reward Finally we have the Innovative organization which places high expectations but also provides high rewards. This organization gets it: if you truly want the best employees you need to apply equal doses of pressure and praise. Realize that I’m not suggesting crazy overtime or un-realistic working conditions. I do not agree with the “Glengary-Glenross” method of encouragement. But as anyone who follows sports can tell you, the teams that win are the ones where the coaches push their players to be their best; to achieve new levels of performance that they didn’t know they could receive. And the result for the players is more money, fame, and opportunity. It’s in this environment that organizations can focus on innovation – true innovation that builds the business and allows everyone involved to truly benefit. In Closing Organizations love to use the word “Innovation” and its derivatives, but very few actually do innovate. For many, the term has just become another marketing buzzword to lump in with all the other business terms that get overused. But for those organizations that truly get the value of innovation, they will be the ones surging forward while other companies simply fade into the background. And they will be the organizations that expect more from their employees, and give them their just rewards.

    Read the article

  • Join the Authors of SSIS Design Patterns at the PASS Summit 2012!

    - by andyleonard
    My fellow authors and I will be presenting a day-long pre-conference session titled SSIS Design Patterns at the PASS Summit 2012 in Seattle Monday 5 Nov 2012! Register to learn patterns for: Package execution Package logging Loading flat file sources Loading XML sources Loading the cloud Dynamic package generation SSIS Frameworks Data warehouse ETL Data flow performance   Presenting this session: Matt Masson Tim Mitchell Jessica Moss Michelle Ufford Andy Leonard I hope to see you in Seattle!...(read more)

    Read the article

  • Pentaho: Open Source BI Sales Soar

    <b>The VAR Guy:</b> "Pentaho, the open source business intelligence company, generated record results in 1Q 2010, according to VP of Marketing Joe McGonnell. Pentaho attributes much of its performance to a growing channel partner program."

    Read the article

  • Stairway to Server-side Tracing - Level 10: Profiler versus Server-Side tracing

    Compares and contrasts tracing using Profiler with server-side tracing, illustrating important performance differences so that one can choose the right tool for the task at hand. Make working with SQL a breezeSQL Prompt 5.3 is the effortless way to write, edit, and explore SQL. It's packed with features such as code completion, script summaries, and SQL reformatting, that make working with SQL a breeze. Try it now.

    Read the article

  • Developing a Cost Model for Cloud Applications

    - by BuckWoody
    Note - please pay attention to the date of this post. As much as I attempt to make the information below accurate, the nature of distributed computing means that components, units and pricing will change over time. The definitive costs for Microsoft Windows Azure and SQL Azure are located here, and are more accurate than anything you will see in this post: http://www.microsoft.com/windowsazure/offers/  When writing software that is run on a Platform-as-a-Service (PaaS) offering like Windows Azure / SQL Azure, one of the questions you must answer is how much the system will cost. I will not discuss the comparisons between on-premise costs (which are nigh impossible to calculate accurately) versus cloud costs, but instead focus on creating a general model for estimating costs for a given application. You should be aware that there are (at this writing) two billing mechanisms for Windows and SQL Azure: “Pay-as-you-go” or consumption, and “Subscription” or commitment. Conceptually, you can consider the former a pay-as-you-go cell phone plan, where you pay by the unit used (at a slightly higher rate) and the latter as a standard cell phone plan where you commit to a contract and thus pay lower rates. In this post I’ll stick with the pay-as-you-go mechanism for simplicity, which should be the maximum cost you would pay. From there you may be able to get a lower cost if you use the other mechanism. In any case, the model you create should hold. Developing a good cost model is essential. As a developer or architect, you’ll most certainly be asked how much something will cost, and you need to have a reliable way to estimate that. Businesses and Organizations have been used to paying for servers, software licenses, and other infrastructure as an up-front cost, and power, people to the systems and so on as an ongoing (and sometimes not factored) cost. When presented with a new paradigm like distributed computing, they may not understand the true cost/value proposition, and that’s where the architect and developer can guide the conversation to make a choice based on features of the application versus the true costs. The two big buckets of use-types for these applications are customer-based and steady-state. In the customer-based use type, each successful use of the program results in a sale or income for your organization. Perhaps you’ve written an application that provides the spot-price of foo, and your customer pays for the use of that application. In that case, once you’ve estimated your cost for a successful traversal of the application, you can build that into the price you charge the user. It’s a standard restaurant model, where the price of the meal is determined by the cost of making it, plus any profit you can make. In the second use-type, the application will be used by a more-or-less constant number of processes or users and no direct revenue is attached to the system. A typical example is a customer-tracking system used by the employees within your company. In this case, the cost model is often created “in reverse” - meaning that you pilot the application, monitor the use (and costs) and that cost is held steady. This is where the comparison with an on-premise system becomes necessary, even though it is more difficult to estimate those on-premise true costs. For instance, do you know exactly how much cost the air conditioning is because you have a team of system administrators? This may sound trivial, but that, along with the insurance for the building, the wiring, and every other part of the system is in fact a cost to the business. There are three primary methods that I’ve been successful with in estimating the cost. None are perfect, all are demand-driven. The general process is to lay out a matrix of: components units cost per unit and then multiply that times the usage of the system, based on which components you use in the program. That sounds a bit simplistic, but using those metrics in a calculation becomes more detailed. In all of the methods that follow, you need to know your application. The components for a PaaS include computing instances, storage, transactions, bandwidth and in the case of SQL Azure, database size. In most cases, architects start with the first model and progress through the other methods to gain accuracy. Simple Estimation The simplest way to calculate costs is to architect the application (even UML or on-paper, no coding involved) and then estimate which of the components you’ll use, and how much of each will be used. Microsoft provides two tools to do this - one is a simple slider-application located here: http://www.microsoft.com/windowsazure/pricing-calculator/  The other is a tool you download to create an “Return on Investment” (ROI) spreadsheet, which has the advantage of leading you through various questions to estimate what you plan to use, located here: https://roianalyst.alinean.com/msft/AutoLogin.do?d=176318219048082115  You can also just create a spreadsheet yourself with a structure like this: Program Element Azure Component Unit of Measure Cost Per Unit Estimated Use of Component Total Cost Per Component Cumulative Cost               Of course, the consideration with this model is that it is difficult to predict a system that is not running or hasn’t even been developed. Which brings us to the next model type. Measure and Project A more accurate model is to actually write the code for the application, using the Software Development Kit (SDK) which can run entirely disconnected from Azure. The code should be instrumented to estimate the use of the application components, logging to a local file on the development system. A series of unit and integration tests should be run, which will create load on the test system. You can use standard development concepts to track this usage, and even use Windows Performance Monitor counters. The best place to start with this method is to use the Windows Azure Diagnostics subsystem in your code, which you can read more about here: http://blogs.msdn.com/b/sumitm/archive/2009/11/18/introducing-windows-azure-diagnostics.aspx This set of API’s greatly simplifies tracking the application, and in fact you can use this information for more than just a cost model. After you have the tracking logs, you can plug the numbers into ay of the tools above, which should give a representative cost or in some cases a unit cost. The consideration with this model is that the SDK fabric is not a one-to-one comparison with performance on the actual Windows Azure fabric. Those differences are usually smaller, but they do need to be considered. Also, you may not be able to accurately predict the load on the system, which might lead to an architectural change, which changes the model. This leads us to the next, most accurate method for a cost model. Sample and Estimate Using standard statistical and other predictive math, once the application is deployed you will get a bill each month from Microsoft for your Azure usage. The bill is quite detailed, and you can export the data from it to do analysis, and using methods like regression and so on project out into the future what the costs will be. I normally advise that the architect also extrapolate a unit cost from those metrics as well. This is the information that should be reported back to the executives that pay the bills: the past cost, future projected costs, and unit cost “per click” or “per transaction”, as your case warrants. The challenge here is in the model itself - statistical methods are not foolproof, and the larger the sample (in this case I recommend the entire population, not a smaller sample) is key. References and Tools Articles: http://blogs.msdn.com/b/patrick_butler_monterde/archive/2010/02/10/windows-azure-billing-overview.aspx http://technet.microsoft.com/en-us/magazine/gg213848.aspx http://blog.codingoutloud.com/2011/06/05/azure-faq-how-much-will-it-cost-me-to-run-my-application-on-windows-azure/ http://blogs.msdn.com/b/johnalioto/archive/2010/08/25/10054193.aspx http://geekswithblogs.net/iupdateable/archive/2010/02/08/qampa-how-can-i-calculate-the-tco-and-roi-when.aspx   Other Tools: http://cloud-assessment.com/ http://communities.quest.com/community/cloud_tools

    Read the article

  • Showplan Operator of the Week - Compute Scalar

    The third part of Fabiano's mission to describe the major Showplan Operators used by SQL Server's Query Optimiser continues with the 'Compute Scalar' operator. Fabiano shows how a tweak to SQL to avoid a 'Compute Scalar' step can improve its performance.

    Read the article

  • Get Started with .Net and Apache Cassandra

    - by Sazzad Hossain
    Just came across a easy and nice to read article explaining how to get started with noSQL database system. These no relational databases are getting increasingly popular to tackle the distribution and large data set problems.Cassandra's ColumnFamily data model offers the convenience of column indexes with the performance of log-structured updates, strong support for materialized views, and powerful built-in caching.The article is nicely written by Kellabyte  and shows step by step process how to get going with the programming in a .net platform.Read more here.

    Read the article

  • SQLAuthority News Public Training Classes In Hyderabad 12-14 May SQL and 10-11 May SharePoint

    There were lots of request about providing more details for the blog post through email address specified in the article SQLAuthority News Public Training Classes In Hyderabad 12-14 May Microsoft SQL Server 2005/2008 Query Optimization & Performance Tuning. Here is the complete brochure of the course. There are two different courses are offered [...]...Did you know that DotNetSlackers also publishes .net articles written by top known .net Authors? We already have over 80 articles in several categories including Silverlight. Take a look: here.

    Read the article

  • How to configure apache2 to just save certain POST requests without even passing them to application?

    - by Robert Grezan
    I'm running apache in front of glassfish server using BalancerMember. For performance reasons I would like that POST requests on certain endpoint are just saved to a file without passing them to application (and to return correct HTTP return code). How to configure apache to do that? EDIT: In other words, if a POST request is for path "http://example.com/upload" then the content of the post (body) should go into a file.

    Read the article

  • Google I/O 2010 - Using Google Chrome Frame

    Google I/O 2010 - Using Google Chrome Frame Google I/O 2010 - Using Google Chrome Frame Chrome 201 Alex Russell Google Chrome Frame brings the HTML5 platform and fast Javascript performance to IE6, 7 & 8. This session will cover the latest on Google Chrome Frame, what it can do for you and your customers, how it can be used, and a sneak peak into what's planned next. For all I/O 2010 sessions, please go to code.google.com From: GoogleDevelopers Views: 4 0 ratings Time: 50:16 More in Science & Technology

    Read the article

  • SQL SERVER Checklist for Analyzing Slow-Running Queries

    I am recently working on upgrading my class Microsoft SQL Server 2005/2008 Query Optimization and & Performance Tuning with additional details and more interesting examples. While working on slide deck I realized that I need to have one solid slide which talks about checklist for analyzing slow running queries. A quick search on my saved [...]...Did you know that DotNetSlackers also publishes .net articles written by top known .net Authors? We already have over 80 articles in several categories including Silverlight. Take a look: here.

    Read the article

  • StreamInsight is in all editions (except express)

    - by simonsabin
    Contrary to many posts and even press releases from Microsoft StreamInsight is not just for Data Center edition. It is available in all paid for editions. If you read the license terms http://go.microsoft.com/fwlink/?LinkID=186261&clcid=0x409 you will see you get StreamInsight in all paid editions. Whats confusing is the performance/limitations in each edition. The only reference I could find of these limitations is here http://blogs.msdn.com/b/streaminsight/archive/2010/02/10/streaminsight-versions...(read more)

    Read the article

  • Tuxedo Load Balancing

    - by Todd Little
    A question I often receive is how does Tuxedo perform load balancing.  This is often asked by customers that see an imbalance in the number of requests handled by servers offering a specific service. First of all let me say that Tuxedo really does load or request optimization instead of load balancing.  What I mean by that is that Tuxedo doesn't attempt to ensure that all servers offering a specific service get the same number of requests, but instead attempts to ensure that requests are processed in the least amount of time.   Simple round robin "load balancing" can be employed to ensure that all servers for a particular service are given the same number of requests.  But the question I ask is, "to what benefit"?  Instead Tuxedo scans the queues (which may or may not correspond to servers based upon SSSQ - Single Server Single Queue or MSSQ - Multiple Server Single Queue) to determine on which queue a request should be placed.  The scan is always performed in the same order and during the scan if a queue is empty the request is immediately placed on that queue and request routing is done.  However, should all the queues be busy, meaning that requests are currently being processed, Tuxedo chooses the queue with the least amount of "work" queued to it where work is the sum of all the requests queued weighted by their "load" value as defined in the UBBCONFIG file.  What this means is that under light loads, only the first few queues (servers) process all the requests as an empty queue is often found before reaching the end of the scan.  Thus the first few servers in the queue handle most of the requests.  While this sounds non-optimal, in fact it capitalizes on the underlying operating systems and hardware behavior to produce the best possible performance.  Round Robin scheduling would spread the requests across all the available servers and thus require all of them to be in memory, and likely not share much in the way of hardware or memory caches.  Tuxedo's system maximizes the various caches and thus optimizes overall performance.  Hopefully this makes sense and now explains why you may see a few servers handling most of the requests.  Under heavy load, meaning enough load to keep all servers that can handle a request busy, you should see a relatively equal number of requests processed.  Next post I'll try and cover how this applies to servers in a clustered (MP) environment because the load balancing there is a little more complicated. Regards,Todd LittleOracle Tuxedo Chief Architect

    Read the article

  • Stairway to XML: Level 7 - Updating Data in an XML Instance

    You need to provide the necessary keywords and define the XQuery and value expressions in your XML DML expression in order to use the modify() method to update element and attribute values in either typed or untyped XML instances in an XML column. Robert Sheldon explains how. "It really helped us isolate where we were experiencing a bottleneck"- John Q Martin, SQL Server DBA. Get started with SQL Monitor today to solve tricky performance problems - download a free trial

    Read the article

  • What&rsquo;s new in RadChart for 2010 Q1 (Silverlight / WPF)

    Greetings, RadChart fans! It is with great pleasure that I present this short highlight of our accomplishments for the Q1 release :). Weve worked very hard to make the best silverlight and WPF charting product even better. Here is some of what we did during the past few months.   1) Zooming&Scrolling and the new sampling engine: Without a doubt one of the most important things we did. This new feature allows you to bind your chart to a very large set of data with blazing performance. Dont take my word for it give it a try!   2) New Smart Label Positioning and Spider-like labels feature: This new feature really helps with very busy graphs. You can play with the different settings we offer in this example.   3) Sorting and Filtering. Much like our RadGridview control the chart now allows you to sort and filter your data out of the box with a single line of code!   4) Legend improvements Weve also been paying attention to those of you who wanted a much improved legend. It is now possible to customize the look and feel of legend items and legend position with a single click.   5) Custom palette brushes. You have told us that you want to easily customize all palette colors using a single clean API from both XAML and code behind. The new custom palette brushes API does exactly that.   There are numerous other improvements as well, as much improved themes, performance optimizations and other features that we did. If you want to dig in further check the release notes and changes and backwards compatibility topics.   Feel free to share the pains and gains of working with RadChart. Our team is always open to receiving constructive feedback and beer :-)Did you know that DotNetSlackers also publishes .net articles written by top known .net Authors? We already have over 80 articles in several categories including Silverlight. Take a look: here.

    Read the article

  • Google Chrome Extensions: Launch Event (part 4)

    Google Chrome Extensions: Launch Event (part 4) Video Footage from the Google Chrome Extensions launch event on 12/09/09. Aaron Boodman and Erik Kay, technical leads for the Google Chrome extensions team discuss the UI surfaces of Google Chrome extensions and the team's content not chrome philosophy. They also highlight the smooth, frictionless install and uninstall process for Google Chrome's extensions system and present the team's initiatives in the space of security and performance. From: GoogleDevelopers Views: 2968 12 ratings Time: 15:44 More in Science & Technology

    Read the article

  • "Building on a Solid Foundation"

    Designing the right IT infrastructure is a critical part of ensuring application availability and performance. See how companies rely on an Oracle grid infrastructure—including Oracle Database and Oracle Real Application Clusters—to provide a solid yet flexible base for their applications.

    Read the article

  • SQL SERVER – Storing 64-bit Unsigned Integer Value in Database

    - by Pinal Dave
    Here is a very interesting question I received in an email just another day. Some questions just are so good that it makes me wonder how come I have not faced it first hand. Anyway here is the question - “Pinal, I am migrating my database from MySQL to SQL Server and I have faced unique situation. I have been using Unsigned 64-bit integer in MySQL but when I try to migrate that column to SQL Server, I am facing an issue as there is no datatype which I find appropriate for my column. It is now too late to change the datatype and I need immediate solution. One chain of thought was to change the data type of the column from Unsigned 64-bit (BIGINT) to VARCHAR(n) but that will just change the data type for me such that I will face quite a lot of performance related issues in future. In SQL Server we also have the BIGINT data type but that is Signed 64-bit datatype. BIGINT datatype in SQL Server have range of -2^63 (-9,223,372,036,854,775,808) to 2^63-1 (9,223,372,036,854,775,807). However, my digit is much larger than this number. Is there anyway, I can store my big 64-bit Unsigned Integer without loosing much of the performance of by converting it to VARCHAR.” Very interesting question, for the sake of the argument, we can ask user that there should be no need of such a big number or if you are taking about identity column I really doubt that if your table will grow beyond this table. Here the real question which I found interesting was how to store 64-bit unsigned integer value in SQL Server without converting it to String data type. After thinking a bit, I found a fairly simple answer. I can use NUMERIC data type. I can use NUMERIC(20) datatype for 64-bit unsigned integer value, NUMERIC(10) datatype for 32-bit unsigned integer value and NUMERIC(5) datatype for 16-bit unsigned integer value. Numeric datatype supports 38 maximum of 38 precision. Now here is another thing to keep in mind. Using NUMERIC datatype will indeed accept the 64-bit unsigned integer but in future if you try to enter negative value, it will also allow the same. Hence, you will need to put any additional constraint over column to only accept positive integer there. Here is another big concern, SQL Server will store the number as numeric and will treat that as a positive integer for all the practical purpose. You will have to write in your application logic to interpret that as a 64-bit Unsigned Integer. On another side if you are using unsigned integers in your application, there are good chance that you already have logic taking care of the same. Reference: Pinal Dave (http://blog.sqlauthority.com) Filed under: PostADay, SQL, SQL Authority, SQL Query, SQL Server, SQL Tips and Tricks, T SQL, Technology Tagged: SQL Datatype

    Read the article

  • Recap - SQL Saturday 151 in Orlando

    - by KKline
    It's always a feel-good experience for me to return to SQL Saturday in Orlando, the place where SQL Saturdays were started by Andy Warren ( Twitter | Blog ). On this trip, I delivered a full-day, pre-conference seminar on Troubleshooting and Performance Tuning SQL Server. I also delivered a session on SQL Server Internals and Architecture to a totally packed house. For those of you who emailed me directly, here's the link for the special SQL Sentry offer . I got to attend the extended events session...(read more)

    Read the article

  • Sales & Technical Tutorials: Updated for OBI, BI-Apps and Hyperion EPM

    - by Mike.Hallett(at)Oracle-BI&EPM
      To get the latest updated OBI, BI-Apps and Hyperion EPM Sales & Technical Tutorials, goto the Oracle Business Intelligence and Enterprise Performance Management library for Partners, a compilation of pre-recorded Oracle BI & EPM online tutorials and webinars that have been delivered recently from Oracle: that you can replay at any time. Sales & Technical Tutorials for OBI, BI-Apps and Hyperion EPM.

    Read the article

  • Téléchargez gratuitement l'ebook sur le développement d'applications 'Threaded' qui utilisent le har

    Téléchargez gratuitement l'ebook sur le développement d'applications ?Threaded' Les logiciels de développement Intel® Parallel Studio accélèrent le développement d'applications ?Threaded' qui utilisent le hardware des utilisateurs finaux, depuis le ?'supercomputer'' jusqu'à l'ordinateur portable ou les mobiles. Optimisez la performance de votre application sur architecture Intel® et obtenez plus des derniers processeurs multi-coeurs d'Intel®. Depuis la manière dont les produits fonctionnent ensemble jusqu'à leurs jeux de fonctionnalités uniques, le Threading est maintenant plus facile et plus viable que jamais. Les outils sont optimisés donc les novices peuvent facilement se former et les développeurs expérimentés peuvent aisément ...

    Read the article

  • NUMA-aware placement of communication variables

    - by Dave
    For classic NUMA-aware programming I'm typically most concerned about simple cold, capacity and compulsory misses and whether we can satisfy the miss by locally connected memory or whether we have to pull the line from its home node over the coherent interconnect -- we'd like to minimize channel contention and conserve interconnect bandwidth. That is, for this style of programming we're quite aware of where memory is homed relative to the threads that will be accessing it. Ideally, a page is collocated on the node with the thread that's expected to most frequently access the page, as simple misses on the page can be satisfied without resorting to transferring the line over the interconnect. The default "first touch" NUMA page placement policy tends to work reasonable well in this regard. When a virtual page is first accessed, the operating system will attempt to provision and map that virtual page to a physical page allocated from the node where the accessing thread is running. It's worth noting that the node-level memory interleaving granularity is usually a multiple of the page size, so we can say that a given page P resides on some node N. That is, the memory underlying a page resides on just one node. But when thinking about accesses to heavily-written communication variables we normally consider what caches the lines underlying such variables might be resident in, and in what states. We want to minimize coherence misses and cache probe activity and interconnect traffic in general. I don't usually give much thought to the location of the home NUMA node underlying such highly shared variables. On a SPARC T5440, for instance, which consists of 4 T2+ processors connected by a central coherence hub, the home node and placement of heavily accessed communication variables has very little impact on performance. The variables are frequently accessed so likely in M-state in some cache, and the location of the home node is of little consequence because a requester can use cache-to-cache transfers to get the line. Or at least that's what I thought. Recently, though, I was exploring a simple shared memory point-to-point communication model where a client writes a request into a request mailbox and then busy-waits on a response variable. It's a simple example of delegation based on message passing. The server polls the request mailbox, and having fetched a new request value, performs some operation and then writes a reply value into the response variable. As noted above, on a T5440 performance is insensitive to the placement of the communication variables -- the request and response mailbox words. But on a Sun/Oracle X4800 I noticed that was not the case and that NUMA placement of the communication variables was actually quite important. For background an X4800 system consists of 8 Intel X7560 Xeons . Each package (socket) has 8 cores with 2 contexts per core, so the system is 8x8x2. Each package is also a NUMA node and has locally attached memory. Every package has 3 point-to-point QPI links for cache coherence, and the system is configured with a twisted ladder "mobius" topology. The cache coherence fabric is glueless -- there's not central arbiter or coherence hub. The maximum distance between any two nodes is just 2 hops over the QPI links. For any given node, 3 other nodes are 1 hop distant and the remaining 4 nodes are 2 hops distant. Using a single request (client) thread and a single response (server) thread, a benchmark harness explored all permutations of NUMA placement for the two threads and the two communication variables, measuring the average round-trip-time and throughput rate between the client and server. In this benchmark the server simply acts as a simple transponder, writing the request value plus 1 back into the reply field, so there's no particular computation phase and we're only measuring communication overheads. In addition to varying the placement of communication variables over pairs of nodes, we also explored variations where both variables were placed on one page (and thus on one node) -- either on the same cache line or different cache lines -- while varying the node where the variables reside along with the placement of the threads. The key observation was that if the client and server threads were on different nodes, then the best placement of variables was to have the request variable (written by the client and read by the server) reside on the same node as the client thread, and to place the response variable (written by the server and read by the client) on the same node as the server. That is, if you have a variable that's to be written by one thread and read by another, it should be homed with the writer thread. For our simple client-server model that means using split request and response communication variables with unidirectional message flow on a given page. This can yield up to twice the throughput of less favorable placement strategies. Our X4800 uses the QPI 1.0 protocol with source-based snooping. Briefly, when node A needs to probe a cache line it fires off snoop requests to all the nodes in the system. Those recipients then forward their response not to the original requester, but to the home node H of the cache line. H waits for and collects the responses, adjudicates and resolves conflicts and ensures memory-model ordering, and then sends a definitive reply back to the original requester A. If some node B needed to transfer the line to A, it will do so by cache-to-cache transfer and let H know about the disposition of the cache line. A needs to wait for the authoritative response from H. So if a thread on node A wants to write a value to be read by a thread on node B, the latency is dependent on the distances between A, B, and H. We observe the best performance when the written-to variable is co-homed with the writer A. That is, we want H and A to be the same node, as the writer doesn't need the home to respond over the QPI link, as the writer and the home reside on the very same node. With architecturally informed placement of communication variables we eliminate at least one QPI hop from the critical path. Newer Intel processors use the QPI 1.1 coherence protocol with home-based snooping. As noted above, under source-snooping a requester broadcasts snoop requests to all nodes. Those nodes send their response to the home node of the location, which provides memory ordering, reconciles conflicts, etc., and then posts a definitive reply to the requester. In home-based snooping the snoop probe goes directly to the home node and are not broadcast. The home node can consult snoop filters -- if present -- and send out requests to retrieve the line if necessary. The 3rd party owner of the line, if any, can respond either to the home or the original requester (or even to both) according to the protocol policies. There are myriad variations that have been implemented, and unfortunately vendor terminology doesn't always agree between vendors or with the academic taxonomy papers. The key is that home-snooping enables the use of a snoop filter to reduce interconnect traffic. And while home-snooping might have a longer critical path (latency) than source-based snooping, it also may require fewer messages and less overall bandwidth. It'll be interesting to reprise these experiments on a platform with home-based snooping. While collecting data I also noticed that there are placement concerns even in the seemingly trivial case when both threads and both variables reside on a single node. Internally, the cores on each X7560 package are connected by an internal ring. (Actually there are multiple contra-rotating rings). And the last-level on-chip cache (LLC) is partitioned in banks or slices, which with each slice being associated with a core on the ring topology. A hardware hash function associates each physical address with a specific home bank. Thus we face distance and topology concerns even for intra-package communications, although the latencies are not nearly the magnitude we see inter-package. I've not seen such communication distance artifacts on the T2+, where the cache banks are connected to the cores via a high-speed crossbar instead of a ring -- communication latencies seem more regular.

    Read the article

  • Efficient SQL Server Indexing by Design

    Having a good set of indexes on your SQL Server database is critical to performance. Efficient indexes don't happen by accident; they are designed to be efficient. Greg Larsen discusses whether primary keys should be clustered, when to use filtered indexes and what to consider when using the Fill Factor.

    Read the article

  • running GL ES 2.0 code under Linux ( no Android no iOS )

    - by user827992
    I need to code OpenGL ES 2.0 bits and i would like to do this and run the programs on my desktop for practical reasons. Now, i already have tried the official GLES SDK from ATI for my videocard but it not even runs the examples that comes with the SDK itself, i'm not looking for performance here, even a software based rendering pipeline could be enough, i just need full support for GLES 2.0 and GLSL to code and run GL stuff. There is a reliable solution for this under Ubuntu Linux ?

    Read the article

< Previous Page | 277 278 279 280 281 282 283 284 285 286 287 288  | Next Page >