Cudaprojekty

Proszę, Zarejestruj się lub Zaloguj, żeby zobaczyć szczegóły.

Proszę, Zarejestruj się lub Zaloguj, żeby zobaczyć szczegóły.

Hi everyone, We need to get the solver based on Jacobi Iterative method written in GPU. The preferred language for the GPU is CUDA and price is a constraint but quality is something we cannot compromise on. You will need to have atleast 1 CUDA enabled GPU for writing and benchmarking the code. Only those who have prior demonstrated experience in CUDA need to apply.

A solver for simultaneous equations that uses the jacobi iteration method needs to be developed. The attached IEEE paper gives details about the same.

...complete API to allow instructor to pass events to the OSG display to control the options such as day and night, light points, weather etc... Simulator is based on Linux OS. It is estimated to take 2-3 months effort as it is mainly integrating and optimizing and creating an API to existing software framework. Mandatory Skills: OpenGL, C/C++ Desired Skills: Openscengraph Nvidia CUDA, Nvidia CG, GLib. What we expect? Follow requirements closely. Flexible to adapt to changing requirements. Good english communication skills. Daily Check-in of Code with no bugs. If we find that you are not following the code of conduct we may terminate your contract immediately. Payment Terms: Weekly/Monthly If you are satisfied with the terms please bid on...

Make a technical illustration for a technical part of our website. The topic is about CUDA encoding and the advantage in speed. You can look to our competitors, like There you can find samples. Our have to be better, more professional and in style of our website In our illustration your also have to put quality paramater into. NEW INFO: Attached is a new document with additional infos. ## Deliverables 1) All deliverables will be considered "work made for hire" under U.S. Copyright law. Employer will receive exclusive and complete copyrights to all work purchased. (No 3rd party components unless all copyright ramifications are explained AND AGREED TO by the employer on the site per the worker's Worker Legal Agreement). *

The job is to test the new version of our software. () 1.) Go through the attached PDF file, answer questions, do all points named there. 2.) Write a own log file of your testing. We are looking for people with modern computers, XP, Vista, Windows 7 and 32/64 bit. The most sense of testing is GPU. We added Cuda to our software and now we some test of different configurations, like NVidia, Ati, Intel and so forth. Attached is the main PDF file. If you questions, please ask before you bid. ## Deliverables 1) All deliverables will be considered "work made for hire" under U.S. Copyright law. Employer will receive exclusive and complete copyrights to all work purchased. (No GPL, GNU, 3rd party components, etc. unless all copyright ramifications are explained AND AGREED

Target is to create a Video converter... -Very simple UI is needed User can just select the DVD-Rom (with copy of encrypted DVD's), chose 480p , 720p or 1080p, and the sound quality. chose the output folder and output name. encoding should be done on the fly of copy the DVD using the nVidia CUDA Technology Codecs to use is xVid and x264 (use can chose) ----- I have about 200 DVD's and want to look it on my WD TV Live station and copy all to my nas. the 4GB movie should not have more then 1,6GB after conversion.

We are looking for a developer who has experience with ffmpeg and the NVidea Cuda Encoder. The job is not to develop something, we need consulting. But it is strongly needed that you already developed with ffmpeg and CUDA SDK. The consulting is about the combination of ffmpeg and CUDA, to receive the data from the CUDA encoder and use in ffmpeg. ## Deliverables 1) All deliverables will be considered "work made for hire" under U.S. Copyright law. Employer will receive exclusive and complete copyrights to all work purchased. (No GPL, GNU, 3rd party components, etc. unless all copyright ramifications are explained AND AGREED TO by the employer on the site per the worker's Worker Legal Agreement). 2) Complete and fully-functional working progra...

...competitors and why they are outdated. Competitors are CloneDVD (Slysoft) DVD-Cloner, DVDNeXtCOPY. 2.) Article: Quality comparsion. Our software brings the best quality. Detailed info you can find on: and (Topic: DVD-Ranger - Quality Craft Transocder) 3.) Article about Nvidia Cuda. DVD-Ranger now supports CUDA. Best way to upscale DVD to HD with high speed. Some words about Cuda and DVD-Ranger and its top Quality. The internet is full of information. 4.) Error Reporting and crash Handling. Write a article about C++ Crash Handling and how to work with it. DVD-Ranger has a similar function like Windows, to send error reports after the software crahed. We will give you a short PDF and some usefull links to get information.

We require an expert OpenGL programmer to work on a Open Source Project for 20 days as a freelancer. We expect him to work 4 hours a day i.e. 80 hours of productive work. Mandatory Skills: OpenGL, C/C++ Desired Skills: Nvidia CUDA, Nvidia CG, Audio/Video Codec Development, DBus, GLib. What we expect? Follow requirements closely. Flexible to adapt to changing requirements. Good english communication skills. Daily communication of status through Skype and Email. Daily Check-in of Code with no bugs. If we find that you are not following the code of conduct we may terminate your contract immediately. Payment Terms: Daily: 20USD. We will pay the developer on a daily basis. If you are satisfied with the terms please bid on the project. We can extend...

I want to compile and run a CUDA app under 64 bit Linux with Eclipse ~catanzar/GPUSVM/ but when I do so I just get errors and do not know where to start. Eventually I want to run it from Matlab I figure this would be fairly straightforward for coders with a good background in Eclipse C++ programming under Linux. I just need someone to hold my hand in setting this up. EDIT: Experience with CUDA and an NVIDIA graphics card that responds to CUDA is seen as highly desirable but not essential. ## Deliverables 1) All deliverables will be considered "work made for hire" under U.S. Copyright law. Employer will receive exclusive and complete copyrights to all work purchased. (No GPL, GNU

This is a simple project for school! My project is writing a program twice: in C++ and in Cuda. The program should evaluate double integrals (<>) The program should read from an input file as much as 100 functions and save the value of their integrals in an output file. The program written in Cuda should clearly show a performance enhancement compared to the program written in C++. The way the integration should be evaluated in the program is by calculating the volume specified by the function's graph within the integral limits. It is preferable that when writing the program in Cuda, this volume should be divided into sub volumes, and each sub volume will be evaluated by a thread/block to gain performance. ## Deliverables vWorker

Hello, I am looking for someone to complete me a very simple project using GpuCV/ OpenCV The program should be able to add and remove noise from an image using the GpuCV CUDA library and compile in visual studio 2010 Thanks.

This is a project for experienced programmers in CUDA, OpenGl or other gpu languages, begginers please dont bid. I have a system builded in C++ using the CImg library, the system is a image processing system (segmentation, feature extraction and classification) the idea is to reprogram this system in a gpu language to make it real time video processing capable. So C++ knowledge is a MUST. The c++ system process each frame of a video input and returns the same frame with some colored regions and labels added, the code is plain simple and well commented, no other libraries are used. The gpu programmed system will have to do the same, but achieving at least 15 frames per second on a VGA stream (640x480) on c++ it takes about 1.5-2.5 seconds per image. The winning bidder will w...

Proszę, Zarejestruj się lub Zaloguj, żeby zobaczyć szczegóły.

You will program the graphics/visualization part of our program using VTK/ITK or Open GL to plot scientific data in 2D and 3D intensity graphs. Emphasis on live frame rate performance and clean code design is important. Ideally you will have experience using VTK/Open GL, and image processing as well. This must be developed i...will program the graphics/visualization part of our program using VTK/ITK or Open GL to plot scientific data in 2D and 3D intensity graphs. Emphasis on live frame rate performance and clean code design is important. Ideally you will have experience using VTK/Open GL, and image processing as well. This must be developed in VC++ You must also have a Nvidia card capable of running CUDA. You must have Windows 7 x64 to develo...

You will be the software architect for an imaging project. You will plan the project then program it, integrating modules developed by other team members. You must have atleast 5 years experience in software development in C/C++ You also must have: Visual Studio 2010 Nvidia card capable of CUDA experience in imaging applications preferable You must demonstrate experience by answering a few of our interview questions. When replying send a copy of your resume/CV in .pdf format, please send a formal resume/CV. Do not link to other sites/forums.

you will develop a program in VC++ using the FFTW3 and CUDA to compute simple FFT of 1D arrays, and place them into 2D arrays as the output. FFT with zero padding and windowing will be used. A very simple windows UI is to be made to allow the user select FFTW3 or CUDA to load the data, Select FFT parameters process the FFT data, view the data graphically (2d graph), and save the data.

Fit multiple curves in parallel using CUDA to nonlinear, nonnormal, nonstationary, dependent data using maximum likelihood and assume the error is from an asymmetric alpha-stable distribution. ## Deliverables Fit multiple curves in parallel using CUDA to nonlinear, nonnormal, nonstationary, dependent data using maximum likelihood and assume the error is from an asymmetric alpha-stable distribution (alpha > 1, for more information on alpha-stable distributions see alpha-stable ~jpnolan/stable/). The curve should be fitted locally, meaning we need to be able to provide the function the number and location of knots/breakpoints. The fitting should be done using bsplines or an other basis function (like neural networks, radial basis function, local

Hi Everyone! I need a complete coding in both C++ and CUDA on the project of paper on Computer Graphics : Ray Tracing with titled "Instant Ray Tracing :Bounding Interval Hierarchy". Since I am working on paper as my thesis project , so i request those people to bid who can complete only in 10-15 days. I am attaching the paper to this post, since original file is larger than 2MB I made it compressed . I will mail the original document to one who made bid. Requirements: 1)project must be completed in 15-20 days compulsory. 2)each step of the coding must explain clearing by commenting. 3)Coding work should be in both C++ and CUDA 4)Comparison must mention with previous methods with this project method 5)General report on the project should submit ,i...

I need a bitmap comparison class that will utilize CUDA or GPU shaders on graphic cards to achieve maximum paralel performance. Class should be made usable from c# interface. ## Deliverables Purpose of software component for image comparison is video scene search. ? In order to do that, it is imperative that many comparison operations will be computed in as short time as possible. ? I have reference application that uses CPU for comparison, but practical application for it is impossible, since it is too slow. Software component should work in several phases, and here is the explanation of that phases: 1. Card Probing Component should be able to probe GPU so it can know various stuff about it - memory available, GPU architecture, ... 2. Setup Co...

I need 200 exam questions and answers prepared according to a specific format for CUDA. (If you don't know what CUDA is, you probably don't want to bid this one.) I'll provide a template for the content. The selected provider will need to be familiar with CUDA and its implementation and usage. I don't want a lot of questions regarding history, etc. - this is a certification exam to evaluate a user's proficiency. As always, no plagiarized content is acceptable and good US English grammar is required. I'm easy to get along with, but I expect certain standards to be met. Please read the attached guidelines thoroughly, EVEN IF YOU'VE WORKED ON MY PROJECTS BEFORE. I HAVE MADE SOME SIGNIFICANT CHANGES TO MAKE THE PROCESS EASIER. ...

We are looking for a coder with experience with CUDA and NVIDIA acceleration cards. I’ve attached the pseudo-code in C language that we want to port to NVIDIA. This function will be called from several threads (16 threads by default, but could be more or less depending on the number of cores and micros installed in the server). The buffers are independent? for each thread, so it is not required any synchronization in order to read or write the buffers among the threads. The objective of the project is to improve the performance of the application based on the parallelization capabilities provided by NVIDIA Tesla cards.

The aim of this project is to generate a very large fractal image (Mandelbrot, etc) and then randomly process a part of the image and convert it to a 2D array using color variations. It has to be built on CUDA and highly customized.

Proszę, Zarejestruj się lub Zaloguj, żeby zobaczyć szczegóły.

We currently have a Telsa C1060 GPU card, and are investigating whether or not it is possible to use the processing power of this GPU card to offload processing on our distributed computing environment into a parallel computing environment. Ideally, your experience requires that you have C#, .NET, C, C++ and CUDA (Nvidia's GPU graphics Library). We have large datasets that may have millions of rows. So for example, we have a table that has a subquery, that may have 100 rows of data for product sku cisco2821. These 100 rows of data are used to build a technical specification into HTML which will then output 1 row of data. As you can imagine if you have a million rows, this will take a long time.? Using Distributed computing we were able to reduce the compu...

We've .c source files which can do volume rendering using four threads. - need to port it to CUDA to leverage parallel processing. - not much work to do if you are already familiar with CUDA. (In fact, you might only need to port one function to CUDA to get it work.) - need to get it done asap. - deadline 2-3 days at most. - download the current working volume rendering project in C from - the program should behave as RENDER.exe.

...integrate FFmpeg with the Spursengine SDK and Nvidia CUDA. Requirements: - FFmpeg Multi Thread Version - Integrate the Spursengine SDK - Add CUDA Support to Spursengine for filtering support. - TRanscode - MPEG2 TS encapsulated in IP (Input) -> H.264/AVC TS encapsulated in IP Output. Both SDKs are freely available. Spursengine SDK available via Nvidia CUDA Drivers SDK are available via I understand support via Leadtek for the Spursengine is quite good. So discussing with them the interaction between the Spursengine and CUDA would be via Leadtek. To the person who accepts the project will have a test system provided to them online with a CUDA GPU and a Spursengine Card. Happy to do the work

Proszę, Zarejestruj się lub Zaloguj, żeby zobaczyć szczegóły.

...implementations: Implementation of the K-means algorithm using the CUDA environment for the exploitation of multi-core graph processors (GPUs) and Combination of the MPI and OpenMP models for the exploitation of a multi-core cluster of computers Your implementation may rely on the sequential implementation of the K-means algorithm as well as on the algorithm’s implementations based entirely on MPI or OpenMP, which you will find here: <~wkliao/Kmeans/> Moreover, in the following link you may find short descriptions of the algorithm <> In the following URL you can find an implementation of the K-means algorithm, which utilizes the CUDA environment. However, you should use the abovementioned implementation

Proszę, Zarejestruj się lub Zaloguj, żeby zobaczyć szczegóły.

This is a school project. We've .c source files which can do volume rendering using four threads. - need to port it to CUDA to leverage parallel processing. - not much work to do if you are already familiar with CUDA. (In fact, you might only need to port one function to CUDA to get it work.) - need to get it done asap. - deadline 2-3 days at most. - download the current working volume rendering project in C from - the program should behave as RENDER.exe.

...JAVA=/usr/lib/jvm/java-6-sun-1.6.0.15 endif LINKPARAMS=-lconfig++ -lxerces-c PARSERCOMPILE=flex && bison -d PFtIF.y && cc -Wall -Wextra -pedantic -Wfloat-equal lex.yy.c PFtIF.tab.c -o PFtIF && mv PFtIF ../../../ ifeq (,$(findstring Ubuntu,$(shell uname -v))) # Gentoo CUDADIR=/opt/cuda/sdk/C/common/inc JAVADIR=$(shell readlink --canonicalize $(JAVA_HOME)) ifeq ($(shell uname -m), x86_64) LINKPARAMS+=-L/opt/cuda/lib64/ -lcudart else LINKPARAMS+=-L/opt/cuda/lib/ -lcudart endif else # Ubuntu CUDADIR=/home/pps-admin/NVIDIA_GPU_Computing_SDK/C/common/inc JAVADIR=/usr/lib/jvm/java-6-sun-1.6.0.15 NVCCFLAGS+=--compiler-bindir=/home/pps-admin/NVIDIA_GPU_Computing_SDK/C/mygcc endif INCLUDEDIRS=-I$(CUDADIR)...

This is a school project. We've .c source files which can do volume rendering using four threads. - need to port it to CUDA to leverage parallel processing. - not much work to do if you are already familiar with CUDA. (In fact, you might only need to port one function to CUDA to get it work.) - need to get it done asap. - deadline 4-5 days at most. - attached is the cuda version of matrix multiplication sample project. - will provide you the current working volume rendering project in C.

I am looking for someone who has experience in developing CUDA applications. The aim goal of the project is to develop a main-frame for so called Smoothed Particle Hydrodynamics (SPH). SPH is a method do describe the physical behavior of fluids, with a set of particles, which interact with each other, to model the fluid. As the number of particles is very high and the interaction between particles is fairly easy, it is idealy suited for parallel GPU computing. A more advanced example of the method is the "PhysX fluid demo". Other examples and papers providing the principles and mathemtatical background behind the method, will be given. Here is a list of what should be done: * Source code of the whole project, well documented in English * Efficient, GPU base...

I need bit slice DES encrypting implementation on Nvidia CUDA that works as fast as 50,000,000 calls per second on Nvidia card 9500 GT. In other words, implementation must be capable to encrypt at least 50,000,000 64-bit words per second on 9500 GT. This is not possible if DES algorithm implemented straightforward. Probably, exactly bit slice method should be here. But the only requirement is speed.

CUDA(*Compute Unified Device Architecture*) based program for private use A CUDA based C program to apply SVD ( singular valued Decomposition) algorithms (any) on sample audio files. ## Deliverables The project requires a program that takes audio file(wav) as input converts it into a matrix using STFT (short time? fourier? transforms) using any available algorithms and then proceed to decompose the matrix into its singular values (SVD) ? again using any? available? algorithm. A simple code is added to this singular value matrix and the process is reversed. The process of breaking the matrix into its singular value should be done on the graphic card requiring the uses of NVIDIAS CUDA language ( an C extension) thus reducing time considerably. Th...

...mission is to recover the password. You can start testing all the combinations of 19 no capital letters + number in the last position (as the example above) but you can do as you want (mix with capital letters also, number in no matter what position, more than one number, etc) You need to provide: - The Password - Time needed to find it - Number and type of CPUs (or GPUs if you use the CUDA version of AIRCRACK -ask for details) The project will be OPEN until one freelancer will provide the requested data. We will pay ONLY to THE FIRST PROVIDER. PS: We will start to publish the first letters of the password if nobody can crack it after the first two months. If you have found the password but you are not the first one, please, contact us (probably we will hav...

I am looking for a person who knows cuda and good at writing some parallel algorithms very quickly. You need to implement some parallel algorithms on cuda. If you are chosen, I will provide sequential code. Note: I don't have much time. You should complete ASAP.

I have a Sparse matrix program which i want to integrated add SPMV block tri diagonal solver functionality to it. I need some one who can convert c++ program to CUDA nvida.

Implement a CUDA or OpenCL (ideal) video encoder based on open source x264 package (essentially regutting the most expensive functions of motion estimation, dct, etc for optimal performance). B-frame support can be considered an additional deliverable and bid. Must be on par performance and quality wise with CyberLink's Espresso CUDA encoder or MediaCoder's CUDA encoder Thanks!

Proszę, Zarejestruj się lub Zaloguj, żeby zobaczyć szczegóły.

I need to implement parallel algorithm for fractals in cuda. Needed cuda expert.I have some fractal based parallel algorithms written. Need to be a good communicator & programmer.

We need a C++ class for processing image-related data on a graphics card using nVidia's CUDA-based methods. The source must be capable of being compiled by MSVC 2003 and the target platforms are both the 32-bit and 64-bit versions of Windows XP. Further information is in the attached document. ## Deliverables 1) Complete and fully-functional working program(s) in executable form as well as complete source code of all work done. 2) Deliverables must be in ready-to-run condition, as follows? (depending on the nature? of the deliverables): a)? For web sites or? other server-side deliverables intended to only ever exist in one place in the Buyer's environment--Deliverables must be installed by the Seller in ready-to-run condition in the Buyer's environment. b) ...

Proszę, Zarejestruj się lub Zaloguj, żeby zobaczyć szczegóły.

Proszę, Zarejestruj się lub Zaloguj, żeby zobaczyć szczegóły.

You will Develop a volume viewer program to load a set of slice images for 3d volume viewing and rendering. The development language will be in C++ using the VTK, ITK 3d volume and image segmentation toolkits. You will further develop the program to speed up volume rendering by implimenting use of the Nvidia CUDA SDK for GPU processing.

Mixed Media Player: Requires Video Processing in 1080p screen size, on multi screens, using both GPU and other forms of optimization with mixed video and Graphic Media and some database components. Programming Languages Required: C , Direct X, Open CL, Windows Media Format, Direct Video Technologies to use: UVD (part of AVIVO HD 'ATI'), CUDA (nvidia), Nvidia Purevideo HD (nvidia), Shaders. You need to have atleast 5 years experience in C, and Good Skills in DirectX, A keen understanding of video processing. I am looking for a creative programmer for a challenging task. This is First Part of this project, for more details on this project contact me. ## Deliverables 1) Complete and fully-functional working program(s) in executable form as well as complete source code of a...

**Mixed Media Player:** Requires Video Processing in 1080p screen size, on multi screens, using both GPU and other forms of optimization with mixed video and Graphic Media and some database components. Programming Languages Required: C , Direct X, Open CL, Cuda ,Windows Media Format, Nvidia Purevideo HD, You need to have alteast 5 years experience in C, I am looking for a creative programmer for a chalenging task. ## Deliverables CONTACT me for more detailed specs, online chat preferred. skype: opticspy msn: <yoohooman@> aim: breaknshake email: <steve@>