f



parallel for loops without parallel computing toolbox

Is this possible?
0
3/7/2011 4:12:20 PM
comp.soft-sys.matlab 211266 articles. 23 followers. lunamoonmoon (257) is leader. Post Follow

1 Replies
868 Views

Similar Articles

[PageSpeed] 16

On 11-03-07 10:12 AM, Nathan Jensen wrote:
> Is this possible?

That depends on what you mean by "parallel for loops".

Matlab has a published external interface. That interface could be used to 
call out to arbitrary routines that might _somehow_ do computations in 
parallel, such as by using OpenMP or POSIX Threads or using an 
operating-system-specific method.

Or you could start multiple Matlab instances and have them communicate with 
each other somehow, such as via shared memory or TCP; there are a couple of 
Mathworks File Exchange (FEX) contributions for such purposes.

You could potentially use Jacket Computing's GPU computing products.

However, PARFOR is only enabled if you have the Parallel Processing Toolbox 
(or perhaps the Distributed Computing Toolbox.)
0
roberson (2980)
3/7/2011 8:35:52 PM
Reply:

Similar Artilces:

Matlab parallel for loop or Matlab open pool
I am trying to to some computations and I would like to do it in parallel using parfor or by Opening the matlabpool.. as the current implementations is too slow: result=zeros(25,16000); for i = 1:length(vector1) % length is 25 for j = 1:length(vector2) % length is 16000 temp1 = vector1(i); temp2 = vector2(j); t1 = load(matfiles1(temp1).name) %load image1 from matfile1 t2 = load(matfiles2(temp2).name) % load image2 from matfile2 result(i,j)=t1.*t2 end end It work fine but I would really like to know if there is a way to speed thing up ... Thanks a lot in advance! ...

Parallel Computing Toolbox and FFT
Hello All, I have just started using the Parallel Computing Toolbox and I am a bit puzzled about some of the results that I am seeing. I have an 8 core Intel Xeon PC with 16GB of RAM and I'm using MATLAB R2010b. I thought that by using the Parallel Computing Toolbox I could speed up my fft computations. However I'm seeing the opposite effect. For example here is a snippet of code that I've been working on. As you can see the parallel version takes a lot longer than just performing a normal fft. Any suggestions to what I'm doing wrong or what I don't understand about this computation. Thanks tic sched = findResource('scheduler', 'type', 'local') j = createJob(sched) createTask(j, @fft, 1, {X(1,:)}) submit(j); waitForState(j) results = fftshift(getAllOutputArguments(j)) test = results{1}; plot(abs(test)) destroy(j); toc tic;output = fft(X(1,:));toc Elapsed time is 3.292587 seconds. Elapsed time is 0.001755 seconds. size(X(1,:)) ans = 1 15000 "Shannon " <shannon.fitzpatrick@drdc-rddc.gc.ca> writes: > I have just started using the Parallel Computing Toolbox and I am a > bit puzzled about some of the results that I am seeing. I have an 8 > core Intel Xeon PC with 16GB of RAM and I'm using MATLAB R2010b. I > thought that by using the Parallel Computing Toolbox I could speed up > my fft computations. However I'm seeing the opposite effect. For > example here is a snippe...

My parallel toolbox does not have GPU computing
Hello My Matlab version is R2010a 64bit Linux. I can see that my Matlab comes with parallel toolbox. However, in that toolbox, I can not find GPU computing subsection. Matlab therefore gives error when I call "gpuArray". I wonder why is that, is that because my Matlab Version is old, or do I have to purchase a separate gpu toolbox? "Peng " <pengguan1983@gmail.com> wrote in message news:j601v9$28v$1@newscl01ah.mathworks.com... > Hello > > My Matlab version is R2010a 64bit Linux. I can see that my Matlab comes > with parallel toolbox. However, in that toolbox, I can not find GPU > computing subsection. Matlab therefore gives error when I call "gpuArray". > I wonder why is that, is that because my Matlab Version is old, or do I > have to purchase a separate gpu toolbox? The Release Notes for Parallel Computing Toolbox indicate GPU capabilities were introduced in release R2010b, which is newer than the release R2010a version that you're using. http://www.mathworks.com/help/toolbox/distcomp/rn/bsloyak-1.html -- Steve Lord slord@mathworks.com To contact Technical Support use the Contact Us link on http://www.mathworks.com Peng, you don't need to upgrade your MATLAB version. Just use Jacket, http://accelereyes.com You'll be better off with this approach for these reasons: http://accelereyes.com/compare Thank you very much, that seems to be a very useful thing! "John Melonakos" ...

Parallel Computing 2 Loops
How to run these two loops at the same time: ie. I have while loop and for loop like this: % this loop to play video while x == 0 -------------- -------------- end % this loop to play the timer for i = 1:n -------------- -------------- end I want to run those two loops when i press a button ie. play button, so how can i do that? I read in internet, we can do that by using matlabpool and spmd but i dont know how to apply that function in my two loops. pls reply regards Adhi ...

Parallel computing toolbox #3
Hi, I am using wring some codes to run my program in parallel using the matlab parallel toolbox. My program is all based on command line and no GUI is provided. So I am wondering if I can use command line to - detect how many cpus can be set to be a worker - set up the local workers, - and any other commands that dealing with this parallel toolbox Thanks very much. "George " <guanjihou@gmail.com> writes: > I am using wring some codes to run my program in parallel using the matlab > parallel toolbox. My program is all based on command line and no GUI is > provided. So I am wondering if I can use command line to - detect how many cpus > can be set to be a worker > - set up the local workers, > - and any other commands that dealing with this parallel toolbox The local scheduler automatically detects how many cores your machine has, providing you do not modify the local profile (you can specify an explicit number which overrides the automatic value). So, for example, if you issue the command matlabpool open local that will start as many workers as you have cores on your machine. The local scheduler keeps track of how many workers are running, and will not exceed the number of cores on your machine. Cheers, Edric. Edric M Ellis <eellis@mathworks.com> wrote in message <ytwvcmxoqpg.fsf@uk-eellis0l.dhcp.mathworks.com>... > "George " <guanjihou@gmail.com> writes: > > > I am using wring some ...

Parallel Computing Toolbox for Academic License
Dear MATLAB experts, currently, I use the academic version of MATLAB and I would like to try out the Parallel Computing Toolbox. Is there any way to acquire this toolbox for my academic MATLAB version? Kind Regards, Dima "Dimitri " <dimitrn@g.clemson.edu> wrote in message news:jiqmsn$bcn$1@newscl01ah.mathworks.com... > Dear MATLAB experts, > > currently, I use the academic version of MATLAB and I would like to try > out the Parallel Computing Toolbox. Is there any way to acquire this > toolbox for my academic MATLAB version? If you're using the Student Version of MATLAB, Parallel Computing Toolbox is available as an add-on product. http://www.mathworks.com/academia/student_version/companion.html Note that MATLAB Distributed Computing Server is NOT available as an add-on product, so I don't believe you will be able to connect multiple machines to create a cluster using Student Version. You should be able to use a local cluster, though. If you're using the Professional Version of MATLAB using Clemson University's license, you will need to check with the IT staff that are responsible for maintaining that license to determine if Parallel Computing Toolbox is included in the license or to discuss setting up a trial version of the toolbox if it is not. -- Steve Lord slord@mathworks.com To contact Technical Support use the Contact Us link on http://www.mathworks.com ...

Parallel computing toolbox running problem
Dear all, I am currently using parallel computing for optimization. I use "matlabpool open 8" command; and use Multistart function for the optimization. In the Multistart function it has been set to be "UseParallel" is "always". Problem is that I see 9 MATLAB image name in Window task manager. Only one of them use 25% of my CPU resource (I have a quad core computer; 25% is equal to one core is fully operating) . All others are 0% CPU usage. I really don't understand the situation. In term of memory usage, the one using 25% of CPU power use 210M bytes. All the others uses 109M bytes. In my computer, open a new MATLAB window but doing nothing is around 109M bytes. What that means?? Please help. I need the parallel computing power. Thanks ...

Is the parallel computing toolbox the solution to this problem?
Hi, I am designing a feedback control loop as part of a project. The MATLAB program reads data through the analog input of a DAC (NI USB 6009), and when there is enough data (say N), it starts to process the data to get a control output and send it through the digital output of the DAC. The reading should be kept going while processing the control signal; and the control signal calculation is refreshed when every time when N/3 data comes in (like a moving window of size N, averaging the old data with the new ones) My problem is how to perform these in parallel? This doesn't need to be in real time, but needs to be fairly quick, the delay still needs to be in orders of seconds. I am not sure if parallel computing toolbox is the solution or there are better (simpler) ways. I am new to Matlab, so please give me some advice on this ^^ thank u all. ...

Parallel computing toolbox setup question
I have a quad core computer; and I use the parallel computing toolbox. I modify the default 'local' setting; and set different number for the "worker" number in the parallel computing setting, for example 2,4,8.. And also set the minimum and maximum worker to work for the task. After the setting, I did the validation to make sure everything is ok. However, no matter what I set, the AVERAGE cpu usage by MATLAB is exactly 25% of total CPU usage; and None of the cores run at 100% (All are around 10%-30%). I am using MATLAB to run optimization problem, so I really want my quad core computer using all its power to do the computing. Please help ...

Recent soft computing papers and MATLAB Toolboxes
Dear Colleagues, I would like to call your kind attention to the updated website of the Soft Computing Research Group at the University of Veszprem (Hungary) http://www.fmt.vein.hu/softcomp/ You can download MATLAB Toolboxes: - Fuzzy Clustering MATLAB Toolbox - Genetic Programming MATLAB Toolbox - Interactive Evolutionary Strategy (EASy) MATLAB Toolbox - Constrained Fuzzy Model Identification for the FMID Toolbox independent MATLAB programs related to: - Data mining * Fuzzy clustering based time-series segmentation * Supervised Fuzzy Clustering for the Identification of Fuzzy Classifiers * Fuzzy Modeling with Multidimensional Membership Functions: Grey-Box Identification and Control Design * Compact TS-Fuzzy Models through Clustering and OLS plus FIS Model Reduction * Inconsistency Analysis of Labeled Data * Star plots - MATLAB files for Graphical Representation of trace elements of clinkers - Process control and monitoring * Feedback Linearizing Control Using Hybrid Neural Networks Identified by Sensitivity Approach * Incorporating Prior Knowledge in Cubic Spline Approximation - Application to the Identification of Reaction Kinetic Models * Identification and Control of Nonlinear Systems Using Fuzzy Hammerstein Models - A Simple Fuzzy Classifier based on manuscripts in PDF about - fuzzy model based process control and monitoring - fuzzy clustering and classification - incorpor...

Recent soft computing papers and MATLAB Toolboxes
Dear Colleagues, I would like to call your kind attention to the updated website of the Soft Computing Research Group at the University of Veszprem (Hungary) http://www.fmt.vein.hu/softcomp/ You can download MATLAB Toolboxes: - Fuzzy Clustering MATLAB Toolbox - Genetic Programming MATLAB Toolbox - Interactive Evolutionary Strategy (EASy) MATLAB Toolbox - Constrained Fuzzy Model Identification for the FMID Toolbox independent MATLAB programs related to: - Data mining * Fuzzy clustering based time-series segmentation * Supervised Fuzzy Clustering for the Identification of Fuzzy Classifiers * Fuzzy Modeling with Multidimensional Membership Functions: Grey-Box Identification and Control Design * Compact TS-Fuzzy Models through Clustering and OLS plus FIS Model Reduction * Inconsistency Analysis of Labeled Data * Star plots - MATLAB files for Graphical Representation of trace elements of clinkers - Process control and monitoring * Feedback Linearizing Control Using Hybrid Neural Networks Identified by Sensitivity Approach * Incorporating Prior Knowledge in Cubic Spline Approximation - Application to the Identification of Reaction Kinetic Models * Identification and Control of Nonlinear Systems Using Fuzzy Hammerstein Models - A Simple Fuzzy Classifier based on manuscripts in PDF about - fuzzy model based process control and monitoring - fuzzy clustering and classification - incorporation of a priori knowledge in the identif...

build a mex for parallel computing without matlabpool ?
Hi all, I'm an absolute newbie in C/C++ and I must say that I found the tutorials to make mex functions very complex. Also, I found threads that said that the speed gain is not as significant anymore because of JIT. My code is already very vectorized, uses preallocation, works mostly in columns and has bsxfun type functions to make it faster. Currently, I would want to make the code able to be run on a computing cluster so that it's faster than on my 4-core workstation. There is no communication between the processes so I'm imagining the speed increase would be linear with the number of nodes used. Below is the code (the initial script is not efficient but it runs only once and serves only to load the parameters. The meat is the parfor loop with cycle.m in it) ############################################ v1=[1 2 3 4]'; v2=(0:0.02:0.2)'; v3=(0:0.02:0.2)'; ln=size(v1,1)*size(v2,1)*size(v3,1); test_var=zeros(ln,3); line=0; for c1=1:size(v1) for c2=1:size(v2) for c3=1:size(v3) line=line+1; test_var(line,:)=[v1(c1) v2(c2) v3(c3)]; end end end param_shared= init_param();%this only loads some fixed simulations parameters param_shared.test_var=test_var; matlabpool open local parfor con=1:ln cycle(con, param_shared);%cycle is the heavy part, with plenty of subroutines and then stores the results in .csv files end matlabpool close clear ########################################...

Matlab 2011a student version/ Parallel computing box
Hi, Does the parallel tool box version 4.3 support GPU computing? If not, how to get GPU computing capanility with Matlab 2011a student version? I thought I will order the Matlab 2011a student but the parallel tool box that is available to students (v 4.3) does not mention GPU computing. I will appreciate any advice. Thank you, H You might consider the student version of Jacket, here: http://www.accelereyes.com See comparison description: http://www.accelereyes.com/products/compare "Hamdi " <hamdi.mani@asu.edu> wrote in message <inoni0$fh7$1@fred.mathworks.com>... > Hi, > > Does the parallel tool box version 4.3 support GPU computing? > > If not, how to get GPU computing capanility with Matlab 2011a student version? > > I thought I will order the Matlab 2011a student but the parallel tool box that is available to students (v 4.3) does not mention GPU computing. > > I will appreciate any advice. > > Thank you, > H The parallel computing toolbox for students should be identical to the full commercial version. I've never seen Matlab do cutdown toolboxes for student use. But the Distributed Computing Server is not for sale to students, so you are limited to GPUs and CPUs on your local machine. For some of the GPU stuff in Matlab, see http://www.mathworks.com/discovery/matlab-gpu.html I also note that finally (as far as I can tell, I have not verified this myself), students can now download the 64 bi...

parallel computing
Hello Everyone, I just purchased the parallel computing toolbox. I have 2 general questions on the 'spmd' function. Is running looping iterations on spmd faster than normal for loops ? Is spmd faster on quad core (4 cores) vs a dual core(2 cores) , again in the case of running looping iterations ? regards,Kate "Kate " <chino_tones@hotmail.com> wrote in message <j7tsjk$5r3$1@newscl01ah.mathworks.com>... > Hello Everyone, > > I just purchased the parallel computing toolbox. I have 2 general questions on the 'spmd' function. > > Is running looping iterations on spmd faster than normal for loops ? ========= The only chance it would be is if you distribute the loop, using for...drange. > Is spmd faster on quad core (4 cores) vs a dual core(2 cores) , again in the case of running looping iterations ? ============= You'll never know until you try. In my experience, It depends too much on what's being parallelized and the specifics of your architecture. ...

question on faster run-time with Parallel Computing toolbox
Good day all, I currently have an optimization algorithm implemented in Matlab. The time to arrive at a solution for this algorithm varies. There is a speed variation since success of ending the optimization relies on randomly selecting a set of data which is hopefully reliable enough for a solution. So for example, my algorithm can end in little as 1 iterations or a maximum of 200 iterations ( i.e. ,a value which I set). I have seen Matlab's Parallel computing toolbox but not sure if would apply to my situation. I would like to know if it is possible to somehow run my algorithm in "parallel" jobs, such that, I can run the script multiple times and end the overall algorithm with the job that terminates first ? Is anything like this or similarly possible with the parallel toolbox? thanks any suggestions, Aiden "Aidy" wrote in message <j7i8jp$1ai$1@newscl01ah.mathworks.com>... > Good day all, > > I currently have an optimization algorithm implemented in Matlab. The time to arrive at a solution for this algorithm varies. > > There is a speed variation since success of ending the optimization relies on randomly selecting a set of data which is hopefully reliable enough for a solution. So for example, my algorithm can end in little as 1 iterations or a maximum of 200 iterations ( i.e. ,a value which I set). > > I have seen Matlab's Parallel computing toolbox but not sure if would apply to my situati...

Compute SVD of a Matrix Without use loop (For ... End ) in matlab
HI ALL. i must compute svd of matrix a=64 x 8357 that each column of a related to one block of image. for compute svd of each column, i need all svd's of each column , then i must use reshape(a(:,1) , [8,8]) and then, compute svd of this result. i can not use loop , because so time consuming. Does Anybody Know how can use reshape with change numbers (that number of numbers equal to columns) and without use loop, compute all columns reshape? Thanks. Mansour Hashemi <mansur.hashemi@gmail.com> wrote in message <2f545a93-2b97-4260-8b90-ffc1e29de7f7@p13g2000yqh.googlegroups.com>... > HI ALL. > i must compute svd of matrix a=64 x 8357 that each column of a related > to one block of image. > for compute svd of each column, i need all svd's of each column , then > i must use reshape(a(:,1) , [8,8]) and then, compute svd of this > result. > i can not use loop , because so time consuming. > > Does Anybody Know how can use reshape with change numbers (that > number of numbers equal to columns) and without use loop, compute all > columns reshape? ==================== You could just do this A=reshape(a,8,8,8357); for i=1:8357 svd(A(:,:,i)) end However, you can't avoid doing the SVD with a for-loop and I find it hard to believe that doing a reshape() in this same loop will dominate the computation time. ...

Parallel LZ4 and my Parallel LZO...
... Hello, I have downloaded the C version of the following compression algorithm: http://code.google.com/p/lz4/ They say that it's the fastest, so i have compiled it into a DLL with mingw to use it from FreePascal and Delphi, so i have wrote the interface and all was working perfectly, but when i have benchmarked the parallel LZ4 , that i have wrote, against my Parallel LZO algorithm , i have noticed that they have the almost the same speed on compression and decompression but my Parallel LZO is 7% better on compression ratio than Parallel LZ4 , so i have decided to not include Parallel LZ4 algorithm inside my Parallel Archiver, so if you want to compress Terabytes files i advice you to use my Parallel LZO algorithm with my Parallel Archiver. My Parallel archiver is very stable now, and you can download it from: http://pages.videotron.com/aminer/ Best Regards, Amine Moulay Ramdane. ...

Parallel computing and
Anyone have insights on the interaction between using the Parallel Computing toolbox, either on a single local machine or using Distributing computing on a cluster, and the built-in use of multiple cores through default multi-threading? Thanks. -Dick Startz ...

Parallel Computing Toolbox se of resources in a multi-core, multi-GPU system
I have a x86-64 system w/ 12 Cores and 8 GPU cards. Supposing I have the parallel toolbox, I am allowed to use up to 12 workers. From what I understand, the following scenario would work (Please correct me if I'm wrong): assign N workers to N GPU cards and (12-N) workers to (12-N) cores. Now, are we allowed to assign multiple cores to a single worker, and have that worker multi thread between cores? For example, use 5 workers: 4 workers to 4 GPU cards, and 1 Worker for 6 cores? I would appreciate any help. ...

parallel computing using Cell Computing Model
Hi, i've written an open source C++ framework for Cell Computing. Cell Computing is alike grid computing, but is leant on the biologic. If you are interested please visit http://www.xatlanits.ch. Unfortunately not all documents are available in english yet. All ideas and improvments are welcome :-) -- ...

parallel computing on a six-core local computer
Hi, I just bought a six-core desktop (12 Threads) and discovered that the maximum worker allowed by the parallel computing toolbox is eight workers. This is really disappointing, and I am just wondering if there is anyway to fully utilize the 12 processes and have 12 workers on one local machine. I browsed the help guide for the Distributed Computing Server toolbox and it seems it only works when you'd like to create workers on remote computers. Your help is greatly appreciated. Thank you! richard "Richard Liu" <richardkailiu@gmail.com> wrote in message news:hrhupd$2v3$1@fred.mathworks.com... > Hi, I just bought a six-core desktop (12 Threads) and discovered that the > maximum worker allowed by the parallel computing toolbox is eight workers. I believe that is the correct behavior, assuming you have just Parallel Computing Toolbox. To use more than 8 local workers, or to use workers across multiple machines, you will need MATLAB Distributed Computing Server as well. > This is really disappointing, and I am just wondering if there is anyway > to fully utilize the 12 processes and have 12 workers on one local > machine. I browsed the help guide for the Distributed Computing Server > toolbox and it seems it only works when you'd like to create workers on > remote computers. That is not the case. Could you post the URL of the documentation page that gave you that impression, so that our d...

[ANN] parallel: simple parallel processing.
If you ever write a shell script along the lines of: some | ppieline | bash then you may be interested in my program parallel. The above line would be written as: some | pipeline | parallel 4 to perform the same task, but with 4 commands running in parallel. There is a companion program, ssh_parallel which will distribute the jobs over a number of machines (assuming you have passwordless SSH set up). Webpage: http://mi.eng.cam.ac.uk/~er258/code/index.html Download: http://mi.eng.cam.ac.uk/~er258/code/dist/parallel-1.0.tar.gz On Tue, 05 Jun 2007 01:41:16 +0000, Edward Rosten wrote: > If you ever write a shell script along the lines of: > > some | ppieline | bash > > then you may be interested in my program parallel. The above line would > be written as: > > some | pipeline | parallel 4 > > to perform the same task, but with 4 commands running in parallel. There > is a companion program, ssh_parallel which will distribute the jobs over > a number of machines (assuming you have passwordless SSH set up). > > Webpage: http://mi.eng.cam.ac.uk/~er258/code/index.html Download: > http://mi.eng.cam.ac.uk/~er258/code/dist/parallel-1.0.tar.gz Well, it is interesting, but your parallel program does not seem to offer anything more than the following script (assuming a GNU xargs is installed), which is about 1% of the size and has better error checking (hint fork() can fail). #!/bin/sh xargs -d'\n' -n1 -P$1 bash -c ssh...

Parallel Computing under FreeBSD
Has anyone of you ever used LAM/MPI (Parallel Computing) under FreeBSD and if so, How has it performed compared to a Linux machine running it. Thanks -- ...

How to run while loops in parallel
Hai i am&nbsp;using labview 7.1 I want to read the data &amp; i should transmit through CAN i have two options 1) Default 2) i&nbsp;will read data from a file 3) By clicking on the LED indicator i will generate the data &amp; transmit &nbsp; when i run the program if i select default data &amp; click send default data should be send to the CAN the LED indicator&nbsp;will be ON or OFF if i select Read from file &amp; click that data i select should send according to the data LED will ON or OFF if i select the othere option by clicking on LED it will generate the data that will be send &nbsp; but always the CAN read should run and display the received data &nbsp; i attached my vi please give me an idea how to&nbsp;do it thanks&nbsp;&nbsp; &nbsp; try.zip: http://forums.ni.com/attachments/ni/170/173982/1/try.zip ...

Web resources about - parallel for loops without parallel computing toolbox - comp.soft-sys.matlab

Computing - Wikipedia, the free encyclopedia
For the formal concept of computation, see computation . For the magazine, see Computing (magazine) . For the scientific journal, see Computing ...

Network Computing
Through a For IT, By IT editorial filter, Network Computing connects the dots between architectural approach and how technology impacts the business, ...

Apple Signs Deal To Use Google’s Cloud Computing
More and more businesses are moving their computing platform to the cloud. Cloud computing is the term given to accessing computer and database ...

Can we stop pretending the iPad represents the future of computing?
... post-PC era was upon us. Not to single out Cook, even Steve Jobs believed that tablets were going to one day eclipse PCs as the future of computing. ...

Skyport Raises $30M from GV and Cisco Investments to Ramp Delivery of Zero-Trust Secure Computing Infrastructure ...
Skyport Systems, the company redefining enterprise security architecture, today announced a $30 million round of funding, enabling the company ...

Breakthrough brings quantum computing a big step closer
Quantum computing is now within closer reach thanks to a major breakthrough in which scientists have demonstrated that a key building block can ...

Could a Fredkin gate be the next quantum leap forward for computing?
Building quantum computers is tricky business, with a range of obstacles to overcome, but scientists have had a recent breakthrough with a new ...

Quanta partners with Ericsson for cloud computing datacenter business
Quanta Computer has partnered with telecom equipment maker Ericsson to push the cloud computing datacenter market and the cooperation is expected ...

Eight Ways Solar Power Is Driving New-Gen Computing
As solar technology advances, it's becoming clear that solar is a vital part of the equation that will grow tech's future.

GPU computing breakthrough? Cloud rendering company claims to run CUDA on non-Nvidia GPUs
The cloud rendering company Otoy is claiming to have invented a new software translation layer that would allow Nvidia's CUDA to run on a variety ...

Resources last updated: 3/30/2016 9:31:15 PM