Anyone have experience with CUDA?

Stiganator

Platinum Member
Oct 14, 2001
2,492
3
81
After seeing that 8 GPU supercomputer, I've been wondering if we could implement that in our own lab. We do some image processing that takes several hours on our lab computers and there is a wait time get use the supercomper clusters. Having our own lab computer would be useful.

Would it be easy to port existing C over to CUDA, is it just a recompile?

Anyone have any experience with it?
 

Biftheunderstudy

Senior member
Aug 15, 2006
375
1
81

PolymerTim

Senior member
Apr 29, 2002
383
0
0
Well, I'm no programmer in real life (I just pretend to be one in my spare time), but I've been a bit fascinated by GPGPU lately and have read a few papers on the topic. I'm not sure about compiling code, but I've read that in order to get effective use of the massively parallel computing power of the GPU, coed often has to be rewritten from the ground up with parallel computation in mind. I've seen programmers speak about the process as taking a step backwards and then several forwards because you often have to introduce what would normally be seen as expensive overhead in order to prepare the data for parallel computation, but that this can be more than made up for in the parallel steps.

That being said, there are a number of people out there developing software for these purposes. Some friends of mine at school are doing molecular dynamics simulations, for instance, and software is currently being written that can perform these computations on GPUs with a very substantial advantage over traditional CPU processing.

This paper gives a good overview of that particular application and exhibits a single 8800GTX performing, in some cases, 80 times faster than a 3.2GHz Xeon (of undisclosed generation).

My friend is in a group with a cluster of about 40 dell desktops networked as their computing cluster and I couldn't help but grin as I explained to him that it appears a single (~$3k-4k) computer could outperform his cluster for his application.
 

Stiganator

Platinum Member
Oct 14, 2001
2,492
3
81
Update:

My advisor bought me an 8800GT to see if I can get CUDA working for our analysis.
 

eLiu

Diamond Member
Jun 4, 2001
6,407
1
0
Eric Darve at Stanford does some work with implementing numerical algorithms on GPUs. He has at least 1 grad student (that I know of) working on this, but I can't remember the name. This is the guy of fast multipole fame.

You might try hunting around on his website (linked from the page I linked to).
 

peller

Junior Member
Oct 30, 2007
11
0
0
I haven't written any CUDA code, but I just took a Computer Architecture course and talked with my professor after class about GPGPU because it fascinated me too. The problem is, C code (or any code, for that matter) when written for a CPU is designed to run in either a linear (if this then that...) or circular fashion (loops). It's often very branch-heavy and requires constant cache access as data is moved into and out of registers. GPUs don't have caches (that's a lie, but for all intensive purposes when comparing to CPUs true) and operate on massively parallel data loads. If you've ever programmed with SIMD it's similar to that. The GPU is good for doing repeated floating point operations of large parallel (ie, not interdependent) data sets. It's terrible at making decisions (branches). This is why GPUs use memory that's incredibly high in bandwidth but not very latency sensitive. The data the GPU is reading is assumed to be aligned in memory so lines can be pulled out in sequence and literally streams data to the GPU. Once the GPU has performed it's calculations on a data set, the data goes straight back to the memory. If a second operation then needs to be done on the same data set, the process is repeated as the entire set is again streamed through the GPU.

Now, like I said I don't have any experience actually programming these things nor any experience working with images, but my understanding of image processing is that you're doing the exact same operation on each individual pixel. GPGPU seams perfect for your application, but it will certainly require a few steps backwards before you can realize the massive performance benefits.
 
sale-70-410-exam    | Exam-200-125-pdf    | we-sale-70-410-exam    | hot-sale-70-410-exam    | Latest-exam-700-603-Dumps    | Dumps-98-363-exams-date    | Certs-200-125-date    | Dumps-300-075-exams-date    | hot-sale-book-C8010-726-book    | Hot-Sale-200-310-Exam    | Exam-Description-200-310-dumps?    | hot-sale-book-200-125-book    | Latest-Updated-300-209-Exam    | Dumps-210-260-exams-date    | Download-200-125-Exam-PDF    | Exam-Description-300-101-dumps    | Certs-300-101-date    | Hot-Sale-300-075-Exam    | Latest-exam-200-125-Dumps    | Exam-Description-200-125-dumps    | Latest-Updated-300-075-Exam    | hot-sale-book-210-260-book    | Dumps-200-901-exams-date    | Certs-200-901-date    | Latest-exam-1Z0-062-Dumps    | Hot-Sale-1Z0-062-Exam    | Certs-CSSLP-date    | 100%-Pass-70-383-Exams    | Latest-JN0-360-real-exam-questions    | 100%-Pass-4A0-100-Real-Exam-Questions    | Dumps-300-135-exams-date    | Passed-200-105-Tech-Exams    | Latest-Updated-200-310-Exam    | Download-300-070-Exam-PDF    | Hot-Sale-JN0-360-Exam    | 100%-Pass-JN0-360-Exams    | 100%-Pass-JN0-360-Real-Exam-Questions    | Dumps-JN0-360-exams-date    | Exam-Description-1Z0-876-dumps    | Latest-exam-1Z0-876-Dumps    | Dumps-HPE0-Y53-exams-date    | 2017-Latest-HPE0-Y53-Exam    | 100%-Pass-HPE0-Y53-Real-Exam-Questions    | Pass-4A0-100-Exam    | Latest-4A0-100-Questions    | Dumps-98-365-exams-date    | 2017-Latest-98-365-Exam    | 100%-Pass-VCS-254-Exams    | 2017-Latest-VCS-273-Exam    | Dumps-200-355-exams-date    | 2017-Latest-300-320-Exam    | Pass-300-101-Exam    | 100%-Pass-300-115-Exams    |
http://www.portvapes.co.uk/    | http://www.portvapes.co.uk/    |