Showing results for

- Intel Community
- Software
- Intel oneAPI Toolkits
- Intel® oneAPI HPC Toolkit
- 2D FFT performance on cluster

- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Mute
- Printer Friendly Page

andrei1

Beginner

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content

04-12-2006
08:32 AM

219 Views

2D FFT performance on cluster

Hi there,

I need to take an advantage of calculation of 2D FFT on the grid, say, 512x512 using the cluster.

Algorithm consists of 3 steps:

1. 1D FFT's on the raws of the matrix

2. Matrix transpose

3. Repetition of the step 1.

One-processor tests show that the Step 2 (matrix transpose) is the most time consuming part of the algorithm. So, while parallelization of Step 1 is pretty straightforward on the cluster, the matrix transpose on the cluster becomes a bottleneck.

There is a group of people from the East Coast who worked on the problem and presumably achieved linear growth of FFT performance on the cluster up to 16 processors, which is quite impressive.

The question is, if Intel cluster library can handle the problem of parallelization of 2D FFT on the cluster?

Andrei

Link Copied

7 Replies

Henry_G_Intel

Employee

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content

04-12-2006
01:18 PM

219 Views

Hello Andrei,

The Intel Cluster Math Kernel Library 8.1can do distributed-memory, parallel FFT's. The following website has more information: http://www.intel.com/cd/software/products/asmo-na/eng/perflib/mkl/266852.htm. You can download Cluster MKL and get a 30-day license from this site too.

Please share your performance results if you try Cluster MKL.

Best regards,

Henry

andrei1

Beginner

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content

04-12-2006
02:51 PM

219 Views

I looked at the performance graphs in the link in your reply.

How can one get 5 Gflops performance on 1.5 Ghz processor (I mean 1D FFT graph)?

Andrei

Message Edited by andrei@cox.net on 04-12-200607:53 AM

Henry_G_Intel

Employee

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content

04-12-2006
03:44 PM

219 Views

Hi Andrei,

The Itanium 2processor can dofour floating-point operations per clock cycle. Therefore, the theoretical peak of a 1.5 GHz Itanium 2 is 6 GFLOPS.

Henry

andrei1

Beginner

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content

04-12-2006
04:12 PM

219 Views

I think that different graphs for the cluster performance estimate would be useful -- acceleration factor versus number of processors used for, say, 512x512 FFT. In fact, they are common in literature.

It is easy to understand from the existing graphs that such dependence is close to linear up to 4 processors. It is also clear that it will start to deviate from linear dependence at specific number of processors. Question -- how many and how fast?

Is there any place to take a look at such graphs?

Thanks, Andrei

Henry_G_Intel

Employee

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content

04-12-2006
06:10 PM

219 Views

Hi Andrei,

I'm not aware ofany other graphs or published benchmarks of MKL DFT performance. I can't estimate the scalability of your calculation. However, a 512x512 FFT is considered a small calculation on a good workstation or server. I recommend that you measure the serialMKLperformance before investing any effort in a distributed-memory, parallel solution. Depending on your system, MKL can probably compute a 512x512 transform in less than a second.Ifso, adistributed-memory, parallel solution will be slower because of the communication overhead.

Henry

andrei1

Beginner

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content

04-13-2006
02:10 PM

219 Views

Thank you for your answers. In fact, 512x512 grid is just entry level

for my problem and I hope that system overhead will be significantly

lower for higher grid dimension.

Appreciate your cooperation, Andrei

tcrony70

Beginner

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content

04-26-2006
01:37 AM

219 Views

Regarding the 1.5GHz Itanium 2's peak performance of 6 GFlops, I would have thought that for short precision data, the peak would be higher through the use of whichever SIMD is actually present.

Tim

- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page

For more complete information about compiler optimizations, see our Optimization Notice.