Folding Forum

When one does folding, how much data gets download by the client and then uploaded during folding? Does it get uploaded by big chunks as once a day?

I would like to get hold of some data from Folding@home, both for data which gets downloaded before performing computation, and data which gets uploaded at the end.

Fah only transfers data to start a new work unit, and then again only when that work is done. Size is KB to MB, as work units vary in size. How often Fah communicates with Stanford depends on both the size of the work unit and the speed of the computer.

Why would you want to "get hold" of work unit data? It's just coordinate data. Start folding and take a look. Nothing to hide. Project has been running 15+ years.

7im wrote:Why would you want to "get hold" of work unit data? It's just coordinate data. Start folding and take a look. Nothing to hide. Project has been running 15+ years.

Maybe because in some countries bandwidth caps are the norm rather than the exception?

As 7im explained, the amount of data transmitted is a function of how quickly your system is able to complete work.

I selected one of my Linux machines at random, an Intel(R) Core(TM) i7 CPU 940 @ 2.93GHz

In the last 28 days +/- the CPU

Downloaded 89 work units for a total of 50 meg data
and Uploaded 88 work units for a total of 138 meg

I selected one of my GPUs at random, a NVIDIA:3 GK110 [GeForce GTX 780 Ti]

In the last 90 days +/- the GPU

Downloaded 306 work units for a total of 506 meg data
and Uploaded 305 work units for a total of 995 meg

_r2w_ben wrote:

7im wrote:Why would you want to "get hold" of work unit data? It's just coordinate data. Start folding and take a look. Nothing to hide. Project has been running 15+ years.

Maybe because in some countries bandwidth caps are the norm rather than the exception?

Please let the topic starter respond before assuming anything.

_r2w_ben wrote:

7im wrote:Why would you want to "get hold" of work unit data? It's just coordinate data. Start folding and take a look. Nothing to hide. Project has been running 15+ years.

Maybe because in some countries bandwidth caps are the norm rather than the exception?

Kind of close .
I am working on a project dealing with efficient data transfer in distributing computing, especially with places or connections having low bandwidth. That's why I would like to find some readily available dataset instead of trying to generate my own data, since I don't know how long it will take to generate substantial (~200-300MB) amount of data.

There are Linux or Windows functions that can easily generate files with random contents of the specified size ... the only limit is your storage size