| Index | Recent Threads | Unanswered Threads | Who's Active | Guidelines | Search |
| World Community Grid Forums
|
| No member browsing this thread |
|
Thread Status: Active Total posts in this thread: 5
|
|
| Author |
|
|
Former Member
Cruncher Joined: May 22, 2018 Post Count: 0 Status: Offline |
First of all sorry for my bad english.
But i have a couple of questions What i'm curious about is. How big is this project? Do we have numbers? Is there a possiblity that we can see how much of this project is already completed just like by the HIV/AIDS projects. How much time would it take if you have to do the whole project it at 1 machine? If we know this than we can promoted it better by our family and friends and get more support! Have a nice day ! |
||
|
|
Former Member
Cruncher Joined: May 22, 2018 Post Count: 0 Status: Offline |
First of all sorry for my bad english. But i have a couple of questions 1) What i'm curious about is. How big is this project? Do we have numbers? - Techs do not know the batch count total, but estimate it to take several years to complete [HCC1 of same team took ~5.6 years]. It finished several years faster because the GPU implementation accelerated the project by a factor > 10. Actually the average GPU task did a task 18x faster than a CPU. The hope is a MCM GPGPU version will be developed in the future. 2) Is there a possibility that we can see how much of this project is already completed just like by the HIV/AIDS projects. - Something was promised by WCG in terms of progress tracking, but how to do that if work volume is unknown [very big]? 3) How much time would it take if you have to do the whole project it at 1 machine? - Same as 1/2 cannot be computed, but since we did last night 152 CPU years equivalent, that's 1 quad core running 24/7 for the next 38 years or so. If we stay doing 152 Years every day for the next 2 years, that would be 28 thousand years on 1 quad. 4) If we know this than we can promoted it better by our family and friends and get more support! - No project is started without some end in view. Even if it takes 5 years, then this reference database will leap diagnostic capability forward [wanna help?]. Been crunching 9 years now. No plan to stop in the next 9 either. Crunching is for the long haul, slow, methodical and tedious, but that's how science has always worked. Maybe after mapping for the next 6-12 months, some mass data insight will speed things up [scientist learn from the output as we compute on]. Several projects completed much faster, one by some smart programming insight finished in 6 months instead of 2 years. Have a nice day ! [Edit 1 times, last edit by Former Member at Nov 24, 2013 11:56:00 AM] |
||
|
|
mali vuk
Advanced Cruncher Slovenia Joined: Apr 27, 2007 Post Count: 138 Status: Offline Project Badges:
|
1) What i'm curious about is. How big is this project? Do we have numbers? - Techs do not know the batch count total, but estimate it to take several years to complete [HCC1 of same team took ~5.6 years]. It finished several years faster because the GPU implementation accelerated the project by a factor > 10. Actually the average GPU task did a task 18x faster than a CPU. The hope is a MCM GPGPU version will be developed in the future. Interesting. I remember only one project with GPU. One wish more for GPU from my side. ![]() ![]() |
||
|
|
Former Member
Cruncher Joined: May 22, 2018 Post Count: 0 Status: Offline |
I know another university (stanford) in USA who use the bennefits of GPU. I have quiet crunching for them because them most projects were not cancer related and impossible to select for. Thats why i support you guys. But is it possible that you meet with each other and they can explain how they did the crunching with GPU! because if we can use it ! that will bennefit the research to the markers!
Its only a sugestion? |
||
|
|
Falconet
Master Cruncher Portugal Joined: Mar 9, 2009 Post Count: 3315 Status: Offline Project Badges:
|
Hi vinbeer.
----------------------------------------The Help Conquer Cancer project which ran until April 2013 was GPU enabled for for a while. But not all projects are suitable for GPU computations. MCM1 was only launched a few weeks ago and, thus, it's too early to say if it will be GPU enabled. ![]() - AMD Ryzen 5 1600AF 6C/12T 3.2 GHz - 85W - AMD Ryzen 5 2500U 4C/8T 2.0 GHz - 28W - AMD Ryzen 7 7730U 8C/16T 3.0 GHz |
||
|
|
|