Ya, for when 32 bit ints won't do it. For me, I'm writing a parallel matrix diagonalization code. Each node can hold an array of size INT_MAX but I can ultimately do the calculations on an array of...
Type: Posts; User: maverick_starst
Ya, for when 32 bit ints won't do it. For me, I'm writing a parallel matrix diagonalization code. Each node can hold an array of size INT_MAX but I can ultimately do the calculations on an array of...
Anyways, thanks for the help everybody. I seem to have it working now but I'm not entirely sure where the problem was. I just went through it all and made sure everything was explicitely cast (like...
I also wrote the title in like half a second and didn't bother reviewing. However, I do find grammar nazi's (mwahahaha) to be incredibly mis-guided individuals. Feynman has some really amusing...
I'm not using constants. I have something like:
long long totalSize = (long long)(pow(2,inputParameterPassedFromConsole));
avgSize = totalSize/numProcessors;
numOverloadedCPUs =...
Hi,
I'm doing something that needs to use a 64 bit integer in c++. I assume this would be the long long. My question is when you use any of the standard operators, *,/,%,etc. you get zero if...
Hi, I can't seem to find a help forum dedicated to MPI, this was the closest I could find. Anyways, I am having problem with the following code:
#include <iostream>
#include <math.h>...
Like I said, the results here are ints because i'm just using a test vector that is b[i]=i+1. However the real vector will have components that are randomly generated numbers between 0 and 1. Is...
Because this is just a test vector when I actually finish the code it'll be decimal numbers.
Is there any way I can make it work with floats? Unfortunately there are severe storage limitations for my code and basically it runs on the biggest vector the computer it's running on can hold so...
Hi, I'm writing an MPI program and part of this program just needs to do a simple dot product. To do this I wrote the following code:
float innerProduct(float *v1,float *v2){
ftemp=0.0;
...
other process might add to b[y] but its value will never be need until all processes have completed. Basically what it is is that if I have a vector q and b which are both huge I want to do q= q+Ab...
Well yes. I am going to need to do an obscene amount of communication (potentially terabytes worth) which is why picking the best implementation is a huge deal.
Hi,
I'm writing an algorithm in MPI which basically splits up a massive vector amongst different nodes (i.e. node 1 has entries 0-1,000,000, node 2 has 1,000,000 - 2,000,000, etc.) and basically...