I have to calculate a functional (it’s a set of matrix vector multiplication in double precision, three matrix and six vector) of size n (square matrix nxn and vector of size n). If i have 4800 MBytes of global memory on my gpu (it’s a K20) and i want to transfer all the data on the gpu at one time, how i choose n to fill all the gpu global memory, take into account a double is 8 bytes?
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| How to select the size of my problem? | 8 | 2264 | January 29, 2016 | |
| Memory allocation cuda c++ | 1 | 1186 | January 2, 2015 | |
| How to deal with a data which need to be read for every thread frequently and larger than constant m | 1 | 1081 | October 27, 2013 | |
| Optimize problem regarding problem size | 4 | 6128 | May 25, 2011 | |
| Transferring data to GPU vs Calculation on GPU | 1 | 2459 | June 27, 2011 | |
| matrix_mul with max_size | 1 | 1085 | May 21, 2010 | |
| Matrix multiplication---not getting correct answer? answer for matrix multiplicatin seems to be wron | 0 | 3203 | August 1, 2009 | |
| Memory size in 'real problem' sizes?! | 6 | 6920 | May 31, 2011 | |
| Advice - Complex Matrix-Vector Multiplication | 3 | 5619 | May 12, 2009 | |
| matrix multiplication for large matrices | 3 | 1579 | August 22, 2011 |