Hello everyone. I’m facing a problem with cublasSgemm and I would like your help, since I’m a beginner in cuda programming. I want to compute the operation C = A*transpose(B), where a is an (m,n) matrix and B is a (p, n) matrix. The result should be (m,p). They’re stored in row-major format. I can’t decide on the parameters m, n, k and lda ldb ldc. Could you help please?
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Row major matrix to Row major matrix multiplication in cublas | 1 | 5675 | September 24, 2014 | |
| cublasSgemm and tansposed results is it possible to calculate trans(trans(A) * trans(B)) | 6 | 4100 | August 20, 2009 | |
| Having trouble using cublas_dgemm with row major matrix [solved] | 1 | 955 | November 23, 2016 | |
| Alternatives to cublas matrix multiplication (row major) | 9 | 17516 | April 7, 2010 | |
| How to use CUBLAS in C ? | 1 | 1010 | August 1, 2011 | |
| Help in using CUBLAS | 2 | 2185 | January 29, 2012 | |
| cublasSetMatrix() and cublasGetMatrix() for dealing with matrices stored in row major order | 4 | 6375 | September 10, 2015 | |
| cublasSgemm - how to correctly use transpose? | 0 | 3477 | October 13, 2008 | |
| Transpose with cublasDgeam routine for row major ordered rectangular matrice | 0 | 849 | October 28, 2016 | |
| Matrix-Vector Multiply with cublasDgemv | 4 | 3180 | January 2, 2010 |