cublas

Recently ,I use Cuda to write an algorithm called 'orthogonal matching pursuit' . In my ugly Cuda code the entire iteration takes 60 sec , and Eigen lib takes just 3 sec... In my code Matrix A is [640,1024] and y is [640,1] , in each step I select some vectors from A to compose a new Matrix called A_temp [640,itera], iter=1:500 . I new a array MaxDex_Host[] in cpu to tell which column to select . I want to get x_temp[itera,1] from A_temp*x_temp=y using least-square , I use a cula API 'culaDeviceSgels' and cublas matrix-vector multiplication API. So the culaDeviceSgels would call 500 times ,

I have a M*N host memory matrix, and upon copying into a device memory, I need it to be transposed into a N*M matrix. Is there any cuda (cuBLAS...) API doing that? I am using CUDA 4. Thanks! In the cublas API : cublas<t>geam() This function performs the matrix-matrix addition/transposition the user can transpose matrix A by setting *alpha=1 and *beta=0. (and specifying the transa operator as CUBLAS_OP_T for transpose) To answer your question on efficiency, I have compared two ways to perform matrix transposition, one using the Thrust library and one using cublas<t>geam , as suggested by Robert

CUDA runtime has a convenience function cudaGetErrorString(cudaError_t error) that translates an error enum into a readable string. cudaGetErrorString is used in the CUDA_SAFE_CALL(someCudaFunction()) macro that many people use for CUDA error handling. I'm familiarizing myself with cuBLAS now, and I'd like to create a macro similar to CUDA_SAFE_CALL for cuBLAS. To make my macro's printouts useful, I'd like to have something analogous to cudaGetErrorString in cuBLAS. Is there an equivalent of cudaGetErrorString() in cuBLAS? Or, have any cuBLAS users written a function like this? In CUDA 5.0,

I know it sound weird, but here is my scenario: I need to do a matrix-matrix multiplication (A(n*k)*B(k*n)), but I only needs the diagonal elements to be evaluated for the output matrix. I searched cublas library and didn't find any level 2 or 3 functions that can do that. So, I decided to distribute each row of A and each column of B into CUDA threads. For each thread (idx), I need to calculate the dot product "A[idx,:]*B[:,idx]" and save it as the corresponding diagonal output. Now since this dot product also takes some time, and I wonder whether I could somehow call cublas function here

Just a general question about cublas. For a single thread, if there is not memory transfer from GPU to CPU (e.g. cublasGetVector), will the cublas kernel functions (eg cublasDgemm) automatically be synchronized with the host? cublasDgemm(); //cublasGetVector(); host_functions() Furthermore, what about between two adjacent kernel calls? cublasDgemm(); cublasDgemm(); and, what about a synchronized transfer that does not involve the global memory used in the previous kernel? cublasDgemm(...gA...gB...gC); cublasGetVector(...gD...D...); No, the CUBLAS API is, with the exception of a few Level 1