Search found 15 matches

by Linuxboy
Wed Mar 02, 2016 6:00 am
Forum: User discussion
Topic: papers to dgeqrf_gpu/dgeqrf algorithms, explanations?
Replies: 6
Views: 4382

Re: papers to dgeqrf_gpu/dgeqrf algorithms, explanations?

Hi mark! How about LU decomposition magma_dgetrf and magma_dgetrf_gpu(magma_dgetrf_mgpu)?
by Linuxboy
Tue Oct 14, 2014 11:43 am
Forum: User discussion
Topic: Dense and Sparse LU decomposition
Replies: 3
Views: 2706

Re: Dense and Sparse LU decomposition

Hi mark!
In what format should be a file for the function magma_d_vread? I try to read vector - i got error. In functions like dgetrf i read this file ok/
by Linuxboy
Mon Oct 13, 2014 4:30 pm
Forum: User discussion
Topic: Dense and Sparse LU decomposition
Replies: 3
Views: 2706

Dense and Sparse LU decomposition

Good day everybody! I've got a question. A have a system with sparse matrix NxN, then I do some transformations and got sparse matrix 2Nx2N. Then solve system with LU like dense (i got enough GPU memory). If i use somedirect/iiterative solver is it be slower or faster? Where i can find some results ...
by Linuxboy
Tue Sep 17, 2013 4:25 pm
Forum: User discussion
Topic: Magma 1.4.0 and MKL
Replies: 1
Views: 2158

Magma 1.4.0 and MKL

Hi! I've compiled magma 1.4.0 with MKL. When i use sequential version all is working fine MAGMA 1.4.0 , capability 3.0 device 0: GeForce GTX TITAN, 875.5 MHz clock, 6143.7 MB memory, capability 3.5 Usage: ./testing_dgetrf [options] [-h|--help] ngpu 1 M N CPU GFlop/s (sec) GPU GFlop/s (sec) |PA-LU|/(...
by Linuxboy
Thu Mar 21, 2013 5:01 pm
Forum: User discussion
Topic: problems with magma 1.3.0 and MKL Intel64
Replies: 4
Views: 3578

Re: problems with magma 1.3.0 and MKL Intel64

Thanks!
I've run testing_dgeqrf and then compared the results with testing_dgetrf with ATLAS! my mistake!
I change int to magma_int_t - some routines working, some not.
by Linuxboy
Thu Mar 21, 2013 2:39 pm
Forum: User discussion
Topic: problems with magma 1.3.0 and MKL Intel64
Replies: 4
Views: 3578

Re: problems with magma 1.3.0 and MKL Intel64

Thanks mark. I use 32 bit int - mkl library is faster but less accurate. I change magma_int_t and got new errors testing_zhemv_mgpu.cpp:409:86: ошибка: cannot convert «int*» to «const magma_int_t* {aka const long int*}» for argument «1» to «void zaxpy_(const magma_int_t*, const cuDoubleComplex*, con...
by Linuxboy
Wed Mar 20, 2013 5:21 pm
Forum: User discussion
Topic: problems with magma 1.3.0 and MKL Intel64
Replies: 4
Views: 3578

problems with magma 1.3.0 and MKL Intel64

Hi! I've got ubuntu 11.10, magma 1.3.0 and MKL 11.0. I've compile magma, make tests and run tests. And got error: MAGMA 1.3.0 device 0: GeForce GTX TITAN, 875.5 MHz clock, 6143.7 MB memory, capability 3.5 Usage: ./testing_dgetrf -N <m,n> -c -c2 -l -N can be repeated up to 10 times. If only m is give...
by Linuxboy
Sat Dec 01, 2012 9:41 am
Forum: User discussion
Topic: troubles with magma_dgetrf_gpu
Replies: 3
Views: 2194

Re: troubles with magma_dgetrf_gpu

Thanks Mark.
As I see - I use magma_dgetrf and then use magma_dgetrs_gpu. In this case I use lda or ldda for matrix A in magma_dgetrs_gpu?
by Linuxboy
Fri Nov 30, 2012 4:26 pm
Forum: User discussion
Topic: troubles with magma_dgetrf_gpu
Replies: 3
Views: 2194

troubles with magma_dgetrf_gpu

Hello,
I'm using magma_dgetrf_gpu for my work and I've got error : Argument 113 of dgetrf had an illegal value. magma_dgetrf_gpu returned with error code -113.
Magma version 1.3,device GeForce GTX 560, Cuda 5.0
size of matrix 10000x10000
by Linuxboy
Wed Apr 11, 2012 4:26 am
Forum: User discussion
Topic: problem with Dtrsm
Replies: 0
Views: 1412

problem with Dtrsm

Hi folks! I've got strange error with magmablas_dtrsm. I solve triangular linear system with right sise Y(nx2). magma_dgetrs_gpu get me Invalid __global__ read of size 8 ========= at 0x00000150 in diag_dtrtri_kernel_lower ========= by thread (12,0,0) in block (0,0,0) ========= Address 0x200200880 is...