Search found 893 matches

by mgates3
Tue Jun 04, 2019 9:45 am
Forum: User discussion
Topic: makefile question when adding a file to magmablas/ directory
Replies: 6
Views: 1412

Re: makefile question when adding a file to magmablas/ directory

Currently, CMake won't see new files. They have to be added with `make` first, which will generate magma/CMake.src. MAGMA uses a precision generator (magma/tools/codegen.py) to generate all 4 precisions (s, d, c, z for single, double, complex-single, complex-double) from, usually, the complex-double...
by mgates3
Sat May 18, 2019 4:47 pm
Forum: User discussion
Topic: What is the best Linux distro for MAGMA 2.5
Replies: 1
Views: 1089

Re: What is the best Linux distro for MAGMA 2.5

Shouldn’t matter, as long as they support CUDA. See Nvidia’s site.

Mark
by mgates3
Sat May 18, 2019 4:45 pm
Forum: User discussion
Topic: vl and vu DSYGVDX_2STAGE
Replies: 1
Views: 1012

Re: vl and vu DSYGVDX_2STAGE

If you want all the eigenvalues, use range = MagmaRangeAll, and you can ignore il, iu, vl, vu by passing in dummy values. If you want a subset of eigenvalues, use range = MagmaRangeV, and pass in vl, vu as the range of eigenvalues to find, e.g., to find all eigenvalues in half-open range (0.0, 1.0],...
by mgates3
Sat May 04, 2019 1:28 am
Forum: User discussion
Topic: LU factorization numerical techniques
Replies: 1
Views: 930

Re: LU factorization numerical techniques

LU is a direct method, not an iterative method (see Matlab code below). It forms matrices L, U such that PA = LU (exactly, in exact arithmetic). L has unit diagonal, U has non-zero diagonal (if it has a zero, then A is singular). There is no tolerance level epsilon in the algorithm. % LU factorizati...
by mgates3
Mon Apr 29, 2019 4:59 pm
Forum: User discussion
Topic: statistics on a matrix's column
Replies: 2
Views: 800

Re: statistics on a matrix's column

If you want to write GPU kernels to compute the mean and stddev, you can model them after magmablas/dnrm2.cu, which computes the 2-norm of each column of an m-by-n matrix dA on the GPU. (You can ignore the adjust functions for updating 2-norms.) It is easiest to do in 2 kernels, one for mean, one fo...
by mgates3
Mon Apr 29, 2019 4:37 pm
Forum: User discussion
Topic: statistics on a matrix's column
Replies: 2
Views: 800

Re: statistics on a matrix's column

MAGMA doesn't have functions to do this. It has the Level 1 BLAS functions to find vector norms:
  • magma_dasum = sum_i abs( x_ i )
  • magma_idamax = argmax_i abs( x_i )
  • magma_dnrm2 = norm( x )_2 = sqrt( sum_i abs( x_i )^2 )
But not the mean and standard deviation.
-mark
by mgates3
Tue Apr 23, 2019 5:01 pm
Forum: User discussion
Topic: Apologies for delayed posts
Replies: 0
Views: 964

Apologies for delayed posts

We apologize for the delay in posts from the past several months. The forum software was reconfigured, causing messages to get stuck in the moderation queue, unbeknownst to us. There were quite a lot of spam messages to clean out, and we may have inadvertently skipped over a legitimate message in th...
by mgates3
Tue Apr 23, 2019 4:51 pm
Forum: User discussion
Topic: Using MAGMA GPU library
Replies: 1
Views: 562

Re: Using MAGMA GPU library

lwork is the length of the work array that is passed to MAGMA's routine. Per the documentation, it should be: - If JOBZ = MagmaNoVec and N > 1, LWORK >= N + N*NB. - If JOBZ = MagmaVec and N > 1, LWORK >= max( N + N*NB, 2*N + N**2 ). NB can be obtained through magma_get_zhetrd_nb(N). I guess whoever ...
by mgates3
Tue Apr 23, 2019 4:47 pm
Forum: User discussion
Topic: Fault Injections
Replies: 1
Views: 493

Re: Fault Injections

MAGMA doesn't have anything built in it to inject faults. You can try doing a bit flip; the result will depend on which bit is flipped. If it is in the floating point mantissa, the accuracy will suffer. If it is in the floating point exponent, probably the result will be entirely wrong, since that i...
by mgates3
Tue Apr 23, 2019 4:43 pm
Forum: User discussion
Topic: magma-2.5.0 with cuda-9.0 - undefined double to half conversion
Replies: 1
Views: 550

Re: magma-2.5.0 with cuda-9.0 - undefined double to half conversion

I think this issue has been resolved in MAGMA's bitbucket repository (https://bitbucket.org/icl/magma). We should be having a bug fix release soon to address it.

-mark

[Sorry for the delay in posting. A misconfiguration left messages in the moderation queue.]