Questions tagged [parallel-computing]
The study of solving computational problems by exploiting the use of multiple processors simultaneously.
39
questions with no upvoted or accepted answers
9
votes
0
answers
137
views
Review of modern homotopy methods and practical techniques
I'm hoping someone can recommend recent literature concerning homotopy methods for solving systems of nonlinear equations. Already by the time of Layne Watson's 1986 paper there were a lot of methods,...
- 297
6
votes
0
answers
284
views
What are the career options for computational scientists other than being in software Industry?
I would like to know the career options for a computational scientist other than getting into software industry. I wish to use the my skills of Numerical Linear Algebra,Parallel Programming, ...
- 99
5
votes
0
answers
116
views
Computing entries of a matrix in parallel using GPU
I am trying to solve $Ax=b$ a system of linear equation. The matrix $A=(a_{ij})$ is constructed as $$a_{ij}=\int_0^1\int_0^1 K(x,y)h_i(x)h_j(y) dxdy.$$ The evaluation of integral takes a lot of time, ...
- 51
4
votes
0
answers
164
views
How amenable is this 2D Frenkel–Kontorova-like energy minimization problem in Python to the use of a modest PC + GPU? (Heavy reliance on indexing)
@Richard's answer to Going to try to move some of my scipy/numpy calculation to a new GPU, how to avoid disappointing results? is quite helpful, and as promised I've added a simple running example ...
- 1,016
4
votes
0
answers
235
views
Can you provide an example of an algorithm that has strong scalability but not weak scalability? Can you also provide an example the other way around?
Strong Scaling and Amdahl's Law
Strong scaling is a measure of how, for a fixed overall problem size, the time to solution decreases as more processors are added to a system. An application that ...
- 41
3
votes
0
answers
85
views
Numerical calculation of out-of-time order correlators (OTOCs)
I want to numerically calculate OTOCs for different quantum mechanical systems. Consider the following Hamiltonian
$$H=p_x^2+p_y^2+x^2y^2$$
and I want to calculate the following OTOC
$$C_T(t)=-\left&...
- 131
3
votes
0
answers
32
views
One cancels the other qsub semantics atop SGE?
Is there a way to achieve "one cancels the other" semantics (http://www.investopedia.com/terms/o/oco.asp) for qsub jobs submitted to Sun Grid Engine? That is, I submit two (or more) jobs and when one ...
- 619
3
votes
0
answers
36
views
An asynchronous version of the Covariance Matrix Adaption (CMA)?
Does anyone know of a variant of the CMA algorithm that is suitable for an asynchronous parallel implementation?
The conventional version of the algorithm allows one to evaluate the fitness function ...
- 703
2
votes
0
answers
33
views
Diagonalization of large sparse matrix, computational programme recommendation and methods
According to this link, All eigenpairs of large sparse symmetric matrix. The guy @Baranas seems to have given a very confident answer about solving the whole Eigen spectrum. May I know if anyone has ...
- 21
2
votes
0
answers
120
views
Why GPU scaling (speedup) is usually worse than CPU scaling?
Let's define scaling, as how linear the speedup of using more than one GPU or CPU is. For example, having 2 GPUs gives you 2x faster execution time.
I have noticed that in many software (e.g. ...
- 123
2
votes
0
answers
77
views
How to find eigvals/eigvecs of huge symmetric tridiagonal matrix using multiple processes or threads?
In python, there is a function in scipy (scipy.linalg.eigh_tridiagonal) which is extremely efficient for an exact diagonalization of a symmetric tridiagonal matrix (...
- 21
2
votes
0
answers
156
views
Parallel In Time with Multigrid
I am trying to solve the linear finite element equation $M\ddot{u}+Ku=F(t)$, where $M$ is the mass matrix ,$K$ the stiffness matrix and $F(t)$ the external load vector, parallel in time using XBraid ...
- 481
2
votes
0
answers
75
views
OpenMP inconsistently segfaulting
I parallelized my code with openMP, and now have this bug in my code that's really odd. If it's the first time I run on a computer, it segfaults, but if I run the program again it runs fine. I've ...
- 2,069
2
votes
0
answers
125
views
What is the state-of-the-art in parallel sparse matrix and dense vector multiplication?
For sure, there has been many highly optimized library on this. But I am working on a matrix-free context since the problem size does not allow explicit storage of sparse matrix elements. I'd love ...
- 61
2
votes
0
answers
74
views
Parallel compact schemes using the Parallal Diagonal Dominant (PDD) algorithm
I would like to use the PDD algorithm developed by Sun to solve tridiagonal matrices in parallel for the following compact finite difference scheme:
$
\begin{align}
\dfrac{1}{4}f^{'}_{i-1} + f^{'}_i +...
- 33
2
votes
0
answers
153
views
scalable parallel mesh/amr on unstructured grid
I am trying to code a scalable parallel AMR for unstructured grid. There seems to be three approaches for this
a) Store some global grid info on each processor and partition with parmetis (The ...
- 233
2
votes
0
answers
156
views
Quasi-Newton Optimization with parallel function evaluation
I have a function of many variables (~200-2000) which I am optimizing with some success using L-BFGS. While the function is expensive to evaluate, the gradient can be computed with not much additional ...
- 121
2
votes
0
answers
210
views
preconditioned Uzawa method with Petsc
I am trying to improve the resolution of a Stokes problem (P2/P1 on unstructured mesh) defined by the matrix $M$:
$M=
\begin{pmatrix}
A_u & 0 & B_u \\
0 & A_v & B_v\\
B_u^T & B_v^...
- 65
1
vote
0
answers
61
views
OpenMP Fortran array operations in target regions
I am asking this here for the possibility that someone here is familiar with OpenMP offloading. Is there some other way to parallelise Fortran array operations outside of unrolling the loops of the ...
- 121
1
vote
0
answers
254
views
Why does Eigen allocate a temporary to evaluate A.noalias() = B.transpose()*C in parallel?
I wrote a program which iteratively transforms data using matrix multiplications. To minimize the number of large memory allocations, I use two roughly equal-sized ...
- 21
1
vote
0
answers
186
views
performance comparison between PETSc and SLATE
We want to start a new project to solve a large-scale inverse problem (O(10^6) number of parameters) to invert for subsurface wave speeds. We will use FEM to solve forward and adjoint PDEs. In our ...
- 19
1
vote
0
answers
54
views
Multigrid Reduction In Time Convergence
I am trying to solve a 2D dynamic linear elasticity model parallel in time using Xbraid. The spatial domain is [0,1]x[0,1] and time domain [0,1]. For time integration I am using a backward Euler ...
- 481
1
vote
0
answers
61
views
Algorithm design to filter on 5,000 stocks each of which has 4 months worth of data points
I want to filter on 5000 stocks, each of which has 4 month or more worth of data (>= 500 data points each). my filtering criteria will be based on 8 calculated values from the data points. for example,...
- 111
1
vote
0
answers
72
views
Parallel dense solve with submatrices from mesh refinement with Petsc
For a Bounday Element Method problem I require the solution of a system of linear equations with multiple right-hand sides. Though this is a dense system, I still want to do it via Petsc in parallel. ...
- 31
1
vote
0
answers
65
views
Parallelizing molecular simulation with full configuration energy
First, let just me stress that I'm not a an expert in computation chemistry, so now the problem:
We have GCMC molecular simulation, in the Grand Canonical ensemble, using the standard metropolis ...
- 11
1
vote
0
answers
136
views
Porting from MPI to GPU
Assuming that the underlying algorithm can be ported to multi GPU, what aspects should one consider while porting from MPI (on multiple nodes) to multi GPU (again on multiple nodes)?
Making use of ...
- 111
1
vote
0
answers
81
views
What is the best option in terms of library or software to solve this system of hyperbolic PDEs?
I want to solve a system of coupled nonlinear 1-D PDE $(\partial_{tt} + \alpha\partial_t)u_i(x,t)=\partial_{xx}(\sum_{j=1}^{j<i}ju_j(x,t)+i\sum_{j=i}^{n}u_j(x,t))-\sin(u_i(x,t))+f$, using method of ...
1
vote
0
answers
50
views
Minimum effort merging of two sets
I have the following problem.
I have two sequences of elements $A = [a_1,a_2,\cdots,a_n]$ and $B = [b_1,b_2,\cdots,b_m]$. I can build a matrix $D[n \times m]$ where $d_{ij} = d(a_i,b_j)$
My greedy ...
- 11
1
vote
0
answers
127
views
Why would this a pair of E5-2670 cpus be faster than 4 E5-2640 cpus for large matrix diagonalisation problems?
Not really much more to say;
Of several computers available for use, these are two of the larger ones; one has 2x E5-2670, and the other has 4x E5-4640. The problems we're looking at essentially boil ...
- 131
1
vote
0
answers
506
views
CUDA Mandelbrot Set effective bandwidth and optimization
I was reading through this article (very good article and excellent blog BTW) to do some measurements in my (very simple) implementation of the Mandelbrot Set.
I'm using a Quadro 2000D card which has ...
- 1,019
0
votes
0
answers
32
views
Unable to validate hypersonic flatplate case in DSMC SPARTA
I'm trying to learn a software called DSMC SPARTA. I'm validating the hypersonic flatplate case mentioned in one of the tutorials on the website (Page 17). This was my test case:
...
- 101
0
votes
0
answers
28
views
Parallel Block-Structured class abstraction for FDM
I’m currently developing a FDM/FVM (using contravariant coordinates) code using Fortran and Co-Arrays (SIMD, in general), and so far I have all sparse matrix (BiCGStab, working on AMG) solvers and ...
- 251
0
votes
0
answers
50
views
Calculate the time taken to run an algorithm on GPU
I want to calculate the total time taken for a fixed code run using an NVIDIA GPU (for instance, Tesla K40). The code has to run 1 million single-bit comparisons. All the comparisons are independent ...
0
votes
0
answers
101
views
How to decouple nodes and cores with MPI?
I have code currently using multiprocessing with joblib to distribute computations from a loop over multiple cores within one cluster node, like so:
...
- 101
0
votes
0
answers
67
views
where to use multiprocessing in multi-loop program
I am running a program that uses [a lot of] looping to perform a type of bootstrap analysis. The computational step - PCA - can take a long time (60+) seconds, which means that collectively this ...
- 101
0
votes
0
answers
67
views
Is there a mathematical algorithm that can determine whether a problem is parallelizable?
Is there a mathematical algorithm that can determine whether a problem is parallelizable?
Possibly similar to how the definition for "computable" works out:
https://en.wikipedia.org/wiki/...
- 427
0
votes
0
answers
77
views
Output solution vector in Petsc
I am using petsc to solve a linear elasticity problem discretized by finite elements.The initial mesh is read by a mesh file and the distribution in each processor is done using METIS.I am using only ...
- 21
0
votes
0
answers
46
views
Methodology to develop parallel GPU simulations
I'm quite new to GPU or in general parallel programming. I am working on a Lattice-Boltzmann simulation that should be parallelized on GPU's. I wanted to asked more experienced people how to attack ...
- 11
0
votes
0
answers
682
views
Openmp critical section inside if conditional statement
I have a function like this
void foo(x, *y) {
some calculations
if (x > *y) {
*y = x/2;
}
more calculations
}
My parallel section is
<...
- 659