7
votes
Accepted
Compiled c++ code runs much faster with double than float. Explanation?
I have looked at your simple code example, and my suspicion is that what you observe in loss of speed is due to the C-heritage requirement that right-hand side expressions be evaluated using ...
- 3,349
7
votes
fastest linear system solve for small square matrices (10x10)
Using an Eigen matrix type where the number of rows and columns is encoded into the type at compile time gives you an edge over LAPACK, where the matrix size is known only at runtime.
This extra ...
- 9,813
6
votes
Which Linux OS for computer science and numerical analysis
There are lots of available Linux distributions and several widely used window managers, and most of them would be perfectly adequate for your needs. It is important to make sure that the ...
- 18.5k
6
votes
Accepted
The difference between mkl_intel_lp64 vs mkl_gf_lp64 in a numerical reproducibility issue with Intel MKL
The various Fortran standards allow a lot of compiler dependent behaviour in terms of function binary interfaces when being called with "complicated" data types such as Fortran90 style arrays and ...
- 2,229
5
votes
HPC : should I compile on the head node or on a compute node?
Let me supply a belated answer from the POV of a cluster user and a cluster administrator.
A well-designed cluster will, in general, be as homogeneous as possible, with login-nodes being generally a ...
- 341
5
votes
Fast evaluation functions given by straight-line programs
OK, you have a very nice problem, I tried to run some benchmarks.
First, I don't have your parameters so I used your small example.
Second, since you do not specify the language, I used C + GSL (...
- 201
4
votes
Compiled c++ code runs much faster with double than float. Explanation?
There are multiple possible explanations:
with floats and doubles the different number of computations happen due to, say, ...
- 8,592
4
votes
fastest linear system solve for small square matrices (10x10)
Another idea could be to use a generative approach (a program writing a program). Author a (meta)program that spits out the sequence of C/C++ instructions to perform unpivoted** LU on a 10x10 system.. ...
- 4,794
3
votes
Fast evaluation functions given by straight-line programs
Once you're at the level of a long list of expressions, there is little you can still do other than hope that the compiler finds opportunities for optimization at the assembly level. This may bring ...
- 53.7k
2
votes
Branch avoidance for performance with modern compilers?
To add to Wolfgang's answer, there are many expressions which look like they could be optimized by a Sufficiently Smart Compiler, but for which a general use of this optimization would be unsafe. As ...
- 9,813
2
votes
Accepted
Branch avoidance for performance with modern compilers?
Yes, modern compilers use branch avoidance if possible. For example, they would pull common subexpressions in the assignments to the variable a out of the if/else ...
- 53.7k
2
votes
fastest linear system solve for small square matrices (10x10)
Your question leads to two different considerations.
First, you need to pick the right algorithm. Hence, the question if the matrices have any structure, should be considered. E.g., when the matrices ...
- 558
2
votes
Which Linux OS for computer science and numerical analysis
I use Debian and OpenSuse Tumbleweed on our Linux desktops. Tubleweed is a rolling distribution, so there is no concept of OS version. You get very latest softwares but could be bit unstable. If your ...
- 2,993
1
vote
Identical .so shared libraries (with no symbols) are generated when compiling different C source files
I don't think this is an appropriate question for this site, but I'll try to give an answer. Did your sysadmin or you update the OS and/or C++ compiler/library under the hood since the last time you ...
- 10.9k
1
vote
Fast evaluation functions given by straight-line programs
Would it be possible to do the 1 billion runs method-parallel? Even if there is no way to parallelize the interior of the method body, depending on your problem, you might reach some form of ...
- 2,621
1
vote
fastest linear system solve for small square matrices (10x10)
I would try blockwise inversion.
https://en.wikipedia.org/wiki/Invertible_matrix#Blockwise_inversion
Eigen uses an optimized routine to calculate the inverse of a 4x4 matrix, which is probably the ...
- 661
1
vote
Which Linux OS for computer science and numerical analysis
I use Ubuntu 18.04 at work and Manjaro Arch Linux on my laptop. I use MATLAB, C++, and Julia ...
- 111
1
vote
Accepted
standard directory for compiling scientific libraries
I don't think there's any one right answer here. I tend to put non-system libraries in /opt, then add link directives for them manually to the Makefiles etc of whatever apps are looking for them (eg, ...
- 4,794
1
vote
How to Run MPI-3.0 in shared memory mode like OpenMP
I also found this link on Stack Overflow. I swear I looked for questions like mine for forever but it seems the best way to search a question on stack overflow is to start to make a question and it ...
- 191
Only top scored, non community-wiki answers of a minimum length are eligible