Closed. This question needs details or clarity. It is not currently accepting answers.
Want to improve this question? Add details and clarify the problem by editing this post.
Closed 5 years ago.
Improve this question
I studied how to optimize algorithms for multiprocessor systems. Now I would understand in main lines how these algorithms can be transformed into code.
I know that exist some libraries MPI based that helps the developement of software portable to different type of systems, but is right the word "portable" that makes me confused: how the program can be authomatically adapted to an arbitrary number of processors at runtime, since this is an option of mpirun? How the software can decide the proper topology (mesh, hypercube, tree, ring, etc)? The programmer can specify the preferred topology through MPI?
you start the application with a fixed number of cores. Thus, you cannot automatically adapted to an arbitrary number of processors at runtime.
You can tune your software to the topology of your cluster. This is really advanced and for sure not portable. It only makes sense if you have a fixed cluster and are striving for the last bit of performance.
Best regards, Georg
Related
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed last month.
Improve this question
So I wanted to learn HPC and I couldn't find any resources list.
Of course we have "Awesome HPC" but last update was for 3 years ago.
My main question is how to learn HPC.
what are the prerequisites?
what programming languages should I know?
And if you have any advice I'm all ears.
There are plenty of books about Parallel Computing, Parallel Algorithms, Scientific Computing, OpenMP and MPI; without to mention HPC books.
Some good books are even free and good to start with such as the Victor Eijkhout's HPC book.
With respect to programing languages, C, C++ and FORTRAN are generally used to code HPC applications. CUDA and OpenCL may be good to know for GPU-based programming.
Note that the HPC landscape should not be very different since 3 years, so it is OK to read such tutorials.
I would say it is very much about understanding the principles of computer architecture and from there on you will be able to write efficient code.
First, one has to be able to write good serial code and then you can have a look on parallelizing it.
I'm a big fan of the book "Introduction to High Performance Computing for Scientists and Engineers" from Hager and Wellein. It will give you the full journey from understanding the hardware to writing fast code and finally to make the fast code even faster by parallelizing. By the way, it's from 2010, but all in there still holds ;-)
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 4 years ago.
Improve this question
How is distributed memory parallelism handled in Rust? By that, I mean language constructs, libraries, or other features to handle computing on something like a cluster akin to what MPI provides C, but not necessarily using the same primitives or methodology. In the Rustonomicon, I see a discussion of threads and concurrency, but I don't see any discussion on parallelizing across multiple computers.
To the best of my knowledge, there isn't really anything built into the language for distributed computing (which is understandable, since that's arguably not really the language's major focus, or at least wasn't back in the day). I don't believe there's any particularly popular crate or another for distributed computing either. Actix is probably the only actor crate that has achieved any traction, and it supports HTTP, but I don't think it is targeted at HPC/supercomputer setups. You also definitely would want to check out Tokio, which seems to be pretty much the library for asynchronous programming in Rust, and is specifically targeted towards network IO operations.
At the present point in time, if you're looking to replicate MPI, my guess would be that your best bet is to use FFI to a C-based MPI library. It appears that there's been a handful of attempts to create bindings to MPI for Rust, but I'm not sure that any of them are particularly complete.
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 6 years ago.
Improve this question
Question:
How do Hardware languages (HDLs) differ from general purpose languages such as Python, Java, etc. In particular, what is the primary trade-off that causes general purpose languages to be sub-optimal for FPGA's when compared to VHDL and Verilog?
Context:
I'm a programmer but definitely work at a high level of abstraction such as JavaScript, tinkering with API's, etc. My low-level knowledge is very limited but I am playing around with an FPGA and have some novice questions that I cannot solve with Google or Wikis.
Considering I am a novice, please do not vote harshly against this post. Just state your suggestions for the question and I will happily revise! :)
Example:
For example, why isn't everyone just coding FPGAs and ASICs with Python or C# instead of Verilog or VHDL? I understand that there are some Python libraries, but I have read that they are limited in their viable use-cases. I would greatly appreciate someone shining some light on why HDLs are necessary and beneficial and why general purpose languages are not optimal in comparison for these scenarios.
Thanks in advance!
This is a broad opinionated question, but I think there is a short answer. In some sense, they are all programming languages, i.e text descriptions that gets compiled into a set of machine instructions to be executed on a host machine(software).
But an HDL is also a text description that gets compiled into a set of machine instructions to build another machine (hardware).
Technically, any programming language could be used to describe hardware (SystemC in C++ as an example), Verilog and VHDL were specifically developed to model and simulate hardware most efficiently.
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 8 years ago.
Improve this question
Lets say that my definition of 'rudimentary programming' refers to the fundamental tools employed for a computer to perform a task.
Considering programming rudiments, the learning spectrum usually looks something like this:
Variables, data types and variable memory
Arrays/Lists and their manipulation
Looping and conditionals
Functions
Classes
Multi threading/processing
Streams (hard-disk and web)
My question is, have I missed any of the major rudiments? Is there a 'next' to the spectrum that still eludes me?
I think you missed the most important one: algorithms. Understanding the complexity, know the situation to use them, why use them and more important, how to implement them.
I'm pretty sure that you already know a lot about algorithms but if you think that your tool-knowledge (aka the programming languages) are good enough, you should start focus, more, on the algorithms.
A great book to start is: Introduction to Algorithms, from Thomas H. Cormen
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 8 years ago.
Improve this question
I'm very impressed to how plagiarism checkers (such as Turnitin website ) works. But how do they do that ? In a very effective way, I'm new to this area thus is there any word matching algorithm or anything that is similar to that is used for detecting alike sentences?
Thank you very much.
I'm sure many real-world plagiarism detection systems use more sophisticated schemes, but the general class of problem of detecting how far apart two things are is called the edit distance. That link includes links to many common algorithms used for this purpose. The gist is effectively answering the question "How many edits must I perform to turn one input into the other?". The challenge for real-world systems is performing this across a large corpus in an efficient manner. A related problem is the longest common subsequence, which might also be useful for such schemes to identify passages that are copied verbatim.