Re: [hpx-users] Recommended approach for hetrogenous computing

Thanks Hartmut for getting back to me on this. I'm sorry to have missed this originally /caught in my spam filter) -- On May 30, 2019 8:03:00 a.m. "Hartmut Kaiser" wrote: > ... >> > > > We've had several attempts to providing higher level support to integrate > GPGPUs with HPX. HPXCL is

Re: [hpx-users] C++20 Modules and HPX library modularization

Hi Hartmut, Thanks for the quick reply - unfortunately it was deemed spam and since my spam folder does not sync on my phone, I didn't see it until I forced an update. I'd certainly be interested and willing to contribute to this effort as well as to looking into a possible solution for GPGPUs,

Re: [hpx-users] Recommended approach for hetrogenous computing

Hi, just following up - can anyone please help me with this? Thanks! On May 29, 2019 9:44:18 a.m. Michael Levine wrote: Hi all, I was wondering whether anyone could provide some direction as to the recommended approach to incorporating GPU-based execution within an HPX application, either

[hpx-users] Recommended approach for hetrogenous computing

Hi all, I was wondering whether anyone could provide some direction as to the recommended approach to incorporating GPU-based execution within an HPX application, either in general or, preferably if possible, for how I (think I) want to use it- Given a number of host systems (CPU), each possibly c

[hpx-users] C++20 Modules and HPX library modularization

Hi, I am wondering whether there are any plans in the short or mid-term to provide support in HPX for the new Modules TS which is expected to be part of C++20? While compile times are not really the main benefit of modules, I understand that we can expect to see some variable degree of improvement

Re: [hpx-users] HPX - guidance regarding inter-locality communications

Hi Thomas, Thank you very much for your prompt response. It was extremely informative and tremendously helpful. I've got a couple follow-up questions below. On Fri, Dec 8, 2017 at 2:30 AM, Thomas Heller wrote: > Hi Shmuel, > > Am 07.12.2017 2:08 nachm. schrieb "Shmuel Levine" >: > > > ## Bro

[hpx-users] Work stealing for components across localities

Hi, Hopefully this is a very easy question, but I was wondering whether hpx performs work stealing across localities for component actions. In other words, in a heterogeneous environment, can I create component instances uniformly and trust hpx to steal work from slower nodes once the faster n

[hpx-users] HPX - load balancing (work stealing) between localities

Hi, As I haven't yet been able to find anything about this, I'm wondering if someone here can help me to answer this question- Does HPX perform load balancing between different localities for actions? Given that I'm working in a heterogeneous environment, it would be much easier for me if I can se

Re: [hpx-users] Troubleshooting (lack of) parallel execution

2017 at 3:52 AM, Michael Levine wrote: > > > On Mon, May 1, 2017 at 7:28 PM, Hartmut Kaiser > wrote: > >> >> > GitHub link in my original email >> >> Sure, I saw that. This code is not really minimal, however... Could you >> try to reduce it

Re: [hpx-users] Troubleshooting (lack of) parallel execution

On Mon, May 1, 2017 at 7:28 PM, Hartmut Kaiser wrote: > > > GitHub link in my original email > > Sure, I saw that. This code is not really minimal, however... Could you > try to reduce it down to not more than a couple of dozen lines, please? > > Point is well taken. I've put up a different test

[hpx-users] Troubleshooting (lack of) parallel execution

Hi, I'm looking for some help in understanding why my code does not appear to be executing in parallel with the HPX system. I've first noticed the issue while working on my main codebase, in which I've been trying to implement a genetic-algorithm-based optimizer for non-linear systems. Since tha

Re: [hpx-users] Debug with HPX

Hi Uri, Just to briefly add to what Thomas and Hartmut mentioned- There is, indeed a command-line option to attach a debugger. Using it, however, isn't completely obvious. Based on some previous direction provided to me by Thomas, attaching a debugger (at least at startup) involves: - invoking

Re: [hpx-users] Serializing type-erased classes

Thanks for getting back to me so quickly. It's great that the boilerplate is able to make polymorphic serialization so straightforward and effortless. Likewise, thanks for the information about those macros. Having gone through the Boost.Serialization documentation numerous times, I had assumed t

Re: [hpx-users] Memory management in a distributed app

From: hpx-users-boun...@stellar.cct.lsu.edu [mailto:hpx-users- > boun...@stellar.cct.lsu.edu] On Behalf Of Thomas Heller > Sent: August-29-16 3:32 PM > To: hpx-users@stellar.cct.lsu.edu > Subject: Re: [hpx-users] Memory management in a distributed app > > On Montag, 29. August

Re: [hpx-users] Memory management in a distributed app

Hi Thomas, > -Original Message- > From: hpx-users-boun...@stellar.cct.lsu.edu [mailto:hpx-users- > boun...@stellar.cct.lsu.edu] On Behalf Of Thomas Heller > Sent: August-29-16 6:11 AM > To: hpx-users@stellar.cct.lsu.edu > Subject: Re: [hpx-users] Memory management in a distributed app > >

Re: [hpx-users] HPX futures and random number generators

Thomas, Thanks for the quick and helpful response. I just sent a response to Hartmut's answer -- I won't repeat the contents of that message here, but I would like to bring up a different point. > One possibility would be to create a thread local random number generator > as > suggested here: >

Re: [hpx-users] HPX futures and random number generators

Hi Hartmut, Thanks for the email and the tip regarding Boost's RNG. If I understand correctly, it still says that the engine itself is not thread-safe. In my mind, that makes sense since the engine does have state, and concurrent access/changes to this state from multiple threads could result in

[hpx-users] HPX futures and random number generators

I’m looking for some advice regarding creating an std::vector > > where the elements of the innermost vector use a random number generator. Typically, if I were to use to generate this vector of random integers, I’d use either boost or standard library random functions (or possibly Intel MKL /

[hpx-users] Looking for guidance / feedback on using HPX for parametric optimiztion with a genetic-type algorithm

Hi, I've been playing around a bit with HPX and am impressed. That said, I'm having a bit of trouble wrapping my head around this model of thinking and hoping someone can help to shed some light for me on. Firstly, I'd appreciate feedback on the general architecture / approach that I am looki

Re: [hpx-users] hpx 0.9.11 segmentation fault running on multiple localities

Quick update- > > This looks odd. It looks like a problem at startup when parsing the SLURM > environment. I never ran into that issue... This sounds like some strange > hickup between different allocators etc. Sometimes, cmake messes up the > installation. Could you please try the same out of a

Re: [hpx-users] hpx 0.9.11 segmentation fault running on multiple localities

Hi Thomas, Thanks for getting back to me. > > This looks odd. It looks like a problem at startup when parsing the > SLURM environment. I never ran into that issue... This sounds like some > strange hickup between different allocators etc. Sometimes, cmake messes > up the installation. Could you p

Re: [hpx-users] hpx 0.9.11 segmentation fault running on multiple localities

Thanks Hartmut, I've re-built using the master branch and it's significantly better than it had been before. I am able to successfully run jobs on multiple nodes and with multiple localities, although certain invocations still result in a segmentation fault. I haven't had too much time to full

[hpx-users] hpx 0.9.11 segmentation fault running on multiple localities

Hi, I've been experimenting with hpx for a hobby project, with a small virtualized cluster of 3 debian 8.2 machines running on esxi server. When I run any hpx code on a single locality, it appears to be working; however, whenever I try to use more than one locality, I invariably get a segmenta

[hpx-users] Component registration causing error C2491 on VS 2013

Hi, I've got a Windows-specific issue trying to build my code, and I'm not sure how to address this. Visual Studio 2013 fails to compile the code with the following error message: error C2491: 'hpx::traits::component_type_database ::get' : definition of dllimport function not allowed Vi