-
I would like to have an option that make HPX applications report the actual hwloc bindings used. This should use hwloc to read the bindings from the OS for each thread.
-
I've noticed that no matter how many cores are available on the CPU, this client seems to only use two per instance at full. Isn't Full supposed to use 100% of the CPU?
-
When having fewer threads than PUs, HPX assigns OS threads to PUs in order. If there are several PUs per core, and the number of threads equals the number of cores, then it is likely to be more effici…
-
When I start an HPX program on OS X, then it aborts during startup with the error message
block_matrix(27778) malloc: **\* error for object 0x7fff76a41570: pointer being freed was not allocated
I…
-
I have a simple benchmark that runs a home-grown DGEMM on a 2000^2 matrix in a single thread. I build HPX in the "Release" configuration, and add "-Ofast -march=native" on an Ubuntu x86-64 system. I u…
-
I want to extract the true layout of HPX threads on the cores. For this, I start one async operations per OS thread (hpx::get_os_thread_count), and then wait in these threads until all such threads ar…
-
My application intermixes S/DGEMM operations with bespoke functions. When using OpenBLAS w/OpenMP I find that some of my bespoke functions, with `for` loops annotated with `#pragma omp parallel for`,…
-
Define the affinity of parcel-pool, io-pool, and timer-pool threads. This should take into account the affinities used for the threads used to execute HPX threads. The main purpose is to avoid unneces…