Chameleon issueshttps://gitlab.inria.fr/solverstack/chameleon/-/issues2020-01-10T16:03:52+01:00https://gitlab.inria.fr/solverstack/chameleon/-/issues/87Default number of threads is 1 in new testing2020-01-10T16:03:52+01:00Philippe SWARTVAGHERDefault number of threads is 1 in new testingWhen running `mpirun -n 2 -nodelist jack0,jack1 -DSTARPU_FXT_TRACE=1 -DSTARPU_FXT_PREFIX=$(pwd)/ ~/chameleon/build/new-testing/snew-testing -o potrf -H`, I get the following output:
```
# jack0: WARNING- InfinibandVerbs: device = mlx4_0;...When running `mpirun -n 2 -nodelist jack0,jack1 -DSTARPU_FXT_TRACE=1 -DSTARPU_FXT_PREFIX=$(pwd)/ ~/chameleon/build/new-testing/snew-testing -o potrf -H`, I get the following output:
```
# jack0: WARNING- InfinibandVerbs: device = mlx4_0; port 2 is not active.
# jack1: WARNING- InfinibandVerbs: device = mlx4_0; port 2 is not active.
[starpu][starpu_initialize] Warning: StarPU was configured with --with-fxt, which slows down a bit, limits scalability and makes worker initialization sequential
[starpu][starpu_initialize] Warning: StarPU was configured with --with-fxt, which slows down a bit, limits scalability and makes worker initialization sequential
# pioman: WARNING- Ignoring call to piom_ltask_set_bound_thread_indexes as PIOM_DEDICATED_WAIT=0.
Id Function threads gpus P Q nb uplo n lda seedA time gflops
# pioman: WARNING- Ignoring call to piom_ltask_set_bound_thread_indexes as PIOM_DEDICATED_WAIT=0.
0 spotrf 1 0 1 2 320 Upper 1000 1000 1804289383 1.952684e-02 1.709614e+01
Connection to jack1 closed.
```
The default number of used threads is 1. In previous timing binaries, it was by default the number of workers allowed by StarPU. If I precise `-t [x]`, the provided number of threads is well used.
Is it a bug ?Chameleon 1.0.0Mathieu FavergeMathieu Favergehttps://gitlab.inria.fr/solverstack/chameleon/-/issues/67Update doc in chameleon.h2019-03-01T00:50:22+01:00Mathieu FavergeUpdate doc in chameleon.hUpdate documentation of Init/InitPar/Finalize after integration of !108Update documentation of Init/InitPar/Finalize after integration of !108Chameleon 1.0.0Mathieu FavergeMathieu Favergehttps://gitlab.inria.fr/solverstack/chameleon/-/issues/41Put a comment on the bound/peak options2017-07-07T18:32:21+02:00Mathieu FavergePut a comment on the bound/peak optionsThe following discussion from !53 should be addressed:
- [ ] @faverge started a [discussion](https://gitlab.inria.fr/solverstack/chameleon/merge_requests/53#note_35024): (+1 comment)
> @stanisic, I just want to replace those 4 tod...The following discussion from !53 should be addressed:
- [ ] @faverge started a [discussion](https://gitlab.inria.fr/solverstack/chameleon/merge_requests/53#note_35024): (+1 comment)
> @stanisic, I just want to replace those 4 todos, and eventually say they are available only for Cholesky and StarPU here too.Chameleon 1.0.0https://gitlab.inria.fr/solverstack/chameleon/-/issues/33Diagonal copy support2017-07-04T11:22:53+02:00Mathieu FavergeDiagonal copy supportAll data descriptor for temporary copies of the diagonal to release dependencies on lower/upper parts should be moved to the driver level to avoid synchronization steps when possible. This is already done in the new HQR kernels but shoul...All data descriptor for temporary copies of the diagonal to release dependencies on lower/upper parts should be moved to the driver level to avoid synchronization steps when possible. This is already done in the new HQR kernels but should be done in:
* [x] pzgelqf.c
* [x] pzgelqfrh.c
* [x] pzgeqrf.c
* [x] pzgeqrfrh.c
* [x] pzhetrd_he2hb.c
* [x] pztpgqrt.c
* [x] pzunglq.c
* [x] pzunglqrh.c
* [x] pzungqr.c
* [x] pzungqrrh.c
* [x] pzunmlq.c
* [x] pzunmlqrh.c
* [x] pzunmqr.c
* [x] pzunmqrrh.cChameleon 1.0.0BOUCHERIE RaphaelBOUCHERIE Raphaelhttps://gitlab.inria.fr/solverstack/chameleon/-/issues/32Fix library dependencies2017-09-20T15:57:25+02:00Mathieu FavergeFix library dependenciesDependencies toward ther libraries should be handle through target_link_libraries, and not through a wide list of libraries in testing, timings, examples, ...Dependencies toward ther libraries should be handle through target_link_libraries, and not through a wide list of libraries in testing, timings, examples, ...Chameleon 1.0.0https://gitlab.inria.fr/solverstack/chameleon/-/issues/16Default number of threads does not count cores2017-06-26T20:08:39+02:00THIBAULT Samuelsamuel.thibault@inria.frDefault number of threads does not count coresWhen running on a hyperthreaded system, chameleon's timing examples uses by default as many threads as logical CPUs, not cores, resulting in overloading which is detrimental to performance.
This is due to timing.c's get_thread_count() w...When running on a hyperthreaded system, chameleon's timing examples uses by default as many threads as logical CPUs, not cores, resulting in overloading which is detrimental to performance.
This is due to timing.c's get_thread_count() which just calls sysconf().
Is there a reason for not just letting the runtime automatically detect what it prefers? (and if a runtime can not detect itself, the corresponding runtime/ directory could use get_thread_count())Chameleon 1.0.0Mathieu FavergeMathieu Faverge