Samuel Thibault
|
e8a62c8fce
move spurious variable initialization
|
hace 11 años |
Samuel Thibault
|
c60d91cb3f
Enable asynchronous OpenCL wherever possible
|
hace 11 años |
Samuel Thibault
|
840af37490
push pending requests at the back of the list of pending requests, not the front
|
hace 11 años |
Samuel Thibault
|
058e113825
port r12533 from 1.1: Do not let non-CUDA workers use non-0 streams, CUDA seems not very threadsafe with that. Make the coherency engine avoid selecting non-CUDA workers to issue transfers, to avoid letting them use the 0 stream.
|
hace 11 años |
Samuel Thibault
|
9e7c9936ce
Use STARPU_MAIN_RAM where appropriate
|
hace 11 años |
Samuel Thibault
|
9aa1c5ba6c
Use STARPU_MAIN_RAM where appropriate
|
hace 11 años |
Samuel Thibault
|
2bafbc890a
fix build
|
hace 11 años |
Samuel Thibault
|
92d443d920
Make documentation clearer
|
hace 11 años |
Samuel Thibault
|
ea5d8f596b
Make a copy of the interface to the memchunk only when the latter gets detached from the data, and thus the interface code will not work on it. Drop the copy when the memchunk gets reattached. This allows interfaces to modify pointers in the interface in unpack, notably
|
hace 11 años |
Samuel Thibault
|
fb03301fdf
port r12523 from 1.1: Fix detaching a memchunk from a handle: the memchunk is not supposed to still have a pointer to the replicate
|
hace 11 años |
Samuel Thibault
|
1aad553cc2
Fix crash with perfmodels having type common
|
hace 11 años |
Andra Hugo
|
aed609a645
rollback r12518: don't allow unregister in callback or task codelets
|
hace 11 años |
Andra Hugo
|
84e77b5ad7
add prolog callbacks to mpi
|
hace 11 años |
Andra Hugo
|
a78e7bdc6a
allow unregisters in callbacks and codelets when we have only CPUs
|
hace 11 años |
Andra Hugo
|
2938dd4805
patch Terry: add a new prologue callback (one executed at pop time)
|
hace 11 años |
Andra Hugo
|
e991168dec
rollback book_workers
|
hace 11 años |
Samuel Thibault
|
5c4a168e72
Do not destroy containers before using them
|
hace 11 años |
Samuel Thibault
|
5a9ffce947
backport r12506: fix disabling out-of-order for data transfers
|
hace 12 años |
Samuel Thibault
|
bf8aa6338d
Let the OpenCL driver progress while the GPU is computing
|
hace 12 años |
Samuel Thibault
|
7d2bf0c630
Enable asynchronous CUDA kernels wherever possible
|
hace 12 años |
Samuel Thibault
|
7ce4ced85d
Let the CUDA driver progress while the GPU is computing
|
hace 12 años |
Samuel Thibault
|
42925b7f8e
Do not define _XOPEN_SOURCE, as it disables GNU extensions, which users don't expect
|
hace 12 años |
Olivier Aumage
|
40432cdc2c
- first word after \section is the section name
|
hace 12 años |
Samuel Thibault
|
163ef6b095
Make statistics only on the part of the trace between start_profiling and stop_profiling
|
hace 12 años |
Andra Hugo
|
aa59ce38c7
rollback
|
hace 12 años |
Andra Hugo
|
1c2f50cec5
fix exec_parallel code when called by the app thread
|
hace 12 años |
Andra Hugo
|
0c40ac6f8a
make the hypervisor point to the good includes
|
hace 12 años |
Andra Hugo
|
044a3e8e31
enable lots of cpus on mic native
|
hace 12 años |
Nathalie Furmento
|
48b95f97ee
doc/doxygen/Makefile.am: add chapters/paje_draw_histogram.pdf to EXTRA_DIST
|
hace 12 años |
Samuel Thibault
|
e1e5feddca
Pass stability option to sort tool, not grep :)
|
hace 12 años |