Samuel Thibault b801a66994 port r 11483 from 1.1: Default to using only 90% of the available GPU memory, to avoid seeing cudaMemset run out of memory.. лет назад: 12
..
common 9bb7bdb07f Increment/decrement submitted/ready tasks per context (instead of doing it per context & globally) лет назад: 12
core c0cb3f849f port r 11459 from 1.1: Do not force calibration systematically when a history-based model is used. Let the scheduler trigger it when it actually needs an expected performance лет назад: 12
datawizard 5d3da08d0e src/datawizard/interfaces/matrix_interface.c: fix cast лет назад: 12
debug 7f56eab83f port r11326 from 1.1: fix typo лет назад: 12
drivers b801a66994 port r 11483 from 1.1: Default to using only 90% of the available GPU memory, to avoid seeing cudaMemset run out of memory.. лет назад: 12
profiling e2b943451f mic (perfmodel): merge trunk + finalize perfmodel лет назад: 12
sched_policies 4eb6989308 Do not let the prio scheduler decrement task stats several times when popping a task with multiple available implementations лет назад: 12
top dbc393bed8 src/top/starpu_top_connection.c: make sure WINVER is defined before including windows include files лет назад: 12
util 8f69d75bdd move implementation of starpu_task_list functions in public .h file лет назад: 12
worker_collection 3a7711af02 src: remove un-needed include pthread.h лет назад: 13
.gitignore 27eaf1ca36 Add `.gitignore'. лет назад: 15
Makefile.am 8f69d75bdd move implementation of starpu_task_list functions in public .h file лет назад: 12
dolib.c f5dee9ca79 Add effective version in dll path лет назад: 13
starpu_parameters.h e2b943451f mic (perfmodel): merge trunk + finalize perfmodel лет назад: 12