| .. |
|
common
|
e1501b5592
port r11308 from 1.1: record allocation size in trace
|
12 years ago |
|
core
|
d9bfb2bacc
port r11334 from 1.1: Prefetching is now done for all schedulers when it can be done whatever the scheduling decision.
|
12 years ago |
|
datawizard
|
336612abd1
port r11320 from 1.1: Do not error out if the user didn't release memory allocated with starpu_malloc_on_node
|
12 years ago |
|
debug
|
7f56eab83f
port r11326 from 1.1: fix typo
|
12 years ago |
|
drivers
|
4bb3fc4b7b
port r11318 from 1.1: Simply use the root object total memory, like in the commented code
|
12 years ago |
|
profiling
|
e2b943451f
mic (perfmodel): merge trunk + finalize perfmodel
|
12 years ago |
|
sched_policies
|
84f45afab5
port r11322 from 1.1: fix prio scheduler termination
|
12 years ago |
|
top
|
dbc393bed8
src/top/starpu_top_connection.c: make sure WINVER is defined before including windows include files
|
12 years ago |
|
util
|
1b82b9cc99
starpu_insert_task had been renamed in starpu_task_insert and kept as
|
12 years ago |
|
worker_collection
|
3a7711af02
src: remove un-needed include pthread.h
|
13 years ago |
|
.gitignore
|
27eaf1ca36
Add `.gitignore'.
|
15 years ago |
|
Makefile.am
|
0e385974a9
port r11312 from 1.1: Small CUDA allocations (<= 4MiB) are now batched to avoid the huge cudaMalloc overhead.
|
12 years ago |
|
dolib.c
|
f5dee9ca79
Add effective version in dll path
|
13 years ago |
|
starpu_parameters.h
|
e2b943451f
mic (perfmodel): merge trunk + finalize perfmodel
|
12 years ago |
Samuel Thibault
d9bfb2bacc
port r11334 from 1.1: Prefetching is now done for all schedulers when it can be done whatever the scheduling decision.