| .. |
|
interfaces
|
b25760aa94
fix warnings
|
11 years ago |
|
coherency.c
|
afade57efa
allow ctx to execute parallel codes by reusing starpu workers (keep the workers alive instead of getting them to sleep) -> TODO try to factorize with parallel tasks on combined workers (doing practically the same, duplicate tasks and barrier_wait before & after exec)
|
11 years ago |
|
coherency.h
|
f43bf86292
Fix complexity of implicit task/data dependency, from quadratic to linear
|
11 years ago |
|
copy_driver.c
|
7240b27585
port r12759 from 1.1: Make sure we use the local stream, and not the stream of another device. Define separate streams for GPU-GPU transfers, depending on which device emits it
|
11 years ago |
|
copy_driver.h
|
03ef97c890
fix some bugs, debug in progress
|
12 years ago |
|
data_request.c
|
9218801246
Do not expose a known-to-be-racy-but-we-re-fine optimization to helgrind
|
11 years ago |
|
data_request.h
|
7ce4ced85d
Let the CUDA driver progress while the GPU is computing
|
12 years ago |
|
datastats.c
|
5f6f2bf55b
port r11529 from 1.1: Ignore data races on statistics
|
12 years ago |
|
datastats.h
|
b227dbcfdc
Use STARPU_ATTRIBUTE_* macros
|
12 years ago |
|
datawizard.c
|
7b91d914cd
Also push requests if some previous requests have terminated
|
11 years ago |
|
datawizard.h
|
38fbca49e9
Fix _starpu_datawizard_progress prototype: it does not actually return anything
|
12 years ago |
|
filters.c
|
f43bf86292
Fix complexity of implicit task/data dependency, from quadratic to linear
|
11 years ago |
|
filters.h
|
5f9a2f7e14
Turn _filter_nparts_compute_chunk_size_and_offset into _starpu_filter_nparts_compute_chunk_size_and_offset.
|
13 years ago |
|
footprint.c
|
940e31bb36
merge trunk
|
11 years ago |
|
footprint.h
|
e2b943451f
mic (perfmodel): merge trunk + finalize perfmodel
|
12 years ago |
|
malloc.c
|
c18275f016
src/datawizard/malloc.c: improve error message
|
11 years ago |
|
malloc.h
|
ddf6a00144
src/datawizard/malloc: define prototypes
|
12 years ago |
|
memalloc.c
|
c90cdf163a
Fix spurious data pointer registration when using scratch or redux buffers
|
11 years ago |
|
memalloc.h
|
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
|
12 years ago |
|
memory_manager.c
|
fbd1b911e7
New starpu_memory_get_total function to get the size of a memory node.
|
12 years ago |
|
memory_manager.h
|
03ef97c890
fix some bugs, debug in progress
|
12 years ago |
|
memory_nodes.c
|
b25760aa94
fix warnings
|
11 years ago |
|
memory_nodes.h
|
63a53f35d2
Also print memory node name in the reclaiming warning
|
11 years ago |
|
memstats.c
|
8f5264b152
data interface: no longer store data size in the handle as some interface may have variable size
|
13 years ago |
|
memstats.h
|
edc236df55
memory stats: group all functions in new file src/datawizard/memstats.c and rename them to follow pattern starpu_memory_...
|
13 years ago |
|
reduction.c
|
bbbf1610c4
Allocate dynamically an array used only while reducing data
|
11 years ago |
|
sort_data_handles.c
|
64e93e4cf2
Use a different structure for ordered buffers
|
12 years ago |
|
sort_data_handles.h
|
64e93e4cf2
Use a different structure for ordered buffers
|
12 years ago |
|
user_interactions.c
|
f43bf86292
Fix complexity of implicit task/data dependency, from quadratic to linear
|
11 years ago |
|
write_back.c
|
9783f21238
Fix of the livelock discovered by Marc Sergent's internship, by adding a maximum trylock threshold before a blocking lock
|
12 years ago |
|
write_back.h
|
c7321a76ff
fix type for node to always be unsigned (instead of uint32_t)
|
13 years ago |
Nathalie Furmento
4c43618b9b
merge trunk