Samuel Thibault
|
cef92ef39b
Catch bogus handling_node early
|
10 years ago |
Samuel Thibault
|
bef481b267
backport r16106 from 1.1: fix get_children_tasks test: setting a tag on a task won't prevent it from starting, one needs to set a dependency on another tag for that
|
10 years ago |
Samuel Thibault
|
f8d3a939b0
Make memory tidying less agressive, matching the numbers with memory reclaiming
|
10 years ago |
Samuel Thibault
|
105bef2aaa
revert 16092: the test is already performed above
|
10 years ago |
Nathalie Furmento
|
c537920e32
mpi/examples/user_datatype/my_interface.c: improve error message
|
10 years ago |
Nathalie Furmento
|
ed58fe6182
mpi/examples/user_datatype/user_datatype.c: call starpu_mpi_datatype_register before starpu_mpi_init to make sure mpi datatype is correctly registered before any communication occurs
|
10 years ago |
Nathalie Furmento
|
32d155333b
sc_hypervisor/examples/cholesky/cholesky_models.c: update for new API starpu_perfmodel_init
|
10 years ago |
Samuel Thibault
|
6ab978fd5d
revert 16092 and part of 16066 to be on the safe side: really wait for all existing requests, to avoid letting any through which would break coherency
|
10 years ago |
Samuel Thibault
|
8f29983c73
Check that a replicate is not busy before writing it back
|
10 years ago |
Samuel Thibault
|
c42090835b
fix using uninitialized key values
|
10 years ago |
Samuel Thibault
|
fdbdfd23f7
Drop spurious change
|
10 years ago |
Samuel Thibault
|
832ef25b5e
fix r16066: we still need to account for the self-hop requests, which we will wait for
|
10 years ago |
Nathalie Furmento
|
93d3ad04f1
src/core/perfmodel/perfmodel_history.c: only free when necessary
|
10 years ago |
Nathalie Furmento
|
fa4120aa82
followup to simplify perfmodel API
|
10 years ago |
Nathalie Furmento
|
fb18de4cba
simplify perfmodel API
|
10 years ago |
Samuel Thibault
|
522d4d97d3
Fix X ldflags order
|
10 years ago |
Samuel Thibault
|
8a36e89cd1
clearly separate task name from perfmodel name
|
10 years ago |
Samuel Thibault
|
44b157bee6
Do not set a task name by default, since task names override model name
|
10 years ago |
Samuel Thibault
|
c448586b85
revert 15931: these tasks already have a name through the performance model
|
10 years ago |
Samuel Thibault
|
d5a7eeec86
explicit what the modification is about
|
10 years ago |
Nathalie Furmento
|
050ef62f8a
tests/disk/mem_reclaim.c: even more verbose
|
10 years ago |
Nathalie Furmento
|
71dc2a5888
tests/disk/mem_reclaim.c: more verbose
|
10 years ago |
Samuel Thibault
|
99dc8831f2
Optimize write invalidation a bit: we don't need a self-hop request when data is already there and we will add a write invalidation request. Also, there is no need for an write invalidation request for waiting for a request whose target is the target of the write request
|
10 years ago |
Samuel Thibault
|
3e3823c78e
optimize requests a bit: only one trivial request is needed when data is already there, and no request is needed if it's also a prefetch request. Also make sure that we don't post the invalidation request
|
10 years ago |
Samuel Thibault
|
84d3418ba4
show handle requests
|
10 years ago |
Samuel Thibault
|
91fd2cfc15
Fix mem_reclaim: on write request, if some requests are pending (notably reclaiming), create an additional write request which will wait for them before invalidating all copies
|
10 years ago |
Samuel Thibault
|
2510a99377
Revert 16000, we will fix this another, better way
|
10 years ago |
Samuel Thibault
|
5ca875c059
Fix build with simgrid without declaration of smpi_process_set_user_data
|
10 years ago |
Samuel Thibault
|
c5d5da6ee7
Fix build with older versions of simgrid
|
10 years ago |
Samuel Thibault
|
7ed5469311
hwloc_obj_attr_snprintf is available since hwloc 1.0 actually
|
10 years ago |