 Nathalie Furmento
|
d053f9e7d6
sc_hypervisor: fix copyrights
|
8 years ago |
|
Nathalie Furmento
|
aae4029d83
INRIA is now called Inria
|
8 years ago |
 Samuel Thibault
|
84e795a1db
fix memleaks
|
8 years ago |
|
Nathalie Furmento
|
6cc8dcb563
fix bugs detected by coverity
|
9 years ago |
 Samuel Pitoiset
|
bdae1fb9cb
hypervisor: fix use of unused variables
|
9 years ago |
|
Samuel Thibault
|
20b88ccf11
Fix callers of starpu_perfmodel_history_based_expected_perf
|
10 years ago |
 Andra Hugo
|
ba3e4d7403
small fixes done while writing my thesis + task window at context level (before pushing tasks to the scheduler) expressed w.r.t. to time and not number of tasks
|
10 years ago |
|
Nathalie Furmento
|
cc9aecb792
merge trunk
|
11 years ago |
|
Samuel Thibault
|
717fbf7ab1
Always call init_iterator, it does not make sense otherwise
|
11 years ago |
|
Andra Hugo
|
5593439277
changing perf_model structure: arch now contains several devices, so we can have for eg one device STARPU_CPU with 2 cores one device STARPU_CUDA_WORKER with 1 core
|
11 years ago |
|
Andra Hugo
|
5f388d2a95
hierarchical contexts - bug fixing and DEBUG macro
|
11 years ago |
|
Andra Hugo
|
491a6c6124
fix hierarchical resizing of contexts
|
11 years ago |
|
Andra Hugo
|
60d44eb737
resize hierarchic ctxs hierarchically :)
|
11 years ago |
|
Andra Hugo
|
2769aaa8cb
hypervisor: correct computation of idle
|
12 years ago |
|
Andra Hugo
|
20906d8d77
hyp only: optimise resize (use idle and speed for the triggering policy)
|
12 years ago |
|
Andra Hugo
|
52459c8508
*eager: wake up workers when we add them to a context
|
12 years ago |
|
Nathalie Furmento
|
483f8e2979
merge trunk
|
12 years ago |
|
Andra Hugo
|
9502f53f25
introduce min max as a constraint for the linear program
|
12 years ago |
 Thibaud Lambert
|
310ac0249e
mic (perfmodel): cholesky correction
|
12 years ago |
|
Andra Hugo
|
9d2ba463c5
remove some warnings
|
12 years ago |
|
Samuel Thibault
|
9c038ac2be
replace starpu_get_bandwidth/latency_CUDA/RAM_RAM/CUDA with calls to starpu_transfer_*
|
12 years ago |
|
Andra Hugo
|
e66dd53eab
cleaning + better managing the types of workers
|
12 years ago |
|
Andra Hugo
|
c94402dfb1
move include math.h in the header principal
|
12 years ago |
|
Andra Hugo
|
45c4f38b10
rename velocity -> speed
|
12 years ago |
|
Andra Hugo
|
99654988a8
consider the time to transfer data from the gpus to the RAM too when resizing
|
12 years ago |
|
Andra Hugo
|
70ee761ed3
correct speed computations for the hyp
|
12 years ago |
|
Andra Hugo
|
6c954c729c
workers must release the scheduling mutex before taking the role of hypervisor, update triggering issues for the other resizing strategies too
|
12 years ago |
|
Andra Hugo
|
db0267f452
fixes for the speed computations
|
12 years ago |
|
Andra Hugo
|
8d8d2aa2f2
fix speed computation in the hypervisor
|
12 years ago |
|
Andra Hugo
|
76282f234b
fixes for triggering the resize
|
12 years ago |
