Startseite Erkunden Hilfe
Anmelden
exa2pro
/
starpu-max
Beobachten 19
Favorit hinzufügen 0
Fork 0
Dateien Issues 0 Pull-Requests 0 Wiki
Struktur: 81110b93f4
Branches Tags

Commit Verlauf

Autor SHA1 Nachricht Datum
  Nathalie Furmento 461a05b22b update copyright holders vor 5 Jahren
  Nathalie Furmento f7abbfa6fc update copyright vor 7 Jahren
  Nathalie Furmento d053f9e7d6 sc_hypervisor: fix copyrights vor 8 Jahren
  Nathalie Furmento aae4029d83 INRIA is now called Inria vor 8 Jahren
  Samuel Thibault 5609817f86 fix format vor 8 Jahren
  Samuel Thibault 7b7f03c698 fix memleak vor 8 Jahren
  Nathalie Furmento 514a24fefe sc_hypervisor: fix cppcheck warnings vor 9 Jahren
  Nathalie Furmento 6cc8dcb563 fix bugs detected by coverity vor 9 Jahren
  Samuel Pitoiset bdae1fb9cb hypervisor: fix use of unused variables vor 10 Jahren
  Andra Hugo 39ccc67d88 add hypervisor strategy monitoring perf counter (not portable, the counter reading the flops dependent on the architecture) vor 10 Jahren
  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 vor 10 Jahren
  Andra Hugo 5f388d2a95 hierarchical contexts - bug fixing and DEBUG macro vor 11 Jahren
  Andra Hugo 491a6c6124 fix hierarchical resizing of contexts vor 12 Jahren
  Andra Hugo 60d44eb737 resize hierarchic ctxs hierarchically :) vor 12 Jahren
  Nathalie Furmento e97679a558 fxt: rename function starpu_trace_user_event() as starpu_fxt_trace_user_event() vor 12 Jahren
  Andra Hugo bfb858fe1d Add hierarchical contexts vor 12 Jahren
  Andra Hugo 20906d8d77 hyp only: optimise resize (use idle and speed for the triggering policy) vor 12 Jahren
  Andra Hugo 12dec4c5cc hypervisor optimisation (avoid unnecessary notifications/locks/trylocks) + add the hyp the traces vor 12 Jahren
  Andra Hugo 5a22d83b5c hypervisor: feft_lp: compute max by using the execution of the last sample instead of the idle time vor 12 Jahren
  Andra Hugo 1289532233 whenever there are a few resources the lp cannot assign, all contexts share these resources vor 12 Jahren
  Andra Hugo 9502f53f25 introduce min max as a constraint for the linear program vor 12 Jahren
  Andra Hugo 9f20f53ce9 fix size_ctxs (do not consider ready tasks for size, only for resize), speed is computed on fixed value of the time vor 12 Jahren
  Andra Hugo 339104ed55 for feft_lp distribute resources at each resize instead of moving idle workers from one ctx to another vor 12 Jahren
  Andra Hugo abebb0c602 cleaning ispeed_lp code + free hwloc_worker_set when deleting the context vor 12 Jahren
  Andra Hugo e66dd53eab cleaning + better managing the types of workers vor 12 Jahren
  Andra Hugo b0b9e3f308 small fix to resize ctxs when only cpus are available vor 12 Jahren
  Andra Hugo 054afc9556 allow calling the resizing linear programs from the appl vor 12 Jahren
  Andra Hugo 45c4f38b10 rename velocity -> speed vor 12 Jahren
  Andra Hugo 5fd5c871e6 too expensive the lock in copmpute_all_performance_prediction, exp_start is update in post_exec/pre_exec/etc also vor 12 Jahren
  Andra Hugo 8d8d2aa2f2 fix speed computation in the hypervisor vor 12 Jahren

Neuer Älter