| Commit message (Collapse) | Author | Age | |
|---|---|---|---|
| * | Final GPUSync implementation.wip-gpu-rtss12 | Glenn Elliott | 2012-05-14 |
| | | |||
| * | fix minor bugs. there is still a bug in GEDF PAI. | Glenn Elliott | 2012-04-27 |
| | | |||
| * | No-op useless unlock calls. | Glenn Elliott | 2012-04-26 |
| | | |||
| * | Fix/test C-EDF for GPU RTSS12. | Glenn Elliott | 2012-04-25 |
| | | |||
| * | Port rtss12 features to C-EDF (untested) | Glenn Elliott | 2012-04-25 |
| | | |||
| * | Match replica before spinlocks in ikglp_unlock() | Glenn Elliott | 2012-04-23 |
| | | |||
| * | Fix line-endings. :P | Glenn Elliott | 2012-04-23 |
| | | |||
| * | Tested/Fixed IKGLP heurs. OS WORK FINALLY DONE! | Glenn Elliott | 2012-04-23 |
| | | |||
| * | Donees cannot be amongst the top-m requests. | Glenn Elliott | 2012-04-23 |
| | | |||
| * | Donor dequeue heuristic for IKGLP. Untested. | Glenn Elliott | 2012-04-20 |
| | | |||
| * | Untested donee selection heuristic for IKGLP. | Glenn Elliott | 2012-04-20 |
| | | |||
| * | Added hooks for IKGLP affinity and a little logic. | Glenn Elliott | 2012-04-18 |
| | | | | | | | | | | | | | simple IKGLP is already done. it does: 1) auto gpu de/registration. 2) distruption amongst simultanous users across queues 3) calls default IKGLP routines when appropriate. Remaining work: 1) FQ advisement. 2) Donor stealing advisement. 3) Donee selection advisement. | ||
| * | Zap line-endings | Glenn Elliott | 2012-04-18 |
| | | |||
| * | Added support for simult-users in kfmlp | Glenn Elliott | 2012-04-18 |
| | | |||
| * | Fixed and tested aff-aware KFMLP. (finally!) | Glenn Elliott | 2012-04-18 |
| | | |||
| * | make gpu registration a little more robust | Glenn Elliott | 2012-04-16 |
| | | |||
| * | Implement GPU-affinity-aware kfmlp (untested) | Glenn Elliott | 2012-04-16 |
| | | |||
| * | Infrastructure for affinity-aware k-exclusion | Glenn Elliott | 2012-04-15 |
| | | |||
| * | PAI::change_prio(): check work before locking | Glenn Elliott | 2012-04-15 |
| | | |||
| * | Update PAI to support multiGPUs (todo: klitirqd) | Glenn Elliott | 2012-04-15 |
| | | |||
| * | remove fifo/rm header files left over | Glenn Elliott | 2012-04-15 |
| | | |||
| * | add kfmlp as separate file | Glenn Elliott | 2012-04-15 |
| | | |||
| * | Merge branch 'wip-gpu-interrupts' into wip-gpu-rtss12 | Glenn Elliott | 2012-04-15 |
| |\ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Conflicts: include/litmus/fdso.h include/litmus/rt_param.h include/litmus/sched_plugin.h include/litmus/unistd_32.h include/litmus/unistd_64.h litmus/Makefile litmus/edf_common.c litmus/litmus.c litmus/locking.c litmus/sched_gsn_edf.c litmus/sched_plugin.c | ||
| | * | Remove option for threading of all softirqs.wip-gpu-interrupts | Glenn Elliott | 2012-03-05 |
| | | | |||
| | * | Clean up PAI. | Glenn Elliott | 2012-03-04 |
| | | | |||
| | * | Merge branch 'wip-pai' into wip-gpu-interrupts | Glenn Elliott | 2012-03-04 |
| | |\ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Conflicts: include/litmus/affinity.h kernel/sched.c kernel/softirq.c litmus/Kconfig litmus/affinity.c litmus/litmus.c litmus/preempt.c litmus/sched_cedf.c litmus/sched_gsn_edf.c | ||
| | | * | Some cleanup of PAIwip-pai | Glenn Elliott | 2012-03-04 |
| | | | | |||
| | | * | Fix bugs in tracing and PAI handling | Glenn Elliott | 2012-01-20 |
| | | | | |||
| | | * | Port PAI interrupts to GSN-EDF, C-RM/RM-SRT/FIFO. | Glenn Elliott | 2012-01-14 |
| | | | | |||
| | | * | Completed PAI for C-EDF. | Glenn Elliott | 2012-01-14 |
| | | | | |||
| | | * | PAI implementation, C-RM, C-FIFO. | Glenn Elliott | 2012-01-11 |
| | | | | |||
| | | * | Full patch for klitirqd with Nvidia GPU support. | Glenn Elliott | 2011-06-02 |
| | | | | |||
| * | | | Move RSM and IKGLP imp. to own .c fileswip-ikglp | Glenn Elliott | 2012-04-13 |
| | | | | | | | | | | | | | | | | Also reformated code to be slightly more standard coding practice compliant. | ||
| * | | | Added support for Dynamic Group Locks (DGLs) | Glenn Elliott | 2012-04-11 |
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Added support for Dynamic Group Locks. Locks are FIFO ordered (no timestamps), so a big DGL lock is needed to enqueue for resources atomically. Unfortunatly, this requires nested inheritance to use coarse-grain locking. Coarse-grain locking is used when DGLs are enabled. Fine-grain locking is used when DGLs are disabled. TODO: Clean up IKGLP implementatio. There is a lot of needless debug/TRACE work. | ||
| * | | | Fix IKGLP bugs discovered in test. | Glenn Elliott | 2012-04-09 |
| | | | | | | | | | | | | | | | | Apply fixes to the IKGLP. Also, break binheap.h into binheap.h/.c | ||
| * | | | Cleanup use of binheap_entry(). | Glenn Elliott | 2012-04-04 |
| | | | | | | | | | | | | | The entry is already casted by the macro. | ||
| * | | | Untested implementation of IKGLP. | Glenn Elliott | 2012-04-04 |
| | | | | | | | | | | | | | | | | I don't like coding so much w/o testing, but it's sort of hard to do without both lock() and unlock(). | ||
| * | | | Infrastructure of IKGLP. lock/unlock are stubs | Glenn Elliott | 2012-03-31 |
| | | | | |||
| * | | | Nested inheritance with fine-grained locking. | Glenn Elliott | 2012-03-30 |
| | | | | | | | | | | | | | | | | | | | Minor hack to lockdep was required too allow the inheritance propagation locking logic to work. | ||
| * | | | Merge branch 'wip-binary-heap' into wip-nested-locks | Glenn Elliott | 2012-03-23 |
| |\ \ \ | |||
| | * | | | Make C-EDF work with simplified binheap_deletewip-binary-heap | Glenn Elliott | 2012-03-21 |
| | | | | | |||
| | * | | | Make GSN-EDF work with simlified binheap_delete() | Glenn Elliott | 2012-03-21 |
| | | | | | |||
| | * | | | Simplify binheap_delete and add binheap_decrease | Glenn Elliott | 2012-03-21 |
| | | | | | |||
| | * | | | C-EDF: Use binary heap instead of binomial heap. | Glenn Elliott | 2012-03-21 |
| | | | | | | | | | | | | | | | | | Use binary heap for ordering priority of CPUs. | ||
| | * | | | GSN-EDF: Use binary heap instead of binomial heap. | Glenn Elliott | 2012-03-21 |
| | | | | | | | | | | | | | | | | | Use binary heap to track CPU priorities. | ||
| | * | | | Binary heap implementation | Glenn Elliott | 2012-03-21 |
| | |/ / | | | | | | | | | | | | | | | | | | | Motivation: Linux's prio_heap.h is of fixed size. Litmus's binomial heap may be overkill (and perhaps not general enough) for some applications. Implemented in the style of linked lists. | ||
| * | | | blah | Glenn Elliott | 2012-03-23 |
| | | | | |||
| * | | | Introduction of basic nesting foundations. | Glenn Elliott | 2012-03-22 |
| |/ / | |||
| * | | Typo in macro | Jonathan Herman | 2012-02-16 |
| | | | |||
| * | | Feather-Trace: keep track of interrupt-related interference.2012.1 | Bjoern B. Brandenburg | 2012-01-30 |
| | | | | | | | | | | | | | | | Increment a processor-local counter whenever an interrupt is handled. This allows Feather-Trace to include a (truncated) counter and a flag to report interference from interrupts. This could be used to filter samples that were disturbed by interrupts. | ||
 |
index : litmus-rt.git | |
| The LITMUS^RT kernel. | Bjoern Brandenburg |
| aboutsummaryrefslogtreecommitdiffstats |