| Commit message (Collapse) | Author | Age |
|---|
| ... | |
| |
|
|
|
| |
These are compatible with the outputs of all the DIS stressmarks
as instumented with `extra.h`.
|
| |
|
|
| |
Also remove some unused code from the cleanupSemaphores utility
|
| |
|
|
| |
Now as used for (rejected) RTSS'20 paper
|
| |
|
|
|
|
|
|
|
|
|
| |
- All: Output times to stderr and nothing to stdout
- Field, Update, Pointer: change definition of a job to match other
stressmark execution times more closely
- Matrix: move all allocations into main()
- Update: Use volatile to prevent computations from being optimized out
- Transitive: Use volatile to prevent computations from being optimized out
- Neighborhood: Use working version of drawLineSegment from original DIS
sample code
|
| |
|
|
|
|
|
|
|
|
|
| |
- No parameter or output format changes
- Better error messages
- Auto-detect core
- Fix off-by-one error in job counting
- Explicitly invoke the scheduler with sched_yield() between jobs
so that there's less work to do when (if) the scheduling timer
interrupt comes around. (This has a surprisingly significant
impact on timings.)
|
| |
|
|
|
| |
Note that this repo does not attempt to keep a copy of the original
DIS benchmark distributions. UNC real-time has another repo for that.
|
| |
|
|
|
|
|
|
|
|
|
|
|
| |
Changes:
- Backpoint fix to randInt range
- Instrument benchmarks with time tracking
- assert inputs are correct length to fix compiler warnings
Problems:
- Timing on a per-loop basis is non representative of real-world
workloads, as we clear the cache after every loop. These all need
to be re-instrumented to record times for the whole benchmark,
rather than per-loop.
|
| | |
|
| |
|
|
|
|
| |
- Use malloc rather than static allocations
- Check that timings array is long enough before inserting each sample
- Include clearer error handling
|
| | |
|
| | |
|
| |
|
|
| |
Works for three-way WSS/cache size/execution time comparisons
|
| |
|
|
| |
A heavily rewritten version of mc2spin as written by Namhoon.
|
| | |
|
| |
|
|
|
|
|
| |
- Revert type change in Neighborhood microbenchmark
- Remove inputs modified to fix in the available memory on the
i.MX6DQ PRP test platform
- Change default configuration to build without LITMUS/MC^2/MMDC
|
| |
|
|
|
| |
***This is the final commit which supports reproducing his
PRP results***
|
| |
|
|
| |
Note that Neighborhood has been modified to use less space
|
| | |
|
| |
|
|
|
|
|
|
| |
- Remove unused parameters to extra.h
- Use floats to avoid integer overflow when timing long loops
- Only include litmus headers and/or MMDC headers if the appropriate
define is set in extra.h
- Update job parameters to match those used in my PRP experiments
|
| | |
|
| | |
|
| | |
|
| | |
|
| |
|
