| Thu, 08 May 2014 09:49:27 +0100 |
Chris Cannam |
Timings for last change
|
| Thu, 08 May 2014 09:47:18 +0100 |
Chris Cannam |
Include in sum only the notes actually in range for an instrument (the other templates should be all zeros anyway)
|
| Thu, 08 May 2014 09:34:22 +0100 |
Chris Cannam |
More notes
|
| Wed, 07 May 2014 20:49:33 +0100 |
Chris Cannam |
Subrepo state
|
| Wed, 07 May 2014 11:55:32 +0100 |
Chris Cannam |
Merge from branch bqvec-openmp
|
| Wed, 07 May 2014 11:51:31 +0100 |
Chris Cannam |
bqvec as subrepo
bqvec-openmp
|
| Wed, 07 May 2014 11:18:30 +0100 |
Chris Cannam |
Comments
bqvec-openmp
|
| Wed, 07 May 2014 11:07:50 +0100 |
Chris Cannam |
Report on last change
bqvec-openmp
|
| Wed, 07 May 2014 11:06:18 +0100 |
Chris Cannam |
Simplify omp loop, leaving more to the omp scheduler
bqvec-openmp
|
| Wed, 07 May 2014 10:48:58 +0100 |
Chris Cannam |
Backed out changeset dfb6e5ce3eb1 -- it was arithmetically quite wrong!
bqvec-openmp
|
| Wed, 07 May 2014 10:44:18 +0100 |
Chris Cannam |
Simplify normalisation
bqvec-openmp
|
| Wed, 07 May 2014 10:44:11 +0100 |
Chris Cannam |
More results
bqvec-openmp
|
| Wed, 07 May 2014 10:38:21 +0100 |
Chris Cannam |
Eliminate a loop
bqvec-openmp
|
| Wed, 07 May 2014 10:00:39 +0100 |
Chris Cannam |
Copy reports to this branch. The other head here is a dead-end.
bqvec-openmp
|
| Wed, 07 May 2014 09:59:20 +0100 |
Chris Cannam |
Another timing report
bqvec-openmp
|
| Wed, 07 May 2014 09:57:19 +0100 |
Chris Cannam |
Reorder the calculations to match the series of vector operations in the most recent bqvec code, just in case it's the order of vector calculations that is saving the time rather than the avoidance of std::vector
timing
|
| Wed, 07 May 2014 09:48:56 +0100 |
Chris Cannam |
Report on last couple of tests
bqvec-openmp
|
| Wed, 07 May 2014 09:43:15 +0100 |
Chris Cannam |
Pull out shifted templates into separate arrays with proper alignment (trading off memory occupied against getting the alignments right)
bqvec-openmp
|
| Wed, 07 May 2014 09:08:52 +0100 |
Chris Cannam |
Simplify slightly, make HQ mode the default
bqvec-openmp
|
| Wed, 07 May 2014 09:01:32 +0100 |
Chris Cannam |
Merge from default branch
bqvec-openmp
|
| Wed, 07 May 2014 08:55:44 +0100 |
Chris Cannam |
Fixed order of with_gain function in bqvec, updating correspondingly
bqvec-openmp
|
| Tue, 06 May 2014 18:55:11 +0100 |
Chris Cannam |
Add draft/intensive mode setting (determines whether to use shifts)
|
| Tue, 06 May 2014 18:28:34 +0100 |
Chris Cannam |
Subrepo state
|
| Tue, 06 May 2014 16:50:25 +0100 |
Chris Cannam |
Bring all branch test reports into default
|
| Tue, 06 May 2014 16:38:39 +0100 |
Chris Cannam |
Report on latest
bqvec-openmp
|
| Tue, 06 May 2014 16:36:46 +0100 |
Chris Cannam |
Merge OpenMP and bqvec stuff into bqvec-openmp branch
bqvec-openmp
|
| Tue, 06 May 2014 16:31:32 +0100 |
Chris Cannam |
Report on results
openmp
|
| Tue, 06 May 2014 16:28:04 +0100 |
Chris Cannam |
OpenMP support in main EM iteration
openmp
|
| Tue, 06 May 2014 16:05:05 +0100 |
Chris Cannam |
Update results, tidy a bit
bqvec
|
| Tue, 06 May 2014 15:12:45 +0100 |
Chris Cannam |
Ooh, that's a trappy one
bqvec
|
| Tue, 06 May 2014 15:09:16 +0100 |
Chris Cannam |
Some results and a question...
bqvec
|
| Tue, 06 May 2014 14:57:09 +0100 |
Chris Cannam |
Cut allocations with temporary storage ready to swap in
bqvec
|
| Tue, 06 May 2014 14:53:11 +0100 |
Chris Cannam |
Use a couple more bqvec calls
bqvec
|
| Tue, 06 May 2014 14:46:46 +0100 |
Chris Cannam |
Report on single-precision performance
timing
|
| Tue, 06 May 2014 14:45:16 +0100 |
Chris Cannam |
Use single-precision floats throughout EM code
timing
|
| Tue, 06 May 2014 14:38:43 +0100 |
Chris Cannam |
Report result
bqvec
|
| Tue, 06 May 2014 14:37:42 +0100 |
Chris Cannam |
Fix silly bug
bqvec
|
| Tue, 06 May 2014 14:29:07 +0100 |
Chris Cannam |
Vectorise some calculations
bqvec
|
| Tue, 06 May 2014 14:20:36 +0100 |
Chris Cannam |
Results from that change
bqvec
|
| Tue, 06 May 2014 14:19:19 +0100 |
Chris Cannam |
Complete using bqvec for allocation etc, but with unchanged processing logic
bqvec
|
| Tue, 06 May 2014 13:49:52 +0100 |
Chris Cannam |
First bit of bqvec adaptation
bqvec
|
| Tue, 06 May 2014 13:05:43 +0100 |
Chris Cannam |
Another result
timing
|
| Tue, 06 May 2014 12:56:18 +0100 |
Chris Cannam |
Initialise new vectors with epsilon instead of copying and then overwriting
timing
|
| Tue, 06 May 2014 12:49:49 +0100 |
Chris Cannam |
Store templates as doubles instead of floats
timing
|
| Tue, 06 May 2014 12:45:09 +0100 |
Chris Cannam |
Report
timing
|
| Tue, 06 May 2014 12:43:59 +0100 |
Chris Cannam |
Reorder internal loops
timing
|
| Tue, 06 May 2014 12:39:19 +0100 |
Chris Cannam |
Merge loops
timing
|
| Tue, 06 May 2014 12:39:12 +0100 |
Chris Cannam |
More results
timing
|
| Tue, 06 May 2014 11:53:02 +0100 |
Chris Cannam |
Hoist variables, add consts
timing
|
| Tue, 06 May 2014 11:31:14 +0100 |
Chris Cannam |
Update results
|
| Tue, 06 May 2014 11:31:04 +0100 |
Chris Cannam |
Further timing test results
timing
|
| Tue, 06 May 2014 11:26:33 +0100 |
Chris Cannam |
Timing outputs
timing
|
| Tue, 06 May 2014 11:23:07 +0100 |
Chris Cannam |
Halve number of iterations
timing
|
| Tue, 06 May 2014 11:22:17 +0100 |
Chris Cannam |
Timing results
|
| Tue, 06 May 2014 11:21:28 +0100 |
Chris Cannam |
Some testing results
timing
|
| Tue, 06 May 2014 11:17:08 +0100 |
Chris Cannam |
Remove debug printouts
timing
|
| Tue, 06 May 2014 11:13:25 +0100 |
Chris Cannam |
Remove FCQ return as well
timing
|
| Tue, 06 May 2014 11:10:52 +0100 |
Chris Cannam |
Remove return of CQ output features
timing
|
| Tue, 06 May 2014 11:09:07 +0100 |
Chris Cannam |
Add initial timing outputs
|
| Tue, 06 May 2014 10:59:04 +0100 |
Chris Cannam |
Add timing test script
|
