Add further notes on our findings on preformance issues.

PERFORMANCE.md

@@ -3,6 +3,10 @@
 #### Commit 52fcb51f - Add basic random stealing
 #### Commit 52fcb51f - Add basic random stealing
 
 
 Slight improvement, needs further measurement after removing more important bottlenecks.
 Slight improvement, needs further measurement after removing more important bottlenecks.
+Below are three individual measurements of the difference.
+Overall the trend (sum of all numbers/last number),
+go down (98.7%, 96.9% and 100.6%), but with the one measurement
+above 100% we think the improvements are minor.
 
 
 | | | | | | | | | | |
 | | | | | | | | | | |
 | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
 | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
@@ -27,3 +31,35 @@ change  |     98.96  %|    100.93  %|     96.13  %|    104.21  %|    103.86  %|
 Big improvements of about 6% in our test. This seems like a little,
 Big improvements of about 6% in our test. This seems like a little,
 but 6% from the scheduler is a lot, as the 'main work' is the tasks
 but 6% from the scheduler is a lot, as the 'main work' is the tasks
 itself, not the scheduler.
 itself, not the scheduler.
+
+This change unsurprisingly yields the biggest improvement yet.
+
+#### Commit b9bb90a4  - Try to figure out the 'high thread bottleneck'
+
+We are currently seeing good performance on low core counts
+(up to 1/2 of the machines cores), but after that performance
+plumishes:
+
+Bana-Pi Best-Case:
+
+<img src="./media/b9bb90a4-banana-pi-best-case.png" width="400"/>
+
+Bana-Pi Average-Case:
+
+<img src="./media/b9bb90a4-banana-pi-average-case.png" width="400"/>
+
+Laptop Best-Case:
+
+<img src="./media/b9bb90a4-laptop-best-case.png" width="400"/>
+
+Laptop Average-Case:
+
+<img src="./media/b9bb90a4-laptop-average-case.png" width="400"/>
+
+
+As we can see, in average the performance of PLS starts getting
+way worse than TBB and EMBB after 4 cores. We suspect this is due
+to contemption, but could not resolve it with any combination
+of `tas_spinlock` vs `ttas_spinlock` and `lock` vs `try_lock`.
+
+This issue clearly needs further investigation.

README.md

@@ -8,6 +8,10 @@
 This section will give a brief introduction on how to get a minimal
 This section will give a brief introduction on how to get a minimal
 project setup that uses the PLS library.
 project setup that uses the PLS library.
 
 
+Further notes on [performance](PERFORMANCE.md) and general
+[notes](NOTES.md) on the development progress can be found in
+the linked documents.
+
 ### Installation
 ### Installation
 
 
 Clone the repository and open a terminal session in its folder.
 Clone the repository and open a terminal session in its folder.