Changeset 836cf647 for doc/theses/thierry_delisle_PhD/thesis/text/conclusion.tex

Timestamp:

Sep 2, 2022, 11:29:51 AM (2 years ago)

Author:

Thierry Delisle <tdelisle@…>

Branches:

ADT, ast-experimental, master, pthread-emulation

Children:

e228f46

Parents:

0e3f80d

Message:

Fixed paragraph in conclusion

File:

• doc/theses/thierry_delisle_PhD/thesis/text/conclusion.tex (modified) (1 diff)

doc/theses/thierry_delisle_PhD/thesis/text/conclusion.tex

@@ -8 +8 @@
 I believed my Masters work would provide the background to make the Ph.D work reasonably straightforward.
 However, in doing so I discovered two expected challenges.
-First, while modern symmetric multiprocessing CPU have a significant penalties for communicating across cores, state-of-the-art work-stealing schedulers are very effective a avoid the need for communication in many common workloads.
-This leaves very little space for adding fairness guarantees without notable performance penalties.
+First, while modern symmetric multiprocessing CPU have significant performance penalties for communicating across cores.
+This makes implementing algorithm notably more difficult, since fairness generally requires \procs to be aware of each other's progress.
+This challenge is made even harder when comparing against MQMS schedulers (see Section\ref{sched}) which have very little inter-\proc communication.
+This is particularly true of state-of-the-art work-stealing schedulers, which can have virtually no inter-\proc communication in some common workloads.
+This means that when adding fairness to work-stealing schedulers, extreme care must be taken to hide the communication costs so performance does not suffer.
 Second, the kernel locking, threading, and I/O in the Linux operating system offers very little flexibility of use.
 There are multiple concurrency aspects in Linux that require carefully following a strict procedure in order to achieve acceptable performance.