Changeset 14e1053 for doc/theses/colby_parsons_MMAth/text/actors.tex
- Timestamp:
- Jun 27, 2023, 4:45:40 PM (12 months ago)
- Branches:
- master
- Children:
- a1f0cb6
- Parents:
- 917e1fd
- File:
-
- 1 edited
Legend:
- Unmodified
- Added
- Removed
-
doc/theses/colby_parsons_MMAth/text/actors.tex
r917e1fd r14e1053 5 5 % ====================================================================== 6 6 7 % C_TODO: add citations throughout chapter8 7 Actors are an indirect concurrent feature that abstracts threading away from a programmer, and instead provides \gls{actor}s and messages as building blocks for concurrency, where message passing means there is no shared data to protect, making actors amenable in a distributed environment. 9 8 Actors are another message passing concurrency feature, similar to channels but with more abstraction, and are in the realm of \gls{impl_concurrency}, where programmers write concurrent code without dealing with explicit thread creation or interaction. … … 423 422 Push operations are amortized $O(1)$ since pushes may cause doubling reallocations of the underlying dynamic-sized array (like \CC @vector@). 424 423 425 % C_TODO: maybe make copy_queue diagram426 427 424 Since the copy queue is an array, envelopes are allocated first on the stack and then copied into the copy queue to persist until they are no longer needed. 428 425 For many workload, the copy queues grow in size to facilitate the average number of messages in flight and there is no further dynamic allocations. … … 834 831 In another example, if the average gulp size is very high, it could indicate that the executor could use more queue sharding. 835 832 836 % C_TODO cite poison pill messages and add languages837 833 Another productivity feature that is included is a group of poison-pill messages. 838 Poison-pill messages are common across actor systems, including Akka and ProtoActor \cite{}.834 Poison-pill messages are common across actor systems, and are used in actor libraries Akka and ProtoActor~\cite{Akka,ProtoActor}. 839 835 Poison-pill messages inform an actor to terminate. 840 836 In \CFA, due to the allocation of actors and lack of garbage collection, there needs to be a suite of poison-pills. … … 881 877 & \multicolumn{1}{c|}{\CFA (100M)} & \multicolumn{1}{c|}{CAF (10M)} & \multicolumn{1}{c|}{Akka (100M)} & \multicolumn{1}{c|}{\uC (100M)} & \multicolumn{1}{c@{}}{ProtoActor (100M)} \\ 882 878 \hline 883 AMD & \input{data/ pykeSendStatic} \\879 AMD & \input{data/nasusSendStatic} \\ 884 880 \hline 885 Intel & \input{data/ nasusSendStatic}881 Intel & \input{data/pykeSendStatic} 886 882 \end{tabular} 887 883 … … 894 890 & \multicolumn{1}{c|}{\CFA (20M)} & \multicolumn{1}{c|}{CAF (2M)} & \multicolumn{1}{c|}{Akka (2M)} & \multicolumn{1}{c|}{\uC (20M)} & \multicolumn{1}{c@{}}{ProtoActor (2M)} \\ 895 891 \hline 896 AMD & \input{data/ pykeSendDynamic} \\892 AMD & \input{data/nasusSendDynamic} \\ 897 893 \hline 898 Intel & \input{data/ nasusSendDynamic}894 Intel & \input{data/pykeSendDynamic} 899 895 \end{tabular} 900 896 \end{table} … … 916 912 The results from the static/dynamic send benchmarks are shown in Figures~\ref{t:StaticActorMessagePerformance} and \ref{t:DynamicActorMessagePerformance} respectively. 917 913 \CFA leads the charts in both benchmarks, largely due to the copy queue removing the majority of the envelope allocations. 914 Additionally, the receive of all messages sent in \CFA is statically known and is determined via a function pointer cast, which incurrs a compile-time cost. 915 All the other systems use their virtual system to find the correct behaviour at message send. 916 This requires two virtual dispatch operations, which is an additional runtime send cost that \CFA does not have. 917 Note that Akka also statically checks message sends, but still uses their virtual system at runtime. 918 918 In the static send benchmark all systems except CAF have static send costs that are in the same ballpark, only varying by ~70ns. 919 919 In the dynamic send benchmark all systems experience slower message sends, as expected due to the extra allocations. … … 1084 1084 1085 1085 Figure~\ref{t:ExecutorMemory} shows the high memory watermark of the actor systems when running the executor benchmark on 48 cores. 1086 \CFA has a high watermark relative to the other non-garbage 1086 \CFA has a high watermark relative to the other non-garbage-collected systems \uC, and CAF. 1087 1087 This is a result of the copy queue data structure, as it will over-allocate storage and not clean up eagerly, whereas the per envelope allocations will always allocate exactly the amount of storage needed. 1088 Despite having a higher watermark, the \CFA memory usage remains comparable to other non-garbage-collected systems. 1088 1089 1089 1090 \subsection{Matrix Multiply}
Note: See TracChangeset
for help on using the changeset viewer.