Changeset 64dc36e for doc


Ignore:
Timestamp:
Jun 24, 2019, 5:00:47 PM (5 years ago)
Author:
Peter A. Buhr <pabuhr@…>
Branches:
ADT, arm-eh, ast-experimental, enum, forall-pointer-decay, jacob/cs343-translation, jenkins-sandbox, master, new-ast, new-ast-unique-expr, pthread-emulation, qualifiedEnum
Children:
28564382
Parents:
1335e6f
Message:

remove qthreads benchmark and correct citation name for public access to benchmarks

Location:
doc
Files:
2 edited

Legend:

Unmodified
Added
Removed
  • doc/bibliography/pl.bib

    r1335e6f r64dc36e  
    954954    key         = {Cforall Benchmarks},
    955955    author      = {{\textsf{C}{$\mathbf{\forall}$} Benchmarks}},
    956     howpublished= {\href{https://plg.uwaterloo.ca/~cforall/benchmarks}{https://\-plg.uwaterloo.ca/\-$\sim$cforall/\-benchmarks}},
     956    howpublished= {\href{https://plg.uwaterloo.ca/~cforall/benchmark.tar}{https://\-plg.uwaterloo.ca/\-$\sim$cforall/\-benchmark.tar}},
    957957}
    958958
  • doc/papers/concurrency/Paper.tex

    r1335e6f r64dc36e  
    316316Finally, performant user-threading implementations (both time and space) meet or exceed direct kernel-threading implementations, while achieving the programming advantages of high concurrency levels and safety.
    317317
    318 A further effort over the past two decades is the development of language memory models to deal with the conflict between language features and compiler/hardware optimizations, \ie, some language features are unsafe in the presence of aggressive sequential optimizations~\cite{Buhr95a,Boehm05}.
     318A further effort over the past two decades is the development of language memory models to deal with the conflict between language features and compiler/hardware optimizations, \ie some language features are unsafe in the presence of aggressive sequential optimizations~\cite{Buhr95a,Boehm05}.
    319319The consequence is that a language must provide sufficient tools to program around safety issues, as inline and library code is all sequential to the compiler.
    320 One solution is low-level qualifiers and functions (\eg, @volatile@ and atomics) allowing \emph{programmers} to explicitly write safe (race-free~\cite{Boehm12}) programs.
     320One solution is low-level qualifiers and functions (\eg @volatile@ and atomics) allowing \emph{programmers} to explicitly write safe (race-free~\cite{Boehm12}) programs.
    321321A safer solution is high-level language constructs so the \emph{compiler} knows the optimization boundaries, and hence, provides implicit safety.
    322322This problem is best known with respect to concurrency, but applies to other complex control-flow, like exceptions\footnote{
     
    324324The key feature that dovetails with this paper is nonlocal exceptions allowing exceptions to be raised across stacks, with synchronous exceptions raised among coroutines and asynchronous exceptions raised among threads, similar to that in \uC~\cite[\S~5]{uC++}
    325325} and coroutines.
    326 Finally, language solutions allow matching constructs with language paradigm, \ie, imperative and functional languages often have different presentations of the same concept to fit their programming model.
     326Finally, language solutions allow matching constructs with language paradigm, \ie imperative and functional languages often have different presentations of the same concept to fit their programming model.
    327327
    328328Finally, it is important for a language to provide safety over performance \emph{as the default}, allowing careful reduction of safety for performance when necessary.
    329 Two concurrency violations of this philosophy are \emph{spurious wakeup} (random wakeup~\cite[\S~8]{Buhr05a}) and \emph{barging} (signals-as-hints~\cite[\S~8]{Buhr05a}), where one is a consequence of the other, \ie, once there is spurious wakeup, signals-as-hints follow.
     329Two concurrency violations of this philosophy are \emph{spurious wakeup} (random wakeup~\cite[\S~8]{Buhr05a}) and \emph{barging} (signals-as-hints~\cite[\S~8]{Buhr05a}), where one is a consequence of the other, \ie once there is spurious wakeup, signals-as-hints follow.
    330330However, spurious wakeup is \emph{not} a foundational concurrency property~\cite[\S~8]{Buhr05a}, it is a performance design choice.
    331331Similarly, signals-as-hints are often a performance decision.
     
    337337Most augmented traditional (Fortran 18~\cite{Fortran18}, Cobol 14~\cite{Cobol14}, Ada 12~\cite{Ada12}, Java 11~\cite{Java11}) and new languages (Go~\cite{Go}, Rust~\cite{Rust}, and D~\cite{D}), except \CC, diverge from C with different syntax and semantics, only interoperate indirectly with C, and are not systems languages, for those with managed memory.
    338338As a result, there is a significant learning curve to move to these languages, and C legacy-code must be rewritten.
    339 While \CC, like \CFA, takes an evolutionary approach to extend C, \CC's constantly growing complex and interdependent features-set (\eg, objects, inheritance, templates, etc.) mean idiomatic \CC code is difficult to use from C, and C programmers must expend significant effort learning \CC.
     339While \CC, like \CFA, takes an evolutionary approach to extend C, \CC's constantly growing complex and interdependent features-set (\eg objects, inheritance, templates, etc.) mean idiomatic \CC code is difficult to use from C, and C programmers must expend significant effort learning \CC.
    340340Hence, rewriting and retraining costs for these languages, even \CC, are prohibitive for companies with a large C software-base.
    341341\CFA with its orthogonal feature-set, its high-performance runtime, and direct access to all existing C libraries circumvents these problems.
     
    367367\section{Stateful Function}
    368368
    369 The stateful function is an old idea~\cite{Conway63,Marlin80} that is new again~\cite{C++20Coroutine19}, where execution is temporarily suspended and later resumed, \eg, plugin, device driver, finite-state machine.
     369The stateful function is an old idea~\cite{Conway63,Marlin80} that is new again~\cite{C++20Coroutine19}, where execution is temporarily suspended and later resumed, \eg plugin, device driver, finite-state machine.
    370370Hence, a stateful function may not end when it returns to its caller, allowing it to be restarted with the data and execution location present at the point of suspension.
    371371This capability is accomplished by retaining a data/execution \emph{closure} between invocations.
    372 If the closure is fixed size, we call it a \emph{generator} (or \emph{stackless}), and its control flow is restricted, \eg, suspending outside the generator is prohibited.
    373 If the closure is variably sized, we call it a \emph{coroutine} (or \emph{stackful}), and as the names implies, often implemented with a separate stack with no programming restrictions.
     372If the closure is fixed size, we call it a \emph{generator} (or \emph{stackless}), and its control flow is restricted, \eg suspending outside the generator is prohibited.
     373If the closure is variable size, we call it a \emph{coroutine} (or \emph{stackful}), and as the names implies, often implemented with a separate stack with no programming restrictions.
    374374Hence, refactoring a stackless coroutine may require changing it to stackful.
    375 A foundational property of all \emph{stateful functions} is that resume/suspend \emph{do not} cause incremental stack growth, \ie, resume/suspend operations are remembered through the closure not the stack.
     375A foundational property of all \emph{stateful functions} is that resume/suspend \emph{do not} cause incremental stack growth, \ie resume/suspend operations are remembered through the closure not the stack.
    376376As well, activating a stateful function is \emph{asymmetric} or \emph{symmetric}, identified by resume/suspend (no cycles) and resume/resume (cycles).
    377377A fixed closure activated by modified call/return is faster than a variable closure activated by context switching.
    378 Additionally, any storage management for the closure (especially in unmanaged languages, \ie, no garbage collection) must also be factored into design and performance.
     378Additionally, any storage management for the closure (especially in unmanaged languages, \ie no garbage collection) must also be factored into design and performance.
    379379Therefore, selecting between stackless and stackful semantics is a tradeoff between programming requirements and performance, where stackless is faster and stackful is more general.
    380380Note, creation cost is amortized across usage, so activation cost is usually the dominant factor.
     
    648648\end{center}
    649649The example takes advantage of resuming a generator in the constructor to prime the loops so the first character sent for formatting appears inside the nested loops.
    650 The destructor provides a newline if formatted text ends with a full line.
     650The destructor provides a newline, if formatted text ends with a full line.
    651651Figure~\ref{f:CFormatSim} shows the C implementation of the \CFA input generator with one additional field and the computed @goto@.
    652652For contrast, Figure~\ref{f:PythonFormatter} shows the equivalent Python format generator with the same properties as the Fibonacci generator.
     
    27192719Each benchmark experiment is run 31 times.
    27202720All omitted tests for other languages are functionally identical to the \CFA tests and available online~\cite{CforallBenchMarks}.
    2721 
     2721% tar --exclude=.deps --exclude=Makefile --exclude=Makefile.in --exclude=c.c --exclude=cxx.cpp --exclude=fetch_add.c -cvhf benchmark.tar benchmark
    27222722
    27232723\paragraph{Object Creation}
     
    27492749\multicolumn{1}{@{}c}{} & \multicolumn{1}{c}{Median} & \multicolumn{1}{c}{Average} & \multicolumn{1}{c@{}}{Std Dev} \\
    27502750\CFA Coroutine Lazy             & 14.3          & 14.3          & 0.32          \\
    2751 \CFA Coroutine Eager    & 2203.7        & 2205.6        & 26.03         \\
     2751\CFA Coroutine Eager    & 522.8         & 525.3         & 5.81          \\
    27522752\CFA Thread                             & 1257.8        & 1291.2        & 86.19         \\
    27532753\uC Coroutine                   & 92.2          & 91.4          & 1.58          \\
Note: See TracChangeset for help on using the changeset viewer.