Ignore:
File:
1 edited

Legend:

Unmodified
Added
Removed

  • doc/papers/concurrency/Paper.tex

    r016b1eb rfd2f4a9  
    224224{}
    225225\lstnewenvironment{C++}[1][]                            % use C++ style
    226 {\lstset{language=C++,moredelim=**[is][\protect\color{red}]{`}{`},#1}\lstset{#1}}
     226{\lstset{language=C++,moredelim=**[is][\protect\color{red}]{`}{`}}\lstset{#1}}
    227227{}
    228228\lstnewenvironment{uC++}[1][]
    229 {\lstset{language=uC++,moredelim=**[is][\protect\color{red}]{`}{`},#1}\lstset{#1}}
     229{\lstset{language=uC++,moredelim=**[is][\protect\color{red}]{`}{`}}\lstset{#1}}
    230230{}
    231231\lstnewenvironment{Go}[1][]
    232 {\lstset{language=Golang,moredelim=**[is][\protect\color{red}]{`}{`},#1}\lstset{#1}}
     232{\lstset{language=Golang,moredelim=**[is][\protect\color{red}]{`}{`}}\lstset{#1}}
    233233{}
    234234\lstnewenvironment{python}[1][]
    235 {\lstset{language=python,moredelim=**[is][\protect\color{red}]{`}{`},#1}\lstset{#1}}
     235{\lstset{language=python,moredelim=**[is][\protect\color{red}]{`}{`}}\lstset{#1}}
    236236{}
    237237\lstnewenvironment{java}[1][]
    238 {\lstset{language=java,moredelim=**[is][\protect\color{red}]{`}{`},#1}\lstset{#1}}
     238{\lstset{language=java,moredelim=**[is][\protect\color{red}]{`}{`}}\lstset{#1}}
    239239{}
    240240
    … …  
    284284
    285285\begin{document}
    286 \linenumbers                            % comment out to turn off line numbering
     286%\linenumbers                           % comment out to turn off line numbering
    287287
    288288\maketitle
    … …  
    450450\hline
    451451stateful                        & thread        & \multicolumn{1}{c|}{No} & \multicolumn{1}{c}{Yes} \\
    452 \hline   
    453 \hline   
     452\hline
     453\hline
    454454No                                      & No            & \textbf{1}\ \ \ @struct@                              & \textbf{2}\ \ \ @mutex@ @struct@              \\
    455 \hline   
     455\hline
    456456Yes (stackless)         & No            & \textbf{3}\ \ \ @generator@                   & \textbf{4}\ \ \ @mutex@ @generator@   \\
    457 \hline   
     457\hline
    458458Yes (stackful)          & No            & \textbf{5}\ \ \ @coroutine@                   & \textbf{6}\ \ \ @mutex@ @coroutine@   \\
    459 \hline   
     459\hline
    460460No                                      & Yes           & \textbf{7}\ \ \ {\color{red}rejected} & \textbf{8}\ \ \ {\color{red}rejected} \\
    461 \hline   
     461\hline
    462462Yes (stackless)         & Yes           & \textbf{9}\ \ \ {\color{red}rejected} & \textbf{10}\ \ \ {\color{red}rejected} \\
    463 \hline   
     463\hline
    464464Yes (stackful)          & Yes           & \textbf{11}\ \ \ @thread@                             & \textbf{12}\ \ @mutex@ @thread@               \\
    465465\end{tabular}
    … …  
    28962896\label{s:RuntimeStructureCluster}
    28972897
    2898 A \newterm{cluster} is a collection of user and kernel threads, where the kernel threads run the user threads from the cluster's ready queue, and the operating system runs the kernel threads on the processors from its ready queue.
     2898A \newterm{cluster} is a collection of user and kernel threads, where the kernel threads run the user threads from the cluster's ready queue, and the operating system runs the kernel threads on the processors from its ready queue~\cite{Buhr90a}.
    28992899The term \newterm{virtual processor} is introduced as a synonym for kernel thread to disambiguate between user and kernel thread.
    29002900From the language perspective, a virtual processor is an actual processor (core).
    … …  
    29922992\end{cfa}
    29932993where CPU time in nanoseconds is from the appropriate language clock.
    2994 Each benchmark is performed @N@ times, where @N@ is selected so the benchmark runs in the range of 2--20 seconds for the specific programming language.
     2994Each benchmark is performed @N@ times, where @N@ is selected so the benchmark runs in the range of 2--20 seconds for the specific programming language;
     2995each @N@ appears after the experiment name in the following tables.
    29952996The total time is divided by @N@ to obtain the average time for a benchmark.
    29962997Each benchmark experiment is run 13 times and the average appears in the table.
     2998For languages with a runtime JIT (Java, Node.js, Python), a single half-hour long experiment is run to check stability;
     2999all long-experiment results are statistically equivalent, \ie median/average/standard-deviation correlate with the short-experiment results, indicating the short experiments reached a steady state.
    29973000All omitted tests for other languages are functionally identical to the \CFA tests and available online~\cite{CforallConcurrentBenchmarks}.
    2998 % tar --exclude-ignore=exclude -cvhf benchmark.tar benchmark
    2999 % cp -p benchmark.tar /u/cforall/public_html/doc/concurrent_benchmark.tar
    30003001
    30013002\paragraph{Creation}
    … …  
    30063007
    30073008\begin{multicols}{2}
    3008 \lstset{language=CFA,moredelim=**[is][\color{red}]{@}{@},deletedelim=**[is][]{`}{`}}
    3009 \begin{cfa}
    3010 @coroutine@ MyCoroutine {};
     3009\begin{cfa}[xleftmargin=0pt]
     3010`coroutine` MyCoroutine {};
    30113011void ?{}( MyCoroutine & this ) {
    30123012#ifdef EAGER
    … …  
    30163016void main( MyCoroutine & ) {}
    30173017int main() {
    3018         BENCH( for ( N ) { @MyCoroutine c;@ } )
     3018        BENCH( for ( N ) { `MyCoroutine c;` } )
    30193019        sout | result;
    30203020}
    … …  
    30303030
    30313031\begin{tabular}[t]{@{}r*{3}{D{.}{.}{5.2}}@{}}
    3032 \multicolumn{1}{@{}c}{} & \multicolumn{1}{c}{Median} & \multicolumn{1}{c}{Average} & \multicolumn{1}{c@{}}{Std Dev} \\
    3033 \CFA generator                  & 0.6           & 0.6           & 0.0           \\
    3034 \CFA coroutine lazy             & 13.4          & 13.1          & 0.5           \\
    3035 \CFA coroutine eager    & 144.7         & 143.9         & 1.5           \\
    3036 \CFA thread                             & 466.4         & 468.0         & 11.3          \\
    3037 \uC coroutine                   & 155.6         & 155.7         & 1.7           \\
    3038 \uC thread                              & 523.4         & 523.9         & 7.7           \\
    3039 Python generator                & 123.2         & 124.3         & 4.1           \\
    3040 Node.js generator               & 33.4          & 33.5          & 0.3           \\
    3041 Goroutine thread                & 751.0         & 750.5         & 3.1           \\
    3042 Rust tokio thread               & 1860.0        & 1881.1        & 37.6          \\
    3043 Rust thread                             & 53801.0       & 53896.8       & 274.9         \\
    3044 Java thread                             & 120274.0      & 120722.9      & 2356.7        \\
    3045 Pthreads thread                 & 31465.5       & 31419.5       & 140.4
     3032\multicolumn{1}{@{}r}{N\hspace*{10pt}} & \multicolumn{1}{c}{Median} & \multicolumn{1}{c}{Average} & \multicolumn{1}{c@{}}{Std Dev} \\
     3033\CFA generator (1B)                     & 0.6           & 0.6           & 0.0           \\
     3034\CFA coroutine lazy     (100M)  & 13.4          & 13.1          & 0.5           \\
     3035\CFA coroutine eager (10M)      & 144.7         & 143.9         & 1.5           \\
     3036\CFA thread (10M)                       & 466.4         & 468.0         & 11.3          \\
     3037\uC coroutine (10M)                     & 155.6         & 155.7         & 1.7           \\
     3038\uC thread (10M)                        & 523.4         & 523.9         & 7.7           \\
     3039Python generator (10M)          & 123.2         & 124.3         & 4.1           \\
     3040Node.js generator (10M)         & 33.4          & 33.5          & 0.3           \\
     3041Goroutine thread (10M)          & 751.0         & 750.5         & 3.1           \\
     3042Rust tokio thread (10M)         & 1860.0        & 1881.1        & 37.6          \\
     3043Rust thread     (250K)                  & 53801.0       & 53896.8       & 274.9         \\
     3044Java thread (250K)                      & 119256.0      & 119679.2      & 2244.0        \\
     3045% Java thread (1 000 000)               & 123100.0      & 123052.5      & 751.6         \\
     3046Pthreads thread (250K)          & 31465.5       & 31419.5       & 140.4
    30463047\end{tabular}
    30473048\end{multicols}
    … …  
    30523053Internal scheduling is measured using a cycle of two threads signalling and waiting.
    30533054Figure~\ref{f:schedint} shows the code for \CFA, with results in Table~\ref{t:schedint}.
    3054 Note, the incremental cost of bulk acquire for \CFA, which is largely a fixed cost for small numbers of mutex objects.
    3055 Java scheduling is significantly greater because the benchmark explicitly creates multiple threads in order to prevent the JIT from making the program sequential, \ie removing all locking.
     3055Note, the \CFA incremental cost for bulk acquire is a fixed cost for small numbers of mutex objects.
     3056User-level threading has one kernel thread, eliminating contention between the threads (direct handoff of the kernel thread).
     3057Kernel-level threading has two kernel threads allowing some contention.
    30563058
    30573059\begin{multicols}{2}
    3058 \lstset{language=CFA,moredelim=**[is][\color{red}]{@}{@},deletedelim=**[is][]{`}{`}}
    3059 \begin{cfa}
     3060\setlength{\tabcolsep}{3pt}
     3061\begin{cfa}[xleftmargin=0pt]
    30603062volatile int go = 0;
    3061 @condition c;@
    3062 @monitor@ M {} m1/*, m2, m3, m4*/;
    3063 void call( M & @mutex p1/*, p2, p3, p4*/@ ) {
    3064         @signal( c );@
    3065 }
    3066 void wait( M & @mutex p1/*, p2, p3, p4*/@ ) {
     3063`condition c;`
     3064`monitor` M {} m1/*, m2, m3, m4*/;
     3065void call( M & `mutex p1/*, p2, p3, p4*/` ) {
     3066        `signal( c );`
     3067}
     3068void wait( M & `mutex p1/*, p2, p3, p4*/` ) {
    30673069        go = 1; // continue other thread
    3068         for ( N ) { @wait( c );@ } );
     3070        for ( N ) { `wait( c );` } );
    30693071}
    30703072thread T {};
    … …  
    30913093
    30923094\begin{tabular}{@{}r*{3}{D{.}{.}{5.2}}@{}}
    3093 \multicolumn{1}{@{}c}{} & \multicolumn{1}{c}{Median} & \multicolumn{1}{c}{Average} & \multicolumn{1}{c@{}}{Std Dev} \\
    3094 \CFA @signal@, 1 monitor        & 364.4         & 364.2         & 4.4           \\
    3095 \CFA @signal@, 2 monitor        & 484.4         & 483.9         & 8.8           \\
    3096 \CFA @signal@, 4 monitor        & 709.1         & 707.7         & 15.0          \\
    3097 \uC @signal@ monitor            & 328.3         & 327.4         & 2.4           \\
    3098 Rust cond. variable                     & 7514.0        & 7437.4        & 397.2         \\
    3099 Java @notify@ monitor           & 9623.0        & 9654.6        & 236.2         \\
    3100 Pthreads cond. variable         & 5553.7        & 5576.1        & 345.6
     3095\multicolumn{1}{@{}r}{N\hspace*{10pt}} & \multicolumn{1}{c}{Median} & \multicolumn{1}{c}{Average} & \multicolumn{1}{c@{}}{Std Dev} \\
     3096\CFA @signal@, 1 monitor (10M)  & 364.4         & 364.2         & 4.4           \\
     3097\CFA @signal@, 2 monitor (10M)  & 484.4         & 483.9         & 8.8           \\
     3098\CFA @signal@, 4 monitor (10M)  & 709.1         & 707.7         & 15.0          \\
     3099\uC @signal@ monitor (10M)              & 328.3         & 327.4         & 2.4           \\
     3100Rust cond. variable     (1M)            & 7514.0        & 7437.4        & 397.2         \\
     3101Java @notify@ monitor (1M)              & 8717.0        & 8774.1        & 471.8         \\
     3102% Java @notify@ monitor (100 000 000)           & 8634.0        & 8683.5        & 330.5         \\
     3103Pthreads cond. variable (1M)    & 5553.7        & 5576.1        & 345.6
    31013104\end{tabular}
    31023105\end{multicols}
    … …  
    31073110External scheduling is measured using a cycle of two threads calling and accepting the call using the @waitfor@ statement.
    31083111Figure~\ref{f:schedext} shows the code for \CFA with results in Table~\ref{t:schedext}.
    3109 Note, the incremental cost of bulk acquire for \CFA, which is largely a fixed cost for small numbers of mutex objects.
     3112Note, the \CFA incremental cost for bulk acquire is a fixed cost for small numbers of mutex objects.
    31103113
    31113114\begin{multicols}{2}
    3112 \lstset{language=CFA,moredelim=**[is][\color{red}]{@}{@},deletedelim=**[is][]{`}{`}}
     3115\setlength{\tabcolsep}{5pt}
    31133116\vspace*{-16pt}
    3114 \begin{cfa}
    3115 @monitor@ M {} m1/*, m2, m3, m4*/;
    3116 void call( M & @mutex p1/*, p2, p3, p4*/@ ) {}
    3117 void wait( M & @mutex p1/*, p2, p3, p4*/@ ) {
    3118         for ( N ) { @waitfor( call : p1/*, p2, p3, p4*/ );@ }
     3117\begin{cfa}[xleftmargin=0pt]
     3118`monitor` M {} m1/*, m2, m3, m4*/;
     3119void call( M & `mutex p1/*, p2, p3, p4*/` ) {}
     3120void wait( M & `mutex p1/*, p2, p3, p4*/` ) {
     3121        for ( N ) { `waitfor( call : p1/*, p2, p3, p4*/ );` }
    31193122}
    31203123thread T {};
    … …  
    31333136\columnbreak
    31343137
    3135 \vspace*{-16pt}
     3138\vspace*{-18pt}
    31363139\captionof{table}{External-scheduling comparison (nanoseconds)}
    31373140\label{t:schedext}
    31383141\begin{tabular}{@{}r*{3}{D{.}{.}{3.2}}@{}}
    3139 \multicolumn{1}{@{}c}{} & \multicolumn{1}{c}{Median} &\multicolumn{1}{c}{Average} & \multicolumn{1}{c@{}}{Std Dev} \\
    3140 \CFA @waitfor@, 1 monitor       & 367.1 & 365.3 & 5.0   \\
    3141 \CFA @waitfor@, 2 monitor       & 463.0 & 464.6 & 7.1   \\
    3142 \CFA @waitfor@, 4 monitor       & 689.6 & 696.2 & 21.5  \\
    3143 \uC \lstinline[language=uC++]|_Accept| monitor  & 328.2 & 329.1 & 3.4   \\
    3144 Go \lstinline[language=Golang]|select| channel  & 365.0 & 365.5 & 1.2
     3142\multicolumn{1}{@{}r}{N\hspace*{10pt}} & \multicolumn{1}{c}{Median} &\multicolumn{1}{c}{Average} & \multicolumn{1}{c@{}}{Std Dev} \\
     3143\CFA @waitfor@, 1 monitor (10M) & 367.1 & 365.3 & 5.0   \\
     3144\CFA @waitfor@, 2 monitor (10M) & 463.0 & 464.6 & 7.1   \\
     3145\CFA @waitfor@, 4 monitor (10M) & 689.6 & 696.2 & 21.5  \\
     3146\uC \lstinline[language=uC++]|_Accept| monitor (10M)    & 328.2 & 329.1 & 3.4   \\
     3147Go \lstinline[language=Golang]|select| channel (10M)    & 365.0 & 365.5 & 1.2
    31453148\end{tabular}
    31463149\end{multicols}
    … …  
    31553158
    31563159\begin{multicols}{2}
    3157 \lstset{language=CFA,moredelim=**[is][\color{red}]{@}{@},deletedelim=**[is][]{`}{`}}
    3158 \begin{cfa}
    3159 @monitor@ M {} m1/*, m2, m3, m4*/;
    3160 call( M & @mutex p1/*, p2, p3, p4*/@ ) {}
     3160\setlength{\tabcolsep}{3pt}
     3161\begin{cfa}[xleftmargin=0pt]
     3162`monitor` M {} m1/*, m2, m3, m4*/;
     3163call( M & `mutex p1/*, p2, p3, p4*/` ) {}
    31613164int main() {
    31623165        BENCH( for( N ) call( m1/*, m2, m3, m4*/ ); )
    … …  
    31733176\label{t:mutex}
    31743177\begin{tabular}{@{}r*{3}{D{.}{.}{3.2}}@{}}
    3175 \multicolumn{1}{@{}c}{} & \multicolumn{1}{c}{Median} &\multicolumn{1}{c}{Average} & \multicolumn{1}{c@{}}{Std Dev} \\
    3176 test-and-test-set lock                  & 19.1  & 18.9  & 0.4   \\
    3177 \CFA @mutex@ function, 1 arg.   & 48.3  & 47.8  & 0.9   \\
    3178 \CFA @mutex@ function, 2 arg.   & 86.7  & 87.6  & 1.9   \\
    3179 \CFA @mutex@ function, 4 arg.   & 173.4 & 169.4 & 5.9   \\
    3180 \uC @monitor@ member rtn.               & 54.8  & 54.8  & 0.1   \\
    3181 Goroutine mutex lock                    & 34.0  & 34.0  & 0.0   \\
    3182 Rust mutex lock                                 & 33.0  & 33.2  & 0.8   \\
    3183 Java synchronized method                & 31.0  & 31.0  & 0.0   \\
    3184 Pthreads mutex Lock                             & 31.0  & 31.1  & 0.4
     3178\multicolumn{1}{@{}r}{N\hspace*{10pt}} & \multicolumn{1}{c}{Median} &\multicolumn{1}{c}{Average} & \multicolumn{1}{c@{}}{Std Dev} \\
     3179test-and-test-set lock (50M)            & 19.1  & 18.9  & 0.4   \\
     3180\CFA @mutex@ function, 1 arg. (50M)     & 48.3  & 47.8  & 0.9   \\
     3181\CFA @mutex@ function, 2 arg. (50M)     & 86.7  & 87.6  & 1.9   \\
     3182\CFA @mutex@ function, 4 arg. (50M)     & 173.4 & 169.4 & 5.9   \\
     3183\uC @monitor@ member rtn. (50M)         & 54.8  & 54.8  & 0.1   \\
     3184Goroutine mutex lock (50M)                      & 34.0  & 34.0  & 0.0   \\
     3185Rust mutex lock (50M)                           & 33.0  & 33.2  & 0.8   \\
     3186Java synchronized method (50M)          & 31.0  & 30.9  & 0.5   \\
     3187% Java synchronized method (10 000 000 000)             & 31.0 & 30.2 & 0.9 \\
     3188Pthreads mutex Lock (50M)                       & 31.0  & 31.1  & 0.4
    31853189\end{tabular}
    31863190\end{multicols}
    … …  
    32013205% To: "Peter A. Buhr" <pabuhr@plg2.cs.uwaterloo.ca>
    32023206% Date: Fri, 24 Jan 2020 13:49:18 -0500
    3203 % 
     3207%
    32043208% I can also verify that the previous version, which just tied a bunch of promises together, *does not* go back to the
    32053209% event loop at all in the current version of Node. Presumably they're taking advantage of the fact that the ordering of
    … …  
    32113215
    32123216\begin{multicols}{2}
    3213 \lstset{language=CFA,moredelim=**[is][\color{red}]{@}{@},deletedelim=**[is][]{`}{`}}
    3214 \begin{cfa}[aboveskip=0pt,belowskip=0pt]
    3215 @coroutine@ C {};
    3216 void main( C & ) { for () { @suspend;@ } }
     3217\begin{cfa}[xleftmargin=0pt]
     3218`coroutine` C {};
     3219void main( C & ) { for () { `suspend;` } }
    32173220int main() { // coroutine test
    32183221        C c;
    3219         BENCH( for ( N ) { @resume( c );@ } )
     3222        BENCH( for ( N ) { `resume( c );` } )
    32203223        sout | result;
    32213224}
    32223225int main() { // thread test
    3223         BENCH( for ( N ) { @yield();@ } )
     3226        BENCH( for ( N ) { `yield();` } )
    32243227        sout | result;
    32253228}
    … …  
    32343237\label{t:ctx-switch}
    32353238\begin{tabular}{@{}r*{3}{D{.}{.}{3.2}}@{}}
    3236 \multicolumn{1}{@{}c}{} & \multicolumn{1}{c}{Median} &\multicolumn{1}{c}{Average} & \multicolumn{1}{c@{}}{Std Dev} \\
    3237 C function                      & 1.8           & 1.8           & 0.0   \\
    3238 \CFA generator          & 1.8           & 2.0           & 0.3   \\
    3239 \CFA coroutine          & 32.5          & 32.9          & 0.8   \\
    3240 \CFA thread                     & 93.8          & 93.6          & 2.2   \\
    3241 \uC coroutine           & 50.3          & 50.3          & 0.2   \\
    3242 \uC thread                      & 97.3          & 97.4          & 1.0   \\
    3243 Python generator        & 40.9          & 41.3          & 1.5   \\
    3244 Node.js await           & 1852.2        & 1854.7        & 16.4  \\
    3245 Node.js generator       & 33.3          & 33.4          & 0.3   \\
    3246 Goroutine thread        & 143.0         & 143.3         & 1.1   \\
    3247 Rust async await        & 32.0          & 32.0          & 0.0   \\
    3248 Rust tokio thread       & 143.0         & 143.0         & 1.7   \\
    3249 Rust thread                     & 332.0         & 331.4         & 2.4   \\
    3250 Java thread                     & 405.0         & 415.0         & 17.6  \\
    3251 Pthreads thread         & 334.3         & 335.2         & 3.9
     3239\multicolumn{1}{@{}r}{N\hspace*{10pt}} & \multicolumn{1}{c}{Median} &\multicolumn{1}{c}{Average} & \multicolumn{1}{c@{}}{Std Dev} \\
     3240C function (10B)                        & 1.8           & 1.8           & 0.0   \\
     3241\CFA generator (5B)                     & 1.8           & 2.0           & 0.3   \\
     3242\CFA coroutine (100M)           & 32.5          & 32.9          & 0.8   \\
     3243\CFA thread (100M)                      & 93.8          & 93.6          & 2.2   \\
     3244\uC coroutine (100M)            & 50.3          & 50.3          & 0.2   \\
     3245\uC thread (100M)                       & 97.3          & 97.4          & 1.0   \\
     3246Python generator (100M)         & 40.9          & 41.3          & 1.5   \\
     3247Node.js await (5M)                      & 1852.2        & 1854.7        & 16.4  \\
     3248Node.js generator (100M)        & 33.3          & 33.4          & 0.3   \\
     3249Goroutine thread (100M)         & 143.0         & 143.3         & 1.1   \\
     3250Rust async await (100M)         & 32.0          & 32.0          & 0.0   \\
     3251Rust tokio thread (100M)        & 143.0         & 143.0         & 1.7   \\
     3252Rust thread (25M)                       & 332.0         & 331.4         & 2.4   \\
     3253Java thread (100M)                      & 405.0         & 415.0         & 17.6  \\
     3254% Java thread (  100 000 000)                   & 413.0 & 414.2 & 6.2 \\
     3255% Java thread (5 000 000 000)                   & 415.0 & 415.2 & 6.1 \\
     3256Pthreads thread (25M)           & 334.3         & 335.2         & 3.9
    32523257\end{tabular}
    32533258\end{multicols}
    … …  
    32583263Languages using 1:1 threading based on pthreads can at best meet or exceed, due to language overhead, the pthread results.
    32593264Note, pthreads has a fast zero-contention mutex lock checked in user space.
    3260 Languages with M:N threading have better performance than 1:1 because there is no operating-system interactions.
     3265Languages with M:N threading have better performance than 1:1 because there is no operating-system interactions (context-switching or locking).
     3266As well, for locking experiments, M:N threading has less contention if only one kernel thread is used.
    32613267Languages with stackful coroutines have higher cost than stackless coroutines because of stack allocation and context switching;
    32623268however, stackful \uC and \CFA coroutines have approximately the same performance as stackless Python and Node.js generators.
    32633269The \CFA stackless generator is approximately 25 times faster for suspend/resume and 200 times faster for creation than stackless Python and Node.js generators.
     3270The Node.js context-switch is costly when asynchronous await must enter the event engine because a promise is not fulfilled.
     3271Finally, the benchmark results correlate across programming languages with and without JIT, indicating the JIT has completed any runtime optimizations.
    32643272
    32653273
    … …  
    33193327
    33203328The authors recognize the design assistance of Aaron Moss, Rob Schluntz, Andrew Beach, and Michael Brooks; David Dice for commenting and helping with the Java benchmarks; and Gregor Richards for helping with the Node.js benchmarks.
    3321 This research is funded by a grant from Waterloo-Huawei (\url{http://www.huawei.com}) Joint Innovation Lab. %, and Peter Buhr is partially funded by the Natural Sciences and Engineering Research Council of Canada.
     3329This research is funded by the NSERC/Waterloo-Huawei (\url{http://www.huawei.com}) Joint Innovation Lab. %, and Peter Buhr is partially funded by the Natural Sciences and Engineering Research Council of Canada.
    33223330
    33233331{%
Note: See TracChangeset for help on using the changeset viewer.