.\" Automatically generated by Pod::Man 4.14 (Pod::Simple 3.43) .\" .\" Standard preamble: .\" ======================================================================== .de Sp \" Vertical space (when we can't use .PP) .if t .sp .5v .if n .sp .. .de Vb \" Begin verbatim text .ft CW .nf .ne \\$1 .. .de Ve \" End verbatim text .ft R .fi .. .\" Set up some character translations and predefined strings. \*(-- will .\" give an unbreakable dash, \*(PI will give pi, \*(L" will give a left .\" double quote, and \*(R" will give a right double quote. \*(C+ will .\" give a nicer C++. Capital omega is used to do unbreakable dashes and .\" therefore won't be available. \*(C` and \*(C' expand to `' in nroff, .\" nothing in troff, for use with C<>. .tr \(*W- .ds C+ C\v'-.1v'\h'-1p'\s-2+\h'-1p'+\s0\v'.1v'\h'-1p' .ie n \{\ . ds -- \(*W- . ds PI pi . if (\n(.H=4u)&(1m=24u) .ds -- \(*W\h'-12u'\(*W\h'-12u'-\" diablo 10 pitch . if (\n(.H=4u)&(1m=20u) .ds -- \(*W\h'-12u'\(*W\h'-8u'-\" diablo 12 pitch . ds L" "" . ds R" "" . ds C` "" . ds C' "" 'br\} .el\{\ . ds -- \|\(em\| . ds PI \(*p . ds L" `` . ds R" '' . ds C` . ds C' 'br\} .\" .\" Escape single quotes in literal strings from groff's Unicode transform. .ie \n(.g .ds Aq \(aq .el .ds Aq ' .\" .\" If the F register is >0, we'll generate index entries on stderr for .\" titles (.TH), headers (.SH), subsections (.SS), items (.Ip), and index .\" entries marked with X<> in POD. Of course, you'll have to process the .\" output yourself in some meaningful fashion. .\" .\" Avoid warning from groff about undefined register 'F'. .de IX .. .nr rF 0 .if \n(.g .if rF .nr rF 1 .if (\n(rF:(\n(.g==0)) \{\ . if \nF \{\ . de IX . tm Index:\\$1\t\\n%\t"\\$2" .. . if !\nF==2 \{\ . nr % 0 . nr F 2 . \} . \} .\} .rr rF .\" ======================================================================== .\" .IX Title "MCE::Flow 3pm" .TH MCE::Flow 3pm "2023-09-29" "perl v5.36.0" "User Contributed Perl Documentation" .\" For nroff, turn off justification. Always turn off hyphenation; it makes .\" way too many mistakes in technical documents. .if n .ad l .nh .SH "NAME" MCE::Flow \- Parallel flow model for building creative applications .SH "VERSION" .IX Header "VERSION" This document describes MCE::Flow version 1.889 .SH "DESCRIPTION" .IX Header "DESCRIPTION" MCE::Flow is great for writing custom apps to maximize on all available cores. This module was created to help one harness user_tasks within \s-1MCE.\s0 .PP It is trivial to parallelize with mce_stream shown below. .PP .Vb 2 \& ## Native map function \& my @a = map { $_ * 4 } map { $_ * 3 } map { $_ * 2 } 1..10000; \& \& ## Same as with MCE::Stream (processing from right to left) \& @a = mce_stream \& sub { $_ * 4 }, sub { $_ * 3 }, sub { $_ * 2 }, 1..10000; \& \& ## Pass an array reference to have writes occur simultaneously \& mce_stream \e@a, \& sub { $_ * 4 }, sub { $_ * 3 }, sub { $_ * 2 }, 1..10000; .Ve .PP However, let's have MCE::Flow compute the same in parallel. MCE::Queue will be used for data flow among the sub-tasks. .PP .Vb 2 \& use MCE::Flow; \& use MCE::Queue; .Ve .PP This calls for preserving output order. .PP .Vb 3 \& sub preserve_order { \& my %tmp; my $order_id = 1; my $gather_ref = $_[0]; \& @{ $gather_ref } = (); ## clear the array (optional) \& \& return sub { \& my ($data_ref, $chunk_id) = @_; \& $tmp{$chunk_id} = $data_ref; \& \& while (1) { \& last unless exists $tmp{$order_id}; \& push @{ $gather_ref }, @{ delete $tmp{$order_id++} }; \& } \& \& return; \& }; \& } .Ve .PP Two queues are needed for data flow between the 3 sub-tasks. Notice task_end and how the value from \f(CW$task_name\fR is used for determining which task has ended. .PP .Vb 2 \& my $b = MCE::Queue\->new; \& my $c = MCE::Queue\->new; \& \& sub task_end { \& my ($mce, $task_id, $task_name) = @_; \& \& if (defined $mce\->{user_tasks}\->[$task_id + 1]) { \& my $n_workers = $mce\->{user_tasks}\->[$task_id + 1]\->{max_workers}; \& \& if ($task_name eq \*(Aqa\*(Aq) { \& $b\->enqueue((undef) x $n_workers); \& } \& elsif ($task_name eq \*(Aqb\*(Aq) { \& $c\->enqueue((undef) x $n_workers); \& } \& } \& \& return; \& } .Ve .PP Next are the 3 sub-tasks. The first one reads input and begins the flow. The 2nd task dequeues, performs the calculation, and enqueues into the next. Finally, the last task calls the gather method. .PP Although serialization is done for you automatically, it is done here to save from double serialization. This is the fastest approach for passing data between sub-tasks. Thus, the least overhead. .PP .Vb 2 \& sub task_a { \& my @ans; my ($mce, $chunk_ref, $chunk_id) = @_; \& \& push @ans, map { $_ * 2 } @{ $chunk_ref }; \& $b\->enqueue(MCE\->freeze([ \e@ans, $chunk_id ])); \& \& return; \& } \& \& sub task_b { \& my ($mce) = @_; \& \& while (1) { \& my @ans; my $chunk = $b\->dequeue; \& last unless defined $chunk; \& \& $chunk = MCE\->thaw($chunk); \& push @ans, map { $_ * 3 } @{ $chunk\->[0] }; \& $c\->enqueue(MCE\->freeze([ \e@ans, $chunk\->[1] ])); \& } \& \& return; \& } \& \& sub task_c { \& my ($mce) = @_; \& \& while (1) { \& my @ans; my $chunk = $c\->dequeue; \& last unless defined $chunk; \& \& $chunk = MCE\->thaw($chunk); \& push @ans, map { $_ * 4 } @{ $chunk\->[0] }; \& MCE\->gather(\e@ans, $chunk\->[1]); \& } \& \& return; \& } .Ve .PP In summary, MCE::Flow builds out a \s-1MCE\s0 instance behind the scene and starts running. The task_name (shown), max_workers, and use_threads options can take an anonymous array for specifying the values uniquely per each sub-task. .PP .Vb 1 \& my @a; \& \& mce_flow { \& task_name => [ \*(Aqa\*(Aq, \*(Aqb\*(Aq, \*(Aqc\*(Aq ], task_end => \e&task_end, \& gather => preserve_order(\e@a) \& \& }, \e&task_a, \e&task_b, \e&task_c, 1..10000; \& \& print "@a\en"; .Ve .PP If speed is not a concern and wanting to rid of all the \s-1MCE\-\s0>freeze and \&\s-1MCE\-\s0>thaw statements, simply enqueue and dequeue 2 items at a time. Or better yet, see MCE::Step introduced in \s-1MCE 1.506.\s0 .PP First, task_end must be updated. The number of undef(s) must match the number of workers times the dequeue count. Otherwise, the script will stall. .PP .Vb 12 \& sub task_end { \& ... \& if ($task_name eq \*(Aqa\*(Aq) { \& # $b\->enqueue((undef) x $n_workers); \& $b\->enqueue((undef) x ($n_workers * 2)); \& } \& elsif ($task_name eq \*(Aqb\*(Aq) { \& # $c\->enqueue((undef) x $n_workers); \& $c\->enqueue((undef) x ($n_workers * 2)); \& } \& ... \& } .Ve .PP Next, the 3 sub-tasks enqueuing and dequeuing 2 elements at a time. .PP .Vb 2 \& sub task_a { \& my @ans; my ($mce, $chunk_ref, $chunk_id) = @_; \& \& push @ans, map { $_ * 2 } @{ $chunk_ref }; \& $b\->enqueue(\e@ans, $chunk_id); \& \& return; \& } \& \& sub task_b { \& my ($mce) = @_; \& \& while (1) { \& my @ans; my ($chunk_ref, $chunk_id) = $b\->dequeue(2); \& last unless defined $chunk_ref; \& \& push @ans, map { $_ * 3 } @{ $chunk_ref }; \& $c\->enqueue(\e@ans, $chunk_id); \& } \& \& return; \& } \& \& sub task_c { \& my ($mce) = @_; \& \& while (1) { \& my @ans; my ($chunk_ref, $chunk_id) = $c\->dequeue(2); \& last unless defined $chunk_ref; \& \& push @ans, map { $_ * 4 } @{ $chunk_ref }; \& MCE\->gather(\e@ans, $chunk_id); \& } \& \& return; \& } .Ve .PP Finally, run as usual. .PP .Vb 1 \& my @a; \& \& mce_flow { \& task_name => [ \*(Aqa\*(Aq, \*(Aqb\*(Aq, \*(Aqc\*(Aq ], task_end => \e&task_end, \& gather => preserve_order(\e@a) \& \& }, \e&task_a, \e&task_b, \e&task_c, 1..10000; \& \& print "@a\en"; .Ve .SH "SYNOPSIS when CHUNK_SIZE EQUALS 1" .IX Header "SYNOPSIS when CHUNK_SIZE EQUALS 1" Although MCE::Loop may be preferred for running using a single code block, the text below also applies to this module, particularly for the first block. .PP All models in \s-1MCE\s0 default to 'auto' for chunk_size. The arguments for the block are the same as writing a user_func block using the Core \s-1API.\s0 .PP Beginning with \s-1MCE 1.5,\s0 the next input item is placed into the input scalar variable \f(CW$_\fR when chunk_size equals 1. Otherwise, \f(CW$_\fR points to \f(CW$chunk_ref\fR containing many items. Basically, line 2 below may be omitted from your code when using \f(CW$_\fR. One can call \s-1MCE\-\s0>chunk_id to obtain the current chunk id. .PP .Vb 9 \& line 1: user_func => sub { \& line 2: my ($mce, $chunk_ref, $chunk_id) = @_; \& line 3: \& line 4: $_ points to $chunk_ref\->[0] \& line 5: in MCE 1.5 when chunk_size == 1 \& line 6: \& line 7: $_ points to $chunk_ref \& line 8: in MCE 1.5 when chunk_size > 1 \& line 9: } .Ve .PP Follow this synopsis when chunk_size equals one. Looping is not required from inside the first block. Hence, the block is called once per each item. .PP .Vb 2 \& ## Exports mce_flow, mce_flow_f, and mce_flow_s \& use MCE::Flow; \& \& MCE::Flow\->init( \& chunk_size => 1 \& ); \& \& ## Array or array_ref \& mce_flow sub { do_work($_) }, 1..10000; \& mce_flow sub { do_work($_) }, \e@list; \& \& ## Important; pass an array_ref for deeply input data \& mce_flow sub { do_work($_) }, [ [ 0, 1 ], [ 0, 2 ], ... ]; \& mce_flow sub { do_work($_) }, \e@deeply_list; \& \& ## File path, glob ref, IO::All::{ File, Pipe, STDIO } obj, or scalar ref \& ## Workers read directly and not involve the manager process \& mce_flow_f sub { chomp; do_work($_) }, "/path/to/file"; # efficient \& \& ## Involves the manager process, therefore slower \& mce_flow_f sub { chomp; do_work($_) }, $file_handle; \& mce_flow_f sub { chomp; do_work($_) }, $io; \& mce_flow_f sub { chomp; do_work($_) }, \e$scalar; \& \& ## Sequence of numbers (begin, end [, step, format]) \& mce_flow_s sub { do_work($_) }, 1, 10000, 5; \& mce_flow_s sub { do_work($_) }, [ 1, 10000, 5 ]; \& \& mce_flow_s sub { do_work($_) }, { \& begin => 1, end => 10000, step => 5, format => undef \& }; .Ve .SH "SYNOPSIS when CHUNK_SIZE is GREATER THAN 1" .IX Header "SYNOPSIS when CHUNK_SIZE is GREATER THAN 1" Follow this synopsis when chunk_size equals 'auto' or greater than 1. This means having to loop through the chunk from inside the first block. .PP .Vb 1 \& use MCE::Flow; \& \& MCE::Flow\->init( ## Chunk_size defaults to \*(Aqauto\*(Aq when \& chunk_size => \*(Aqauto\*(Aq ## not specified. Therefore, the init \& ); ## function may be omitted. \& \& ## Syntax is shown for mce_flow for demonstration purposes. \& ## Looping inside the block is the same for mce_flow_f and \& ## mce_flow_s. \& \& ## Array or array_ref \& mce_flow sub { do_work($_) for (@{ $_ }) }, 1..10000; \& mce_flow sub { do_work($_) for (@{ $_ }) }, \e@list; \& \& ## Important; pass an array_ref for deeply input data \& mce_flow sub { do_work($_) for (@{ $_ }) }, [ [ 0, 1 ], [ 0, 2 ], ... ]; \& mce_flow sub { do_work($_) for (@{ $_ }) }, \e@deeply_list; \& \& ## Resembles code using the core MCE API \& mce_flow sub { \& my ($mce, $chunk_ref, $chunk_id) = @_; \& \& for (@{ $chunk_ref }) { \& do_work($_); \& } \& \& }, 1..10000; .Ve .PP Chunking reduces the number of \s-1IPC\s0 calls behind the scene. Think in terms of chunks whenever processing a large amount of data. For relatively small data, choosing 1 for chunk_size is fine. .SH "OVERRIDING DEFAULTS" .IX Header "OVERRIDING DEFAULTS" The following list options which may be overridden when loading the module. .PP .Vb 3 \& use Sereal qw( encode_sereal decode_sereal ); \& use CBOR::XS qw( encode_cbor decode_cbor ); \& use JSON::XS qw( encode_json decode_json ); \& \& use MCE::Flow \& max_workers => 8, # Default \*(Aqauto\*(Aq \& chunk_size => 500, # Default \*(Aqauto\*(Aq \& tmp_dir => "/path/to/app/tmp", # $MCE::Signal::tmp_dir \& freeze => \e&encode_sereal, # \e&Storable::freeze \& thaw => \e&decode_sereal, # \e&Storable::thaw \& init_relay => 0, # Default undef; MCE 1.882+ \& use_threads => 0, # Default undef; MCE 1.882+ \& ; .Ve .PP From \s-1MCE 1.8\s0 onwards, Sereal 3.015+ is loaded automatically if available. Specify \f(CW\*(C`Sereal => 0\*(C'\fR to use Storable instead. .PP .Vb 1 \& use MCE::Flow Sereal => 0; .Ve .SH "CUSTOMIZING MCE" .IX Header "CUSTOMIZING MCE" .IP "MCE::Flow\->init ( options )" 3 .IX Item "MCE::Flow->init ( options )" .PD 0 .IP "MCE::Flow::init { options }" 3 .IX Item "MCE::Flow::init { options }" .PD .PP The init function accepts a hash of \s-1MCE\s0 options. Unlike with MCE::Stream, both gather and bounds_only options may be specified when calling init (not shown below). .PP .Vb 1 \& use MCE::Flow; \& \& MCE::Flow\->init( \& chunk_size => 1, max_workers => 4, \& \& user_begin => sub { \& print "## ", MCE\->wid, " started\en"; \& }, \& \& user_end => sub { \& print "## ", MCE\->wid, " completed\en"; \& } \& ); \& \& my %a = mce_flow sub { MCE\->gather($_, $_ * $_) }, 1..100; \& \& print "\en", "@a{1..100}", "\en"; \& \& \-\- Output \& \& ## 3 started \& ## 2 started \& ## 4 started \& ## 1 started \& ## 2 completed \& ## 4 completed \& ## 3 completed \& ## 1 completed \& \& 1 4 9 16 25 36 49 64 81 100 121 144 169 196 225 256 289 324 361 \& 400 441 484 529 576 625 676 729 784 841 900 961 1024 1089 1156 \& 1225 1296 1369 1444 1521 1600 1681 1764 1849 1936 2025 2116 2209 \& 2304 2401 2500 2601 2704 2809 2916 3025 3136 3249 3364 3481 3600 \& 3721 3844 3969 4096 4225 4356 4489 4624 4761 4900 5041 5184 5329 \& 5476 5625 5776 5929 6084 6241 6400 6561 6724 6889 7056 7225 7396 \& 7569 7744 7921 8100 8281 8464 8649 8836 9025 9216 9409 9604 9801 \& 10000 .Ve .PP Like with MCE::Flow\->init above, \s-1MCE\s0 options may be specified using an anonymous hash for the first argument. Notice how task_name, max_workers, and use_threads can take an anonymous array for setting uniquely per each code block. .PP Unlike MCE::Stream which processes from right-to-left, MCE::Flow begins with the first code block, thus processing from left-to-right. .PP .Vb 2 \& use threads; \& use MCE::Flow; \& \& my @a = mce_flow { \& task_name => [ \*(Aqa\*(Aq, \*(Aqb\*(Aq, \*(Aqc\*(Aq ], \& max_workers => [ 3, 4, 2, ], \& use_threads => [ 1, 0, 0, ], \& \& user_end => sub { \& my ($mce, $task_id, $task_name) = @_; \& MCE\->print("$task_id \- $task_name completed\en"); \& }, \& \& task_end => sub { \& my ($mce, $task_id, $task_name) = @_; \& MCE\->print("$task_id \- $task_name ended\en"); \& } \& }, \& sub { sleep 1; }, ## 3 workers, named a \& sub { sleep 2; }, ## 4 workers, named b \& sub { sleep 3; }; ## 2 workers, named c \& \& \-\- Output \& \& 0 \- a completed \& 0 \- a completed \& 0 \- a completed \& 0 \- a ended \& 1 \- b completed \& 1 \- b completed \& 1 \- b completed \& 1 \- b completed \& 1 \- b ended \& 2 \- c completed \& 2 \- c completed \& 2 \- c ended .Ve .SH "API DOCUMENTATION" .IX Header "API DOCUMENTATION" Although input data is optional for MCE::Flow, the following assumes chunk_size equals 1 in order to demonstrate all the possibilities for providing input data. .IP "MCE::Flow\->run ( sub { code }, list )" 3 .IX Item "MCE::Flow->run ( sub { code }, list )" .PD 0 .IP "mce_flow sub { code }, list" 3 .IX Item "mce_flow sub { code }, list" .PD .PP Input data may be defined using a list, an array ref, or a hash ref. .PP Unlike MCE::Loop, Map, and Grep which take a block as \f(CW\*(C`{ ... }\*(C'\fR, Flow takes a \&\f(CW\*(C`sub { ... }\*(C'\fR or a code reference. The other difference is that the comma is needed after the block. .PP .Vb 1 \& # $_ contains the item when chunk_size => 1 \& \& mce_flow sub { do_work($_) }, 1..1000; \& mce_flow sub { do_work($_) }, \e@list; \& \& # Important; pass an array_ref for deeply input data \& \& mce_flow sub { do_work($_) }, [ [ 0, 1 ], [ 0, 2 ], ... ]; \& mce_flow sub { do_work($_) }, \e@deeply_list; \& \& # Chunking; any chunk_size => 1 or greater \& \& my %res = mce_flow sub { \& my ($mce, $chunk_ref, $chunk_id) = @_; \& my %ret; \& for my $item (@{ $chunk_ref }) { \& $ret{$item} = $item * 2; \& } \& MCE\->gather(%ret); \& }, \& \e@list; \& \& # Input hash; current API available since 1.828 \& \& my %res = mce_flow sub { \& my ($mce, $chunk_ref, $chunk_id) = @_; \& my %ret; \& for my $key (keys %{ $chunk_ref }) { \& $ret{$key} = $chunk_ref\->{$key} * 2; \& } \& MCE\->gather(%ret); \& }, \& \e%hash; \& \& # Unlike MCE::Loop, MCE::Flow doesn\*(Aqt need input to run \& \& mce_flow { max_workers => 4 }, sub { \& MCE\->say( MCE\->wid ); \& }; \& \& # ... and can run multiple tasks \& \& mce_flow { \& max_workers => [ 1, 3 ], \& task_name => [ \*(Aqp\*(Aq, \*(Aqc\*(Aq ] \& }, \& sub { \& # 1 producer \& MCE\->say( "producer: ", MCE\->wid ); \& }, \& sub { \& # 3 consumers \& MCE\->say( "consumer: ", MCE\->wid ); \& }; \& \& # Here, options are specified via init \& \& MCE::Flow\->init( \& max_workers => [ 1, 3 ], \& task_name => [ \*(Aqp\*(Aq, \*(Aqc\*(Aq ] \& ); \& \& mce_flow \e&producer, \e&consumers; .Ve .IP "MCE::Flow\->run_file ( sub { code }, file )" 3 .IX Item "MCE::Flow->run_file ( sub { code }, file )" .PD 0 .IP "mce_flow_f sub { code }, file" 3 .IX Item "mce_flow_f sub { code }, file" .PD .PP The fastest of these is the /path/to/file. Workers communicate the next offset position among themselves with zero interaction by the manager process. .PP \&\f(CW\*(C`IO::All\*(C'\fR { File, Pipe, \s-1STDIO\s0 } is supported since \s-1MCE 1.845.\s0 .PP .Vb 1 \& # $_ contains the line when chunk_size => 1 \& \& mce_flow_f sub { $_ }, "/path/to/file"; # faster \& mce_flow_f sub { $_ }, $file_handle; \& mce_flow_f sub { $_ }, $io; # IO::All \& mce_flow_f sub { $_ }, \e$scalar; \& \& # chunking, any chunk_size => 1 or greater \& \& my %res = mce_flow_f sub { \& my ($mce, $chunk_ref, $chunk_id) = @_; \& my $buf = \*(Aq\*(Aq; \& for my $line (@{ $chunk_ref }) { \& $buf .= $line; \& } \& MCE\->gather($chunk_id, $buf); \& }, \& "/path/to/file"; .Ve .ie n .IP "MCE::Flow\->run_seq ( sub { code }, $beg, $end [, $step, $fmt ] )" 3 .el .IP "MCE::Flow\->run_seq ( sub { code }, \f(CW$beg\fR, \f(CW$end\fR [, \f(CW$step\fR, \f(CW$fmt\fR ] )" 3 .IX Item "MCE::Flow->run_seq ( sub { code }, $beg, $end [, $step, $fmt ] )" .PD 0 .ie n .IP "mce_flow_s sub { code }, $beg, $end [, $step, $fmt ]" 3 .el .IP "mce_flow_s sub { code }, \f(CW$beg\fR, \f(CW$end\fR [, \f(CW$step\fR, \f(CW$fmt\fR ]" 3 .IX Item "mce_flow_s sub { code }, $beg, $end [, $step, $fmt ]" .PD .PP Sequence may be defined as a list, an array reference, or a hash reference. The functions require both begin and end values to run. Step and format are optional. The format is passed to sprintf (% may be omitted below). .PP .Vb 1 \& my ($beg, $end, $step, $fmt) = (10, 20, 0.1, "%4.1f"); \& \& # $_ contains the sequence number when chunk_size => 1 \& \& mce_flow_s sub { $_ }, $beg, $end, $step, $fmt; \& mce_flow_s sub { $_ }, [ $beg, $end, $step, $fmt ]; \& \& mce_flow_s sub { $_ }, { \& begin => $beg, end => $end, \& step => $step, format => $fmt \& }; \& \& # chunking, any chunk_size => 1 or greater \& \& my %res = mce_flow_s sub { \& my ($mce, $chunk_ref, $chunk_id) = @_; \& my $buf = \*(Aq\*(Aq; \& for my $seq (@{ $chunk_ref }) { \& $buf .= "$seq\en"; \& } \& MCE\->gather($chunk_id, $buf); \& }, \& [ $beg, $end ]; .Ve .PP The sequence engine can compute 'begin' and 'end' items only, for the chunk, and not the items in between (hence boundaries only). This option applies to sequence only and has no effect when chunk_size equals 1. .PP The time to run is 0.006s below. This becomes 0.827s without the bounds_only option due to computing all items in between, thus creating a very large array. Basically, specify bounds_only => 1 when boundaries is all you need for looping inside the block; e.g. Monte Carlo simulations. .PP Time was measured using 1 worker to emphasize the difference. .PP .Vb 1 \& use MCE::Flow; \& \& MCE::Flow\->init( \& max_workers => 1, chunk_size => 1_250_000, \& bounds_only => 1 \& ); \& \& # Typically, the input scalar $_ contains the sequence number \& # when chunk_size => 1, unless the bounds_only option is set \& # which is the case here. Thus, $_ points to $chunk_ref. \& \& mce_flow_s sub { \& my ($mce, $chunk_ref, $chunk_id) = @_; \& \& # $chunk_ref contains 2 items, not 1_250_000 \& # my ( $begin, $end ) = ( $_\->[0], $_\->[1] ); \& \& my $begin = $chunk_ref\->[0]; \& my $end = $chunk_ref\->[1]; \& \& # for my $seq ( $begin .. $end ) { \& # ... \& # } \& \& MCE\->printf("%7d .. %8d\en", $begin, $end); \& }, \& [ 1, 10_000_000 ]; \& \& \-\- Output \& \& 1 .. 1250000 \& 1250001 .. 2500000 \& 2500001 .. 3750000 \& 3750001 .. 5000000 \& 5000001 .. 6250000 \& 6250001 .. 7500000 \& 7500001 .. 8750000 \& 8750001 .. 10000000 .Ve .IP "MCE::Flow\->run ( { input_data => iterator }, sub { code } )" 3 .IX Item "MCE::Flow->run ( { input_data => iterator }, sub { code } )" .PD 0 .IP "mce_flow { input_data => iterator }, sub { code }" 3 .IX Item "mce_flow { input_data => iterator }, sub { code }" .PD .PP An iterator reference may be specified for input_data. The only other way is to specify input_data via MCE::Flow\->init. This prevents MCE::Flow from configuring the iterator reference as another user task which will not work. .PP Iterators are described under section \*(L"\s-1SYNTAX\s0 for \s-1INPUT_DATA\*(R"\s0 at MCE::Core. .PP .Vb 3 \& MCE::Flow\->init( \& input_data => iterator \& ); \& \& mce_flow sub { $_ }; .Ve .SH "GATHERING DATA" .IX Header "GATHERING DATA" Unlike MCE::Map where gather and output order are done for you automatically, the gather method is used to have results sent back to the manager process. .PP .Vb 1 \& use MCE::Flow chunk_size => 1; \& \& ## Output order is not guaranteed. \& my @a1 = mce_flow sub { MCE\->gather($_ * 2) }, 1..100; \& print "@a1\en\en"; \& \& ## Outputs to a hash instead (key, value). \& my %h1 = mce_flow sub { MCE\->gather($_, $_ * 2) }, 1..100; \& print "@h1{1..100}\en\en"; \& \& ## This does the same thing due to chunk_id starting at one. \& my %h2 = mce_flow sub { MCE\->gather(MCE\->chunk_id, $_ * 2) }, 1..100; \& print "@h2{1..100}\en\en"; .Ve .PP The gather method may be called multiple times within the block unlike return which would leave the block. Therefore, think of gather as yielding results immediately to the manager process without actually leaving the block. .PP .Vb 1 \& use MCE::Flow chunk_size => 1, max_workers => 3; \& \& my @hosts = qw( \& hosta hostb hostc hostd hoste \& ); \& \& my %h3 = mce_flow sub { \& my ($output, $error, $status); my $host = $_; \& \& ## Do something with $host; \& $output = "Worker ". MCE\->wid .": Hello from $host"; \& \& if (MCE\->chunk_id % 3 == 0) { \& ## Simulating an error condition \& local $? = 1; $status = $?; \& $error = "Error from $host" \& } \& else { \& $status = 0; \& } \& \& ## Ensure unique keys (key, value) when gathering to \& ## a hash. \& MCE\->gather("$host.out", $output); \& MCE\->gather("$host.err", $error) if (defined $error); \& MCE\->gather("$host.sta", $status); \& \& }, @hosts; \& \& foreach my $host (@hosts) { \& print $h3{"$host.out"}, "\en"; \& print $h3{"$host.err"}, "\en" if (exists $h3{"$host.err"}); \& print "Exit status: ", $h3{"$host.sta"}, "\en\en"; \& } \& \& \-\- Output \& \& Worker 3: Hello from hosta \& Exit status: 0 \& \& Worker 2: Hello from hostb \& Exit status: 0 \& \& Worker 1: Hello from hostc \& Error from hostc \& Exit status: 1 \& \& Worker 3: Hello from hostd \& Exit status: 0 \& \& Worker 2: Hello from hoste \& Exit status: 0 .Ve .PP The following uses an anonymous array containing 3 elements when gathering data. Serialization is automatic behind the scene. .PP .Vb 2 \& my %h3 = mce_flow sub { \& ... \& \& MCE\->gather($host, [$output, $error, $status]); \& \& }, @hosts; \& \& foreach my $host (@hosts) { \& print $h3{$host}\->[0], "\en"; \& print $h3{$host}\->[1], "\en" if (defined $h3{$host}\->[1]); \& print "Exit status: ", $h3{$host}\->[2], "\en\en"; \& } .Ve .PP Although MCE::Map comes to mind, one may want additional control when gathering data such as retaining output order. .PP .Vb 1 \& use MCE::Flow; \& \& sub preserve_order { \& my %tmp; my $order_id = 1; my $gather_ref = $_[0]; \& \& return sub { \& $tmp{ (shift) } = \e@_; \& \& while (1) { \& last unless exists $tmp{$order_id}; \& push @{ $gather_ref }, @{ delete $tmp{$order_id++} }; \& } \& \& return; \& }; \& } \& \& ## Workers persist for the most part after running. Though, not always \& ## the case and depends on Perl. Pass a reference to a subroutine if \& ## workers must persist; e.g. mce_flow { ... }, \e&foo, 1..100000. \& \& MCE::Flow\->init( \& chunk_size => \*(Aqauto\*(Aq, max_workers => \*(Aqauto\*(Aq \& ); \& \& for (1..2) { \& my @m2; \& \& mce_flow { \& gather => preserve_order(\e@m2) \& }, \& sub { \& my @a; my ($mce, $chunk_ref, $chunk_id) = @_; \& \& ## Compute the entire chunk data at once. \& push @a, map { $_ * 2 } @{ $chunk_ref }; \& \& ## Afterwards, invoke the gather feature, which \& ## will direct the data to the callback function. \& MCE\->gather(MCE\->chunk_id, @a); \& \& }, 1..100000; \& \& print scalar @m2, "\en"; \& } \& \& MCE::Flow\->finish; .Ve .PP All 6 models support 'auto' for chunk_size unlike the Core \s-1API.\s0 Think of the models as the basis for providing \s-1JIT\s0 for \s-1MCE.\s0 They create the instance, tune max_workers, and tune chunk_size automatically regardless of the hardware. .PP The following does the same thing using the Core \s-1API.\s0 Workers persist after running. .PP .Vb 1 \& use MCE; \& \& sub preserve_order { \& ... \& } \& \& my $mce = MCE\->new( \& max_workers => \*(Aqauto\*(Aq, chunk_size => 8000, \& \& user_func => sub { \& my @a; my ($mce, $chunk_ref, $chunk_id) = @_; \& \& ## Compute the entire chunk data at once. \& push @a, map { $_ * 2 } @{ $chunk_ref }; \& \& ## Afterwards, invoke the gather feature, which \& ## will direct the data to the callback function. \& MCE\->gather(MCE\->chunk_id, @a); \& } \& ); \& \& for (1..2) { \& my @m2; \& \& $mce\->process({ gather => preserve_order(\e@m2) }, [1..100000]); \& \& print scalar @m2, "\en"; \& } \& \& $mce\->shutdown; .Ve .SH "MANUAL SHUTDOWN" .IX Header "MANUAL SHUTDOWN" .IP "MCE::Flow\->finish" 3 .IX Item "MCE::Flow->finish" .PD 0 .IP "MCE::Flow::finish" 3 .IX Item "MCE::Flow::finish" .PD .PP Workers remain persistent as much as possible after running. Shutdown occurs automatically when the script terminates. Call finish when workers are no longer needed. .PP .Vb 1 \& use MCE::Flow; \& \& MCE::Flow\->init( \& chunk_size => 20, max_workers => \*(Aqauto\*(Aq \& ); \& \& mce_flow sub { ... }, 1..100; \& \& MCE::Flow\->finish; .Ve .SH "INDEX" .IX Header "INDEX" \&\s-1MCE\s0, MCE::Core .SH "AUTHOR" .IX Header "AUTHOR" Mario E. Roy,