LongMult_conf.pm 7.3 KB
Newer Older
Leo Gordon's avatar
Leo Gordon committed
1 2 3 4
=pod 

=head1 NAME

Leo Gordon's avatar
Leo Gordon committed
5
    Bio::EnsEMBL::Hive::PipeConfig::LongMult_conf;
Leo Gordon's avatar
Leo Gordon committed
6 7 8

=head1 SYNOPSIS

9 10
       # initialize the database and build the graph in it (it will also print the value of EHIVE_URL) :
    init_pipeline.pl Bio::EnsEMBL::Hive::PipeConfig::LongMult_conf -password <mypass>
Leo Gordon's avatar
Leo Gordon committed
11

12 13
        # optionally also seed it with your specific values:
    seed_pipeline.pl -url $EHIVE_URL -logic_name take_b_apart -input_id '{ "a_multiplier" => "12345678", "b_multiplier" => "3359559666" }'
Leo Gordon's avatar
Leo Gordon committed
14

15 16
        # run the pipeline:
    beekeeper.pl -url $EHIVE_URL -loop
Leo Gordon's avatar
Leo Gordon committed
17 18 19

=head1 DESCRIPTION

Leo Gordon's avatar
Leo Gordon committed
20 21
    This is the PipeConfig file for the long multiplication pipeline example.
    The main point of this pipeline is to provide an example of how to write Hive Runnables and link them together into a pipeline.
Leo Gordon's avatar
Leo Gordon committed
22

Leo Gordon's avatar
Leo Gordon committed
23
    Please refer to Bio::EnsEMBL::Hive::PipeConfig::HiveGeneric_conf module to understand the interface implemented here.
Leo Gordon's avatar
Leo Gordon committed
24

25 26
    The setting. let's assume we are given two loooooong numbers to multiply. reeeeally long.
    soooo long that they do not fit into registers of the cpu and should be multiplied digit-by-digit.
Leo Gordon's avatar
Leo Gordon committed
27
    For the purposes of this example we also assume this task is very computationally intensive and has to be done in parallel.
Leo Gordon's avatar
Leo Gordon committed
28

29 30
    The long multiplication pipeline consists of three "analyses" (types of tasks):
        'take_b_apart', 'part_multiply' and 'add_together' that we use to examplify various features of the Hive.
Leo Gordon's avatar
Leo Gordon committed
31

32
        * A 'take_b_apart' job takes in two string parameters, 'a_multiplier' and 'b_multiplier',
Leo Gordon's avatar
Leo Gordon committed
33 34
          takes the second one apart into digits, finds what _different_ digits are there,
          creates several jobs of the 'part_multiply' analysis and one job of 'add_together' analysis.
Leo Gordon's avatar
Leo Gordon committed
35

36
        * A 'part_multiply' job takes in 'a_multiplier' and 'digit', multiplies them and accumulates the result in 'partial_product' accumulator.
Leo Gordon's avatar
Leo Gordon committed
37

Leo Gordon's avatar
Leo Gordon committed
38
        * An 'add_together' job waits for the first two analyses to complete,
39
          takes in 'a_multiplier', 'b_multiplier' and 'partial_product' hash and produces the final result in 'final_result' table.
Leo Gordon's avatar
Leo Gordon committed
40

Leo Gordon's avatar
Leo Gordon committed
41
    Please see the implementation details in Runnable modules themselves.
Leo Gordon's avatar
Leo Gordon committed
42

43 44
=head1 LICENSE

45
    Copyright [1999-2014] Wellcome Trust Sanger Institute and the EMBL-European Bioinformatics Institute
46 47 48 49 50 51 52 53 54 55

    Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with the License.
    You may obtain a copy of the License at

         http://www.apache.org/licenses/LICENSE-2.0

    Unless required by applicable law or agreed to in writing, software distributed under the License
    is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
    See the License for the specific language governing permissions and limitations under the License.

Leo Gordon's avatar
Leo Gordon committed
56 57
=head1 CONTACT

Leo Gordon's avatar
Leo Gordon committed
58
    Please contact ehive-users@ebi.ac.uk mailing list with questions/suggestions.
Leo Gordon's avatar
Leo Gordon committed
59 60 61

=cut

62 63 64 65 66

package Bio::EnsEMBL::Hive::PipeConfig::LongMult_conf;

use strict;
use warnings;
Leo Gordon's avatar
Leo Gordon committed
67

Leo Gordon's avatar
Leo Gordon committed
68
use base ('Bio::EnsEMBL::Hive::PipeConfig::HiveGeneric_conf');  # All Hive databases configuration files should inherit from HiveGeneric, directly or indirectly
69

70

Leo Gordon's avatar
Leo Gordon committed
71 72 73 74 75 76 77
=head2 pipeline_create_commands

    Description : Implements pipeline_create_commands() interface method of Bio::EnsEMBL::Hive::PipeConfig::HiveGeneric_conf that lists the commands that will create and set up the Hive database.
                  In addition to the standard creation of the database and populating it with Hive tables and procedures it also creates two pipeline-specific tables used by Runnables to communicate.

=cut

78 79 80
sub pipeline_create_commands {
    my ($self) = @_;
    return [
Leo Gordon's avatar
Leo Gordon committed
81
        @{$self->SUPER::pipeline_create_commands},  # inheriting database and hive tables' creation
82 83

            # additional tables needed for long multiplication pipeline's operation:
84
        $self->db_cmd('CREATE TABLE final_result (a_multiplier char(40) NOT NULL, b_multiplier char(40) NOT NULL, result char(80) NOT NULL, PRIMARY KEY (a_multiplier, b_multiplier))'),
85 86 87
    ];
}

88

89 90 91 92 93 94 95 96 97 98 99 100 101
=head2 pipeline_wide_parameters

    Description : Interface method that should return a hash of pipeline_wide_parameter_name->pipeline_wide_parameter_value pairs.
                  The value doesn't have to be a scalar, can be any Perl structure now (will be stringified and de-stringified automagically).
                  Please see existing PipeConfig modules for examples.

=cut

sub pipeline_wide_parameters {
    my ($self) = @_;
    return {
        %{$self->SUPER::pipeline_wide_parameters},          # here we inherit anything from the base class

102
        'take_time'     => 1,
103 104 105 106
    };
}


Leo Gordon's avatar
Leo Gordon committed
107 108 109 110
=head2 pipeline_analyses

    Description : Implements pipeline_analyses() interface method of Bio::EnsEMBL::Hive::PipeConfig::HiveGeneric_conf that defines the structure of the pipeline: analyses, jobs, rules, etc.
                  Here it defines three analyses:
111
                    * 'take_b_apart' that is auto-seeded with a pair of jobs (to check the commutativity of multiplication).
Leo Gordon's avatar
Leo Gordon committed
112 113
                      Each job will dataflow (create more jobs) via branch #2 into 'part_multiply' and via branch #1 into 'add_together'.

114 115
                    * 'part_multiply' with jobs fed from take_b_apart#2.
                        It multiplies input parameters 'a_multiplier' and 'digit' and dataflows 'partial_product' parameter into branch #1.
116

117 118 119 120
                    * 'add_together' with jobs fed from take_b_apart#1.
                        It adds together results of partial multiplication computed by 'part_multiply'.
                        These results are accumulated in 'partial_product' hash.
                        Until the hash is complete the corresponding 'add_together' job is blocked by a semaphore.
Leo Gordon's avatar
Leo Gordon committed
121 122 123

=cut

124 125 126
sub pipeline_analyses {
    my ($self) = @_;
    return [
127 128
        {   -logic_name => 'take_b_apart',
            -module     => 'Bio::EnsEMBL::Hive::RunnableDB::LongMult::DigitFactory',
129
            -meadow_type=> 'LOCAL',     # do not bother the farm with such a simple task (and get it done faster)
130
            -analysis_capacity  =>  2,  # use per-analysis limiter
131
            -input_ids => [
132 133
                { 'a_multiplier' => '9650156169', 'b_multiplier' => '327358788' },
                { 'a_multiplier' => '327358788', 'b_multiplier' => '9650156169' },
134 135
            ],
            -flow_into => {
136 137 138 139
                    # will create a semaphored fan of jobs; will use a template to top-up the hashes:
                '2->A' => { 'part_multiply' => { 'a_multiplier' => '#a_multiplier#', 'digit' => '#digit#', 'take_time' => '#take_time#' } },
                    # will create a semaphored funnel job to wait for the fan to complete and add the results:
                'A->1' => [ 'add_together'  ],
140 141 142
            },
        },

143 144
        {   -logic_name => 'part_multiply',
            -module     => 'Bio::EnsEMBL::Hive::RunnableDB::LongMult::PartMultiply',
145
            -analysis_capacity  =>  4,  # use per-analysis limiter
146
            -flow_into => {
147
                1 => [ ':////accu?partial_product={digit}' ],
148
            },
149 150 151 152
        },
        
        {   -logic_name => 'add_together',
            -module     => 'Bio::EnsEMBL::Hive::RunnableDB::LongMult::AddTogether',
153
#           -analysis_capacity  =>  0,  # this is a way to temporarily block a given analysis
154
            -flow_into => {
155
                1 => [ ':////final_result' ],
156
            },
157 158 159 160 161 162
        },
    ];
}

1;