Skip to content

GitLab

Commit af386167 authored by COULAUD Olivier's avatar COULAUD Olivier
Browse files

Merge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/scalfmm/scalfmm

parents d3844968 5c1aff90
Hide whitespace changes
Inline Side-by-side
Showing with 1696 additions and 6057 deletions
Addons/BenchEfficiency/execAllHomogeneous.sh
View file @ af386167
......@@ -13,14 +13,14 @@ cpu=1
STARPU_NCPUS=$cpu
STARPU_NCUDA=0
logoutput=`./Tests/Release/testBlockedUnifCudaBench -nb $SCALFMM_NB -h $SCALFMM_H -bs $SCALFMM_BS_CPU_SEQ`
logoutput=`./Tests/Release/testBlockedUniformBench -nb $SCALFMM_NB -h $SCALFMM_H -bs $SCALFMM_BS_CPU_SEQ`
if [[ $VERBOSE ]] ; then
echo $logoutput
fi
$SCALFMM_STARPU_DIR/bin/starpu_fxt_tool -i "/tmp/prof_file_"$USER"_0"
$TUTORIAL_STARPU_DIR/bin/starpu_fxt_tool -i "/tmp/prof_file_"$USER"_0"
rec_name="$SCALFMM_RES_DIR/trace-nb_$SCALFMM_NB-h_$SCALFMM_H-bs_$SCALFMM_BS_CPU_SEQ-CPU_$cpu.rec"
mv trace.rec $rec_name
python $SCALFMM_STARPU_DIR/bin/starpu_trace_state_stats.py -t $rec_name > $rec_name.time
python $TUTORIAL_STARPU_DIR/bin/starpu_trace_state_stats.py -t $rec_name > $rec_name.time
for (( cpu=1 ; cpu<=$SCALFMM_MAX_NB_CPU ; cpu++)) ; do
......@@ -29,13 +29,13 @@ for (( cpu=1 ; cpu<=$SCALFMM_MAX_NB_CPU ; cpu++)) ; do
STARPU_NCPUS=$cpu
STARPU_NCUDA=0
logoutput=`./Tests/Release/testBlockedUnifCudaBench -nb $SCALFMM_NB -h $SCALFMM_H -bs $SCALFMM_BS_CPU_PAR`
logoutput=`./Tests/Release/testBlockedUniformBench -nb $SCALFMM_NB -h $SCALFMM_H -bs $SCALFMM_BS_CPU_PAR`
if [[ $VERBOSE ]] ; then
echo $logoutput
fi
$SCALFMM_STARPU_DIR/bin/starpu_fxt_tool -i "/tmp/prof_file_"$USER"_0"
$TUTORIAL_STARPU_DIR/bin/starpu_fxt_tool -i "/tmp/prof_file_"$USER"_0"
rec_name="$SCALFMM_RES_DIR/trace-nb_$SCALFMM_NB-h_$SCALFMM_H-bs_$SCALFMM_BS_CPU_PAR-CPU_$cpu.rec"
mv trace.rec $rec_name
python $SCALFMM_STARPU_DIR/bin/starpu_trace_state_stats.py -t $rec_name > $rec_name.time
python $TUTORIAL_STARPU_DIR/bin/starpu_trace_state_stats.py -t $rec_name > $rec_name.time
done
Addons/BenchEfficiency/global-eff.data deleted 100644 → 0
View file @ d3844968
0 granularity-eff tasks-eff runtime-eff pipeline-eff
1 1.000000e+00 1.000000e+00 1.000000e+00 1.000000e+00
2 9.588832e-01 9.588832e-01 9.972215e-01 9.999844e-01
3 9.984195e-01 9.984195e-01 9.992539e-01 9.999840e-01
4 9.936055e-01 9.936055e-01 9.992505e-01 9.999843e-01
5 9.859209e-01 9.859209e-01 9.991938e-01 9.999840e-01
6 9.913540e-01 9.913540e-01 9.992224e-01 9.999848e-01
7 9.980442e-01 9.980442e-01 9.993216e-01 9.999841e-01
8 9.932070e-01 9.932070e-01 9.993356e-01 9.999844e-01
9 9.953908e-01 9.953908e-01 9.993136e-01 9.999852e-01
10 9.930517e-01 9.930517e-01 9.991280e-01 9.999848e-01
11 9.937148e-01 9.937148e-01 9.992802e-01 9.999838e-01
12 9.895039e-01 9.895039e-01 9.992958e-01 9.999842e-01
13 9.934571e-01 9.934571e-01 9.992770e-01 9.999845e-01
14 9.939346e-01 9.939346e-01 9.993242e-01 9.999845e-01
15 9.929928e-01 9.929928e-01 9.993077e-01 9.999849e-01
16 9.946804e-01 9.946804e-01 9.993051e-01 9.999838e-01
17 9.959137e-01 9.959137e-01 9.992893e-01 9.999839e-01
18 9.652375e-01 9.652375e-01 9.961152e-01 9.999832e-01
19 9.937258e-01 9.937258e-01 9.992987e-01 9.999845e-01
20 9.949256e-01 9.949256e-01 9.992757e-01 9.999843e-01
21 9.886613e-01 9.886613e-01 9.992616e-01 9.999838e-01
22 9.921982e-01 9.921982e-01 9.992499e-01 9.999842e-01
23 1.001717e+00 1.001717e+00 9.992881e-01 9.999846e-01
24 9.957642e-01 9.957642e-01 9.992461e-01 9.999836e-01
Addons/BenchEfficiency/mergetimefile.cpp
View file @ af386167
......@@ -68,7 +68,7 @@ struct LineData{
}
}
if(words.size() != 4){
printf("Error line is no composed of 4 words\n");
printf("Error line is no composed of 4 words, has %lu for %s\n", words.size(), line);
exit(111);
}
name = ReduceName(words[0].substr(1, words[0].size() - 2));
......@@ -186,30 +186,32 @@ int main(int argc, char** argv){
}
while((sizeLine = getline((char**)&line, &sizeLine, timeFile)) != -1){
LineData dt(line);
// Task, Runtime, Other
if(dt.type == "Task"){
if(dt.name != "execute_on_all_wrapper"){
timeTasks[idxFile][dt.name] += dt.duration;
allTaskNames.insert(dt.name);
times[idxFile].tt += dt.duration;
if(strncmp(line, "WARNING", 7) != 0){
LineData dt(line);
// Task, Runtime, Other
if(dt.type == "Task"){
if(dt.name != "execute_on_all_wrapper"){
timeTasks[idxFile][dt.name] += dt.duration;
allTaskNames.insert(dt.name);
times[idxFile].tt += dt.duration;
}
}
}
else if(dt.type == "Runtime"){
if(dt.name == "Scheduling"
|| dt.name == "FetchingInput"
|| dt.name == "PushingOutput"){
times[idxFile].tr += dt.duration;
else if(dt.type == "Runtime"){
if(dt.name == "Scheduling"
|| dt.name == "FetchingInput"
|| dt.name == "PushingOutput"){
times[idxFile].tr += dt.duration;
}
}
}
else if(dt.type == "Other"){
if(dt.name == "Idle"){
times[idxFile].ti += dt.duration;
else if(dt.type == "Other"){
if(dt.name == "Idle"){
times[idxFile].ti += dt.duration;
}
}
else {
printf("Arg do not know type %s\n", dt.type.c_str());
//return 3;
}
}
else {
printf("Arg do not know type %s\n", dt.type.c_str());
return 3;
}
}
......
Addons/BenchEfficiency/scalfmm.html deleted 100644 → 0
View file @ d3844968
<!DOCTYPE html>
<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
<title>scalfmm.html</title>
<meta name="generator" content="Haroopad 0.13.1" />
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<style>div.oembedall-githubrepos{border:1px solid #DDD;border-radius:4px;list-style-type:none;margin:0 0 10px;padding:8px 10px 0;font:13.34px/1.4 helvetica,arial,freesans,clean,sans-serif;width:452px;background-color:#fff}div.oembedall-githubrepos .oembedall-body{background:-moz-linear-gradient(center top,#FAFAFA,#EFEFEF);background:-webkit-gradient(linear,left top,left bottom,from(#FAFAFA),to(#EFEFEF));border-bottom-left-radius:4px;border-bottom-right-radius:4px;border-top:1px solid #EEE;margin-left:-10px;margin-top:8px;padding:5px 10px;width:100%}div.oembedall-githubrepos h3{font-size:14px;margin:0;padding-left:18px;white-space:nowrap}div.oembedall-githubrepos p.oembedall-description{color:#444;font-size:12px;margin:0 0 3px}div.oembedall-githubrepos p.oembedall-updated-at{color:#888;font-size:11px;margin:0}div.oembedall-githubrepos ul.oembedall-repo-stats{border:none;float:right;font-size:11px;font-weight:700;padding-left:15px;position:relative;z-index:5;margin:0}div.oembedall-githubrepos ul.oembedall-repo-stats li{border:none;color:#666;display:inline-block;list-style-type:none;margin:0!important}div.oembedall-githubrepos ul.oembedall-repo-stats li a{background-color:transparent;border:none;color:#666!important;background-position:5px -2px;background-repeat:no-repeat;border-left:1px solid #DDD;display:inline-block;height:21px;line-height:21px;padding:0 5px 0 23px}div.oembedall-githubrepos ul.oembedall-repo-stats li:first-child a{border-left:medium none;margin-right:-3px}div.oembedall-githubrepos ul.oembedall-repo-stats li a:hover{background:5px -27px no-repeat #4183C4;color:#FFF!important;text-decoration:none}div.oembedall-githubrepos ul.oembedall-repo-stats li:first-child a:hover{border-bottom-left-radius:3px;border-top-left-radius:3px}ul.oembedall-repo-stats li:last-child a:hover{border-bottom-right-radius:3px;border-top-right-radius:3px}span.oembedall-closehide{background-color:#aaa;border-radius:2px;cursor:pointer;margin-right:3px}div.oembedall-container{margin-top:5px;text-align:left}.oembedall-ljuser{font-weight:700}.oembedall-ljuser img{vertical-align:bottom;border:0;padding-right:1px}.oembedall-stoqembed{border-bottom:1px dotted #999;float:left;overflow:hidden;width:730px;line-height:1;background:#FFF;color:#000;font-family:Arial,Liberation Sans,DejaVu Sans,sans-serif;font-size:80%;text-align:left;margin:0;padding:0}.oembedall-stoqembed a{color:#07C;text-decoration:none;margin:0;padding:0}.oembedall-stoqembed a:hover{text-decoration:underline}.oembedall-stoqembed a:visited{color:#4A6B82}.oembedall-stoqembed h3{font-family:Trebuchet MS,Liberation Sans,DejaVu Sans,sans-serif;font-size:130%;font-weight:700;margin:0;padding:0}.oembedall-stoqembed .oembedall-reputation-score{color:#444;font-size:120%;font-weight:700;margin-right:2px}.oembedall-stoqembed .oembedall-user-info{height:35px;width:185px}.oembedall-stoqembed .oembedall-user-info .oembedall-user-gravatar32{float:left;height:32px;width:32px}.oembedall-stoqembed .oembedall-user-info .oembedall-user-details{float:left;margin-left:5px;overflow:hidden;white-space:nowrap;width:145px}.oembedall-stoqembed .oembedall-question-hyperlink{font-weight:700}.oembedall-stoqembed .oembedall-stats{background:#EEE;margin:0 0 0 7px;padding:4px 7px 6px;width:58px}.oembedall-stoqembed .oembedall-statscontainer{float:left;margin-right:8px;width:86px}.oembedall-stoqembed .oembedall-votes{color:#555;padding:0 0 7px;text-align:center}.oembedall-stoqembed .oembedall-vote-count-post{font-size:240%;color:#808185;display:block;font-weight:700}.oembedall-stoqembed .oembedall-views{color:#999;padding-top:4px;text-align:center}.oembedall-stoqembed .oembedall-status{margin-top:-3px;padding:4px 0;text-align:center;background:#75845C;color:#FFF}.oembedall-stoqembed .oembedall-status strong{color:#FFF;display:block;font-size:140%}.oembedall-stoqembed .oembedall-summary{float:left;width:635px}.oembedall-stoqembed .oembedall-excerpt{line-height:1.2;margin:0;padding:0 0 5px}.oembedall-stoqembed .oembedall-tags{float:left;line-height:18px}.oembedall-stoqembed .oembedall-tags a:hover{text-decoration:none}.oembedall-stoqembed .oembedall-post-tag{background-color:#E0EAF1;border-bottom:1px solid #3E6D8E;border-right:1px solid #7F9FB6;color:#3E6D8E;font-size:90%;line-height:2.4;margin:2px 2px 2px 0;padding:3px 4px;text-decoration:none;white-space:nowrap}.oembedall-stoqembed .oembedall-post-tag:hover{background-color:#3E6D8E;border-bottom:1px solid #37607D;border-right:1px solid #37607D;color:#E0EAF1}.oembedall-stoqembed .oembedall-fr{float:right}.oembedall-stoqembed .oembedall-statsarrow{background-image:url(http://cdn.sstatic.net/stackoverflow/img/sprites.png?v=3);background-repeat:no-repeat;overflow:hidden;background-position:0 -435px;float:right;height:13px;margin-top:12px;width:7px}.oembedall-facebook1{border:1px solid #1A3C6C;padding:0;font:13.34px/1.4 verdana;width:500px}.oembedall-facebook2{background-color:#627add}.oembedall-facebook2 a{color:#e8e8e8;text-decoration:none}.oembedall-facebookBody{background-color:#fff;vertical-align:top;padding:5px}.oembedall-facebookBody .contents{display:inline-block;width:100%}.oembedall-facebookBody div img{float:left;margin-right:5px}div.oembedall-lanyard{-webkit-box-shadow:none;-webkit-transition-delay:0s;-webkit-transition-duration:.4000000059604645s;-webkit-transition-property:width;-webkit-transition-timing-function:cubic-bezier(0.42,0,.58,1);background-attachment:scroll;background-clip:border-box;background-color:transparent;background-image:none;background-origin:padding-box;border-width:0;box-shadow:none;color:#112644;display:block;float:left;font-family:'Trebuchet MS',Trebuchet,sans-serif;font-size:16px;height:253px;line-height:19px;margin:0;max-width:none;min-height:0;outline:#112644 0;overflow-x:visible;overflow-y:visible;padding:0;position:relative;text-align:left;vertical-align:baseline;width:804px}div.oembedall-lanyard .tagline{font-size:1.5em}div.oembedall-lanyard .wrapper{overflow:hidden;clear:both}div.oembedall-lanyard .split{float:left;display:inline}div.oembedall-lanyard .prominent-place .flag:active,div.oembedall-lanyard .prominent-place .flag:focus,div.oembedall-lanyard .prominent-place .flag:hover,div.oembedall-lanyard .prominent-place .flag:link,div.oembedall-lanyard .prominent-place .flag:visited{float:left;display:block;width:48px;height:48px;position:relative;top:-5px;margin-right:10px}div.oembedall-lanyard .place-context{font-size:.889em}div.oembedall-lanyard .prominent-place .sub-place{display:block}div.oembedall-lanyard .prominent-place{font-size:1.125em;line-height:1.1em;font-weight:400}div.oembedall-lanyard .main-date{color:#8CB4E0;font-weight:700;line-height:1.1}div.oembedall-lanyard .first{width:48.57%;margin:0 0 0 2.857%}.mermaid .label{color:#333}.node circle,.node polygon,.node rect{fill:#cde498;stroke:#13540c;stroke-width:1px}.edgePath .path{stroke:green;stroke-width:1.5px}.cluster rect{fill:#cdffb2;rx:40;stroke:#6eaa49;stroke-width:1px}.cluster text{fill:#333}.actor{stroke:#13540c;fill:#cde498}text.actor{fill:#000;stroke:none}.actor-line{stroke:grey}.messageLine0{stroke-width:1.5;stroke-dasharray:"2 2";marker-end:"url(#arrowhead)";stroke:#333}.messageLine1{stroke-width:1.5;stroke-dasharray:"2 2";stroke:#333}#arrowhead{fill:#333}#crosshead path{fill:#333!important;stroke:#333!important}.messageText{fill:#333;stroke:none}.labelBox{stroke:#326932;fill:#cde498}.labelText,.loopText{fill:#000;stroke:none}.loopLine{stroke-width:2;stroke-dasharray:"2 2";marker-end:"url(#arrowhead)";stroke:#326932}.note{stroke:#6eaa49;fill:#fff5ad}.noteText{fill:#000;stroke:none;font-family:'trebuchet ms',verdana,arial;font-size:14px}.section{stroke:none;opacity:.2}.section0,.section2{fill:#6eaa49}.section1,.section3{fill:#fff;opacity:.2}.sectionTitle0,.sectionTitle1,.sectionTitle2,.sectionTitle3{fill:#333}.sectionTitle{text-anchor:start;font-size:11px;text-height:14px}.grid .tick{stroke:lightgrey;opacity:.3;shape-rendering:crispEdges}.grid path{stroke-width:0}.today{fill:none;stroke:red;stroke-width:2px}.task{stroke-width:2}.taskText{text-anchor:middle;font-size:11px}.taskTextOutsideRight{fill:#000;text-anchor:start;font-size:11px}.taskTextOutsideLeft{fill:#000;text-anchor:end;font-size:11px}.taskText0,.taskText1,.taskText2,.taskText3{fill:#fff}.task0,.task1,.task2,.task3{fill:#487e3a;stroke:#13540c}.taskTextOutside0,.taskTextOutside1,.taskTextOutside2,.taskTextOutside3{fill:#000}.active0,.active1,.active2,.active3{fill:#cde498;stroke:#13540c}.activeText0,.activeText1,.activeText2,.activeText3{fill:#000!important}.done0,.done1,.done2,.done3{stroke:grey;fill:lightgrey;stroke-width:2}.doneText0,.doneText1,.doneText2,.doneText3{fill:#000!important}.crit0,.crit1,.crit2,.crit3{stroke:#f88;fill:red;stroke-width:2}.activeCrit0,.activeCrit1,.activeCrit2,.activeCrit3{stroke:#f88;fill:#cde498;stroke-width:2}.doneCrit0,.doneCrit1,.doneCrit2,.doneCrit3{stroke:#f88;fill:lightgrey;stroke-width:2;cursor:pointer;shape-rendering:crispEdges}.activeCritText0,.activeCritText1,.activeCritText2,.activeCritText3,.doneCritText0,.doneCritText1,.doneCritText2,.doneCritText3{fill:#000!important}.titleText{text-anchor:middle;font-size:18px;fill:#000}text{font-family:'trebuchet ms',verdana,arial;font-size:14px}html{height:100%}body{margin:0!important;padding:5px 20px 26px!important;background-color:#fff;font-family:"Lucida Grande","Segoe UI","Apple SD Gothic Neo","Malgun Gothic","Lucida Sans Unicode",Helvetica,Arial,sans-serif;font-size:.9em;overflow-x:hidden;overflow-y:auto}br,h1,h2,h3,h4,h5,h6{clear:both}hr.page{background:url(data:image/png;base64,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) repeat-x;border:0;height:3px;padding:0}hr.underscore{border-top-style:dashed!important}body >:first-child{margin-top:0!important}img.plugin{box-shadow:0 1px 3px rgba(0,0,0,.1);border-radius:3px}iframe{border:0}figure{-webkit-margin-before:0;-webkit-margin-after:0;-webkit-margin-start:0;-webkit-margin-end:0}kbd{border:1px solid #aaa;-moz-border-radius:2px;-webkit-border-radius:2px;border-radius:2px;-moz-box-shadow:1px 2px 2px #ddd;-webkit-box-shadow:1px 2px 2px #ddd;box-shadow:1px 2px 2px #ddd;background-color:#f9f9f9;background-image:-moz-linear-gradient(top,#eee,#f9f9f9,#eee);background-image:-o-linear-gradient(top,#eee,#f9f9f9,#eee);background-image:-webkit-linear-gradient(top,#eee,#f9f9f9,#eee);background-image:linear-gradient(top,#eee,#f9f9f9,#eee);padding:1px 3px;font-family:inherit;font-size:.85em}.oembeded .oembed_photo{display:inline-block}img[data-echo]{margin:25px 0;width:100px;height:100px;background:url(../img/ajax.gif) center center no-repeat #fff}.spinner{display:inline-block;width:10px;height:10px;margin-bottom:-.1em;border:2px solid rgba(0,0,0,.5);border-top-color:transparent;border-radius:100%;-webkit-animation:spin 1s infinite linear;animation:spin 1s infinite linear}.spinner:after{content:'';display:block;width:0;height:0;position:absolute;top:-6px;left:0;border:4px solid transparent;border-bottom-color:rgba(0,0,0,.5);-webkit-transform:rotate(45deg);transform:rotate(45deg)}@-webkit-keyframes spin{to{-webkit-transform:rotate(360deg)}}@keyframes spin{to{transform:rotate(360deg)}}p.toc{margin:0!important}p.toc ul{padding-left:10px}p.toc>ul{padding:10px;margin:0 10px;display:inline-block;border:1px solid #ededed;border-radius:5px}p.toc li,p.toc ul{list-style-type:none}p.toc li{width:100%;padding:0;overflow:hidden}p.toc li a::after{content:"."}p.toc li a:before{content:"• "}p.toc h5{text-transform:uppercase}p.toc .title{float:left;padding-right:3px}p.toc .number{margin:0;float:right;padding-left:3px;background:#fff;display:none}input.task-list-item{margin-left:-1.62em}.markdown{font-family:"Hiragino Sans GB","Microsoft YaHei",STHeiti,SimSun,"Lucida Grande","Lucida Sans Unicode","Lucida Sans",'Segoe UI',AppleSDGothicNeo-Medium,'Malgun Gothic',Verdana,Tahoma,sans-serif;padding:20px}.markdown a{text-decoration:none;vertical-align:baseline}.markdown a:hover{text-decoration:underline}.markdown h1{font-size:2.2em;font-weight:700;margin:1.5em 0 1em}.markdown h2{font-size:1.8em;font-weight:700;margin:1.275em 0 .85em}.markdown h3{font-size:1.6em;font-weight:700;margin:1.125em 0 .75em}.markdown h4{font-size:1.4em;font-weight:700;margin:.99em 0 .66em}.markdown h5{font-size:1.2em;font-weight:700;margin:.855em 0 .57em}.markdown h6{font-size:1em;font-weight:700;margin:.75em 0 .5em}.markdown h1+p,.markdown h1:first-child,.markdown h2+p,.markdown h2:first-child,.markdown h3+p,.markdown h3:first-child,.markdown h4+p,.markdown h4:first-child,.markdown h5+p,.markdown h5:first-child,.markdown h6+p,.markdown h6:first-child{margin-top:0}.markdown hr{border:1px solid #ccc}.markdown p{margin:1em 0;word-wrap:break-word}.markdown ol{list-style-type:decimal}.markdown li{display:list-item;line-height:1.4em}.markdown blockquote{margin:1em 20px}.markdown blockquote>:first-child{margin-top:0}.markdown blockquote>:last-child{margin-bottom:0}.markdown blockquote cite:before{content:'\2014 \00A0'}.markdown .code{border-radius:3px;word-wrap:break-word}.markdown pre{border-radius:3px;word-wrap:break-word;border:1px solid #ccc;overflow:auto;padding:.5em}.markdown pre code{border:0;display:block}.markdown pre>code{font-family:Consolas,Inconsolata,Courier,monospace;font-weight:700;white-space:pre;margin:0}.markdown code{border-radius:3px;word-wrap:break-word;border:1px solid #ccc;padding:0 5px;margin:0 2px}.markdown img{max-width:100%}.markdown mark{color:#000;background-color:#fcf8e3}.markdown table{padding:0;border-collapse:collapse;border-spacing:0;margin-bottom:16px}.markdown table tr td,.markdown table tr th{border:1px solid #ccc;margin:0;padding:6px 13px}.markdown table tr th{font-weight:700}.markdown table tr th>:first-child{margin-top:0}.markdown table tr th>:last-child{margin-bottom:0}.markdown table tr td>:first-child{margin-top:0}.markdown table tr td>:last-child{margin-bottom:0}@import url(http://fonts.googleapis.com/css?family=Roboto+Condensed:300italic,400italic,700italic,400,300,700);.haroopad{padding:20px;color:#222;font-size:15px;font-family:"Roboto Condensed",Tauri,"Hiragino Sans GB","Microsoft YaHei",STHeiti,SimSun,"Lucida Grande","Lucida Sans Unicode","Lucida Sans",'Segoe UI',AppleSDGothicNeo-Medium,'Malgun Gothic',Verdana,Tahoma,sans-serif;background:#fff;line-height:1.6;-webkit-font-smoothing:antialiased}.haroopad a{color:#3269a0}.haroopad a:hover{color:#4183c4}.haroopad h2{border-bottom:1px solid #e6e6e6}.haroopad h6{color:#777}.haroopad hr{border:1px solid #e6e6e6}.haroopad blockquote>code,.haroopad h1>code,.haroopad h2>code,.haroopad h3>code,.haroopad h4>code,.haroopad h5>code,.haroopad h6>code,.haroopad li>code,.haroopad p>code,.haroopad td>code{font-family:Consolas,"Liberation Mono",Menlo,Courier,monospace;font-size:85%;background-color:rgba(0,0,0,.02);padding:.2em .5em;border:1px solid #efefef}.haroopad pre>code{font-size:1em;letter-spacing:-1px;font-weight:700}.haroopad blockquote{border-left:4px solid #e6e6e6;padding:0 15px;color:#777}.haroopad table{background-color:#fafafa}.haroopad table tr td,.haroopad table tr th{border:1px solid #e6e6e6}.haroopad table tr:nth-child(2n){background-color:#f2f2f2}.hljs{display:block;overflow-x:auto;padding:.5em;background:#282b2e;-webkit-text-size-adjust:none}.css .hljs-id,.hljs-change,.hljs-flow,.hljs-keyword,.hljs-literal,.hljs-winutils,.nginx .hljs-title,.tex .hljs-special{color:#93c763}.hljs-number{color:#ffcd22}.hljs{color:#e0e2e4}.css .hljs-pseudo,.css .hljs-tag{color:#d0d2b5}.hljs .hljs-constant,.hljs-attribute{color:#668bb0}.xml .hljs-attribute{color:#b3b689}.xml .hljs-tag .hljs-value{color:#e8e2b7}.hljs-class .hljs-title,.hljs-code,.hljs-header{color:#fff}.hljs-class,.hljs-hexcolor{color:#93c763}.hljs-regexp{color:#d39745}.hljs-at_rule,.hljs-at_rule .hljs-keyword{color:#a082bd}.hljs-doctype{color:#557182}.apache .hljs-cbracket,.apache .hljs-tag,.django .hljs-filter .hljs-argument,.django .hljs-template_tag,.django .hljs-variable,.hljs-addition,.hljs-attr_selector,.hljs-built_in,.hljs-bullet,.hljs-emphasis,.hljs-envvar,.hljs-javadoc,.hljs-link_url,.hljs-pragma,.hljs-preprocessor,.hljs-prompt,.hljs-pseudo,.hljs-stream,.hljs-subst,.hljs-tag,.hljs-tag .hljs-title,.hljs-type,.ruby .hljs-class .hljs-parent,.smalltalk .hljs-array,.smalltalk .hljs-class,.smalltalk .hljs-localvars,.tex .hljs-command{color:#8cbbad}.hljs-string{color:#ec7600}.apache .hljs-sqbracket,.hljs-annotation,.hljs-blockquote,.hljs-comment,.hljs-decorator,.hljs-deletion,.hljs-horizontal_rule,.hljs-pi,.hljs-shebang,.tex .hljs-formula{color:#818e96}.apache .hljs-tag,.bash .hljs-variable,.css .hljs-id,.diff .hljs-header,.hljs-at_rule .hljs-keyword,.hljs-chunk,.hljs-dartdoc,.hljs-header,.hljs-keyword,.hljs-literal,.hljs-phpdoc,.hljs-request,.hljs-status,.hljs-title,.hljs-type,.hljs-winutils,.rsl .hljs-built_in,.smalltalk .hljs-class,.tex .hljs-special,.vbscript .hljs-built_in{font-weight:700}.coffeescript .javascript,.javascript .xml,.tex .hljs-formula,.xml .css,.xml .hljs-cdata,.xml .javascript,.xml .vbscript{opacity:.5}.MathJax_Hover_Frame{border-radius:.25em;-webkit-border-radius:.25em;-moz-border-radius:.25em;-khtml-border-radius:.25em;box-shadow:0 0 15px #83A;-webkit-box-shadow:0 0 15px #83A;-moz-box-shadow:0 0 15px #83A;-khtml-box-shadow:0 0 15px #83A;border:1px solid #A6D!important;display:inline-block;position:absolute}.MathJax_Hover_Arrow{position:absolute;width:15px;height:11px;cursor:pointer}#MathJax_About{position:fixed;left:50%;width:auto;text-align:center;border:3px outset;padding:1em 2em;background-color:#DDD;color:#000;cursor:default;font-family:message-box;font-size:120%;font-style:normal;text-indent:0;text-transform:none;line-height:normal;letter-spacing:normal;word-spacing:normal;word-wrap:normal;white-space:nowrap;float:none;z-index:201;border-radius:15px;-webkit-border-radius:15px;-moz-border-radius:15px;-khtml-border-radius:15px;box-shadow:0 10px 20px gray;-webkit-box-shadow:0 10px 20px gray;-moz-box-shadow:0 10px 20px gray;-khtml-box-shadow:0 10px 20px gray;filter:progid:DXImageTransform.Microsoft.dropshadow(OffX=2, OffY=2, Color='gray', Positive='true')}.MathJax_Menu{position:absolute;background-color:#fff;color:#000;width:auto;padding:5px 0;border:1px solid #CCC;margin:0;cursor:default;font:menu;text-align:left;text-indent:0;text-transform:none;line-height:normal;letter-spacing:normal;word-spacing:normal;word-wrap:normal;white-space:nowrap;float:none;z-index:201;border-radius:5px;-webkit-border-radius:5px;-moz-border-radius:5px;-khtml-border-radius:5px;box-shadow:0 10px 20px gray;-webkit-box-shadow:0 10px 20px gray;-moz-box-shadow:0 10px 20px gray;-khtml-box-shadow:0 10px 20px gray;filter:progid:DXImageTransform.Microsoft.dropshadow(OffX=2, OffY=2, Color='gray', Positive='true')}.MathJax_MenuItem{padding:1px 2em;background:0 0}.MathJax_MenuArrow{position:absolute;right:.5em;color:#666}.MathJax_MenuActive .MathJax_MenuArrow{color:#fff}.MathJax_MenuArrow.RTL{left:.5em;right:auto}.MathJax_MenuCheck{position:absolute;left:.7em}.MathJax_MenuCheck.RTL{right:.7em;left:auto}.MathJax_MenuRadioCheck{position:absolute;left:.7em}.MathJax_MenuRadioCheck.RTL{right:.7em;left:auto}.MathJax_MenuLabel{padding:1px 2em 3px 1.33em;font-style:italic}.MathJax_MenuRule{border-top:1px solid #DDD;margin:4px 3px}.MathJax_MenuDisabled{color:GrayText}.MathJax_MenuActive{background-color:#606872;color:#fff}.MathJax_Menu_Close{position:absolute;width:31px;height:31px;top:-15px;left:-15px}#MathJax_Zoom{position:absolute;background-color:#F0F0F0;overflow:auto;display:block;z-index:301;padding:.5em;border:1px solid #000;margin:0;font-weight:400;font-style:normal;text-align:left;text-indent:0;text-transform:none;line-height:normal;letter-spacing:normal;word-spacing:normal;word-wrap:normal;white-space:nowrap;float:none;box-shadow:5px 5px 15px #AAA;-webkit-box-shadow:5px 5px 15px #AAA;-moz-box-shadow:5px 5px 15px #AAA;-khtml-box-shadow:5px 5px 15px #AAA;filter:progid:DXImageTransform.Microsoft.dropshadow(OffX=2, OffY=2, Color='gray', Positive='true')}#MathJax_ZoomOverlay{position:absolute;left:0;top:0;z-index:300;display:inline-block;width:100%;height:100%;border:0;padding:0;margin:0;background-color:#fff;opacity:0;filter:alpha(opacity=0)}#MathJax_ZoomFrame{position:relative;display:inline-block;height:0;width:0}#MathJax_ZoomEventTrap{position:absolute;left:0;top:0;z-index:302;display:inline-block;border:0;padding:0;margin:0;background-color:#fff;opacity:0;filter:alpha(opacity=0)}.MathJax_Preview{color:#888}#MathJax_Message{position:fixed;left:1px;bottom:2px;background-color:#E6E6E6;border:1px solid #959595;margin:0;padding:2px 8px;z-index:102;color:#000;font-size:80%;width:auto;white-space:nowrap}#MathJax_MSIE_Frame{position:absolute;top:0;left:0;width:0;z-index:101;border:0;margin:0;padding:0}.MathJax_Error{color:#C00;font-style:italic}footer{position:fixed;font-size:.8em;text-align:right;bottom:0;margin-left:-25px;height:20px;width:100%}</style>
</head>
<body class="markdown haroopad">
<h1 id="scalfmm-with-starpu+cuda"><a name="scalfmm-with-starpu+cuda" href="#scalfmm-with-starpu+cuda"></a>ScalFMM with StarPU+CUDA</h1><p>In this tutorial, we provide the commands to install ScalFMM and the needed tools in order to compute parallel efficiencies.<br>We first show how to obtain the homogeneous efficencies and then the heterogeneous ones (not done yet).</p><h2 id="installing-the-libraries"><a name="installing-the-libraries" href="#installing-the-libraries"></a>Installing the libraries</h2><p>For some installation steps, we provide a “valid-if” test which shows if the previous command has been done correctly or not.<br>In case of success <code>STEP-OK</code> will be print-out.<br>In addition, if a library is already installed on the system, it is possible to set the output variables directly and test with the “valid-if” command if it will work.</p><p>It is possible to follow these steps only to compile ScalFMM above StarPU and so we marked the installation of execution-trace tools as <strong>Optional</strong>.<br>However, we higly recommended to install them and to follow all the steps since they let have the efficiencies.<br>But if one wants to execute without any overhead, it might need to remove the usage of FXT.</p><h3 id="pre-requiste:"><a name="pre-requiste:" href="#pre-requiste:"></a>Pre-requiste:</h3><p>In order to follow this tutorial, it is needed to have the following applications installed:</p><ul>
<li>autoconf (&gt;= 2.69)</li><li>gawk (Awk &gt;= 4.0.1)</li><li>make (&gt;= 3.81) </li><li>cmake (&gt;= 3.2.2)</li><li>gcc/g<ins> (&gt;= 4.9) and the gcc/g</ins> names should point to the correct binaries</li><li>BLAS/LAPACK (The configure of ScalFMM is different if the MKL is used or not, but with the MKL it is recommended to set environment variable <code>MKLROOT</code>)</li><li>CUDA (&gt;= 7) and <code>CUDA_PATH</code> must be set. In our case, <code>CUDA_PATH=/usr/local/cuda-7.5/</code></li><li><strong>Optional</strong> Vite (from <code>sudo apt-get install vite</code> or see <a href="http://vite.gforge.inria.fr/download.php"></a><a href="http://vite.gforge.inria.fr/download.php">http://vite.gforge.inria.fr/download.php</a>)</li><li><strong>Optional</strong> Qt5 library to be able to change the colors of the execution traces in order to visualize the different FMM operators</li><li>gnuplot to generate the figures</li></ul><blockquote>
<p>[Remark] Some installations of CUDA does not have libcuda file.<br>In this case, one needs to create a link : <code>sudo ln /usr/local/cuda-7.5/lib64/libcudart.so /usr/local/cuda-7.5/lib64/libcuda.so</code></p>
<p>[Plafrim-Developers] </p>
<p>For those who use this tutorial on Plafrim (or a similar cluster), we provide extra informations.</p>
<p>To allocate an heterogeneous node : <code>salloc -N 1 --time=03:00:00 --exclusive -p court_sirocco -CHaswell --gres=gpu:4 -x sirocco06</code></p>
<p>Then, find it using <code>squeue</code> and access it by <code>ssh</code>.</p>
<p>We have run this tutorial with the modules : <code>module load compiler/gcc/4.9.2 cuda75/toolkit/7.5.18 intel/mkl/64/11.2/2016.0.0 build/cmake/3.2.1</code></p>
</blockquote><h3 id="working-directory"><a name="working-directory" href="#working-directory"></a>Working directory</h3><p>The variable <code>SCALFMM_TEST_DIR</code> is used to specify the working directory where all the tools are going to be installed:</p><pre class="bash hljs"><code class="bash" data-origin="<pre><code class=&quot;bash&quot;>export SCALFMM_TEST_DIR=~/scalfmm_test
cd $SCALFMM_TEST_DIR
</code></pre>"><span class="hljs-built_in">export</span> SCALFMM_TEST_DIR=~/scalfmm_<span class="hljs-built_in">test</span>
<span class="hljs-built_in">cd</span> <span class="hljs-variable">$SCALFMM_TEST_DIR</span>
</code></pre><p>In order to be able to stop the tutorial in the middle and restart later, we will register the variables in a file that should be source to restart later:</p><pre class="bash hljs"><code class="bash" data-origin="<pre><code class=&quot;bash&quot;># function scalfmmRegisterVariable() { echo &quot;export $1=${!1}&quot; &amp;gt;&amp;gt; &quot;$SCALFMM_TEST_DIR/environment.source&quot;; }
echo &quot;function scalfmmRegisterVariable() { echo \&quot;export \$1=\${!1}\&quot; &amp;gt;&amp;gt; \&quot;$SCALFMM_TEST_DIR/environment.source\&quot;; }&quot; &amp;gt; &quot;$SCALFMM_TEST_DIR/environment.source&quot;
source &quot;$SCALFMM_TEST_DIR/environment.source&quot;
</code></pre>"><span class="hljs-comment"># function scalfmmRegisterVariable() { echo "export $1=${!1}" &gt;&gt; "$SCALFMM_TEST_DIR/environment.source"; }</span>
<span class="hljs-built_in">echo</span> <span class="hljs-string">"function scalfmmRegisterVariable() { echo \"export \$1=\${!1}\" &gt;&gt; \"<span class="hljs-variable">$SCALFMM_TEST_DIR</span>/environment.source\"; }"</span> &gt; <span class="hljs-string">"<span class="hljs-variable">$SCALFMM_TEST_DIR</span>/environment.source"</span>
<span class="hljs-built_in">source</span> <span class="hljs-string">"<span class="hljs-variable">$SCALFMM_TEST_DIR</span>/environment.source"</span>
</code></pre><p><em>Output variables:</em> <code>scalfmmRegisterVariable SCALFMM_TEST_DIR</code></p><p>Valid-if</p><pre class="bash hljs"><code class="bash" data-origin="<pre><code class=&quot;bash&quot;>if [[ -n $SCALFMM_TEST_DIR ]] &amp;amp;&amp;amp; [[ -d $SCALFMM_TEST_DIR ]] ; then
echo “STEP-OK”
fi
</code></pre>"><span class="hljs-keyword">if</span> [[ -n <span class="hljs-variable">$SCALFMM_TEST_DIR</span> ]] &amp;&amp; [[ <span class="hljs-operator">-d</span> <span class="hljs-variable">$SCALFMM_TEST_DIR</span> ]] ; <span class="hljs-keyword">then</span>
<span class="hljs-built_in">echo</span> “STEP-OK”
<span class="hljs-keyword">fi</span>
</code></pre><ul>
<li>Restarting the tutorial</li></ul><p>To restart the tutorial, one needs to re-define the working directory and to source the save file before to resume:</p><pre class="bash hljs"><code class="bash" data-origin="<pre><code class=&quot;bash&quot;>export SCALFMM_TEST_DIR=~/scalfmm_test
if [[ ! -d $SCALFMM_TEST_DIR ]] ; then
mkdir $SCALFMM_TEST_DIR
else
source &quot;$SCALFMM_TEST_DIR/environment.source&quot;
fi
cd $SCALFMM_TEST_DIR
</code></pre>"><span class="hljs-built_in">export</span> SCALFMM_TEST_DIR=~/scalfmm_<span class="hljs-built_in">test</span>
<span class="hljs-keyword">if</span> [[ ! <span class="hljs-operator">-d</span> <span class="hljs-variable">$SCALFMM_TEST_DIR</span> ]] ; <span class="hljs-keyword">then</span>
mkdir <span class="hljs-variable">$SCALFMM_TEST_DIR</span>
<span class="hljs-keyword">else</span>
<span class="hljs-built_in">source</span> <span class="hljs-string">"<span class="hljs-variable">$SCALFMM_TEST_DIR</span>/environment.source"</span>
<span class="hljs-keyword">fi</span>
<span class="hljs-built_in">cd</span> <span class="hljs-variable">$SCALFMM_TEST_DIR</span>
</code></pre><h3 id="downloading-the-packages-(in-advance)"><a name="downloading-the-packages-(in-advance)" href="#downloading-the-packages-(in-advance)"></a>Downloading the Packages (in Advance)</h3><p>If the computational node does not have access to internet, we provide a command to download the needed packages (otherwise the next commands still include just in time download):</p><pre class="bash hljs"><code class="bash" data-origin="<pre><code class=&quot;bash&quot;>cd $SCALFMM_TEST_DIR
wget https://www.open-mpi.org/software/hwloc/v1.11/downloads/hwloc-1.11.2.tar.gz
wget http://download.savannah.gnu.org/releases/fkt/fxt-0.2.11.tar.gz # Optional
wget http://www.fftw.org/fftw-3.3.4.tar.gz
svn export svn://scm.gforge.inria.fr/svnroot/starpu/trunk starpu
git clone --depth=1 https://scm.gforge.inria.fr/anonscm/git/scalfmm-public/scalfmm-public.git
</code></pre>"><span class="hljs-built_in">cd</span> <span class="hljs-variable">$SCALFMM_TEST_DIR</span>
wget https://www.open-mpi.org/software/hwloc/v1.<span class="hljs-number">11</span>/downloads/hwloc-<span class="hljs-number">1.11</span>.<span class="hljs-number">2</span>.tar.gz
wget http://download.savannah.gnu.org/releases/fkt/fxt-<span class="hljs-number">0.2</span>.<span class="hljs-number">11</span>.tar.gz <span class="hljs-comment"># Optional</span>
wget http://www.fftw.org/fftw-<span class="hljs-number">3.3</span>.<span class="hljs-number">4</span>.tar.gz
svn <span class="hljs-built_in">export</span> svn://scm.gforge.inria.fr/svnroot/starpu/trunk starpu
git <span class="hljs-built_in">clone</span> --depth=<span class="hljs-number">1</span> https://scm.gforge.inria.fr/anonscm/git/scalfmm-public/scalfmm-public.git
</code></pre><h3 id="hwloc"><a name="hwloc" href="#hwloc"></a>HWLOC</h3><pre class="bash hljs"><code class="bash" data-origin="<pre><code class=&quot;bash&quot;>cd $SCALFMM_TEST_DIR
if [[ ! -f hwloc-1.11.2.tar.gz ]] ; then
wget https://www.open-mpi.org/software/hwloc/v1.11/downloads/hwloc-1.11.2.tar.gz
fi
tar xvf hwloc-1.11.2.tar.gz
cd hwloc-1.11.2/
export SCALFMM_HWLOC_DIR=$SCALFMM_TEST_DIR/hwlocinstall
./configure --prefix=$SCALFMM_HWLOC_DIR
make install
</code></pre>"><span class="hljs-built_in">cd</span> <span class="hljs-variable">$SCALFMM_TEST_DIR</span>
<span class="hljs-keyword">if</span> [[ ! <span class="hljs-operator">-f</span> hwloc-<span class="hljs-number">1.11</span>.<span class="hljs-number">2</span>.tar.gz ]] ; <span class="hljs-keyword">then</span>
wget https://www.open-mpi.org/software/hwloc/v1.<span class="hljs-number">11</span>/downloads/hwloc-<span class="hljs-number">1.11</span>.<span class="hljs-number">2</span>.tar.gz
<span class="hljs-keyword">fi</span>
tar xvf hwloc-<span class="hljs-number">1.11</span>.<span class="hljs-number">2</span>.tar.gz
<span class="hljs-built_in">cd</span> hwloc-<span class="hljs-number">1.11</span>.<span class="hljs-number">2</span>/
<span class="hljs-built_in">export</span> SCALFMM_HWLOC_DIR=<span class="hljs-variable">$SCALFMM_TEST_DIR</span>/hwlocinstall
./configure --prefix=<span class="hljs-variable">$SCALFMM_HWLOC_DIR</span>
make install
</code></pre><p><em>Output variables:</em> <code>scalfmmRegisterVariable SCALFMM_HWLOC_DIR</code></p><p>Valid-if:</p><pre class="bash hljs"><code class="bash" data-origin="<pre><code class=&quot;bash&quot;>if [[ -n $SCALFMM_HWLOC_DIR ]] &amp;amp;&amp;amp; [[ -d $SCALFMM_HWLOC_DIR/lib/ ]] &amp;amp;&amp;amp; [[ -f $SCALFMM_HWLOC_DIR/lib/libhwloc.so ]]; then
echo &quot;STEP-OK&quot;
fi
</code></pre>"><span class="hljs-keyword">if</span> [[ -n <span class="hljs-variable">$SCALFMM_HWLOC_DIR</span> ]] &amp;&amp; [[ <span class="hljs-operator">-d</span> <span class="hljs-variable">$SCALFMM_HWLOC_DIR</span>/lib/ ]] &amp;&amp; [[ <span class="hljs-operator">-f</span> <span class="hljs-variable">$SCALFMM_HWLOC_DIR</span>/lib/libhwloc.so ]]; <span class="hljs-keyword">then</span>
<span class="hljs-built_in">echo</span> <span class="hljs-string">"STEP-OK"</span>
<span class="hljs-keyword">fi</span>
</code></pre><h3 id="fxt-(__optional__)"><a name="fxt-(__optional__)" href="#fxt-(__optional__)"></a>FXT (<strong>Optional</strong>)</h3><pre class="bash hljs"><code class="bash" data-origin="<pre><code class=&quot;bash&quot;>cd $SCALFMM_TEST_DIR
if [[ ! -f fxt-0.2.11.tar.gz ]] ; then
wget http://download.savannah.gnu.org/releases/fkt/fxt-0.2.11.tar.gz
fi
tar xvf fxt-0.2.11.tar.gz
cd fxt-0.2.11/
export SCALFMM_FXT_DIR=$SCALFMM_TEST_DIR/fxtinstall
./configure --prefix=$SCALFMM_FXT_DIR
make install
</code></pre>"><span class="hljs-built_in">cd</span> <span class="hljs-variable">$SCALFMM_TEST_DIR</span>
<span class="hljs-keyword">if</span> [[ ! <span class="hljs-operator">-f</span> fxt-<span class="hljs-number">0.2</span>.<span class="hljs-number">11</span>.tar.gz ]] ; <span class="hljs-keyword">then</span>
wget http://download.savannah.gnu.org/releases/fkt/fxt-<span class="hljs-number">0.2</span>.<span class="hljs-number">11</span>.tar.gz
<span class="hljs-keyword">fi</span>
tar xvf fxt-<span class="hljs-number">0.2</span>.<span class="hljs-number">11</span>.tar.gz
<span class="hljs-built_in">cd</span> fxt-<span class="hljs-number">0.2</span>.<span class="hljs-number">11</span>/
<span class="hljs-built_in">export</span> SCALFMM_FXT_DIR=<span class="hljs-variable">$SCALFMM_TEST_DIR</span>/fxtinstall
./configure --prefix=<span class="hljs-variable">$SCALFMM_FXT_DIR</span>
make install
</code></pre><p><em>Output variables:</em> <code>scalfmmRegisterVariable SCALFMM_FXT_DIR</code></p><p>Valid-if:</p><pre class="bash hljs"><code class="bash" data-origin="<pre><code class=&quot;bash&quot;>if [[ -n $SCALFMM_FXT_DIR ]] &amp;amp;&amp;amp; [[ -d $SCALFMM_FXT_DIR/lib/ ]] &amp;amp;&amp;amp; [[ -f $SCALFMM_FXT_DIR/lib/libfxt.so ]]; then
echo &quot;STEP-OK&quot;
fi
</code></pre>"><span class="hljs-keyword">if</span> [[ -n <span class="hljs-variable">$SCALFMM_FXT_DIR</span> ]] &amp;&amp; [[ <span class="hljs-operator">-d</span> <span class="hljs-variable">$SCALFMM_FXT_DIR</span>/lib/ ]] &amp;&amp; [[ <span class="hljs-operator">-f</span> <span class="hljs-variable">$SCALFMM_FXT_DIR</span>/lib/libfxt.so ]]; <span class="hljs-keyword">then</span>
<span class="hljs-built_in">echo</span> <span class="hljs-string">"STEP-OK"</span>
<span class="hljs-keyword">fi</span>
</code></pre><h3 id="fftw-(if-no-mkl-fft)"><a name="fftw-(if-no-mkl-fft)" href="#fftw-(if-no-mkl-fft)"></a>FFTW (If No MKL-FFT)</h3><p>For those who do not use MKL FFT interface, they have to install FFTW (float/double):</p><pre class="bash hljs"><code class="bash" data-origin="<pre><code class=&quot;bash&quot;>cd $SCALFMM_TEST_DIR
if [[ ! -f fftw-3.3.4.tar.gz ]] ; then
wget http://www.fftw.org/fftw-3.3.4.tar.gz
fi
tar xvf fftw-3.3.4.tar.gz
cd fftw-3.3.4/
export SCALFMM_FFTW_DIR=$SCALFMM_TEST_DIR/fftinstall
./configure --prefix=$SCALFMM_FFTW_DIR
make install
./configure --prefix=$SCALFMM_FFTW_DIR --enable-float
make install
</code></pre>"><span class="hljs-built_in">cd</span> <span class="hljs-variable">$SCALFMM_TEST_DIR</span>
<span class="hljs-keyword">if</span> [[ ! <span class="hljs-operator">-f</span> fftw-<span class="hljs-number">3.3</span>.<span class="hljs-number">4</span>.tar.gz ]] ; <span class="hljs-keyword">then</span>
wget http://www.fftw.org/fftw-<span class="hljs-number">3.3</span>.<span class="hljs-number">4</span>.tar.gz
<span class="hljs-keyword">fi</span>
tar xvf fftw-<span class="hljs-number">3.3</span>.<span class="hljs-number">4</span>.tar.gz
<span class="hljs-built_in">cd</span> fftw-<span class="hljs-number">3.3</span>.<span class="hljs-number">4</span>/
<span class="hljs-built_in">export</span> SCALFMM_FFTW_DIR=<span class="hljs-variable">$SCALFMM_TEST_DIR</span>/fftinstall
./configure --prefix=<span class="hljs-variable">$SCALFMM_FFTW_DIR</span>
make install
./configure --prefix=<span class="hljs-variable">$SCALFMM_FFTW_DIR</span> --enable-float
make install
</code></pre><p><em>Output variables:</em> <code>scalfmmRegisterVariable SCALFMM_FFTW_DIR</code></p><p>Valid-if:</p><pre class="bash hljs"><code class="bash" data-origin="<pre><code class=&quot;bash&quot;>if [[ -n $SCALFMM_FFTW_DIR ]] &amp;amp;&amp;amp; [[ -d $SCALFMM_FFTW_DIR/lib/ ]] &amp;amp;&amp;amp; [[ -f $SCALFMM_FFTW_DIR/lib/libfftw3.a ]] &amp;amp;&amp;amp; [[ -f $SCALFMM_FFTW_DIR/lib/libfftw3f.a ]]; then
echo &quot;STEP-OK&quot;
fi
</code></pre>"><span class="hljs-keyword">if</span> [[ -n <span class="hljs-variable">$SCALFMM_FFTW_DIR</span> ]] &amp;&amp; [[ <span class="hljs-operator">-d</span> <span class="hljs-variable">$SCALFMM_FFTW_DIR</span>/lib/ ]] &amp;&amp; [[ <span class="hljs-operator">-f</span> <span class="hljs-variable">$SCALFMM_FFTW_DIR</span>/lib/libfftw3.a ]] &amp;&amp; [[ <span class="hljs-operator">-f</span> <span class="hljs-variable">$SCALFMM_FFTW_DIR</span>/lib/libfftw3f.a ]]; <span class="hljs-keyword">then</span>
<span class="hljs-built_in">echo</span> <span class="hljs-string">"STEP-OK"</span>
<span class="hljs-keyword">fi</span>
</code></pre><h3 id="starpu"><a name="starpu" href="#starpu"></a>StarPU</h3><pre class="bash hljs"><code class="bash" data-origin="<pre><code class=&quot;bash&quot;>cd $SCALFMM_TEST_DIR
if [[ ! -d starpu ]] ; then
svn export svn://scm.gforge.inria.fr/svnroot/starpu/trunk starpu
fi
cd starpu/
export SCALFMM_STARPU_DIR=$SCALFMM_TEST_DIR/starpuinstall
./autogen.sh
./configure --prefix=$SCALFMM_STARPU_DIR --with-fxt=$SCALFMM_FXT_DIR --with-hwloc=$SCALFMM_HWLOC_DIR --with-cuda-dir=$CUDA_PATH --disable-opencl
make install
</code></pre>"><span class="hljs-built_in">cd</span> <span class="hljs-variable">$SCALFMM_TEST_DIR</span>
<span class="hljs-keyword">if</span> [[ ! <span class="hljs-operator">-d</span> starpu ]] ; <span class="hljs-keyword">then</span>
svn <span class="hljs-built_in">export</span> svn://scm.gforge.inria.fr/svnroot/starpu/trunk starpu
<span class="hljs-keyword">fi</span>
<span class="hljs-built_in">cd</span> starpu/
<span class="hljs-built_in">export</span> SCALFMM_STARPU_DIR=<span class="hljs-variable">$SCALFMM_TEST_DIR</span>/starpuinstall
./autogen.sh
./configure --prefix=<span class="hljs-variable">$SCALFMM_STARPU_DIR</span> --with-fxt=<span class="hljs-variable">$SCALFMM_FXT_DIR</span> --with-hwloc=<span class="hljs-variable">$SCALFMM_HWLOC_DIR</span> --with-cuda-dir=<span class="hljs-variable">$CUDA_PATH</span> --disable-opencl
make install
</code></pre><blockquote>
<p><strong>Optional</strong> In case you do not want to use trace (FXT) please remove the <code>--with-fxt=$SCALFMM_FXT_DIR</code> parameter from the command</p>
</blockquote><p><em>Output variables:</em> <code>scalfmmRegisterVariable SCALFMM_STARPU_DIR</code></p><p>Valid-if:</p><pre class="bash hljs"><code class="bash" data-origin="<pre><code class=&quot;bash&quot;>if [[ -n $SCALFMM_STARPU_DIR ]] &amp;amp;&amp;amp; [[ -d $SCALFMM_STARPU_DIR/lib/ ]] &amp;amp;&amp;amp; [[ -f $SCALFMM_STARPU_DIR/lib/libstarpu.so ]] ; then
echo &quot;STEP-OK&quot;
fi
</code></pre>"><span class="hljs-keyword">if</span> [[ -n <span class="hljs-variable">$SCALFMM_STARPU_DIR</span> ]] &amp;&amp; [[ <span class="hljs-operator">-d</span> <span class="hljs-variable">$SCALFMM_STARPU_DIR</span>/lib/ ]] &amp;&amp; [[ <span class="hljs-operator">-f</span> <span class="hljs-variable">$SCALFMM_STARPU_DIR</span>/lib/libstarpu.so ]] ; <span class="hljs-keyword">then</span>
<span class="hljs-built_in">echo</span> <span class="hljs-string">"STEP-OK"</span>
<span class="hljs-keyword">fi</span>
</code></pre><h3 id="scalfmm"><a name="scalfmm" href="#scalfmm"></a>ScalFMM</h3><h4 id="configure"><a name="configure" href="#configure"></a>Configure</h4><ul>
<li>Getting the source from the last commit:<pre class="bash hljs"><code class="bash" data-origin="<pre><code class=&quot;bash&quot;>cd $SCALFMM_TEST_DIR
if [[ ! -d scalfmm-public ]] ; then
git clone --depth=1 https://scm.gforge.inria.fr/anonscm/git/scalfmm-public/scalfmm-public.git
fi
cd scalfmm-public/
export SCALFMM_SOURCE_DIR=`pwd`
cd Build/
export SCALFMM_BUILD_DIR=`pwd`
</code></pre>"><span class="hljs-built_in">cd</span> <span class="hljs-variable">$SCALFMM_TEST_DIR</span>
<span class="hljs-keyword">if</span> [[ ! <span class="hljs-operator">-d</span> scalfmm-public ]] ; <span class="hljs-keyword">then</span>
git <span class="hljs-built_in">clone</span> --depth=<span class="hljs-number">1</span> https://scm.gforge.inria.fr/anonscm/git/scalfmm-public/scalfmm-public.git
<span class="hljs-keyword">fi</span>
<span class="hljs-built_in">cd</span> scalfmm-public/
<span class="hljs-built_in">export</span> SCALFMM_SOURCE_DIR=`<span class="hljs-built_in">pwd</span>`
<span class="hljs-built_in">cd</span> Build/
<span class="hljs-built_in">export</span> SCALFMM_BUILD_DIR=`<span class="hljs-built_in">pwd</span>`
</code></pre>
</li></ul><p><em>Output variables:</em> <code>scalfmmRegisterVariable SCALFMM_BUILD_DIR</code> <code>scalfmmRegisterVariable SCALFMM_SOURCE_DIR</code></p><ul>
<li>Configure (No MKL):<pre class="bash hljs"><code class="bash" data-origin="<pre><code class=&quot;bash&quot;>cmake .. -DSCALFMM_BUILD_DEBUG=OFF -DSCALFMM_USE_MPI=OFF \
-DSCALFMM_BUILD_TESTS=ON -DSCALFMM_BUILD_UTESTS=OFF \
-DSCALFMM_USE_BLAS=ON -DSCALFMM_USE_MKL_AS_BLAS=OFF \
-DSCALFMM_USE_LOG=ON -DSCALFMM_USE_STARPU=ON \
-DSCALFMM_USE_CUDA=ON -DSCALFMM_USE_OPENCL=OFF \
-DHWLOC_DIR=$SCALFMM_HWLOC_DIR -DSTARPU_DIR=$SCALFMM_STARPU_DIR \
-DSCALFMM_USE_FFT=ON -DFFT_DIR=$SCALFMM_FFT_DIR
</code></pre>">cmake .. -DSCALFMM_BUILD_DEBUG=OFF -DSCALFMM_USE_MPI=OFF \
-DSCALFMM_BUILD_TESTS=ON -DSCALFMM_BUILD_UTESTS=OFF \
-DSCALFMM_USE_BLAS=ON -DSCALFMM_USE_MKL_AS_BLAS=OFF \
-DSCALFMM_USE_LOG=ON -DSCALFMM_USE_STARPU=ON \
-DSCALFMM_USE_CUDA=ON -DSCALFMM_USE_OPENCL=OFF \
-DHWLOC_DIR=<span class="hljs-variable">$SCALFMM_HWLOC_DIR</span> -DSTARPU_DIR=<span class="hljs-variable">$SCALFMM_STARPU_DIR</span> \
-DSCALFMM_USE_FFT=ON -DFFT_DIR=<span class="hljs-variable">$SCALFMM_FFT_DIR</span>
</code></pre>
</li><li>Configure (MKL BLAS/LAPACK and FFTW):<pre class="bash hljs"><code class="bash" data-origin="<pre><code class=&quot;bash&quot;>cmake .. -DSCALFMM_BUILD_DEBUG=OFF -DSCALFMM_USE_MPI=OFF \
-DSCALFMM_BUILD_TESTS=ON -DSCALFMM_BUILD_UTESTS=OFF \
-DSCALFMM_USE_BLAS=ON -DSCALFMM_USE_MKL_AS_BLAS=ON \
-DSCALFMM_USE_LOG=ON -DSCALFMM_USE_STARPU=ON \
-DSCALFMM_USE_CUDA=ON -DSCALFMM_USE_OPENCL=OFF \
-DHWLOC_DIR=$SCALFMM_HWLOC_DIR -DSTARPU_DIR=$SCALFMM_STARPU_DIR \
-DSCALFMM_USE_FFT=ON -DFFT_DIR=$SCALFMM_FFT_DIR
</code></pre>">cmake .. -DSCALFMM_BUILD_DEBUG=OFF -DSCALFMM_USE_MPI=OFF \
-DSCALFMM_BUILD_TESTS=ON -DSCALFMM_BUILD_UTESTS=OFF \
-DSCALFMM_USE_BLAS=ON -DSCALFMM_USE_MKL_AS_BLAS=ON \
-DSCALFMM_USE_LOG=ON -DSCALFMM_USE_STARPU=ON \
-DSCALFMM_USE_CUDA=ON -DSCALFMM_USE_OPENCL=OFF \
-DHWLOC_DIR=<span class="hljs-variable">$SCALFMM_HWLOC_DIR</span> -DSTARPU_DIR=<span class="hljs-variable">$SCALFMM_STARPU_DIR</span> \
-DSCALFMM_USE_FFT=ON -DFFT_DIR=<span class="hljs-variable">$SCALFMM_FFT_DIR</span>
</code></pre>
</li><li>Configure (MKL BLAS/LAPACK/FFT and No FFTW):</li></ul><blockquote>
<p>[Plafrim-Developers] Should use that one</p>
</blockquote><pre class="bash hljs"><code class="bash" data-origin="<pre><code class=&quot;bash&quot;>cmake .. -DSCALFMM_BUILD_DEBUG=OFF -DSCALFMM_USE_MPI=OFF \
-DSCALFMM_BUILD_TESTS=ON -DSCALFMM_BUILD_UTESTS=OFF \
-DSCALFMM_USE_BLAS=ON -DSCALFMM_USE_MKL_AS_BLAS=ON \
-DSCALFMM_USE_LOG=ON -DSCALFMM_USE_STARPU=ON \
-DSCALFMM_USE_CUDA=ON -DSCALFMM_USE_OPENCL=OFF \
-DHWLOC_DIR=$SCALFMM_HWLOC_DIR -DSTARPU_DIR=$SCALFMM_STARPU_DIR \
-DSCALFMM_USE_FFT=ON -DSCALFMM_USE_MKL_AS_FFTW=ON
</code></pre>">cmake .. -DSCALFMM_BUILD_DEBUG=OFF -DSCALFMM_USE_MPI=OFF \
-DSCALFMM_BUILD_TESTS=ON -DSCALFMM_BUILD_UTESTS=OFF \
-DSCALFMM_USE_BLAS=ON -DSCALFMM_USE_MKL_AS_BLAS=ON \
-DSCALFMM_USE_LOG=ON -DSCALFMM_USE_STARPU=ON \
-DSCALFMM_USE_CUDA=ON -DSCALFMM_USE_OPENCL=OFF \
-DHWLOC_DIR=<span class="hljs-variable">$SCALFMM_HWLOC_DIR</span> -DSTARPU_DIR=<span class="hljs-variable">$SCALFMM_STARPU_DIR</span> \
-DSCALFMM_USE_FFT=ON -DSCALFMM_USE_MKL_AS_FFTW=ON
</code></pre><p>Valid-if:</p><pre class="bash hljs"><code class="bash" data-origin="<pre><code class=&quot;bash&quot;>cmake .. ; if [[ &quot;$?&quot; == &quot;0&quot; ]] ; then echo &quot;STEP-OK&quot; ; fi
</code></pre>">cmake .. ; <span class="hljs-keyword">if</span> [[ <span class="hljs-string">"$?"</span> == <span class="hljs-string">"0"</span> ]] ; <span class="hljs-keyword">then</span> <span class="hljs-built_in">echo</span> <span class="hljs-string">"STEP-OK"</span> ; <span class="hljs-keyword">fi</span>
</code></pre><h4 id="build"><a name="build" href="#build"></a>Build</h4><pre class="bash hljs"><code class="bash" data-origin="<pre><code class=&quot;bash&quot;>cd $SCALFMM_BUILD_DIR
make testBlockedUnifCudaBench
</code></pre>"><span class="hljs-built_in">cd</span> <span class="hljs-variable">$SCALFMM_BUILD_DIR</span>
make <span class="hljs-built_in">test</span>BlockedUnifCudaBench
</code></pre><p>Valid-if:</p><pre class="bash hljs"><code class="bash" data-origin="<pre><code class=&quot;bash&quot;>ls ./Tests/Release/testBlockedUnifCudaBench ; if [[ &quot;$?&quot; == &quot;0&quot; ]] ; then echo &quot;STEP-OK&quot; ; fi
</code></pre>">ls ./Tests/Release/<span class="hljs-built_in">test</span>BlockedUnifCudaBench ; <span class="hljs-keyword">if</span> [[ <span class="hljs-string">"$?"</span> == <span class="hljs-string">"0"</span> ]] ; <span class="hljs-keyword">then</span> <span class="hljs-built_in">echo</span> <span class="hljs-string">"STEP-OK"</span> ; <span class="hljs-keyword">fi</span>
</code></pre><h4 id="first-execution"><a name="first-execution" href="#first-execution"></a>First Execution</h4><p>In this section we compute a simulation and look at the resulting trace.<br>ScalFMM binary parameters and descriptions:</p><ul>
<li>Passing <code>--help</code> as parameter provide the possible/valid parameters</li><li>Simulation properties are choosen by :<ul>
<li><code>-h</code> : height of the tree</li><li><code>-bs</code> : granularity/size of the group</li><li><code>-nb</code> : number of particles generated</li></ul>
</li><li>Execution properties are choosen by the StarPU environment variables :<ul>
<li><code>STARPU_NCPUS</code> : the number of CPU workers</li><li><code>STARPU_NCUDA</code> : the number of GPU workers (for heterogeneous binary)</li></ul>
</li><li>By default the application will not compare the FMM interactions against the direct method (which is N^2) and so it is recommended to avoid the validation for large test cases. But to get the accuracy one must pass the parameter <code>-validation</code></li><li><code>-p2p-m2l-cuda-only</code> : to compute the P2P and the M2L only on GPU (the rest on the CPU)</li></ul><p>Examples:</p><pre class="bash hljs"><code class="bash" data-origin="<pre><code class=&quot;bash&quot;>export STARPU_NCPUS=12
export STARPU_NCUDA=2
./Tests/Release/testBlockedUnifCudaBench -nb 30000000 -h 7 -bs 800
</code></pre>"><span class="hljs-built_in">export</span> STARPU_NCPUS=<span class="hljs-number">12</span>
<span class="hljs-built_in">export</span> STARPU_NCUDA=<span class="hljs-number">2</span>
./Tests/Release/<span class="hljs-built_in">test</span>BlockedUnifCudaBench -nb <span class="hljs-number">30000000</span> -h <span class="hljs-number">7</span> -bs <span class="hljs-number">800</span>
</code></pre><p>Last part of the output should be:</p><pre class="bash hljs"><code class="bash" data-origin="<pre><code class=&quot;bash&quot;> Start FGroupTaskStarPUAlgorithm
directPass in 0.0406482s
inblock in 0.000780428s
outblock in 0.0398674s
bottomPass in 0.00586269s
upwardPass in 0.00265723s
transferPass in 0.00323571s
inblock in 0.000124817s
outblock in 0.00298331s
downardPass in 0.00257975s
transferPass in 0.0652285s
inblock in 0.00164774s
outblock in 0.0635799s
L2P in 0.0115733s
Submitting the tasks took 0.139101s
Moving data to the host took 0.0578765s
@EXEC TIME = 14.6321s
</code></pre>"> Start FGroupTaskStarPUAlgorithm
directPass <span class="hljs-keyword">in</span> <span class="hljs-number">0.0406482</span>s
inblock <span class="hljs-keyword">in</span> <span class="hljs-number">0.000780428</span>s
outblock <span class="hljs-keyword">in</span> <span class="hljs-number">0.0398674</span>s
bottomPass <span class="hljs-keyword">in</span> <span class="hljs-number">0.00586269</span>s
upwardPass <span class="hljs-keyword">in</span> <span class="hljs-number">0.00265723</span>s
transferPass <span class="hljs-keyword">in</span> <span class="hljs-number">0.00323571</span>s
inblock <span class="hljs-keyword">in</span> <span class="hljs-number">0.000124817</span>s
outblock <span class="hljs-keyword">in</span> <span class="hljs-number">0.00298331</span>s
downardPass <span class="hljs-keyword">in</span> <span class="hljs-number">0.00257975</span>s
transferPass <span class="hljs-keyword">in</span> <span class="hljs-number">0.0652285</span>s
inblock <span class="hljs-keyword">in</span> <span class="hljs-number">0.00164774</span>s
outblock <span class="hljs-keyword">in</span> <span class="hljs-number">0.0635799</span>s
L2P <span class="hljs-keyword">in</span> <span class="hljs-number">0.0115733</span>s
Submitting the tasks took <span class="hljs-number">0.139101</span>s
Moving data to the host took <span class="hljs-number">0.0578765</span>s
@EXEC TIME = <span class="hljs-number">14.6321</span>s
</code></pre><ul>
<li>Visualize the execution trace (<strong>Optional</strong>)</li></ul><p>Convert the fxt file</p><pre class="bash hljs"><code class="bash" data-origin="<pre><code class=&quot;bash&quot;>$SCALFMM_STARPU_DIR/bin/starpu_fxt_tool -i &quot;/tmp/prof_file_&quot;$USER&quot;_0&quot;
</code></pre>"><span class="hljs-variable">$SCALFMM_STARPU_DIR</span>/bin/starpu_fxt_tool -i <span class="hljs-string">"/tmp/prof_file_"</span><span class="hljs-variable">$USER</span><span class="hljs-string">"_0"</span>
</code></pre><p>Then visualize the output with <code>vite</code> (maybe by copying the paje.trace file locally)</p><pre class="bash hljs"><code class="bash" data-origin="<pre><code class=&quot;bash&quot;>vite ./paje.trace
</code></pre>">vite ./paje.trace
</code></pre><p>Should be like:<br><img src="/home/bbramas/Projects/ScalfmmGit/scalfmm/Addons/BenchEfficiency/trace-example.png" alt="Trace"></p><p>We can convert the color of the trace by (requiere Qt5 library):</p><pre class="bash hljs"><code class="bash" data-origin="<pre><code class=&quot;bash&quot;>$SCALFMM_SOURCE_DIR/Addons/BenchEfficiency/pajecolor paje.trace $SCALFMM_SOURCE_DIR/Addons/BenchEfficiency/paintmodel.fmm.colors
vite ./paje.trace.painted
</code></pre>"><span class="hljs-variable">$SCALFMM_SOURCE_DIR</span>/Addons/BenchEfficiency/pajecolor paje.trace <span class="hljs-variable">$SCALFMM_SOURCE_DIR</span>/Addons/BenchEfficiency/paintmodel.fmm.colors
vite ./paje.trace.painted
</code></pre><p>Should be like:<br><img src="/home/bbramas/Projects/ScalfmmGit/scalfmm/Addons/BenchEfficiency/trace-example-colors.png" alt="Trace"></p><ul>
<li>Get execution times</li></ul><pre class="bash hljs"><code class="bash" data-origin="<pre><code class=&quot;bash&quot;>python $SCALFMM_STARPU_DIR/bin/starpu_trace_state_stats.py -t trace.rec
</code></pre>">python <span class="hljs-variable">$SCALFMM_STARPU_DIR</span>/bin/starpu_trace_state_stats.py -t trace.rec
</code></pre><p>Should give something like:</p><pre><code data-origin="<pre><code>&quot;Name&quot;,&quot;Count&quot;,&quot;Type&quot;,&quot;Duration&quot;
&quot;Initializing&quot;,14,&quot;Runtime&quot;,7153.096196
&quot;Overhead&quot;,57010,&quot;Runtime&quot;,376.473463
&quot;Idle&quot;,14355,&quot;Other&quot;,12.815899
&quot;Scheduling&quot;,28441,&quot;Runtime&quot;,238.367394
&quot;Sleeping&quot;,610,&quot;Other&quot;,13786.513208
&quot;FetchingInput&quot;,14341,&quot;Runtime&quot;,13918.805814
&quot;execute_on_all_wrapper&quot;,30,&quot;Task&quot;,21.288802
&quot;Executing&quot;,414,&quot;Runtime&quot;,26852.864578
&quot;PushingOutput&quot;,14341,&quot;Runtime&quot;,284.96123
&quot;P2P-out&quot;,3846,&quot;Task&quot;,60378.266619
&quot;Callback&quot;,13559,&quot;Runtime&quot;,4.210633
&quot;P2P&quot;,328,&quot;Task&quot;,15383.426991
&quot;M2L-level-5&quot;,41,&quot;Task&quot;,2354.702554
&quot;M2L-level-6&quot;,328,&quot;Task&quot;,18349.915495
&quot;Deinitializing&quot;,14,&quot;Runtime&quot;,109.87483
&quot;M2L-level-4&quot;,6,&quot;Task&quot;,275.088295
&quot;P2M&quot;,328,&quot;Task&quot;,11312.022842
&quot;M2M-level-5&quot;,328,&quot;Task&quot;,829.9055
&quot;M2M-level-4&quot;,41,&quot;Task&quot;,93.130498
&quot;M2L-out-level-5&quot;,638,&quot;Task&quot;,1914.900053
&quot;M2M-level-3&quot;,6,&quot;Task&quot;,11.053067
&quot;M2M-level-2&quot;,1,&quot;Task&quot;,1.363157
&quot;M2L-out-level-4&quot;,22,&quot;Task&quot;,159.580457
&quot;L2L-level-4&quot;,41,&quot;Task&quot;,84.554065
&quot;L2L-level-5&quot;,328,&quot;Task&quot;,1087.717767
&quot;M2L-out-level-6&quot;,7692,&quot;Task&quot;,18322.518045
&quot;L2P&quot;,328,&quot;Task&quot;,27146.256793
&quot;M2L-level-2&quot;,1,&quot;Task&quot;,2.661235
&quot;L2L-level-3&quot;,6,&quot;Task&quot;,11.346978
&quot;M2L-level-3&quot;,1,&quot;Task&quot;,47.612555
&quot;L2L-level-2&quot;,1,&quot;Task&quot;,1.471873
</code></pre>">"Name","Count","Type","Duration"
"Initializing",14,"Runtime",7153.096196
"Overhead",57010,"Runtime",376.473463
"Idle",14355,"Other",12.815899
"Scheduling",28441,"Runtime",238.367394
"Sleeping",610,"Other",13786.513208
"FetchingInput",14341,"Runtime",13918.805814
"execute_on_all_wrapper",30,"Task",21.288802
"Executing",414,"Runtime",26852.864578
"PushingOutput",14341,"Runtime",284.96123
"P2P-out",3846,"Task",60378.266619
"Callback",13559,"Runtime",4.210633
"P2P",328,"Task",15383.426991