/* * Copyright 2010 OpenSourceResearchInstitute * * Licensed under BSD */ #include #include #include "PR.h" #include "VSs_impl/VSs.h" /* void PRHandle_CreateTask_SL(SlaveVP *slave); void PRHandle_CreateSlave_SL(SlaveVP *slave); void PRHandle_Dissipate_SL(SlaveVP *slave); void PR_int__handle_PRServiceReq_SL(SlaveVP *slave); */ inline void PRHandle_CreateTask( PRReqst *req, SlaveVP *slave ); inline void PRHandle_EndTask( PRReqst *req, SlaveVP *slave ); inline void PRHandle_CreateSlave(PRReqst *req, SlaveVP *slave ); void PRHandle_Dissipate( PRReqst *req, SlaveVP *slave ); //inline void masterFunction_SingleLang( PRLangEnv *protoLangEnv, AnimSlot *slot ); inline void masterFunction_MultiLang( AnimSlot *slot ); inline PRProcess * pickAProcess( AnimSlot *slot ); inline SlaveVP * assignWork( PRProcess *process, AnimSlot *slot ); /*The animationMaster embodies most of the animator of the language. The * animator is what emodies the behavior of language constructs. * As such, it is the animationMaster, in combination with the plugin * functions, that make the language constructs do their behavior. * *Within the code, this is the top-level-function of the masterVPs, and * runs when the coreController has no more slave VPs. It's job is to * refill the animation slots with slaves that have work. * *There are multiple versions of the master, each tuned to a specific * combination of modes. This keeps the master simple, with reduced overhead, * when the application is not using the extra complexity. * *As of Sept 2012, the versions available will be: * 1) Single langauge, which only exposes slaves (such as SSR or Vthread) * 2) Single language, which only exposes tasks (such as pure dataflow) * 3) Single language, which exposes both (like Cilk, StarSs, and OpenMP) * 4) Multi-language, which always assumes both tasks and slaves * 5) Multi-language and multi-process, which also assumes both tasks and slaves * * * */ //This version of the master selects one of three loops, depending upon // whether stand-alone single language (just slaves), or standalone with // tasks, or multi-lang (implies multi-process) void animationMaster( void *_environment, SlaveVP *masterVP ) { TopEnv *masterEnv = (TopEnv *)_environment; int32 slotIdx; AnimSlot *currSlot; //Used while scanning and filling animation slots AnimSlot **animSlots; //Local copies, for performance int32 thisCoresIdx; //======================== Initializations ======================== thisCoresIdx = masterVP->coreAnimatedBy; animSlots = masterEnv->allAnimSlots[thisCoresIdx]; HOLISTIC__Insert_Master_Global_Vars; //======================== animationMaster ======================== //Have three different modes, and the master behavior is different for // each, so jump to the loop that corresponds to the mode. // switch(masterEnv->mode) { /* { case SingleLang: while(1) { MEAS__Capture_Pre_Master_Point for( slotIdx = 0; slotIdx < NUM_ANIM_SLOTS; slotIdx++) { currSlot = animSlots[ slotIdx ]; masterFunction_StandaloneSlavesOnly( masterEnv, currSlot ); } MEAS__Capture_Post_Master_Point; masterSwitchToCoreCtlr( masterVP ); //returns when ctlr switches back to master flushRegisters(); } case SingleLang: { PRLangEnv *protoLangEnv = _PRTopEnv->protoLangEnv; while(1) { MEAS__Capture_Pre_Master_Point for( slotIdx = 0; slotIdx < NUM_ANIM_SLOTS; slotIdx++) { currSlot = animSlots[ slotIdx ]; masterFunction_SingleLang( protoLangEnv, currSlot ); } MEAS__Capture_Post_Master_Point; masterSwitchToCoreCtlr( masterVP ); //returns when ctlr switches back to master flushRegisters(); } } */ case MultiLang: { while(1) { MEAS__Capture_Pre_Master_Point for( slotIdx = 0; slotIdx < NUM_ANIM_SLOTS; slotIdx++) { currSlot = animSlots[ slotIdx ]; masterFunction_MultiLang( currSlot ); } MEAS__Capture_Post_Master_Point; masterSwitchToCoreCtlr( masterVP ); //returns when ctlr switches back to master flushRegisters(); } } } } //===================== The versions of the Animation Master ================= // //============================================================================== /* 1) This version is for a single language, that has only slaves, no tasks, * such as Vthread or SSR. *This version is for when an application has only a single language, and * that language exposes slaves explicitly (as opposed to a task based * language like pure dataflow). * * *It scans the animation slots for just-completed slaves. * Each completed slave has a request in it. So, the master hands each to * the plugin's request handler (there is only one plugin, because only one * lang). *Each request represents a language construct that has been encountered * by the application code in the slave. Passing the request to the * request handler is how that language construct's behavior gets invoked. * The request handler then performs the actions of the construct's * behavior. So, the request handler encodes the behavior of the * language's parallelism constructs, and performs that when the master * hands it a slave containing a request to perform that construct. * *On a shared-memory machine, the behavior of parallelism constructs * equals control, over order of execution of code. Hence, the behavior * of the language constructs performed by the request handler is to * choose the order that slaves get animated, and thereby control the * order that application code in the slaves executes. * *To control order of animation of slaves, the request handler has a * language environment that holds data structures used to hold slaves * and choose when they're ready to be animated. * *Once a slave is marked as ready to be animated by the request handler, * it is the second plugin function, the Assigner, which chooses the core * the slave gets assigned to for animation. Hence, the Assigner doesn't * perform any of the semantic behavior of language constructs, rather * it gives the language a chance to improve performance. The performance * of application code is strongly related to communication between * cores. On shared-memory machines, communication is caused during * execution of code, by memory accesses, and how much depends on contents * of caches connected to the core executing the code. So, the placement * of slaves determines the communication caused during execution of the * slave's code. *The point of the Assigner, then, is to use application information during * execution of the program, to make choices about slave placement onto * cores, with the aim to put slaves close to caches containing the data * used by the slave's code. * *========================================================================== *In summary, the animationMaster scans the slots, finds slaves * just-finished, which hold requests, pass those to the request handler, * along with the language environment, and the request handler then manages * the structures in the language env, which controls the order of * animation of slaves, and so embodies the behavior of the language * constructs. *The animationMaster then rescans the slots, offering each empty one to * the Assigner, along with the language environment. The Assigner chooses * among the ready slaves in the language env, finding the one best suited * to be animated by that slot's associated core. * *========================================================================== *Implementation Details: * *There is a separate masterVP for each core, but a single language * environment shared by all cores. Each core also has its own scheduling * slots, which are used to communicate slaves between animationMaster and * coreController. There is only one global variable, _PRTopEnv, which * holds the language env and other things shared by the different * masterVPs. The request handler and Assigner are registered with * the animationMaster by the language's init function, and a pointer to * each is in the _PRTopEnv. (There are also some pthread related global * vars, but they're only used during init of PR). *PR gains control over the cores by essentially "turning off" the OS's * scheduler, using pthread pin-to-core commands. * *The masterVPs are created during init, with this animationMaster as their * top level function. The masterVPs use the same SlaveVP data structure, * even though they're not slave VPs. *A "seed slave" is also created during init -- this is equivalent to the * "main" function in C, and acts as the entry-point to the PR-language- * based application. *The masterVPs share a single system-wide master-lock, so only one * masterVP may be animated at a time. *The core controllers access _PRTopEnv to get the masterVP, and when * they start, the slots are all empty, so they run their associated core's * masterVP. The first of those to get the master lock sees the seed slave * in the shared language environment, so when it runs the Assigner, that * returns the seed slave, which the animationMaster puts into a scheduling * slot then switches to the core controller. That then switches the core * over to the seed slave, which then proceeds to execute language * constructs to create more slaves, and so on. Each of those constructs * causes the seed slave to suspend, switching over to the core controller, * which eventually switches to the masterVP, which executes the * request handler, which uses PR primitives to carry out the creation of * new slave VPs, which are marked as ready for the Assigner, and so on.. * *On animation slots, and system behavior: * A request may linger in an animation slot for a long time while * the slaves in the other slots are animated. This only becomes a problem * when such a request is a choke-point in the constraints, and is needed * to free work for *other* cores. To reduce this occurrence, the number * of animation slots should be kept low. In balance, having multiple * animation slots amortizes the overhead of switching to the masterVP and * executing the animationMaster code, which drives for more than one. In * practice, the best balance should be discovered by profiling. */ /* void masterFunction_StandaloneSlavesOnly( AnimSlot *slot ) { SlaveVP *slave; PRReqst *req; PRLangEnv *langEnv = _PRTopEnv->langEnv; //======================== animationMaster ======================== //Check if newly-done slave in slot, which will need request handled if( slot->workIsDone ) { slot->workIsDone = FALSE; slot->needsWorkAssigned = TRUE; HOLISTIC__Record_AppResponder_start; MEAS__startReqHdlr; //process the request made by the slave (held inside slave struc) slave = slot->slaveAssignedToSlot; req = slave->request; //Handle task create and end first -- they're special cases.. switch( req->reqType ) { case SlvCreate: PRHandle_CreateSlave( slave ); break; case SlvDissipate: PRHandle_Dissipate( slave ); break; case Service: PR_int__handle_PRServiceReq( slave ); break; //resume into PR's own language env case Hardware: //for future expansion case IO: //for future expansion case OSCall: //for future expansion PR_int__throw_exception("Not implemented"); break; case Language: //normal lang request { (*langEnv->requestHdlr)( req->langReq, slave, langEnv ); } } HOLISTIC__Record_AppResponder_end; MEAS__endReqHdlr; } //If slot empty, hand to Assigner to fill with a slave if( slot->needsWorkAssigned ) { //Call plugin's Assigner to give slot a new slave HOLISTIC__Record_Assigner_start; if( langEnv->hasWork ) { (*langEnv->slaveAssigner)( langEnv, slot ); //calls PR fn that inserts work into slot goto ReturnAfterAssigningWork; //quit for-loop, cause found work } else goto NoWork; } NoWork: //No work, if reach here.. { #ifdef HOLISTIC__TURN_ON_OBSERVE_UCC coreNum = slot->coreSlotIsOn; returnSlv = process->idleSlv[coreNum][slotNum]; //things that would normally happen in resume(), but idle VPs // never go there returnSlv->numTimesAssignedToASlot++; //gives each idle unit a unique ID Unit newU; newU.vp = returnSlv->slaveNum; newU.task = returnSlv->numTimesAssignedToASlot; addToListOfArrays(Unit,newU,process->unitList); if (returnSlv->numTimesAssignedToASlot > 1) //make a dependency from prev idle unit { Dependency newD; // to this one newD.from_vp = returnSlv->slaveNum; newD.from_task = returnSlv->numTimesAssignedToASlot - 1; newD.to_vp = returnSlv->slaveNum; newD.to_task = returnSlv->numTimesAssignedToASlot; addToListOfArrays(Dependency, newD ,process->ctlDependenciesList); } #endif HOLISTIC__Record_Assigner_end; return; } ReturnAfterAssigningWork: //All paths goto here.. to provide single point for holistic.. { HOLISTIC__Record_Assigner_end; return; } } */ /*This is the master when just multi-lang, but not multi-process mode is on. * This version has to handle both tasks and slaves, and do extra work of * looking up the language env and handlers to use, for each completed bit of * work. *It also has to search through the language envs to find one with work, * then ask that env's assigner to return a unit of that work. * *The language is written to startup in the same way as if it were the only * language in the app, and it operates in the same way, * the only difference between single language and multi-lang is here, in the * master. *This invisibility to mode is why the language has to use registration calls * for everything during startup -- those calls do different things depending * on whether it's single-language or multi-language mode. * *In this version of the master, work can either be a task or a resumed slave *Having two cases makes this logic complex.. can be finishing either, and * then the next available work may be either.. so really have two distinct * loops that are inter-twined.. * *Some special cases: * A task-end is a special case for a few reasons (below). * A task-end can't block a slave (can't cause it to "logically suspend") * A task available for work can only be assigned to a special slave, which * has been set aside for doing tasks, one such task-slave is always * assigned to each slot. So, when a task ends, a new task is assigned to * that slot's task-slave right away. * But if no tasks are available, then have to switch over to looking at * slaves to find one ready to resume, to find work for the slot. * If a task just suspends, not ends, then its task-slave is no longer * available to take new tasks, so a new task-slave has to be assigned to * that slot. Then the slave of the suspended task is turned into a free * task-slave and request handling is done on it as if it were a slave * that suspended. * After request handling, do the same sequence of looking for a task to be * work, and if none, look for a slave ready to resume, as work for the slot. * If a slave suspends, handle its request, then look for work.. first for a * task to assign, and if none, slaves ready to resume. * Another special case is when task-end is done on a free task-slave.. in * that case, the slave has no more work and no way to get more.. so place * it into a recycle queue. * If no work is found of either type, then do a special thing to prune down * the extra slaves in the recycle queue, just so don't get too many.. * *The multi-lang thing complicates matters.. * *For request handling, it means have to first fetch the language environment * of the language, and then do the request handler pointed to by that * language env. *For assigning, things get more complex because of competing goals.. One * goal is for language specific stuff to be used during assignment, so * assigner can make higher quality decisions.. but with multiple languages, * which only get mixed in the application, the assigners can't be written * with knowledge of each other. So, they can only make localized decisions, * and so different language's assigners may interfere with each other.. * *So, have some possibilities available: *1) can have a fixed scheduler in the proto-runtime, that all the * languages give their work to.. (but then lose language-specific info, * there is a standard PR format for assignment info, and the langauge * attaches this to the work-unit when it gives it to PR.. also have issue * with HWSim, which uses a priority Q instead of FIFO, and requests can * "undo" previous work put in, so request handlers need way to manipulate * the work-holding Q..) (this might be fudgeable with * HWSim, if the master did a lang-supplied callback each time it assigns a * unit to a slot.. then HWSim can keep exactly one unit of work in PR's * queue at a time.. but this is quite hack-like.. or perhaps HWSim supplies * a task-end handler that kicks the next unit of work from HWSim internal * priority queue, over to PR readyQ) *2) can have each language have its own language env, that holds its own * work, which is assigned by its own assigner.. then the master searches * through all the language envs to find one with work and asks it give work.. * (this has downside of blinding assigners to each other.. but does work * for HWSim case) *3) could make PR have a different readyQ for each core, and ask the lang * to put work to the core it prefers.. but the work may be moved by PR if * needed, say if one core idles for too long. This is a hybrid approach, * letting the language decide which core, but PR keeps the work and does it * FIFO style.. (this might als be fudgeable with HWSim, in similar fashion, * but it would be complicated by having to track cores separately) * *Choosing 2, to keep compatibility with single-lang mode.. it allows the same * assigner to be used for single-lang as for multi-lang.. the overhead of * the extra master search for work is part of the price of the flexibility, * but should be fairly small.. takes the first env that has work available, * and whatever it returns is assigned to the slot.. * *As a hybrid, giving an option for a unified override assigner to be registered * and used.. This allows something like a static analysis to detect * which languages are grouped together, and then analyze the pattern of * construct calls, and generate a custom assigner that uses info from all * the languages in a unified way.. Don't really expect this to happen, * but making it possible. */ /* inline void masterFunction_SingleLang( PRLangEnv *protoLangEnv, AnimSlot *slot ) { //Scan the animation slots SlaveVP *slave; PRReqst *req; //Check if newly-done slave in slot, which will need request handled if( slot->workIsDone ) { slot->workIsDone = FALSE; slot->needsWorkAssigned = TRUE; HOLISTIC__Record_AppResponder_start; //TODO: update to check which process for each slot MEAS__startReqHdlr; //process the request made by the slave (held inside slave struc) slave = slot->slaveAssignedToSlot; req = slave->request; //If the requesting slave is a slot slave, and request is not // task-end, then turn it into a free task slave. if( slave->typeOfVP == SlotTaskSlv && req->reqType != TaskEnd ) PR_int__replace_with_new_slot_slv( slave ); //Handle task create and end first -- they're special cases.. switch( req->reqType ) { case TaskEnd: { //do PR handler, which calls lang's hdlr and does recycle of // free task slave if needed -- PR handler checks for free task Slv PRHandle_EndTask_SL( slave ); break; } case TaskCreate: { //Do PR's create-task handler, which calls the lang's hdlr // PR handler checks for free task Slv PRHandle_CreateTask_SL( slave ); break; } case SlvCreate: PRHandle_CreateSlave_SL( slave ); break; case SlvDissipate: PRHandle_Dissipate_SL( slave ); break; case Service: PR_int__handle_PRServiceReq_SL( slave ); break; //resume into PR's own language env case Hardware: //for future expansion case IO: //for future expansion case OSCall: //for future expansion PR_int__throw_exception("Not implemented", slave, NULL); break; case Language: //normal lang request { (*protoLangEnv->requestHdlr)( req->langReq, slave, (void*)PR_int__give_lang_env(protoLangEnv )); } } MEAS__endReqHdlr; HOLISTIC__Record_AppResponder_end; } //if have request to be handled //If slot empty, hand to Assigner to fill with a slave if( slot->needsWorkAssigned ) { //Call plugin's Assigner to give slot a new slave HOLISTIC__Record_Assigner_start; if( protoLangEnv->hasWork ) { (*protoLangEnv->slaveAssigner)( protoLangEnv, slot ); //calls PR fn that inserts work into slot goto ReturnAfterAssigningWork; //quit for-loop, cause found work } else goto NoWork; } NoWork: //No work, if reach here.. { #ifdef HOLISTIC__TURN_ON_OBSERVE_UCC coreNum = slot->coreSlotIsOn; returnSlv = process->idleSlv[coreNum][slotNum]; //things that would normally happen in resume(), but idle VPs // never go there returnSlv->numTimesAssignedToASlot++; //gives each idle unit a unique ID Unit newU; newU.vp = returnSlv->slaveNum; newU.task = returnSlv->numTimesAssignedToASlot; addToListOfArrays(Unit,newU,process->unitList); if (returnSlv->numTimesAssignedToASlot > 1) //make a dependency from prev idle unit { Dependency newD; // to this one newD.from_vp = returnSlv->slaveNum; newD.from_task = returnSlv->numTimesAssignedToASlot - 1; newD.to_vp = returnSlv->slaveNum; newD.to_task = returnSlv->numTimesAssignedToASlot; addToListOfArrays(Dependency, newD ,process->ctlDependenciesList); } #endif HOLISTIC__Record_Assigner_end; return; } ReturnAfterAssigningWork: //All paths goto here.. to provide single point for holistic.. { HOLISTIC__Record_Assigner_end; return; } } */ inline void masterFunction_MultiLang( AnimSlot *slot ) { //Scan the animation slots int32 magicNumber; SlaveVP *slave; PRLangEnv *langEnv; PRReqst *req; RequestHandler requestHandler; PRProcess *process; //Check if newly-done slave in slot, which will need request handled if( slot->workIsDone ) { slot->workIsDone = FALSE; slot->needsWorkAssigned = TRUE; HOLISTIC__Record_AppResponder_start; //TODO: update to check which process for each slot MEAS__startReqHdlr; //process the request made by the slave (held inside slave struc) slave = slot->slaveAssignedToSlot; req = slave->request; //If the requesting slave is a slot slave, and request is not // task-end, then turn it into a free task slave. if( slave->typeOfVP == SlotTaskSlv && req->reqType != TaskEnd ) PR_int__replace_with_new_slot_slv( slave ); //Handle task create and end first -- they're special cases.. switch( req->reqType ) { case TaskEnd: { //do PR handler, which calls lang's hdlr and does recycle of // free task slave if needed -- PR handler checks for free task Slv PRHandle_EndTask( req, slave ); break; } case TaskCreate: { //Do PR's create-task handler, which calls the lang's hdlr // PR handler checks for free task Slv PRHandle_CreateTask( req, slave ); break; } case SlvCreate: PRHandle_CreateSlave( req, slave ); break; case SlvDissipate: PRHandle_Dissipate( req, slave ); break; case Service: PR_int__handle_PRServiceReq( slave ); break; //resume into PR's own language env case Hardware: //for future expansion case IO: //for future expansion case OSCall: //for future expansion PR_int__throw_exception("Not implemented", slave, NULL); break; case Language: //normal lang request { magicNumber = req->langMagicNumber; langEnv = PR_PI__give_lang_env_for( slave, magicNumber ); (*req->handler)( req->langReq, slave, langEnv ); } } MEAS__endReqHdlr; HOLISTIC__Record_AppResponder_end; } //if have request to be handled if( slot->needsWorkAssigned ) { HOLISTIC__Record_Assigner_start; //Pick a process to get this slot process = pickAProcess( slot ); //Scan lang environs, looking for langEnv with ready work. // call the Assigner for that lang Env, to get a slave for the slot assignWork( process, slot ); HOLISTIC__Record_Assigner_end; }//if slot needs slave assigned } /*When several processes exist, use some pattern for picking one to give * the animation slot to. *First, it has to be a process that has work available. *For now, just do a round-robin */ inline PRProcess * pickAProcess( AnimSlot *slot ) { int32 idx; PRProcess *process; for( idx = _PRTopEnv->currProcessIdx; idx < _PRTopEnv->numProcesses; idx++) { process = _PRTopEnv->processes[ idx ]; if( process->numEnvsWithWork != 0 ) { _PRTopEnv->currProcessIdx = idx; return process; } } for( idx = 0; idx < _PRTopEnv->currProcessIdx; idx++) { process = _PRTopEnv->processes[ idx ]; if( process->numEnvsWithWork != 0 ) { _PRTopEnv->currProcessIdx = idx; return process; } } //none found return NULL; } /*This does: * 1) searches the language environments for one with work ready * if finds one, asks its assigner to return work * 2) checks what kind of work: new task, resuming task, resuming slave * if new task, gets the slot slave and assigns task to it and returns slave * else, gets the slave attached to the metaTask and returns that. * 3) if no work found, then prune former task slaves waiting to be recycled. * If no work and no slaves to prune, check for shutdown conditions. * * language env keeps its own work in its own structures, and has its own * assigner. It chooses * However, include a switch that switches-in an override assigner, which * sees all the work in all the language env's. This is most likely * generated by static tools and included in the executable. That means it * has to be called via a registered pointer from here. The idea is that * the static tools know which languages are grouped together.. and the * override enables them to generate a custom assigner that uses info from * all the languages in a unified way.. Don't really expect this to happen, * but am making it possible. */ inline SlaveVP * assignWork( PRProcess *process, AnimSlot *slot ) { SlaveVP *returnSlv; int32 coreNum, slotNum; PRMetaTask *assignedMetaTask; coreNum = slot->coreSlotIsOn; if( process->overrideAssigner != NULL ) { if( process->numEnvsWithWork != 0 ) { (*process->overrideAssigner)( process, slot ); //calls PR fn that inserts work into slot goto ReturnAfterAssigningWork; //quit for-loop, cause found work } else goto NoWork; } //If here, then no override assigner, so search language envs for work int32 envIdx, numEnvs; PRLangEnv **langEnvsList, *langEnv; langEnvsList = process->langEnvsList; numEnvs = process->numLangEnvs; for( envIdx = 0; envIdx < numEnvs; envIdx++ ) //keep langEnvs in hash & array { langEnv = langEnvsList[envIdx]; if( langEnv->hasWork ) { (*langEnv->slaveAssigner)( langEnv, slot ); //assigner calls PR to put slave/task into slot goto ReturnAfterAssigningWork; //quit for-loop, cause found work //NOTE: bad search alg -- should start where left off, then wrap around } } //If reach here, then have searched all langEnv's & none have work.. NoWork: //No work, if end up here.. { #ifdef HOLISTIC__TURN_ON_OBSERVE_UCC returnSlv = process->idleSlv[coreNum][slotNum]; //things that would normally happen in resume(), but idle VPs // never go there returnSlv->numTimesAssignedToASlot++; //gives each idle unit a unique ID Unit newU; newU.vp = returnSlv->slaveNum; newU.task = returnSlv->numTimesAssignedToASlot; addToListOfArrays(Unit,newU,process->unitList); if (returnSlv->numTimesAssignedToASlot > 1) //make a dependency from prev idle unit { Dependency newD; // to this one newD.from_vp = returnSlv->slaveNum; newD.from_task = returnSlv->numTimesAssignedToASlot - 1; newD.to_vp = returnSlv->slaveNum; newD.to_task = returnSlv->numTimesAssignedToASlot; addToListOfArrays(Dependency, newD ,process->ctlDependenciesList); } #endif HOLISTIC__Record_Assigner_end; return; } ReturnAfterAssigningWork: //All paths goto here.. to provide single point for holistic.. { HOLISTIC__Record_Assigner_end; return; } } /*This is first thing called when creating a slave.. it hands off to the * langlet's creator, then adds updates of its own.. * *There's a question of things like lang data, meta tasks, and such.. *In creator, only PR related things happen, and things for the langlet whose * creator construct was used. * *Other langlets still get a chance to create langData -- but by registering a * "createLangData" handler in the langEnv. When a construct of the langlet * calls "PR__give_lang_data()", if there is no langData for that langlet, * the PR will call the creator in the langlet's langEnv, place whatever it * makes as the langData in that slave for that langlet, and return that langData * *So, as far as counting things, a langlet is only allowed to count creation * of slaves it creates itself.. may have to change this later.. add a way for * langlet to register a trigger Fn called each time a slave gets created.. * need more experience with what langlets will do at create time.. think Cilk * has interesting create behavior.. not sure how that will differ in light * of true tasks and langlet approach. Look at it after all done and start * modifying the langs to be langlets.. * *PR itself needs to create the slave, then update numLiveSlaves in process, * copy processID from requestor to newly created */ inline void PRHandle_CreateSlave( PRReqst *req, SlaveVP *slave ) { SlaveVP *newSlv; PRProcess *process; PRLangEnv *protoLangEnv; process = slave->processSlaveIsIn; protoLangEnv = PR_int__give_proto_lang_env_for_slave__ML( slave, req->langMagicNumber ); // newSlv = PR_int__create_slave( req->topLevelFn, req->initData ); //create slv has diff prototype than standard reqst hdlr newSlv = (*req->createHdlr)(req->langReq, slave, PR_int__give_lang_env(protoLangEnv)); newSlv->typeOfVP = GenericSlv; newSlv->processSlaveIsIn = process; newSlv->ID = req->ID; process->numLiveGenericSlvs += 1; } /*The dissipate handler has to, update the number of slaves of the type, within * the process, and call the langlet handler linked into the request, * and after that returns, then call the PR function that frees the slave state * (or recycles the slave). * *The PR function that frees the slave state has to also free all of the * langData in the slave.. or else reset all of the langDatas.. by, say, marking * them, then in PR__give_langData( magicNum ) call the langlet registered * "resetLangData" Fn. */ inline void PRHandle_Dissipate( PRReqst *req, SlaveVP *slave ) { PRProcess *process; PRLangEnv *protoLangEnv; process = slave->processSlaveIsIn; //do the language's dissipate handler protoLangEnv = PR_int__give_proto_lang_env_for_slave__ML( slave, slave->request->langMagicNumber ); if(req->handler != NULL) (*req->handler)( req->langReq, slave, PR_int__give_lang_env(protoLangEnv) ); process->numLiveGenericSlvs -= 1; PR_int__recycle_slave__ML( slave ); //check End Of Process Condition if( process->numLiveTasks == 0 && process->numLiveGenericSlvs == 0 ) PR_SS__shutdown_process__ML( process ); } /*Create task is a special form, that has PR behavior in addition to plugin * behavior. Master calls this first, and it then calls the plugin's * create task handler. * *Note: the requesting slave must be either generic slave or free task slave */ inline void PRHandle_CreateTask( PRReqst *req, SlaveVP *slave ) { PRMetaTask *metaTask; PRProcess *process; PRLangEnv *protoLangEnv; void *task; process = slave->processSlaveIsIn; protoLangEnv = PR_int__give_proto_lang_env_for_slave__ML( slave, req->langMagicNumber ); //Do the langlet's create-task handler, which keeps the task // inside the langlet's lang env, but returns the langMetaTask // so PR can put stuff into the prolog task = (*req->createHdlr)(req->langReq, slave, PR_int__give_lang_env(protoLangEnv) ); metaTask = PR_int__give_prolog_of_task( task ); metaTask->ID = req->ID; //may be NULL metaTask->topLevelFn = req->topLevelFn; metaTask->initData = req->initData; process->numLiveTasks += 1; return; } /*When a task ends, are two scenarios: 1) task ran to completion, or 2) task * suspended at some point in its code. *For 1, just decr count of live tasks (and check for end condition) -- the * master loop will decide what goes into the slot freed up by this task end, * so, here, don't worry about assigning a new task to the slot slave. *For 2, the task's slot slave has been converted to a free task slave, which * now has nothing more to do, so send it to the recycle Q (which includes * freeing all the langData and meta task structs alloc'd for it). Then * decrement the live task count and check end condition. * *PR has to update count of live tasks, and check end of process condition. * The "main" can invoke constructs that wait for a process to end, so when * end detected, have to resume what's waiting.. *Thing is, that wait involves the main OS thread. That means * PR internals have to do OS thread signaling. Want to do that in the * core controller, which has the original stack of an OS thread. So the * end process handling happens in the core controller. * *So here, when detect process end, signal to the core controller, which will * then do the condition variable notify to the OS thread that's waiting. * *Note: slave may be either a slot slave or a free task slave. */ inline void PRHandle_EndTask( PRReqst *req, SlaveVP *requestingSlv ) { void *langEnv; PRProcess *process; void *langMetaTask; langEnv = PR_int__give_lang_env_of_req__ML( req, requestingSlv ); //magic num in req langMetaTask = PR_int__give_lang_meta_task_from_slave__ML( requestingSlv, req->langMagicNumber); //Do the langlet's request handler //Want to keep PR structs hidden from plugin, so extract langReq.. (*req->handler)( req->langReq, requestingSlv, langEnv ); //Now that the langlet's done with it, recycle the slave if it's a freeTaskSlv if( requestingSlv->typeOfVP == FreeTaskSlv ) PR_int__recycle_slave__ML( requestingSlv ); process->numLiveTasks -= 1; //check End Of Process Condition if( process->numLiveTasks == 0 && process->numLiveGenericSlvs == 0 ) { //Tell the core controller to do wakeup of any waiting OS thread PR_SS__shutdown_process__ML( process ); } }