updates of XLeader

source/train/XLeader.cpp

@@ -184,47 +184,6 @@ void XLeader::MakeAll(XConfig * config, XModel * model)
     MakeParamMap();
 }
 
-/*
-wait for finished states (i.e., all workers finish their jobs)
->> activeJobWorkers - indicates whether each job worker is active
->> isToUpdate - indicates whether the model is updated
-*/
-void XLeader::WaitForFinishing(const int* activeJobWorkers, const int isToUpdate)
-{
-    int activeCount = 0;
-    for (int i = 0; i < jworkers.count; i++) {
-        if (activeJobWorkers[i] > 0) {
-            XWorker* worker = (XWorker*)jworkers[i];
-            worker->DequeueFinishedJob();
-            activeCount++;
-            CheckNTErrors(worker->GetFinishedNumInQueue() == 0, "Incorrect job number!");
-        }
-    }
-
-    if (activeCount > 0 && isToUpdate) {
-        for (int i = 0; i < cworkers.count; i++) {
-            XWorker* worker = (XWorker*)cworkers[i];
-            for(int j = 0; j < serverModel.paramNum * activeCount; j++)
-                worker->DequeueFinishedJob();
-            CheckNTErrors(worker->GetFinishedNumInQueue() == 0, "Incorrect job number!");
-        }
-
-        for (int i = 0; i < uworkers.count; i++) {
-            XWorker* worker = (XWorker*)uworkers[i];
-            for (int j = 0; j < serverModel.paramNum; j++)
-                worker->DequeueFinishedJob();
-            CheckNTErrors(worker->GetFinishedNumInQueue() == 0, "Incorrect job number!");
-        }
-
-        for (int i = 0; i < bworkers.count; i++) {
-            XWorker* worker = (XWorker*)bworkers[i];
-            for (int j = 0; j < serverModel.paramNum; j++)
-                worker->DequeueFinishedJob();
-            CheckNTErrors(worker->GetFinishedNumInQueue() == 0, "Incorrect job number!");
-        }
-    }
-}
-
 /* get loss */
 float XLeader::GetLoss()
 {

source/train/XLeader.h

@@ -138,9 +138,6 @@ public:
     /* prepare for running */
     void MakeAll(XConfig * config, XModel * model);
 
-    /* wait for finished states (i.e., all workers finish their jobs) */
-    void WaitForFinishing(const int * activeJobWorkers, const int isToUpdate);
-
     /* get loss */
     float GetLoss();
     

source/train/XLeaderAllReduce.h

@@ -49,6 +49,21 @@ public:
 
 	/* deconstructor */
 	~XLeaderAllReduce();
+
+    /* create workers and other stuff used in training */
+    void MakeAll(XConfig * config, XModel * model, const int * devIDs, const int jobWorkerNum);
+
+    /* wait for finished states (i.e., all workers finish their jobs) */
+    void WaitForFinishing(const int * activeJobWorkers, const int isToUpdate);
+
+    /* run the model and update it (for one time) */
+    bool Run(XConfig* config, DataDistributeBase* dataDistributor, XOptimizer* optimizer);
+
+    /* run the model */
+    int RunModel(XConfig* config, DataDistributeBase* dataDistributor, int* active);
+
+    /* update the model */
+    void RunUpdate(XConfig* config, XOptimizer* optimizer, const int* active);
 };
 
 }

source/train/XLeaderPS.cpp

@@ -44,7 +44,7 @@ XLeaderPS::~XLeaderPS()
 }
 
 /* 
-create workers 
+create workers and other stuff
 >> config - configuration
 >> model - the model that we run
 >> devIDs - device ids of the workers (the first id is for server)
@@ -63,6 +63,47 @@ void XLeaderPS::MakeAll(XConfig * config, XModel * model, const int * devIDs, co
 }
 
 /*
+wait for finished states (i.e., all workers finish their jobs)
+>> activeJobWorkers - indicates whether each job worker is active
+>> isToUpdate - indicates whether the model is updated
+*/
+void XLeaderPS::WaitForFinishing(const int* activeJobWorkers, const int isToUpdate)
+{
+    int activeCount = 0;
+    for (int i = 0; i < jworkers.count; i++) {
+        if (activeJobWorkers[i] > 0) {
+            XWorker* worker = (XWorker*)jworkers[i];
+            worker->DequeueFinishedJob();
+            activeCount++;
+            CheckNTErrors(worker->GetFinishedNumInQueue() == 0, "Incorrect job number!");
+        }
+    }
+
+    if (activeCount > 0 && isToUpdate) {
+        for (int i = 0; i < cworkers.count; i++) {
+            XWorker* worker = (XWorker*)cworkers[i];
+            for (int j = 0; j < serverModel.paramNum * activeCount; j++)
+                worker->DequeueFinishedJob();
+            CheckNTErrors(worker->GetFinishedNumInQueue() == 0, "Incorrect job number!");
+        }
+
+        for (int i = 0; i < uworkers.count; i++) {
+            XWorker* worker = (XWorker*)uworkers[i];
+            for (int j = 0; j < serverModel.paramNum; j++)
+                worker->DequeueFinishedJob();
+            CheckNTErrors(worker->GetFinishedNumInQueue() == 0, "Incorrect job number!");
+        }
+
+        for (int i = 0; i < bworkers.count; i++) {
+            XWorker* worker = (XWorker*)bworkers[i];
+            for (int j = 0; j < serverModel.paramNum; j++)
+                worker->DequeueFinishedJob();
+            CheckNTErrors(worker->GetFinishedNumInQueue() == 0, "Incorrect job number!");
+        }
+    }
+}
+
+/*
 run the model (for one time). Basically this is a map-reduce process.
 >> config - the configuration
 >> dataDistributor - data distributor
@@ -133,8 +174,8 @@ int XLeaderPS::RunModel(XConfig* config, DataDistributeBase* dataDistributor, in
 
             /* job in queue 1: run the model */
             worker->AddJobNeuralNet(jmodel,
-                worker->GetInput(), worker->GetOutput(),
-                worker->GetGold(), worker->GetLoss());
+                                    worker->GetInput(), worker->GetOutput(),
+                                    worker->GetGold(), worker->GetLoss());
 
             /* job in queue 1: make a record of the run */
             worker->AddJobRecord(&serverRecord);

source/train/XLeaderPS.h

@@ -50,6 +50,9 @@ public:
     /* create workers and other stuff used in training */
     void MakeAll(XConfig * config, XModel * model, const int * devIDs, const int jobWorkerNum);
 
+    /* wait for finished states (i.e., all workers finish their jobs) */
+    void WaitForFinishing(const int * activeJobWorkers, const int isToUpdate);
+
 	/* run the model and update it (for one time) */
 	bool Run(XConfig* config, DataDistributeBase* dataDistributor, XOptimizer* optimizer);