CNTK now delay-loads msmpi.dll in case it is not installed;

moved Profiled.cpp/h;
disabled MultiNetworksSGD--seems not missing, not used

CNTK.sln

@@ -199,6 +199,10 @@ Project("{2150E333-8FDC-42A3-9474-1A3956D46DE8}") = "Data", "Data", "{5F733BBA-F
 EndProject
 Project("{2150E333-8FDC-42A3-9474-1A3956D46DE8}") = "LSTM", "LSTM", "{19EE975B-232D-49F0-94C7-6F1C6424FB53}"
 	ProjectSection(SolutionItems) = preProject
+		Tests\Speech\LSTM\baseline.cpu.txt = Tests\Speech\LSTM\baseline.cpu.txt
+		Tests\Speech\LSTM\baseline.gpu.txt = Tests\Speech\LSTM\baseline.gpu.txt
+		Tests\Speech\LSTM\baseline.windows.cpu.txt = Tests\Speech\LSTM\baseline.windows.cpu.txt
+		Tests\Speech\LSTM\baseline.windows.gpu.txt = Tests\Speech\LSTM\baseline.windows.gpu.txt
 		Tests\Speech\LSTM\cntk.config = Tests\Speech\LSTM\cntk.config
 		Tests\Speech\LSTM\lstmp-3layer_WithSelfStab.ndl = Tests\Speech\LSTM\lstmp-3layer_WithSelfStab.ndl
 		Tests\Speech\LSTM\run-test = Tests\Speech\LSTM\run-test

MachineLearning/CNTK/CNTK.vcxproj

@@ -80,7 +80,7 @@
       <GenerateDebugInformation>true</GenerateDebugInformation>
       <AdditionalDependencies>CNTKSGDLib.lib; CNTKComputationNetworkLib.lib; CNTKMath.lib; kernel32.lib; user32.lib; shell32.lib; %(AdditionalDependencies)</AdditionalDependencies>
       <AdditionalLibraryDirectories>"c:\Program Files\NVIDIA Corporation\GDK\gdk_win7_amd64_release\nvml\lib"</AdditionalLibraryDirectories>
-      <DelayLoadDLLs>CNTKMath.dll; nvml.dll; cudart64_70.dll</DelayLoadDLLs>
+      <DelayLoadDLLs>CNTKMath.dll; msmpi.dll; nvml.dll; cudart64_70.dll</DelayLoadDLLs>
       <StackReserveSize>100000000</StackReserveSize>
     </Link>
     <PostBuildEvent>
@@ -122,7 +122,7 @@
       <OptimizeReferences>true</OptimizeReferences>
       <AdditionalDependencies>CNTKSGDLib.lib; CNTKComputationNetworkLib.lib; CNTKMath.lib; kernel32.lib; user32.lib; shell32.lib; %(AdditionalDependencies)</AdditionalDependencies>
       <Profile>true</Profile>
-      <DelayLoadDLLs>CNTKMath.dll; nvml.dll; cudart64_70.dll</DelayLoadDLLs>
+      <DelayLoadDLLs>CNTKMath.dll; msmpi.dll; nvml.dll; cudart64_70.dll</DelayLoadDLLs>
       <AdditionalLibraryDirectories>"c:\Program Files\NVIDIA Corporation\GDK\gdk_win7_amd64_release\nvml\lib"</AdditionalLibraryDirectories>
     </Link>
     <PostBuildEvent>

MachineLearning/CNTKSGDLib/MultiNetworksSGD.h

@@ -7,7 +7,7 @@
 
 #include "basetypes.h"
 #include "ComputationNetwork.h"
-#include "IComputationNetBuilder.h"
+#include "..\CNTK\IComputationNetBuilder.h"
 #include "SimpleEvaluator.h"
 #include "DataReader.h"
 #include <vector>
@@ -305,8 +305,8 @@ namespace Microsoft { namespace MSR { namespace CNTK {
                 auto t_start_epoch = clock();
 
                 //set dropout rate
-                SetDropoutRate(*encoderNet, encoderEvaluationNodes[0], m_dropoutRates[i], prevDropoutRate, dropOutSeed);
-                SetDropoutRate(*decoderNet, decoderCriterionNodes[0], m_dropoutRates[i], prevDropoutRate, dropOutSeed);
+                ComputationNetwork::SetDropoutRate<ElemType>(*encoderNet, encoderEvaluationNodes[0], m_dropoutRates[i], prevDropoutRate, dropOutSeed);
+                ComputationNetwork::SetDropoutRate<ElemType>(*decoderNet, decoderCriterionNodes[0], m_dropoutRates[i], prevDropoutRate, dropOutSeed);
 
                 //learning rate adjustment
                 if (m_autoLearnRateSearchType == LearningRateSearchAlgorithm::None || (m_learningRatesPerSample.size() > 0 && m_learningRatesPerSample.size() > i))

MachineLearning/CNTKSGDLib/SGD.cpp

@@ -11,7 +11,8 @@ namespace Microsoft { namespace MSR { namespace CNTK {
 template class SGD<float>;
 template class SGD<double>;
 
-template class MultiNetworksSGD<float>;
-template class MultiNetworksSGD<double>;
+// TODO: does not build--does this mean it is not used?
+//template class MultiNetworksSGD<float>;
+//template class MultiNetworksSGD<double>;
 
 }}}

MachineLearning/CNTKSGDLib/SGD.h

@@ -11,6 +11,7 @@
 #include "CompositeComputationNodes.h"  // for PrecomputeNode
 #include "SimpleEvaluator.h"
 #include "DataReader.h"
+#include "..\CNTK\IComputationNetBuilder.h" // TODO: separate out the building part, leave to an outer level
 #include <vector>
 #include <string>
 #include <stdexcept>