private T InitRR <T>(T rr, MyMemoryBlock <float> targetMemBlock, MyMemoryBlock <float> targetDepthMemBlock, Action <T> initializer = null)
where T : class, IRenderRequestBase
{
if (initializer != null)
{
initializer.Invoke(rr);
}
rr.FlipYAxis = true;
targetMemBlock.ExternalPointer = 0; // first reset ExternalPointer
// Setup image copying from RR through Cpu
if (Owner.CopyDataThroughCPU)
{
ImageSettings imageSettings = new ImageSettings(RenderRequestImageCopyingMode.Cpu)
{
CopyDepth = Owner.CopyDepthData && targetDepthMemBlock != null,
};
imageSettings.OnSceneBufferPrepared += (request, data, depthData) =>
{
int width = rr.Resolution.Width;
int stride = width * sizeof(uint);
int lines = data.Length / width;
for (int i = 0; i < lines; ++i)
{
Buffer.BlockCopy(data, i * stride, targetMemBlock.Host, i * width * sizeof(uint), stride);
}
if (imageSettings.CopyDepth)
{
for (int i = 0; i < lines; ++i)
{
Buffer.BlockCopy(depthData, i * stride, targetDepthMemBlock.Host, i * width * sizeof(float), stride);
}
}
// targetMemBlock.SafeCopyToDevice(); this needs to be called on the BrainSim thread
// targetDepthMemBlock.SafeCopyToDevice(); this needs to be called on the BrainSim thread
};
rr.Image = imageSettings;
return(rr);
}
// Setup image copying from RR through Pbo
ImageSettings image = new ImageSettings(RenderRequestImageCopyingMode.OpenglPbo)
{
CopyDepth = Owner.CopyDepthData && targetDepthMemBlock != null,
};
// Setup data copying to our unmanaged memblocks
uint renderTextureHandle = 0;
uint depthRenderTextureHandle = 0;
CudaOpenGLBufferInteropResource renderResource = null;
CudaOpenGLBufferInteropResource depthRenderResource = null;
image.OnPreRenderingEvent += (sender, vbo, depthVbo) =>
{
if (renderResource != null && renderResource.IsMapped)
{
renderResource.UnMap();
}
if (image.CopyDepth)
{
if (depthRenderResource != null && depthRenderResource.IsMapped)
{
depthRenderResource.UnMap();
}
}
};
image.OnPostRenderingEvent += (sender, vbo, depthVbo) =>
{
// Vbo can be allocated during drawing, create the resource after that (post-rendering)
MyKernelFactory.Instance.GetContextByGPU(Owner.GPU).SetCurrent();
// Fill color memblock
if (renderResource == null || vbo != renderTextureHandle)
{
if (renderResource != null)
{
renderResource.Dispose();
}
renderTextureHandle = vbo;
try
{
renderResource = new CudaOpenGLBufferInteropResource(renderTextureHandle,
image.CopyDepth ? CUGraphicsRegisterFlags.None : CUGraphicsRegisterFlags.ReadOnly); // Read only by CUDA
}
catch (Exception e)
{
MyLog.ERROR.WriteLine("calling CudaOpenGLBufferInteropResource returns " + e +
". Go to World properties and in Runtime section set Copy data through CPU to True");
throw e;
}
}
renderResource.Map();
targetMemBlock.ExternalPointer = renderResource.GetMappedPointer <uint>().DevicePointer.Pointer;
targetMemBlock.FreeDevice();
targetMemBlock.AllocateDevice();
// Fill depth memblock
if (image.CopyDepth)
{
if (depthRenderResource == null || depthVbo != depthRenderTextureHandle)
{
if (depthRenderResource != null)
{
depthRenderResource.Dispose();
}
depthRenderTextureHandle = depthVbo;
depthRenderResource = new CudaOpenGLBufferInteropResource(
depthRenderTextureHandle,
CUGraphicsRegisterFlags.ReadOnly); // Read only by CUDA
}
depthRenderResource.Map();
targetDepthMemBlock.ExternalPointer = depthRenderResource.GetMappedPointer <float>().DevicePointer.Pointer;
targetDepthMemBlock.FreeDevice();
targetDepthMemBlock.AllocateDevice();
}
};
rr.Image = image;
// Initialize the target memory block
// Use a dummy number that will get replaced on first Execute call to suppress MemBlock error during init
targetMemBlock.ExternalPointer = 1;
if (targetDepthMemBlock != null)
{
targetDepthMemBlock.ExternalPointer = 1;
}
return(rr);
}
// Sets up the genetic task
public override void Init(int nGPU)
{
currentGen = 0;
m_weights = 0;
// Load the relevant kernels
m_coeffGenKernel = MyKernelFactory.Instance.Kernel(nGPU, @"Genetic\CosyneGenetics", "generateCoefficients");
m_geneticKernel = MyKernelFactory.Instance.Kernel(nGPU, @"Genetic\CosyneGenetics", "grow");
m_extractKernel = MyKernelFactory.Instance.Kernel(nGPU, @"Genetic\CosyneGenetics", "extractCoeffs");
m_cosineGenKernel = MyKernelFactory.Instance.Kernel(nGPU, @"Genetic\CosyneGenetics", "createCosineMatrix");
m_implantKernel = MyKernelFactory.Instance.Kernel(nGPU, @"Genetic\CosyneGenetics", "implantCoeffs");
// Init the random generator
m_rand = new Random();
// Set up coefficient Generation
m_coeffGenKernel.SetupExecution(Owner.PopulationSize);
// Set up genetic recombination
m_geneticKernel.SetupExecution(Owner.PopulationSize);
// This finds the first nn group in the network. Possibility of getting a list of networks and evolving them all seperately?
List<MyNode> ch = Owner.Owner.Network.Children;
foreach (MyNode n in ch)
{
if (n is MyNeuralNetworkGroup)
{
nn = n as MyNeuralNetworkGroup;
MyLog.INFO.WriteLine("Evolving the layers of node: " + nn.Name);
break;
}
}
if (nn == null)
{
throw new NullReferenceException("There is no top level NeuralNetworkGroup.");
}
// Construct the layerlist which is to be read from and written to
constructLayerList(nn);
// This is how big the weight matrix will be
arr_size = (int)Math.Ceiling(Math.Sqrt(m_weights));
// Get the relevant execution plan
m_executionPlan = Owner.Owner.SimulationHandler.Simulation.ExecutionPlan[0];
#region MemoryBlocks
// Initialise the population
population = new List<MyMemoryBlock<float>>();
outputPop = new List<MyMemoryBlock<float>>();
for (int i = 0; i < Owner.PopulationSize; i++)
{
population.Add(new MyMemoryBlock<float>());
population[i].Owner = Owner;
population[i].Count = arr_size * arr_size;
population[i].AllocateMemory();
outputPop.Add(new MyMemoryBlock<float>());
outputPop[i].Owner = Owner;
outputPop[i].Count = arr_size * arr_size;
outputPop[i].AllocateMemory();
}
// Allocate space to manipulate weight matrices on the device
cudaMatrices = new MyMemoryBlock<float>();
cudaMatrices.Owner = Owner;
cudaMatrices.Count = arr_size * arr_size * Owner.PopulationSize;
cudaMatrices.AllocateDevice();
// Allocate a memory block for the Cosine matrix
multiplier = new MyMemoryBlock<float>();
multiplier.Owner = Owner;
multiplier.Count = arr_size * arr_size;
multiplier.AllocateDevice();
// Fill the cosine Matrices
m_cosineGenKernel.SetupExecution(arr_size);
m_cosineGenKernel.Run(multiplier, arr_size);
// Allocate space needed for chromosomes
chromosomePop = new MyMemoryBlock<float>();
chromosomePop.Owner = Owner;
if (DirectEvolution)
chromosomePop.Count = m_weights * Owner.PopulationSize;
else
chromosomePop.Count = CoefficientsSaved * Owner.PopulationSize;
chromosomePop.AllocateMemory();
// Allocate some space for noise to seed the cuda_rand generator
noise = new MyMemoryBlock<float>();
noise.Owner = Owner;
noise.Count = Owner.PopulationSize;
noise.AllocateMemory();
// Write some noise to the initial array
for (int i = 0; i < Owner.PopulationSize; i++)
{
noise.Host[i] = (float)m_rand.NextDouble() * 100000 + (float)m_rand.NextDouble() * 40;
}
noise.SafeCopyToDevice();
// Allocate space for the fitnesses
fitnesses = new MyMemoryBlock<float>();
fitnesses.Owner = Owner;
fitnesses.Count = Owner.PopulationSize;
fitnesses.AllocateMemory();
// Allocate some temporary storage
tempMB = new MyMemoryBlock<float>();
tempPop = new MyMemoryBlock<float>();
tempMB.Owner = Owner;
tempMB.Count = CoefficientsSaved;
tempMB.AllocateDevice();
tempPop.Owner = Owner;
tempPop.Count = arr_size * arr_size;
tempPop.AllocateDevice();
marking = new MyMemoryBlock<int>();
marking.Owner = Owner;
marking.Count = CoefficientsSaved * Owner.PopulationSize;
marking.AllocateDevice();
#endregion
// Check saved Coeffs size
if (CoefficientsSaved > m_weights)
{
MyLog.WARNING.Write("Saving more Coefficients than exist in the weight matrix. Setting to max permissable value\n");
CoefficientsSaved = m_weights;
}
if (CoefficientsSaved == m_weights)
{
MyLog.INFO.Write("Saving a coefficient for every weight. Evolving weights directly\n");
DirectEvolution = true;
}
if (DirectEvolution)
CoefficientsSaved = m_weights;
// Generate the rest of the population
if (DirectEvolution)
m_coeffGenKernel.Run(chromosomePop, CoefficientsSaved, noise, Owner.PopulationSize, WeightMagnitude);
else
m_coeffGenKernel.Run(chromosomePop, CoefficientsSaved, noise, Owner.PopulationSize, Alpha);
//Disable Backprop tasks in Network
if (nn.GetActiveBackpropTask() != null)
{
if (!nn.GetActiveBackpropTask().DisableLearning)
{
MyLog.WARNING.WriteLine("Disabling backprop learning for Neural Network");
nn.GetActiveBackpropTask().DisableLearning = true;
}
}
}
// Sets up the genetic task
public override void Init(int nGPU)
{
currentGen = 0;
m_weights = 0;
// Load the relevant kernels
m_coeffGenKernel = MyKernelFactory.Instance.Kernel(nGPU, @"Genetic\CosyneGenetics", "generateCoefficients");
m_geneticKernel = MyKernelFactory.Instance.Kernel(nGPU, @"Genetic\CosyneGenetics", "grow");
m_extractKernel = MyKernelFactory.Instance.Kernel(nGPU, @"Genetic\CosyneGenetics", "extractCoeffs");
m_cosineGenKernel = MyKernelFactory.Instance.Kernel(nGPU, @"Genetic\CosyneGenetics", "createCosineMatrix");
m_implantKernel = MyKernelFactory.Instance.Kernel(nGPU, @"Genetic\CosyneGenetics", "implantCoeffs");
// Init the random generator
m_rand = new Random();
// Set up coefficient Generation
m_coeffGenKernel.SetupExecution(Owner.PopulationSize);
// Set up genetic recombination
m_geneticKernel.SetupExecution(Owner.PopulationSize);
// This finds the first nn group in the network. Possibility of getting a list of networks and evolving them all seperately?
List <MyNode> ch = Owner.Owner.Network.Children;
foreach (MyNode n in ch)
{
if (n is MyNeuralNetworkGroup)
{
nn = n as MyNeuralNetworkGroup;
MyLog.INFO.WriteLine("Evolving the layers of node: " + nn.Name);
break;
}
}
if (nn == null)
{
throw new NullReferenceException("There is no top level NeuralNetworkGroup.");
}
// Construct the layerlist which is to be read from and written to
constructLayerList(nn);
// This is how big the weight matrix will be
arr_size = (int)Math.Ceiling(Math.Sqrt(m_weights));
// Get the relevant execution plan
m_executionPlan = Owner.Owner.SimulationHandler.Simulation.ExecutionPlan;
#region MemoryBlocks
// Initialise the population
population = new List <MyMemoryBlock <float> >();
outputPop = new List <MyMemoryBlock <float> >();
for (int i = 0; i < Owner.PopulationSize; i++)
{
population.Add(new MyMemoryBlock <float>());
population[i].Owner = Owner;
population[i].Count = arr_size * arr_size;
population[i].AllocateMemory();
outputPop.Add(new MyMemoryBlock <float>());
outputPop[i].Owner = Owner;
outputPop[i].Count = arr_size * arr_size;
outputPop[i].AllocateMemory();
}
// Allocate space to manipulate weight matrices on the device
cudaMatrices = new MyMemoryBlock <float>();
cudaMatrices.Owner = Owner;
cudaMatrices.Count = arr_size * arr_size * Owner.PopulationSize;
cudaMatrices.AllocateDevice();
// Allocate a memory block for the Cosine matrix
multiplier = new MyMemoryBlock <float>();
multiplier.Owner = Owner;
multiplier.Count = arr_size * arr_size;
multiplier.AllocateDevice();
// Fill the cosine Matrices
m_cosineGenKernel.SetupExecution(arr_size);
m_cosineGenKernel.Run(multiplier, arr_size);
// Allocate space needed for chromosomes
chromosomePop = new MyMemoryBlock <float>();
chromosomePop.Owner = Owner;
if (DirectEvolution)
{
chromosomePop.Count = m_weights * Owner.PopulationSize;
}
else
{
chromosomePop.Count = CoefficientsSaved * Owner.PopulationSize;
}
chromosomePop.AllocateMemory();
// Allocate some space for noise to seed the cuda_rand generator
noise = new MyMemoryBlock <float>();
noise.Owner = Owner;
noise.Count = Owner.PopulationSize;
noise.AllocateMemory();
// Write some noise to the initial array
for (int i = 0; i < Owner.PopulationSize; i++)
{
noise.Host[i] = (float)m_rand.NextDouble() * 100000 + (float)m_rand.NextDouble() * 40;
}
noise.SafeCopyToDevice();
// Allocate space for the fitnesses
fitnesses = new MyMemoryBlock <float>();
fitnesses.Owner = Owner;
fitnesses.Count = Owner.PopulationSize;
fitnesses.AllocateMemory();
// Allocate some temporary storage
tempMB = new MyMemoryBlock <float>();
tempPop = new MyMemoryBlock <float>();
tempMB.Owner = Owner;
tempMB.Count = CoefficientsSaved;
tempMB.AllocateDevice();
tempPop.Owner = Owner;
tempPop.Count = arr_size * arr_size;
tempPop.AllocateDevice();
marking = new MyMemoryBlock <int>();
marking.Owner = Owner;
marking.Count = CoefficientsSaved * Owner.PopulationSize;
marking.AllocateDevice();
#endregion
// Check saved Coeffs size
if (CoefficientsSaved > m_weights)
{
MyLog.WARNING.Write("Saving more Coefficients than exist in the weight matrix. Setting to max permissable value\n");
CoefficientsSaved = m_weights;
}
if (CoefficientsSaved == m_weights)
{
MyLog.INFO.Write("Saving a coefficient for every weight. Evolving weights directly\n");
DirectEvolution = true;
}
if (DirectEvolution)
{
CoefficientsSaved = m_weights;
}
// Generate the rest of the population
if (DirectEvolution)
{
m_coeffGenKernel.Run(chromosomePop, CoefficientsSaved, noise, Owner.PopulationSize, WeightMagnitude);
}
else
{
m_coeffGenKernel.Run(chromosomePop, CoefficientsSaved, noise, Owner.PopulationSize, Alpha);
}
//Disable Backprop tasks in Network
if (nn.GetActiveBackpropTask() != null)
{
if (!nn.GetActiveBackpropTask().DisableLearning)
{
MyLog.WARNING.WriteLine("Disabling backprop learning for Neural Network");
nn.GetActiveBackpropTask().DisableLearning = true;
}
}
}