void InitializePCpu()
{
int N = cc.c.N;
const float DistanceScale = 100.0f;
const float eps = 2.22e-16f;
int bandSize = Math.Min(N, MaxGroupNumberHyp * GroupSizeHyp);
PBuf = gpu.CreateBufferRW(bandSize * N, 4, 1);
P2Buf = gpu.CreateBufferDynamic(bandSize * N, 4, 7); // dynamic buffer for fast uploading. Linked to Pcpu[] on HLSL.
int blockSize = 128; // Calculate so many rows per dispatch.
cpuP = new float[N][];
for (int i = 0; i < N; i++)
{
cpuP[i] = new float[N];
}
using (var distanceBuf = gpu.CreateBufferRW(blockSize * N, 4, 0))
using (var stagingBuf = gpu.CreateStagingBuffer(distanceBuf))
using (var sd = gpu.LoadShader("TsneDx.PartialDistance2.cso")) {
gpu.SetShader(sd);
for (int iBlock = 0; iBlock < N; iBlock += blockSize)
{
cc.c.blockIdx = iBlock;
cc.Upload();
gpu.Run(blockSize);
int iBlock2 = Math.Min(iBlock + blockSize, N);
int blockLen = (iBlock2 * (iBlock2 - 1) - iBlock * (iBlock - 1)) / 2;
float[] ret = gpu.ReadRange <float>(stagingBuf, distanceBuf, blockLen);
int idx = 0;
for (int row = iBlock; row < iBlock2; row++)
{
Array.Copy(ret, idx, cpuP[row], 0, row);
idx += row;
}
}
}
double distanceFactor = double.MinValue;
MT.For(1, N, i => {
float maxV = cpuP[i].Max();
lock (this)
distanceFactor = Math.Max(distanceFactor, maxV);
});
if (distanceFactor == 0)
{
throw new System.Exception("Distance metric degenerated: all components are zero.");
}
// Scale the distance to managable range [0, 100.0] to avoid degredation
// with exp function.
distanceFactor = DistanceScale / distanceFactor;
MT.For(1, N, i => {
for (int j = 0; j < i; j++)
{
cpuP[i][j] = (float)(cpuP[i][j] * distanceFactor);
}
});
MT.For(0, N, i => {
for (int j = 0; j < i; j++)
{
cpuP[j][i] = cpuP[i][j];
}
cpuP[i][i] = 0;
});
int bSize = MaxGroupNumberHyp * GroupSizeHyp;
using (var sd = gpu.LoadShader("TsneDx.Dist2Affinity.cso"))
using (var stagingBuf = gpu.CreateStagingBuffer(PBuf)) {
gpu.SetShader(sd);
for (int iBlock = 0; iBlock < N; iBlock += bSize)
{
cc.c.blockIdx = iBlock;
cc.Upload();
int iBlock2 = Math.Min(N, iBlock + bSize);
using (var ws = gpu.NewWriteStream(PBuf))
for (int row = iBlock; row < iBlock2; row++)
{
ws.WriteRange(cpuP[row]);
}
gpu.Run(MaxGroupNumberHyp);
using (var rs = gpu.NewReadStream(stagingBuf, PBuf))
for (int row = iBlock; row < iBlock2; row++)
{
rs.ReadRange(cpuP[row], 0, N);
}
}
}
double sum = 0;
MT.For(0, N, i => {
double sum2 = 0.0;
for (int j = i + 1; j < N; j++)
{
cpuP[i][j] += cpuP[j][i];
sum2 += cpuP[i][j];
}
lock (this)
sum += sum2;
});
if (sum == 0)
{
throw new System.Exception("Perplexity too small!");
}
sum *= 2;
MT.For(0, N, i => {
for (int j = i + 1; j < N; j++)
{
cpuP[i][j] = (float)Math.Max(cpuP[i][j] / sum, eps);
cpuP[j][i] = cpuP[i][j];
}
cpuP[i][i] = 1.0f;
});
}
