// TGr06E_MomentumBias_v3.cpp - Zorro64 Strategy DLL
// Strategy E v3: Momentum-Biased with MX06 OOP + OpenCL (real offload) + Memory Optimization
// Notes:
// - Keeps full CPU fallback.
// - OpenCL is optional: if OpenCL.dll missing / no device / kernel build fails -> CPU path.
// - OpenCL accelerates the heavy correlation matrix step by offloading pairwise correlations.
// - Correlation is computed in float on GPU; results are stored back into fvar corrMatrix.

#define _CRT_SECURE_NO_WARNINGS
#include <zorro.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <math.h>
#include <windows.h>
#include <stddef.h>

#define INF 1e30
#define EPS 1e-12
#define N_ASSETS 28
#define FEAT_N 9
#define FEAT_WINDOW 200
#define UPDATE_EVERY 5
#define TOP_K 5

#define ALPHA 0.1
#define BETA 0.2
#define GAMMA 3.5
#define LAMBDA_META 0.7

#ifdef TIGHT_MEM
typedef float fvar;
#else
typedef double fvar;
#endif

static const char* ASSET_NAMES[] = {
  "EURUSD","GBPUSD","USDCHF","USDJPY","AUDUSD","AUDCAD","AUDCHF","AUDJPY","AUDNZD",
  "CADJPY","CADCHF","EURAUD","EURCAD","EURCHF","EURGBP","EURJPY","EURNZD","GBPAUD",
  "GBPCAD","GBPCHF","GBPJPY","GBPNZD","NZDCAD","NZDCHF","NZDJPY","NZDUSD","USDCAD"
};
static const char* CURRENCIES[] = {"EUR","GBP","USD","CHF","JPY","AUD","CAD","NZD"};
#define N_CURRENCIES 8

// ---------------------------- Exposure Table ----------------------------

struct ExposureTable {
  int exposure[N_ASSETS][N_CURRENCIES];
  double exposureDist[N_ASSETS][N_ASSETS];

  void init() {
    for(int i=0;i<N_ASSETS;i++){
      for(int c=0;c<N_CURRENCIES;c++){
        exposure[i][c] = 0;
      }
    }
    for(int i=0;i<N_ASSETS;i++){
      for(int j=0;j<N_ASSETS;j++){
        exposureDist[i][j] = 0.0;
      }
    }
  }

  inline double getDist(int i,int j) const { return exposureDist[i][j]; }
};

// ---------------------------- Slab Allocator ----------------------------

template<typename T>
class SlabAllocator {
public:
  T* data;
  int capacity;

  SlabAllocator() : data(NULL), capacity(0) {}
  ~SlabAllocator() { shutdown(); }

  void init(int size) {
    shutdown();
    capacity = size;
    data = (T*)malloc((size_t)capacity * sizeof(T));
    if(data) memset(data, 0, (size_t)capacity * sizeof(T));
  }

  void shutdown() {
    if(data) free(data);
    data = NULL;
    capacity = 0;
  }

  T& operator[](int i) { return data[i]; }
  const T& operator[](int i) const { return data[i]; }
};

// ---------------------------- Feature Buffer (SoA ring) ----------------------------

struct FeatureBufferSoA {
  SlabAllocator<fvar> buffer;
  int windowSize;
  int currentIndex;

  void init(int assets, int window) {
    windowSize = window;
    currentIndex = 0;
    buffer.init(FEAT_N * assets * window);
  }

  void shutdown() { buffer.shutdown(); }

  inline int offset(int feat,int asset,int t) const {
    return (feat * N_ASSETS + asset) * windowSize + t;
  }

  void push(int feat,int asset,fvar value) {
    buffer[offset(feat, asset, currentIndex)] = value;
    currentIndex = (currentIndex + 1) % windowSize;
  }

  // t=0 => most recent
  fvar get(int feat,int asset,int t) const {
    int idx = (currentIndex - 1 - t + windowSize) % windowSize;
    return buffer[offset(feat, asset, idx)];
  }
};

// ---------------------------- Minimal OpenCL (dynamic) ----------------------------

typedef struct _cl_platform_id*   cl_platform_id;
typedef struct _cl_device_id*     cl_device_id;
typedef struct _cl_context*       cl_context;
typedef struct _cl_command_queue* cl_command_queue;
typedef struct _cl_program*       cl_program;
typedef struct _cl_kernel*        cl_kernel;
typedef struct _cl_mem*           cl_mem;
typedef unsigned int              cl_uint;
typedef int                       cl_int;
typedef unsigned long long        cl_ulong;
typedef size_t                    cl_bool;

#define CL_SUCCESS 0
#define CL_DEVICE_TYPE_CPU (1ULL << 1)
#define CL_DEVICE_TYPE_GPU (1ULL << 2)
#define CL_MEM_READ_ONLY   (1ULL << 2)
#define CL_MEM_WRITE_ONLY  (1ULL << 1)
#define CL_MEM_READ_WRITE  (1ULL << 0)
#define CL_TRUE  1
#define CL_FALSE 0
#define CL_PROGRAM_BUILD_LOG 0x1183

class OpenCLBackend {
public:
  HMODULE hOpenCL;
  int ready;

  cl_platform_id platform;
  cl_device_id device;
  cl_context context;
  cl_command_queue queue;
  cl_program program;
  cl_kernel kCorr;

  cl_mem bufFeat;
  cl_mem bufCorr;

  int featBytes;
  int corrBytes;

  cl_int (*clGetPlatformIDs)(cl_uint, cl_platform_id*, cl_uint*);
  cl_int (*clGetDeviceIDs)(cl_platform_id, cl_ulong, cl_uint, cl_device_id*, cl_uint*);
  cl_context (*clCreateContext)(void*, cl_uint, const cl_device_id*, void*, void*, cl_int*);
  cl_command_queue (*clCreateCommandQueue)(cl_context, cl_device_id, cl_ulong, cl_int*);
  cl_program (*clCreateProgramWithSource)(cl_context, cl_uint, const char**, const size_t*, cl_int*);
  cl_int (*clBuildProgram)(cl_program, cl_uint, const cl_device_id*, const char*, void*, void*);
  cl_int (*clGetProgramBuildInfo)(cl_program, cl_device_id, cl_uint, size_t, void*, size_t*);
  cl_kernel (*clCreateKernel)(cl_program, const char*, cl_int*);
  cl_int (*clSetKernelArg)(cl_kernel, cl_uint, size_t, const void*);
  cl_mem (*clCreateBuffer)(cl_context, cl_ulong, size_t, void*, cl_int*);
  cl_int (*clEnqueueWriteBuffer)(cl_command_queue, cl_mem, cl_bool, size_t, size_t, const void*, cl_uint, const void*, void*);
  cl_int (*clEnqueueReadBuffer)(cl_command_queue, cl_mem, cl_bool, size_t, size_t, void*, cl_uint, const void*, void*);
  cl_int (*clEnqueueNDRangeKernel)(cl_command_queue, cl_kernel, cl_uint, const size_t*, const size_t*, const size_t*, cl_uint, const void*, void*);
  cl_int (*clFinish)(cl_command_queue);
  cl_int (*clReleaseMemObject)(cl_mem);
  cl_int (*clReleaseKernel)(cl_kernel);
  cl_int (*clReleaseProgram)(cl_program);
  cl_int (*clReleaseCommandQueue)(cl_command_queue);
  cl_int (*clReleaseContext)(cl_context);

  OpenCLBackend()
  : hOpenCL(NULL), ready(0),
    platform(NULL), device(NULL), context(NULL), queue(NULL), program(NULL), kCorr(NULL),
    bufFeat(NULL), bufCorr(NULL),
    featBytes(0), corrBytes(0),
    clGetPlatformIDs(NULL), clGetDeviceIDs(NULL), clCreateContext(NULL), clCreateCommandQueue(NULL),
    clCreateProgramWithSource(NULL), clBuildProgram(NULL), clGetProgramBuildInfo(NULL),
    clCreateKernel(NULL), clSetKernelArg(NULL),
    clCreateBuffer(NULL), clEnqueueWriteBuffer(NULL), clEnqueueReadBuffer(NULL),
    clEnqueueNDRangeKernel(NULL), clFinish(NULL),
    clReleaseMemObject(NULL), clReleaseKernel(NULL), clReleaseProgram(NULL),
    clReleaseCommandQueue(NULL), clReleaseContext(NULL)
  {}

  int loadSymbol(void** fp, const char* name) {
    *fp = (void*)GetProcAddress(hOpenCL, name);
    return (*fp != NULL);
  }

  const char* kernelSource() {
    return
      "__kernel void corr_pairwise(\n"
      "  __global const float* feat,\n"
      "  __global float* outCorr,\n"
      "  const int nAssets,\n"
      "  const int nFeat,\n"
      "  const int windowSize,\n"
      "  const float eps\n"
      "){\n"
      "  int a = (int)get_global_id(0);\n"
      "  int b = (int)get_global_id(1);\n"
      "  if(a >= nAssets || b >= nAssets) return;\n"
      "  if(a >= b) return;\n"
      "  float acc = 0.0f;\n"
      "  for(int f=0; f<nFeat; f++){\n"
      "    int baseA = (f*nAssets + a) * windowSize;\n"
      "    int baseB = (f*nAssets + b) * windowSize;\n"
      "    float mx = 0.0f;\n"
      "    float my = 0.0f;\n"
      "    for(int t=0; t<windowSize; t++){\n"
      "      mx += feat[baseA + t];\n"
      "      my += feat[baseB + t];\n"
      "    }\n"
      "    mx /= (float)windowSize;\n"
      "    my /= (float)windowSize;\n"
      "    float sxx = 0.0f;\n"
      "    float syy = 0.0f;\n"
      "    float sxy = 0.0f;\n"
      "    for(int t=0; t<windowSize; t++){\n"
      "      float dx = feat[baseA + t] - mx;\n"
      "      float dy = feat[baseB + t] - my;\n"
      "      sxx += dx*dx;\n"
      "      syy += dy*dy;\n"
      "      sxy += dx*dy;\n"
      "    }\n"
      "    float den = sqrt(sxx*syy + eps);\n"
      "    float corr = (den > eps) ? (sxy/den) : 0.0f;\n"
      "    acc += corr;\n"
      "  }\n"
      "  outCorr[a*nAssets + b] = acc / (float)nFeat;\n"
      "}\n";
  }

  void printBuildLog() {
    if(!clGetProgramBuildInfo || !program || !device) return;
    size_t logSize = 0;
    clGetProgramBuildInfo(program, device, CL_PROGRAM_BUILD_LOG, 0, NULL, &logSize);
    if(logSize == 0) return;
    char* log = (char*)malloc(logSize + 1);
    if(!log) return;
    memset(log, 0, logSize + 1);
    clGetProgramBuildInfo(program, device, CL_PROGRAM_BUILD_LOG, logSize, log, NULL);
    printf("OpenCL build log:\n%s\n", log);
    free(log);
  }

  void init() {
    ready = 0;

    hOpenCL = LoadLibraryA("OpenCL.dll");
    if(!hOpenCL) {
      printf("OpenCL: CPU (OpenCL.dll missing)\n");
      return;
    }

    if(!loadSymbol((void**)&clGetPlatformIDs,       "clGetPlatformIDs")) return;
    if(!loadSymbol((void**)&clGetDeviceIDs,         "clGetDeviceIDs")) return;
    if(!loadSymbol((void**)&clCreateContext,        "clCreateContext")) return;
    if(!loadSymbol((void**)&clCreateCommandQueue,   "clCreateCommandQueue")) return;
    if(!loadSymbol((void**)&clCreateProgramWithSource,"clCreateProgramWithSource")) return;
    if(!loadSymbol((void**)&clBuildProgram,         "clBuildProgram")) return;
    if(!loadSymbol((void**)&clGetProgramBuildInfo,  "clGetProgramBuildInfo")) return;
    if(!loadSymbol((void**)&clCreateKernel,         "clCreateKernel")) return;
    if(!loadSymbol((void**)&clSetKernelArg,         "clSetKernelArg")) return;
    if(!loadSymbol((void**)&clCreateBuffer,         "clCreateBuffer")) return;
    if(!loadSymbol((void**)&clEnqueueWriteBuffer,   "clEnqueueWriteBuffer")) return;
    if(!loadSymbol((void**)&clEnqueueReadBuffer,    "clEnqueueReadBuffer")) return;
    if(!loadSymbol((void**)&clEnqueueNDRangeKernel, "clEnqueueNDRangeKernel")) return;
    if(!loadSymbol((void**)&clFinish,               "clFinish")) return;
    if(!loadSymbol((void**)&clReleaseMemObject,     "clReleaseMemObject")) return;
    if(!loadSymbol((void**)&clReleaseKernel,        "clReleaseKernel")) return;
    if(!loadSymbol((void**)&clReleaseProgram,       "clReleaseProgram")) return;
    if(!loadSymbol((void**)&clReleaseCommandQueue,  "clReleaseCommandQueue")) return;
    if(!loadSymbol((void**)&clReleaseContext,       "clReleaseContext")) return;

    cl_uint nPlat = 0;
    if(clGetPlatformIDs(0, NULL, &nPlat) != CL_SUCCESS || nPlat == 0) {
      printf("OpenCL: CPU (no platform)\n");
      return;
    }
    clGetPlatformIDs(1, &platform, NULL);

    cl_uint nDev = 0;
    cl_int ok = clGetDeviceIDs(platform, CL_DEVICE_TYPE_GPU, 1, &device, &nDev);
    if(ok != CL_SUCCESS || nDev == 0) {
      ok = clGetDeviceIDs(platform, CL_DEVICE_TYPE_CPU, 1, &device, &nDev);
      if(ok != CL_SUCCESS || nDev == 0) {
        printf("OpenCL: CPU (no device)\n");
        return;
      }
    }

    cl_int err = 0;
    context = clCreateContext(NULL, 1, &device, NULL, NULL, &err);
    if(err != CL_SUCCESS || !context) {
      printf("OpenCL: CPU (context fail)\n");
      return;
    }

    queue = clCreateCommandQueue(context, device, 0, &err);
    if(err != CL_SUCCESS || !queue) {
      printf("OpenCL: CPU (queue fail)\n");
      return;
    }

    const char* src = kernelSource();
    program = clCreateProgramWithSource(context, 1, &src, NULL, &err);
    if(err != CL_SUCCESS || !program) {
      printf("OpenCL: CPU (program fail)\n");
      return;
    }

    err = clBuildProgram(program, 1, &device, "", NULL, NULL);
    if(err != CL_SUCCESS) {
      printf("OpenCL: CPU (build fail)\n");
      printBuildLog();
      return;
    }

    kCorr = clCreateKernel(program, "corr_pairwise", &err);
    if(err != CL_SUCCESS || !kCorr) {
      printf("OpenCL: CPU (kernel fail)\n");
      printBuildLog();
      return;
    }

    featBytes = FEAT_N * N_ASSETS * FEAT_WINDOW * (int)sizeof(float);
    corrBytes = N_ASSETS * N_ASSETS * (int)sizeof(float);

    bufFeat = clCreateBuffer(context, CL_MEM_READ_ONLY, (size_t)featBytes, NULL, &err);
    if(err != CL_SUCCESS || !bufFeat) {
      printf("OpenCL: CPU (bufFeat fail)\n");
      return;
    }

    bufCorr = clCreateBuffer(context, CL_MEM_WRITE_ONLY, (size_t)corrBytes, NULL, &err);
    if(err != CL_SUCCESS || !bufCorr) {
      printf("OpenCL: CPU (bufCorr fail)\n");
      return;
    }

    ready = 1;
    printf("OpenCL: READY (kernel+buffers)\n");
  }

  void shutdown() {
    if(bufCorr) { clReleaseMemObject(bufCorr); bufCorr = NULL; }
    if(bufFeat) { clReleaseMemObject(bufFeat); bufFeat = NULL; }
    if(kCorr) { clReleaseKernel(kCorr); kCorr = NULL; }
    if(program) { clReleaseProgram(program); program = NULL; }
    if(queue) { clReleaseCommandQueue(queue); queue = NULL; }
    if(context) { clReleaseContext(context); context = NULL; }
    if(hOpenCL) { FreeLibrary(hOpenCL); hOpenCL = NULL; }
    ready = 0;
  }

  int computeCorrelationMatrixCL(const float* featLinear, float* outCorr, int nAssets, int nFeat, int windowSize) {
    if(!ready) return 0;
    if(!featLinear || !outCorr) return 0;

    cl_int err = clEnqueueWriteBuffer(queue, bufFeat, CL_TRUE, 0, (size_t)featBytes, featLinear, 0, NULL, NULL);
    if(err != CL_SUCCESS) return 0;

    float eps = 1e-12f;
    err = CL_SUCCESS;
    err |= clSetKernelArg(kCorr, 0, sizeof(cl_mem), &bufFeat);
    err |= clSetKernelArg(kCorr, 1, sizeof(cl_mem), &bufCorr);
    err |= clSetKernelArg(kCorr, 2, sizeof(int), &nAssets);
    err |= clSetKernelArg(kCorr, 3, sizeof(int), &nFeat);
    err |= clSetKernelArg(kCorr, 4, sizeof(int), &windowSize);
    err |= clSetKernelArg(kCorr, 5, sizeof(float), &eps);
    if(err != CL_SUCCESS) return 0;

    size_t global[2];
    global[0] = (size_t)nAssets;
    global[1] = (size_t)nAssets;

    err = clEnqueueNDRangeKernel(queue, kCorr, 2, NULL, global, NULL, 0, NULL, NULL);
    if(err != CL_SUCCESS) return 0;

    err = clFinish(queue);
    if(err != CL_SUCCESS) return 0;

    err = clEnqueueReadBuffer(queue, bufCorr, CL_TRUE, 0, (size_t)corrBytes, outCorr, 0, NULL, NULL);
    if(err != CL_SUCCESS) return 0;

    return 1;
  }
};

// ---------------------------- Strategy ----------------------------

class MomentumBiasStrategy {
public:
  ExposureTable exposureTable;
  FeatureBufferSoA featSoA;
  OpenCLBackend openCL;

  SlabAllocator<fvar> corrMatrix;
  SlabAllocator<fvar> distMatrix;
  SlabAllocator<fvar> compactness;
  SlabAllocator<fvar> momentum;
  SlabAllocator<fvar> scores;

  SlabAllocator<float> featLinear;
  SlabAllocator<float> corrLinear;

  int barCount;
  int updateCount;
  int isReady;

  MomentumBiasStrategy() : barCount(0), updateCount(0), isReady(0) {}

  void init() {
    char buf[256];
    sprintf(buf, "MomentumBias_v3: Initializing...\n");
    printf(buf);
    OutputDebugStringA(buf);

    sprintf(buf, "1. exposureTable.init...\n");
    printf(buf);
    OutputDebugStringA(buf);
    exposureTable.init();

    sprintf(buf, "2. featSoA.init...\n");
    printf(buf);
    OutputDebugStringA(buf);
    featSoA.init(N_ASSETS, FEAT_WINDOW);

    sprintf(buf, "3. corrMatrix.init...\n");
    printf(buf);
    OutputDebugStringA(buf);
    corrMatrix.init(N_ASSETS * N_ASSETS);

    sprintf(buf, "4. distMatrix.init...\n");
    printf(buf);
    OutputDebugStringA(buf);
    distMatrix.init(N_ASSETS * N_ASSETS);

    sprintf(buf, "5. compactness.init...\n");
    printf(buf);
    OutputDebugStringA(buf);
    compactness.init(N_ASSETS);

    sprintf(buf, "6. momentum.init...\n");
    printf(buf);
    OutputDebugStringA(buf);
    momentum.init(N_ASSETS);

    sprintf(buf, "7. scores.init...\n");
    printf(buf);
    OutputDebugStringA(buf);
    scores.init(N_ASSETS);

    sprintf(buf, "8. featLinear.init...\n");
    printf(buf);
    OutputDebugStringA(buf);
    featLinear.init(FEAT_N * N_ASSETS * FEAT_WINDOW);

    sprintf(buf, "9. corrLinear.init...\n");
    printf(buf);
    OutputDebugStringA(buf);
    corrLinear.init(N_ASSETS * N_ASSETS);

    sprintf(buf, "10. openCL.init...\n");
    printf(buf);
    OutputDebugStringA(buf);
    openCL.init();

    sprintf(buf, "MomentumBias_v3: Ready (OpenCL=%d)\n", openCL.ready);
    printf(buf);
    OutputDebugStringA(buf);

    barCount = 0;
    updateCount = 0;
    isReady = 1;
  }

  void shutdown() {
    printf("MomentumBias_v3: Shutting down...\n");

    openCL.shutdown();

    featSoA.shutdown();
    corrMatrix.shutdown();
    distMatrix.shutdown();
    compactness.shutdown();
    momentum.shutdown();
    scores.shutdown();

    featLinear.shutdown();
    corrLinear.shutdown();
    isReady = 0;
  }

  void computeFeatures(int assetIdx) {
    asset((char*)ASSET_NAMES[assetIdx]);

    vars C = series(priceClose(0));
    vars V = series(Volatility(C, 20));

    if(Bar < 50) return;

    fvar r1 = (fvar)log(C[0] / C[1]);
    fvar rN = (fvar)log(C[0] / C[12]);
    fvar vol = (fvar)V[0];
    fvar zscore = (fvar)((C[0] - C[50]) / (V[0] * 20.0 + EPS));
    fvar rangeP = (fvar)((C[0] - C[50]) / (C[0] + EPS));
    fvar flow = (fvar)(r1 * vol);
    fvar regime = (fvar)((vol > 0.001) ? 1.0 : 0.0);
    fvar volOfVol = (fvar)(vol * vol);
    fvar persistence = (fvar)fabs(r1);

    featSoA.push(0, assetIdx, r1);
    featSoA.push(1, assetIdx, rN);
    featSoA.push(2, assetIdx, vol);
    featSoA.push(3, assetIdx, zscore);
    featSoA.push(4, assetIdx, rangeP);
    featSoA.push(5, assetIdx, flow);
    featSoA.push(6, assetIdx, regime);
    featSoA.push(7, assetIdx, volOfVol);
    featSoA.push(8, assetIdx, persistence);
  }

  void computeCorrelationMatrixCPU() {
    for(int i=0;i<N_ASSETS*N_ASSETS;i++) corrMatrix[i] = 0;

    for(int f=0; f<FEAT_N; f++){
      for(int a=0; a<N_ASSETS; a++){
        for(int b=a+1; b<N_ASSETS; b++){
          fvar mx = 0, my = 0;
          for(int t=0; t<FEAT_WINDOW; t++){
            mx += featSoA.get(f,a,t);
            my += featSoA.get(f,b,t);
          }
          mx /= (fvar)FEAT_WINDOW;
          my /= (fvar)FEAT_WINDOW;

          fvar sxx = 0, syy = 0, sxy = 0;
          for(int t=0; t<FEAT_WINDOW; t++){
            fvar dx = featSoA.get(f,a,t) - mx;
            fvar dy = featSoA.get(f,b,t) - my;
            sxx += dx*dx;
            syy += dy*dy;
            sxy += dx*dy;
          }

          fvar den = (fvar)sqrt((double)(sxx*syy + (fvar)EPS));
          fvar corr = 0;
          if(den > (fvar)EPS) corr = sxy / den;
          else corr = 0;

          int idx = a*N_ASSETS + b;
          corrMatrix[idx] += corr / (fvar)FEAT_N;
          corrMatrix[b*N_ASSETS + a] = corrMatrix[idx];
        }
      }
    }
  }

  void buildFeatLinear() {
    int idx = 0;
    for(int f=0; f<FEAT_N; f++){
      for(int a=0; a<N_ASSETS; a++){
        for(int t=0; t<FEAT_WINDOW; t++){
          featLinear[idx] = (float)featSoA.get(f, a, t);
          idx++;
        }
      }
    }
  }

  void computeCorrelationMatrix() {
    if(openCL.ready) {
      buildFeatLinear();

      for(int i=0;i<N_ASSETS*N_ASSETS;i++) corrLinear[i] = 0.0f;

      int ok = openCL.computeCorrelationMatrixCL(
        featLinear.data,
        corrLinear.data,
        N_ASSETS,
        FEAT_N,
        FEAT_WINDOW
      );

      if(ok) {
        for(int i=0;i<N_ASSETS*N_ASSETS;i++) corrMatrix[i] = (fvar)0;

        for(int a=0; a<N_ASSETS; a++){
          corrMatrix[a*N_ASSETS + a] = (fvar)1.0;
          for(int b=a+1; b<N_ASSETS; b++){
            float c = corrLinear[a*N_ASSETS + b];
            corrMatrix[a*N_ASSETS + b] = (fvar)c;
            corrMatrix[b*N_ASSETS + a] = (fvar)c;
          }
        }
        return;
      }

      printf("OpenCL: runtime fail -> CPU fallback\n");
      openCL.ready = 0;
    }

    computeCorrelationMatrixCPU();
  }

  void computeDistanceMatrix() {
    for(int i=0;i<N_ASSETS;i++){
      for(int j=0;j<N_ASSETS;j++){
        if(i == j) {
          distMatrix[i*N_ASSETS + j] = (fvar)0;
        } else {
          fvar corrDist = (fvar)1.0 - (fvar)fabs((double)corrMatrix[i*N_ASSETS + j]);
          fvar expDist  = (fvar)exposureTable.getDist(i, j);
          fvar blended = (fvar)LAMBDA_META * corrDist + (fvar)(1.0 - (double)LAMBDA_META) * expDist;
          distMatrix[i*N_ASSETS + j] = blended;
        }
      }
    }
  }

  void floydWarshall() {
    fvar d[28][28];

    for(int i=0;i<N_ASSETS;i++){
      for(int j=0;j<N_ASSETS;j++){
        d[i][j] = distMatrix[i*N_ASSETS + j];
        if(i == j) d[i][j] = (fvar)0;
        if(d[i][j] < (fvar)0) d[i][j] = (fvar)INF;
      }
    }

    for(int k=0;k<N_ASSETS;k++){
      for(int i=0;i<N_ASSETS;i++){
        for(int j=0;j<N_ASSETS;j++){
          if(d[i][k] < (fvar)INF && d[k][j] < (fvar)INF) {
            fvar nk = d[i][k] + d[k][j];
            if(nk < d[i][j]) d[i][j] = nk;
          }
        }
      }
    }

    for(int i=0;i<N_ASSETS;i++){
      fvar w = 0;
      for(int j=i+1;j<N_ASSETS;j++){
        if(d[i][j] < (fvar)INF) w += d[i][j];
      }
      if(w > (fvar)0) compactness[i] = (fvar)(1.0 / (1.0 + (double)w));
      else compactness[i] = (fvar)0;
      momentum[i] = featSoA.get(1, i, 0);
    }
  }

  void computeScores() {
    for(int i=0;i<N_ASSETS;i++){
      fvar coupling = 0;
      int count = 0;

      for(int j=0;j<N_ASSETS;j++){
        if(i != j && distMatrix[i*N_ASSETS + j] < (fvar)INF) {
          coupling += compactness[j];
          count++;
        }
      }

      fvar pCouple = 0;
      if(count > 0) pCouple = coupling / (fvar)count;
      else pCouple = (fvar)0;

      fvar rawScore = (fvar)GAMMA * momentum[i] + (fvar)ALPHA * compactness[i] - (fvar)BETA * pCouple;

      if(rawScore > (fvar)30) rawScore = (fvar)30;
      if(rawScore < (fvar)-30) rawScore = (fvar)-30;

      scores[i] = (fvar)(1.0 / (1.0 + exp(-(double)rawScore)));
    }
  }

  void onBar() {
    barCount++;

    for(int i=0;i<N_ASSETS;i++) computeFeatures(i);

    if(barCount % UPDATE_EVERY == 0) {
      updateCount++;

      computeCorrelationMatrix();
      computeDistanceMatrix();
      floydWarshall();
      computeScores();
      printTopK();
    }
  }

  void printTopK() {
    int indices[N_ASSETS];
    for(int i=0;i<N_ASSETS;i++) indices[i] = i;

    for(int i=0;i<TOP_K;i++){
      for(int j=i+1;j<N_ASSETS;j++){
        if(scores[indices[j]] > scores[indices[i]]) {
          int tmp = indices[i];
          indices[i] = indices[j];
          indices[j] = tmp;
        }
      }
    }

    if(updateCount % 10 == 0) {
      printf("===MomentumBias_v3 Top-K(update#%d,OpenCL=%d)===\n",
        updateCount, openCL.ready);

      for(int i=0;i<TOP_K;i++){
        int idx = indices[i];
        printf(" %d.%s: score=%.4f, M=%.4f, C=%.4f\n", i+1, ASSET_NAMES[idx], (double)scores[idx], (double)momentum[idx], (double)compactness[idx]);
      }
    }
  }
};

// ---------------------------- Zorro DLL entry ----------------------------

static MomentumBiasStrategy* S = NULL;

DLLFUNC void run()
{
  if(is(INITRUN)) {
    BarPeriod = 60;
    LookBack = max(LookBack, FEAT_WINDOW + 50);

    asset((char*)ASSET_NAMES[0]);

    if(!S) {
      S = new MomentumBiasStrategy();
      S->init();
    }
  }

  if(is(EXITRUN)) {
    if(S) {
      S->shutdown();
      delete S;
      S = NULL;
    }
    return;
  }

  if(!S) return;
  if(Bar < LookBack) return;
  if(!S->isReady) return;

  S->onBar();
}