[v0.24] Remove cuda-samples dependency

src/cuda/gpufetch_helper_cuda.hpp

@@ -0,0 +1,60 @@
+#ifndef __GPUFETCH_HELPER_CUDA__
+#define __GPUFETCH_HELPER_CUDA__
+
+// gpufetch self contained helper_cuda.h
+//
+// Avoids relying on helper_cuda.h, which is
+// often very hard to include properly, causing
+// compilation issues.
+//
+// URL: https://github.com/NVIDIA/cuda-samples
+// Commit: 2e41896
+
+inline int _ConvertSMVer2Cores(int major, int minor) {
+  // Defines for GPU Architecture types (using the SM version to determine
+  // the # of cores per SM
+  typedef struct {
+    int SM;  // 0xMm (hexidecimal notation), M = SM Major version,
+    // and m = SM minor version
+    int Cores;
+  } sSMtoCores;
+
+  sSMtoCores nGpuArchCoresPerSM[] = {
+      {0x30, 192},
+      {0x32, 192},
+      {0x35, 192},
+      {0x37, 192},
+      {0x50, 128},
+      {0x52, 128},
+      {0x53, 128},
+      {0x60,  64},
+      {0x61, 128},
+      {0x62, 128},
+      {0x70,  64},
+      {0x72,  64},
+      {0x75,  64},
+      {0x80,  64},
+      {0x86, 128},
+      {0x87, 128},
+      {-1, -1}};
+
+  int index = 0;
+
+  while (nGpuArchCoresPerSM[index].SM != -1) {
+    if (nGpuArchCoresPerSM[index].SM == ((major << 4) + minor)) {
+      return nGpuArchCoresPerSM[index].Cores;
+    }
+
+    index++;
+  }
+
+  // If we don't find the values, we default use the previous one
+  // to run properly
+  printf(
+      "MapSMtoCores for SM %d.%d is undefined."
+      "  Default to use %d Cores/SM\n",
+      major, minor, nGpuArchCoresPerSM[index - 1].Cores);
+  return nGpuArchCoresPerSM[index - 1].Cores;
+}
+
+#endif