// Raw-pointer launch interface for the pathtracer-diff kernels. Torch-free so
// the .cu never sees libtorch headers (required for local MSVC builds).
#pragma once

#include <cuda_runtime_api.h>

extern "C" {

// All device pointers; ints/floats are host scalars. env*/med* may be
// null/0 when absent.
struct PtdSceneArgs {
  const float* tris;         // [F, 9]
  const int* mat_ids;        // [F]
  const float* uvs;          // [F, 3, 2]
  int n_faces;
  const float* nodes_f;      // [N, 6]
  const int* nodes_i;        // [N, 3]
  int n_nodes;
  const int* light_faces;    // [L]
  const float* light_cdf;    // [L]
  int n_lights;
  float total_light_area;
  const float* tex;          // [T, 3] albedo texels
  const int* tex_hdr;        // [M, 3]
  int n_texels;
  const float* emi_tex;      // [Te, 3] emission texels
  const int* emi_hdr;        // [M, 3]
  int n_emi_texels;
  const int* mat_type;       // [M] 0 diffuse | 1 conductor | 2 dielectric |
                             //     3 plastic | 4 rough dielectric
  const float* mat_rough;    // [M]
  const float* mat_ior;      // [M]
  int n_mats;
  const float* med_sa;       // [3] live absorption or null
  const float* med_ss;       // [3] live scattering
  float med_sbar;            // frozen sampling rate
  int has_med;
  const float* env;          // [Eh*Ew, 3] or null
  int env_w, env_h;
  const float* env_cdf_m;    // [Eh]
  const float* env_cdf_c;    // [Eh*Ew]
  const float* env_pdf;      // [Eh*Ew], sums to 1
};

void ptd_forward_launch(const PtdSceneArgs* args, const float* cam, int H,
                        int W, int spp, int max_bounces, int mode,
                        long long seed, float* image, cudaStream_t stream);

void ptd_backward_launch(const PtdSceneArgs* args, const float* cam, int H,
                         int W, int spp, int max_bounces, int mode,
                         long long seed, const float* grad_image,
                         float* grad_tex, float* grad_emi_tex,
                         float* grad_env, float* grad_med,
                         cudaStream_t stream);

}  // extern "C"