Files
test/intern/cycles/kernel/device/optix/kernel.cu

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

59 lines
2.2 KiB
Plaintext
Raw Normal View History

/* SPDX-License-Identifier: Apache-2.0
* Copyright 2019, NVIDIA Corporation.
* Copyright 2019-2022 Blender Foundation. */
// clang-format off
#include "kernel/device/optix/compat.h"
#include "kernel/device/optix/globals.h"
Cycles: Rework OptiX visibility flags handling Before the visibility test against the visibility flags was performed in an any-hit program in OptiX (called `__anyhit__kernel_optix_visibility_test`), which was using the `__prim_visibility` array. This is not entirely correct however, since `__prim_visibility` is filled with the merged visibility flags of all objects that reference that primitive, so if one object uses different visibility flags than another object, but they both are instances of the same geometry, they would appear the same way. The reason that the any-hit program was used rather than the OptiX instance visibility mask is that the latter is currently limited to 8 bits only, which is not sufficient to contain all Cycles visibility flags (12 bits). To mostly fix the problem with multiple instances and different visibility flags, I changed things to use the OptiX instance visibility mask for a subset of the Cycles visibility flags (`PATH_RAY_CAMERA` to `PATH_RAY_VOLUME_SCATTER`, which fit into 8 bits) and only fall back to the visibility test any-hit program if that isn't enough (e.g. the ray visibility mask exceeds 8 bits or when using the built-in curves from OptiX, since the any-hit program is then also used to skip the curve endcaps). This may also improve performance in some cases, since by default OptiX can now perform the normal scene intersection trace calls entirely on RT cores without having to jump back to the SM on every hit to execute the any-hit program. Fixes T89801 Differential Revision: https://developer.blender.org/D12604
2021-09-22 16:23:08 +02:00
#include "kernel/device/gpu/image.h" /* Texture lookup uses normal CUDA intrinsics. */
#include "kernel/tables.h"
#include "kernel/integrator/state.h"
#include "kernel/integrator/state_flow.h"
#include "kernel/integrator/state_util.h"
#include "kernel/integrator/intersect_closest.h"
#include "kernel/integrator/intersect_shadow.h"
#include "kernel/integrator/intersect_subsurface.h"
#include "kernel/integrator/intersect_volume_stack.h"
// clang-format on
extern "C" __global__ void __raygen__kernel_optix_integrator_intersect_closest()
{
const int global_index = optixGetLaunchIndex().x;
const int path_index = (kernel_params.path_index_array) ?
kernel_params.path_index_array[global_index] :
global_index;
integrator_intersect_closest(nullptr, path_index, kernel_params.render_buffer);
}
extern "C" __global__ void __raygen__kernel_optix_integrator_intersect_shadow()
{
const int global_index = optixGetLaunchIndex().x;
const int path_index = (kernel_params.path_index_array) ?
kernel_params.path_index_array[global_index] :
global_index;
integrator_intersect_shadow(nullptr, path_index);
}
extern "C" __global__ void __raygen__kernel_optix_integrator_intersect_subsurface()
{
const int global_index = optixGetLaunchIndex().x;
const int path_index = (kernel_params.path_index_array) ?
kernel_params.path_index_array[global_index] :
global_index;
integrator_intersect_subsurface(nullptr, path_index);
}
extern "C" __global__ void __raygen__kernel_optix_integrator_intersect_volume_stack()
{
const int global_index = optixGetLaunchIndex().x;
const int path_index = (kernel_params.path_index_array) ?
kernel_params.path_index_array[global_index] :
global_index;
integrator_intersect_volume_stack(nullptr, path_index);
}