This repository has been archived on 2023-10-09. You can view files and clone it. You cannot open issues or pull requests or push a commit.
Files
blender-archive/intern/cycles/kernel/integrator/integrator_intersect_shadow.h
Michael Jones (Apple) a0f269f682 Cycles: Kernel address space changes for MSL
This is the first of a sequence of changes to support compiling Cycles kernels as MSL (Metal Shading Language) in preparation for a Metal GPU device implementation.

MSL requires that all pointer types be declared with explicit address space attributes (device, thread, etc...). There is already precedent for this with Cycles' address space macros (ccl_global, ccl_private, etc...), therefore the first step of MSL-enablement is to apply these consistently. Line-for-line this represents the largest change required to enable MSL. Applying this change first will simplify future patches as well as offering the emergent benefit of enhanced descriptiveness.

The vast majority of deltas in this patch fall into one of two cases:

- Ensuring ccl_private is specified for thread-local pointer types
- Ensuring ccl_global is specified for device-wide pointer types

Additionally, the ccl_addr_space qualifier can be removed. Prior to Cycles X, ccl_addr_space was used as a context-dependent address space qualifier, but now it is either redundant (e.g. in struct typedefs), or can be replaced by ccl_global in the case of pointer types. Associated function variants (e.g. lcg_step_float_addrspace) are also redundant.

In cases where address space qualifiers are chained with "const", this patch places the address space qualifier first. The rationale for this is that the choice of address space is likely to have the greater impact on runtime performance and overall architecture.

The final part of this patch is the addition of a metal/compat.h header. This is partially complete and will be extended in future patches, paving the way for the full Metal implementation.

Ref T92212

Reviewed By: brecht

Maniphest Tasks: T92212

Differential Revision: https://developer.blender.org/D12864
2021-10-14 16:14:43 +01:00

145 lines
5.1 KiB
C++

/*
* Copyright 2011-2021 Blender Foundation
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
#pragma once
CCL_NAMESPACE_BEGIN
/* Visibility for the shadow ray. */
ccl_device_forceinline uint integrate_intersect_shadow_visibility(INTEGRATOR_STATE_CONST_ARGS)
{
uint visibility = PATH_RAY_SHADOW;
#ifdef __SHADOW_CATCHER__
const uint32_t path_flag = INTEGRATOR_STATE(shadow_path, flag);
visibility = SHADOW_CATCHER_PATH_VISIBILITY(path_flag, visibility);
#endif
return visibility;
}
ccl_device bool integrate_intersect_shadow_opaque(INTEGRATOR_STATE_ARGS,
ccl_private const Ray *ray,
const uint visibility)
{
/* Mask which will pick only opaque visibility bits from the `visibility`.
* Calculate the mask at compile time: the visibility will either be a high bits for the shadow
* catcher objects, or lower bits for the regular objects (there is no need to check the path
* state here again). */
constexpr const uint opaque_mask = SHADOW_CATCHER_VISIBILITY_SHIFT(PATH_RAY_SHADOW_OPAQUE) |
PATH_RAY_SHADOW_OPAQUE;
Intersection isect;
const bool opaque_hit = scene_intersect(kg, ray, visibility & opaque_mask, &isect);
if (!opaque_hit) {
INTEGRATOR_STATE_WRITE(shadow_path, num_hits) = 0;
}
return opaque_hit;
}
ccl_device_forceinline int integrate_shadow_max_transparent_hits(INTEGRATOR_STATE_CONST_ARGS)
{
const int transparent_max_bounce = kernel_data.integrator.transparent_max_bounce;
const int transparent_bounce = INTEGRATOR_STATE(shadow_path, transparent_bounce);
return max(transparent_max_bounce - transparent_bounce - 1, 0);
}
#ifdef __TRANSPARENT_SHADOWS__
ccl_device bool integrate_intersect_shadow_transparent(INTEGRATOR_STATE_ARGS,
ccl_private const Ray *ray,
const uint visibility)
{
Intersection isect[INTEGRATOR_SHADOW_ISECT_SIZE];
/* Limit the number hits to the max transparent bounces allowed and the size that we
* have available in the integrator state. */
const uint max_transparent_hits = integrate_shadow_max_transparent_hits(INTEGRATOR_STATE_PASS);
const uint max_hits = min(max_transparent_hits, (uint)INTEGRATOR_SHADOW_ISECT_SIZE);
uint num_hits = 0;
bool opaque_hit = scene_intersect_shadow_all(kg, ray, isect, visibility, max_hits, &num_hits);
/* If number of hits exceed the transparent bounces limit, make opaque. */
if (num_hits > max_transparent_hits) {
opaque_hit = true;
}
if (!opaque_hit) {
uint num_recorded_hits = min(num_hits, max_hits);
if (num_recorded_hits > 0) {
sort_intersections(isect, num_recorded_hits);
/* Write intersection result into global integrator state memory. */
for (int hit = 0; hit < num_recorded_hits; hit++) {
integrator_state_write_shadow_isect(INTEGRATOR_STATE_PASS, &isect[hit], hit);
}
}
INTEGRATOR_STATE_WRITE(shadow_path, num_hits) = num_hits;
}
else {
INTEGRATOR_STATE_WRITE(shadow_path, num_hits) = 0;
}
return opaque_hit;
}
#endif
ccl_device void integrator_intersect_shadow(INTEGRATOR_STATE_ARGS)
{
PROFILING_INIT(kg, PROFILING_INTERSECT_SHADOW);
/* Read ray from integrator state into local memory. */
Ray ray ccl_optional_struct_init;
integrator_state_read_shadow_ray(INTEGRATOR_STATE_PASS, &ray);
/* Compute visibility. */
const uint visibility = integrate_intersect_shadow_visibility(INTEGRATOR_STATE_PASS);
#ifdef __TRANSPARENT_SHADOWS__
/* TODO: compile different kernels depending on this? Especially for OptiX
* conditional trace calls are bad. */
const bool opaque_hit =
(kernel_data.integrator.transparent_shadows) ?
integrate_intersect_shadow_transparent(INTEGRATOR_STATE_PASS, &ray, visibility) :
integrate_intersect_shadow_opaque(INTEGRATOR_STATE_PASS, &ray, visibility);
#else
const bool opaque_hit = integrate_intersect_shadow_opaque(
INTEGRATOR_STATE_PASS, &ray, visibility);
#endif
if (opaque_hit) {
/* Hit an opaque surface, shadow path ends here. */
INTEGRATOR_SHADOW_PATH_TERMINATE(DEVICE_KERNEL_INTEGRATOR_INTERSECT_SHADOW);
return;
}
else {
/* Hit nothing or transparent surfaces, continue to shadow kernel
* for shading and render buffer output.
*
* TODO: could also write to render buffer directly if no transparent shadows?
* Could save a kernel execution for the common case. */
INTEGRATOR_SHADOW_PATH_NEXT(DEVICE_KERNEL_INTEGRATOR_INTERSECT_SHADOW,
DEVICE_KERNEL_INTEGRATOR_SHADE_SHADOW);
return;
}
}
CCL_NAMESPACE_END