bevy/crates/bevy_pbr/src/render/shadows.wgsl

135 lines
6.8 KiB
WebGPU Shading Language
Raw Normal View History

#define_import_path bevy_pbr::shadows
fn fetch_point_shadow(light_id: u32, frag_position: vec4<f32>, surface_normal: vec3<f32>) -> f32 {
let light = &point_lights.data[light_id];
// because the shadow maps align with the axes and the frustum planes are at 45 degrees
// we can get the worldspace depth by taking the largest absolute axis
let surface_to_light = (*light).position_radius.xyz - frag_position.xyz;
let surface_to_light_abs = abs(surface_to_light);
let distance_to_light = max(surface_to_light_abs.x, max(surface_to_light_abs.y, surface_to_light_abs.z));
// The normal bias here is already scaled by the texel size at 1 world unit from the light.
// The texel size increases proportionally with distance from the light so multiplying by
// distance to light scales the normal bias to the texel size at the fragment distance.
let normal_offset = (*light).shadow_normal_bias * distance_to_light * surface_normal.xyz;
let depth_offset = (*light).shadow_depth_bias * normalize(surface_to_light.xyz);
let offset_position = frag_position.xyz + normal_offset + depth_offset;
// similar largest-absolute-axis trick as above, but now with the offset fragment position
let frag_ls = (*light).position_radius.xyz - offset_position.xyz;
let abs_position_ls = abs(frag_ls);
let major_axis_magnitude = max(abs_position_ls.x, max(abs_position_ls.y, abs_position_ls.z));
// NOTE: These simplifications come from multiplying:
// projection * vec4(0, 0, -major_axis_magnitude, 1.0)
// and keeping only the terms that have any impact on the depth.
// Projection-agnostic approach:
let zw = -major_axis_magnitude * (*light).light_custom_data.xy + (*light).light_custom_data.zw;
let depth = zw.x / zw.y;
// do the lookup, using HW PCF and comparison
// NOTE: Due to the non-uniform control flow above, we must use the Level variant of
// textureSampleCompare to avoid undefined behaviour due to some of the fragments in
// a quad (2x2 fragments) being processed not being sampled, and this messing with
// mip-mapping functionality. The shadow maps have no mipmaps so Level just samples
// from LOD 0.
#ifdef NO_ARRAY_TEXTURES_SUPPORT
return textureSampleCompare(point_shadow_textures, point_shadow_textures_sampler, frag_ls, depth);
#else
return textureSampleCompareLevel(point_shadow_textures, point_shadow_textures_sampler, frag_ls, i32(light_id), depth);
#endif
}
Spotlights (#4715) # Objective add spotlight support ## Solution / Changelog - add spotlight angles (inner, outer) to ``PointLight`` struct. emitted light is linearly attenuated from 100% to 0% as angle tends from inner to outer. Direction is taken from the existing transform rotation. - add spotlight direction (vec3) and angles (f32,f32) to ``GpuPointLight`` struct (60 bytes -> 80 bytes) in ``pbr/render/lights.rs`` and ``mesh_view_bind_group.wgsl`` - reduce no-buffer-support max point light count to 204 due to above - use spotlight data to attenuate light in ``pbr.wgsl`` - do additional cluster culling on spotlights to minimise cost in ``assign_lights_to_clusters`` - changed one of the lights in the lighting demo to a spotlight - also added a ``spotlight`` demo - probably not justified but so reviewers can see it more easily ## notes increasing the size of the GpuPointLight struct on my machine reduces the FPS of ``many_lights -- sphere`` from ~150fps to 140fps. i thought this was a reasonable tradeoff, and felt better than handling spotlights separately which is possible but would mean introducing a new bind group, refactoring light-assignment code and adding new spotlight-specific code in pbr.wgsl. the FPS impact for smaller numbers of lights should be very small. the cluster culling strategy reintroduces the cluster aabb code which was recently removed... sorry. the aabb is used to get a cluster bounding sphere, which can then be tested fairly efficiently using the strategy described at the end of https://bartwronski.com/2017/04/13/cull-that-cone/. this works well with roughly cubic clusters (where the cluster z size is close to the same as x/y size), less well for other cases like single Z slice / tiled forward rendering. In the worst case we will end up just keeping the culling of the equivalent point light. Co-authored-by: François <mockersf@gmail.com>
2022-07-08 19:57:43 +00:00
fn fetch_spot_shadow(light_id: u32, frag_position: vec4<f32>, surface_normal: vec3<f32>) -> f32 {
let light = &point_lights.data[light_id];
Spotlights (#4715) # Objective add spotlight support ## Solution / Changelog - add spotlight angles (inner, outer) to ``PointLight`` struct. emitted light is linearly attenuated from 100% to 0% as angle tends from inner to outer. Direction is taken from the existing transform rotation. - add spotlight direction (vec3) and angles (f32,f32) to ``GpuPointLight`` struct (60 bytes -> 80 bytes) in ``pbr/render/lights.rs`` and ``mesh_view_bind_group.wgsl`` - reduce no-buffer-support max point light count to 204 due to above - use spotlight data to attenuate light in ``pbr.wgsl`` - do additional cluster culling on spotlights to minimise cost in ``assign_lights_to_clusters`` - changed one of the lights in the lighting demo to a spotlight - also added a ``spotlight`` demo - probably not justified but so reviewers can see it more easily ## notes increasing the size of the GpuPointLight struct on my machine reduces the FPS of ``many_lights -- sphere`` from ~150fps to 140fps. i thought this was a reasonable tradeoff, and felt better than handling spotlights separately which is possible but would mean introducing a new bind group, refactoring light-assignment code and adding new spotlight-specific code in pbr.wgsl. the FPS impact for smaller numbers of lights should be very small. the cluster culling strategy reintroduces the cluster aabb code which was recently removed... sorry. the aabb is used to get a cluster bounding sphere, which can then be tested fairly efficiently using the strategy described at the end of https://bartwronski.com/2017/04/13/cull-that-cone/. this works well with roughly cubic clusters (where the cluster z size is close to the same as x/y size), less well for other cases like single Z slice / tiled forward rendering. In the worst case we will end up just keeping the culling of the equivalent point light. Co-authored-by: François <mockersf@gmail.com>
2022-07-08 19:57:43 +00:00
let surface_to_light = (*light).position_radius.xyz - frag_position.xyz;
Spotlights (#4715) # Objective add spotlight support ## Solution / Changelog - add spotlight angles (inner, outer) to ``PointLight`` struct. emitted light is linearly attenuated from 100% to 0% as angle tends from inner to outer. Direction is taken from the existing transform rotation. - add spotlight direction (vec3) and angles (f32,f32) to ``GpuPointLight`` struct (60 bytes -> 80 bytes) in ``pbr/render/lights.rs`` and ``mesh_view_bind_group.wgsl`` - reduce no-buffer-support max point light count to 204 due to above - use spotlight data to attenuate light in ``pbr.wgsl`` - do additional cluster culling on spotlights to minimise cost in ``assign_lights_to_clusters`` - changed one of the lights in the lighting demo to a spotlight - also added a ``spotlight`` demo - probably not justified but so reviewers can see it more easily ## notes increasing the size of the GpuPointLight struct on my machine reduces the FPS of ``many_lights -- sphere`` from ~150fps to 140fps. i thought this was a reasonable tradeoff, and felt better than handling spotlights separately which is possible but would mean introducing a new bind group, refactoring light-assignment code and adding new spotlight-specific code in pbr.wgsl. the FPS impact for smaller numbers of lights should be very small. the cluster culling strategy reintroduces the cluster aabb code which was recently removed... sorry. the aabb is used to get a cluster bounding sphere, which can then be tested fairly efficiently using the strategy described at the end of https://bartwronski.com/2017/04/13/cull-that-cone/. this works well with roughly cubic clusters (where the cluster z size is close to the same as x/y size), less well for other cases like single Z slice / tiled forward rendering. In the worst case we will end up just keeping the culling of the equivalent point light. Co-authored-by: François <mockersf@gmail.com>
2022-07-08 19:57:43 +00:00
// construct the light view matrix
var spot_dir = vec3<f32>((*light).light_custom_data.x, 0.0, (*light).light_custom_data.y);
Spotlights (#4715) # Objective add spotlight support ## Solution / Changelog - add spotlight angles (inner, outer) to ``PointLight`` struct. emitted light is linearly attenuated from 100% to 0% as angle tends from inner to outer. Direction is taken from the existing transform rotation. - add spotlight direction (vec3) and angles (f32,f32) to ``GpuPointLight`` struct (60 bytes -> 80 bytes) in ``pbr/render/lights.rs`` and ``mesh_view_bind_group.wgsl`` - reduce no-buffer-support max point light count to 204 due to above - use spotlight data to attenuate light in ``pbr.wgsl`` - do additional cluster culling on spotlights to minimise cost in ``assign_lights_to_clusters`` - changed one of the lights in the lighting demo to a spotlight - also added a ``spotlight`` demo - probably not justified but so reviewers can see it more easily ## notes increasing the size of the GpuPointLight struct on my machine reduces the FPS of ``many_lights -- sphere`` from ~150fps to 140fps. i thought this was a reasonable tradeoff, and felt better than handling spotlights separately which is possible but would mean introducing a new bind group, refactoring light-assignment code and adding new spotlight-specific code in pbr.wgsl. the FPS impact for smaller numbers of lights should be very small. the cluster culling strategy reintroduces the cluster aabb code which was recently removed... sorry. the aabb is used to get a cluster bounding sphere, which can then be tested fairly efficiently using the strategy described at the end of https://bartwronski.com/2017/04/13/cull-that-cone/. this works well with roughly cubic clusters (where the cluster z size is close to the same as x/y size), less well for other cases like single Z slice / tiled forward rendering. In the worst case we will end up just keeping the culling of the equivalent point light. Co-authored-by: François <mockersf@gmail.com>
2022-07-08 19:57:43 +00:00
// reconstruct spot dir from x/z and y-direction flag
spot_dir.y = sqrt(1.0 - spot_dir.x * spot_dir.x - spot_dir.z * spot_dir.z);
if (((*light).flags & POINT_LIGHT_FLAGS_SPOT_LIGHT_Y_NEGATIVE) != 0u) {
Spotlights (#4715) # Objective add spotlight support ## Solution / Changelog - add spotlight angles (inner, outer) to ``PointLight`` struct. emitted light is linearly attenuated from 100% to 0% as angle tends from inner to outer. Direction is taken from the existing transform rotation. - add spotlight direction (vec3) and angles (f32,f32) to ``GpuPointLight`` struct (60 bytes -> 80 bytes) in ``pbr/render/lights.rs`` and ``mesh_view_bind_group.wgsl`` - reduce no-buffer-support max point light count to 204 due to above - use spotlight data to attenuate light in ``pbr.wgsl`` - do additional cluster culling on spotlights to minimise cost in ``assign_lights_to_clusters`` - changed one of the lights in the lighting demo to a spotlight - also added a ``spotlight`` demo - probably not justified but so reviewers can see it more easily ## notes increasing the size of the GpuPointLight struct on my machine reduces the FPS of ``many_lights -- sphere`` from ~150fps to 140fps. i thought this was a reasonable tradeoff, and felt better than handling spotlights separately which is possible but would mean introducing a new bind group, refactoring light-assignment code and adding new spotlight-specific code in pbr.wgsl. the FPS impact for smaller numbers of lights should be very small. the cluster culling strategy reintroduces the cluster aabb code which was recently removed... sorry. the aabb is used to get a cluster bounding sphere, which can then be tested fairly efficiently using the strategy described at the end of https://bartwronski.com/2017/04/13/cull-that-cone/. this works well with roughly cubic clusters (where the cluster z size is close to the same as x/y size), less well for other cases like single Z slice / tiled forward rendering. In the worst case we will end up just keeping the culling of the equivalent point light. Co-authored-by: François <mockersf@gmail.com>
2022-07-08 19:57:43 +00:00
spot_dir.y = -spot_dir.y;
}
// view matrix z_axis is the reverse of transform.forward()
let fwd = -spot_dir;
let distance_to_light = dot(fwd, surface_to_light);
let offset_position =
-surface_to_light
+ ((*light).shadow_depth_bias * normalize(surface_to_light))
+ (surface_normal.xyz * (*light).shadow_normal_bias) * distance_to_light;
Spotlights (#4715) # Objective add spotlight support ## Solution / Changelog - add spotlight angles (inner, outer) to ``PointLight`` struct. emitted light is linearly attenuated from 100% to 0% as angle tends from inner to outer. Direction is taken from the existing transform rotation. - add spotlight direction (vec3) and angles (f32,f32) to ``GpuPointLight`` struct (60 bytes -> 80 bytes) in ``pbr/render/lights.rs`` and ``mesh_view_bind_group.wgsl`` - reduce no-buffer-support max point light count to 204 due to above - use spotlight data to attenuate light in ``pbr.wgsl`` - do additional cluster culling on spotlights to minimise cost in ``assign_lights_to_clusters`` - changed one of the lights in the lighting demo to a spotlight - also added a ``spotlight`` demo - probably not justified but so reviewers can see it more easily ## notes increasing the size of the GpuPointLight struct on my machine reduces the FPS of ``many_lights -- sphere`` from ~150fps to 140fps. i thought this was a reasonable tradeoff, and felt better than handling spotlights separately which is possible but would mean introducing a new bind group, refactoring light-assignment code and adding new spotlight-specific code in pbr.wgsl. the FPS impact for smaller numbers of lights should be very small. the cluster culling strategy reintroduces the cluster aabb code which was recently removed... sorry. the aabb is used to get a cluster bounding sphere, which can then be tested fairly efficiently using the strategy described at the end of https://bartwronski.com/2017/04/13/cull-that-cone/. this works well with roughly cubic clusters (where the cluster z size is close to the same as x/y size), less well for other cases like single Z slice / tiled forward rendering. In the worst case we will end up just keeping the culling of the equivalent point light. Co-authored-by: François <mockersf@gmail.com>
2022-07-08 19:57:43 +00:00
// the construction of the up and right vectors needs to precisely mirror the code
Spotlights (#4715) # Objective add spotlight support ## Solution / Changelog - add spotlight angles (inner, outer) to ``PointLight`` struct. emitted light is linearly attenuated from 100% to 0% as angle tends from inner to outer. Direction is taken from the existing transform rotation. - add spotlight direction (vec3) and angles (f32,f32) to ``GpuPointLight`` struct (60 bytes -> 80 bytes) in ``pbr/render/lights.rs`` and ``mesh_view_bind_group.wgsl`` - reduce no-buffer-support max point light count to 204 due to above - use spotlight data to attenuate light in ``pbr.wgsl`` - do additional cluster culling on spotlights to minimise cost in ``assign_lights_to_clusters`` - changed one of the lights in the lighting demo to a spotlight - also added a ``spotlight`` demo - probably not justified but so reviewers can see it more easily ## notes increasing the size of the GpuPointLight struct on my machine reduces the FPS of ``many_lights -- sphere`` from ~150fps to 140fps. i thought this was a reasonable tradeoff, and felt better than handling spotlights separately which is possible but would mean introducing a new bind group, refactoring light-assignment code and adding new spotlight-specific code in pbr.wgsl. the FPS impact for smaller numbers of lights should be very small. the cluster culling strategy reintroduces the cluster aabb code which was recently removed... sorry. the aabb is used to get a cluster bounding sphere, which can then be tested fairly efficiently using the strategy described at the end of https://bartwronski.com/2017/04/13/cull-that-cone/. this works well with roughly cubic clusters (where the cluster z size is close to the same as x/y size), less well for other cases like single Z slice / tiled forward rendering. In the worst case we will end up just keeping the culling of the equivalent point light. Co-authored-by: François <mockersf@gmail.com>
2022-07-08 19:57:43 +00:00
// in render/light.rs:spot_light_view_matrix
var sign = -1.0;
if (fwd.z >= 0.0) {
sign = 1.0;
}
let a = -1.0 / (fwd.z + sign);
let b = fwd.x * fwd.y * a;
let up_dir = vec3<f32>(1.0 + sign * fwd.x * fwd.x * a, sign * b, -sign * fwd.x);
let right_dir = vec3<f32>(-b, -sign - fwd.y * fwd.y * a, fwd.y);
let light_inv_rot = mat3x3<f32>(right_dir, up_dir, fwd);
// because the matrix is a pure rotation matrix, the inverse is just the transpose, and to calculate
// the product of the transpose with a vector we can just post-multiply instead of pre-multplying.
Spotlights (#4715) # Objective add spotlight support ## Solution / Changelog - add spotlight angles (inner, outer) to ``PointLight`` struct. emitted light is linearly attenuated from 100% to 0% as angle tends from inner to outer. Direction is taken from the existing transform rotation. - add spotlight direction (vec3) and angles (f32,f32) to ``GpuPointLight`` struct (60 bytes -> 80 bytes) in ``pbr/render/lights.rs`` and ``mesh_view_bind_group.wgsl`` - reduce no-buffer-support max point light count to 204 due to above - use spotlight data to attenuate light in ``pbr.wgsl`` - do additional cluster culling on spotlights to minimise cost in ``assign_lights_to_clusters`` - changed one of the lights in the lighting demo to a spotlight - also added a ``spotlight`` demo - probably not justified but so reviewers can see it more easily ## notes increasing the size of the GpuPointLight struct on my machine reduces the FPS of ``many_lights -- sphere`` from ~150fps to 140fps. i thought this was a reasonable tradeoff, and felt better than handling spotlights separately which is possible but would mean introducing a new bind group, refactoring light-assignment code and adding new spotlight-specific code in pbr.wgsl. the FPS impact for smaller numbers of lights should be very small. the cluster culling strategy reintroduces the cluster aabb code which was recently removed... sorry. the aabb is used to get a cluster bounding sphere, which can then be tested fairly efficiently using the strategy described at the end of https://bartwronski.com/2017/04/13/cull-that-cone/. this works well with roughly cubic clusters (where the cluster z size is close to the same as x/y size), less well for other cases like single Z slice / tiled forward rendering. In the worst case we will end up just keeping the culling of the equivalent point light. Co-authored-by: François <mockersf@gmail.com>
2022-07-08 19:57:43 +00:00
// this allows us to keep the matrix construction code identical between CPU and GPU.
let projected_position = offset_position * light_inv_rot;
// divide xy by perspective matrix "f" and by -projected.z (projected.z is -projection matrix's w)
// to get ndc coordinates
let f_div_minus_z = 1.0 / ((*light).spot_light_tan_angle * -projected_position.z);
Spotlights (#4715) # Objective add spotlight support ## Solution / Changelog - add spotlight angles (inner, outer) to ``PointLight`` struct. emitted light is linearly attenuated from 100% to 0% as angle tends from inner to outer. Direction is taken from the existing transform rotation. - add spotlight direction (vec3) and angles (f32,f32) to ``GpuPointLight`` struct (60 bytes -> 80 bytes) in ``pbr/render/lights.rs`` and ``mesh_view_bind_group.wgsl`` - reduce no-buffer-support max point light count to 204 due to above - use spotlight data to attenuate light in ``pbr.wgsl`` - do additional cluster culling on spotlights to minimise cost in ``assign_lights_to_clusters`` - changed one of the lights in the lighting demo to a spotlight - also added a ``spotlight`` demo - probably not justified but so reviewers can see it more easily ## notes increasing the size of the GpuPointLight struct on my machine reduces the FPS of ``many_lights -- sphere`` from ~150fps to 140fps. i thought this was a reasonable tradeoff, and felt better than handling spotlights separately which is possible but would mean introducing a new bind group, refactoring light-assignment code and adding new spotlight-specific code in pbr.wgsl. the FPS impact for smaller numbers of lights should be very small. the cluster culling strategy reintroduces the cluster aabb code which was recently removed... sorry. the aabb is used to get a cluster bounding sphere, which can then be tested fairly efficiently using the strategy described at the end of https://bartwronski.com/2017/04/13/cull-that-cone/. this works well with roughly cubic clusters (where the cluster z size is close to the same as x/y size), less well for other cases like single Z slice / tiled forward rendering. In the worst case we will end up just keeping the culling of the equivalent point light. Co-authored-by: François <mockersf@gmail.com>
2022-07-08 19:57:43 +00:00
let shadow_xy_ndc = projected_position.xy * f_div_minus_z;
// convert to uv coordinates
let shadow_uv = shadow_xy_ndc * vec2<f32>(0.5, -0.5) + vec2<f32>(0.5, 0.5);
// 0.1 must match POINT_LIGHT_NEAR_Z
let depth = 0.1 / -projected_position.z;
#ifdef NO_ARRAY_TEXTURES_SUPPORT
return textureSampleCompare(directional_shadow_textures, directional_shadow_textures_sampler,
Spotlights (#4715) # Objective add spotlight support ## Solution / Changelog - add spotlight angles (inner, outer) to ``PointLight`` struct. emitted light is linearly attenuated from 100% to 0% as angle tends from inner to outer. Direction is taken from the existing transform rotation. - add spotlight direction (vec3) and angles (f32,f32) to ``GpuPointLight`` struct (60 bytes -> 80 bytes) in ``pbr/render/lights.rs`` and ``mesh_view_bind_group.wgsl`` - reduce no-buffer-support max point light count to 204 due to above - use spotlight data to attenuate light in ``pbr.wgsl`` - do additional cluster culling on spotlights to minimise cost in ``assign_lights_to_clusters`` - changed one of the lights in the lighting demo to a spotlight - also added a ``spotlight`` demo - probably not justified but so reviewers can see it more easily ## notes increasing the size of the GpuPointLight struct on my machine reduces the FPS of ``many_lights -- sphere`` from ~150fps to 140fps. i thought this was a reasonable tradeoff, and felt better than handling spotlights separately which is possible but would mean introducing a new bind group, refactoring light-assignment code and adding new spotlight-specific code in pbr.wgsl. the FPS impact for smaller numbers of lights should be very small. the cluster culling strategy reintroduces the cluster aabb code which was recently removed... sorry. the aabb is used to get a cluster bounding sphere, which can then be tested fairly efficiently using the strategy described at the end of https://bartwronski.com/2017/04/13/cull-that-cone/. this works well with roughly cubic clusters (where the cluster z size is close to the same as x/y size), less well for other cases like single Z slice / tiled forward rendering. In the worst case we will end up just keeping the culling of the equivalent point light. Co-authored-by: François <mockersf@gmail.com>
2022-07-08 19:57:43 +00:00
shadow_uv, depth);
#else
return textureSampleCompareLevel(directional_shadow_textures, directional_shadow_textures_sampler,
Spotlights (#4715) # Objective add spotlight support ## Solution / Changelog - add spotlight angles (inner, outer) to ``PointLight`` struct. emitted light is linearly attenuated from 100% to 0% as angle tends from inner to outer. Direction is taken from the existing transform rotation. - add spotlight direction (vec3) and angles (f32,f32) to ``GpuPointLight`` struct (60 bytes -> 80 bytes) in ``pbr/render/lights.rs`` and ``mesh_view_bind_group.wgsl`` - reduce no-buffer-support max point light count to 204 due to above - use spotlight data to attenuate light in ``pbr.wgsl`` - do additional cluster culling on spotlights to minimise cost in ``assign_lights_to_clusters`` - changed one of the lights in the lighting demo to a spotlight - also added a ``spotlight`` demo - probably not justified but so reviewers can see it more easily ## notes increasing the size of the GpuPointLight struct on my machine reduces the FPS of ``many_lights -- sphere`` from ~150fps to 140fps. i thought this was a reasonable tradeoff, and felt better than handling spotlights separately which is possible but would mean introducing a new bind group, refactoring light-assignment code and adding new spotlight-specific code in pbr.wgsl. the FPS impact for smaller numbers of lights should be very small. the cluster culling strategy reintroduces the cluster aabb code which was recently removed... sorry. the aabb is used to get a cluster bounding sphere, which can then be tested fairly efficiently using the strategy described at the end of https://bartwronski.com/2017/04/13/cull-that-cone/. this works well with roughly cubic clusters (where the cluster z size is close to the same as x/y size), less well for other cases like single Z slice / tiled forward rendering. In the worst case we will end up just keeping the culling of the equivalent point light. Co-authored-by: François <mockersf@gmail.com>
2022-07-08 19:57:43 +00:00
shadow_uv, i32(light_id) + lights.spot_light_shadowmap_offset, depth);
#endif
}
fn fetch_directional_shadow(light_id: u32, frag_position: vec4<f32>, surface_normal: vec3<f32>) -> f32 {
let light = &lights.directional_lights[light_id];
// The normal bias is scaled to the texel size.
let normal_offset = (*light).shadow_normal_bias * surface_normal.xyz;
let depth_offset = (*light).shadow_depth_bias * (*light).direction_to_light.xyz;
let offset_position = vec4<f32>(frag_position.xyz + normal_offset + depth_offset, frag_position.w);
let offset_position_clip = (*light).view_projection * offset_position;
if (offset_position_clip.w <= 0.0) {
return 1.0;
}
let offset_position_ndc = offset_position_clip.xyz / offset_position_clip.w;
// No shadow outside the orthographic projection volume
if (any(offset_position_ndc.xy < vec2<f32>(-1.0)) || offset_position_ndc.z < 0.0
|| any(offset_position_ndc > vec3<f32>(1.0))) {
return 1.0;
}
// compute texture coordinates for shadow lookup, compensating for the Y-flip difference
// between the NDC and texture coordinates
let flip_correction = vec2<f32>(0.5, -0.5);
let light_local = offset_position_ndc.xy * flip_correction + vec2<f32>(0.5, 0.5);
let depth = offset_position_ndc.z;
// do the lookup, using HW PCF and comparison
// NOTE: Due to non-uniform control flow above, we must use the level variant of the texture
// sampler to avoid use of implicit derivatives causing possible undefined behavior.
#ifdef NO_ARRAY_TEXTURES_SUPPORT
return textureSampleCompareLevel(directional_shadow_textures, directional_shadow_textures_sampler, light_local, depth);
#else
return textureSampleCompareLevel(directional_shadow_textures, directional_shadow_textures_sampler, light_local, i32(light_id), depth);
#endif
}