Clay custom dispatch improvements & DPI scaling fixes (#26)

Co-authored-by: Zachary Levy <zachary@sunforge.is>
Reviewed-on: #26
This commit was merged in pull request #26.
This commit is contained in:
2026-05-06 04:17:24 +00:00
parent e8ffa28de3
commit 43f08ed30c
19 changed files with 627 additions and 407 deletions
@@ -25,9 +25,9 @@ struct main0_in
{
float2 p_local [[user(locn0)]];
float4 f_color [[user(locn1)]];
float2 f_half_size [[user(locn2), flat]];
float4 f_radii [[user(locn3), flat]];
float f_half_feather [[user(locn4), flat]];
float2 f_half_size_ppx [[user(locn2), flat]];
float4 f_radii_ppx [[user(locn3), flat]];
float f_half_feather_ppx [[user(locn4), flat]];
};
static inline __attribute__((always_inline))
@@ -96,16 +96,16 @@ fragment main0_out main0(main0_in in [[stage_in]], constant Uniforms& _108 [[buf
return out;
}
float2 param_1 = in.p_local;
float2 param_2 = in.f_half_size;
float4 param_3 = in.f_radii;
float2 param_2 = in.f_half_size_ppx;
float4 param_3 = in.f_radii_ppx;
float d = sdRoundedBox(param_1, param_2, param_3);
if (d > in.f_half_feather)
if (d > in.f_half_feather_ppx)
{
discard_fragment();
}
float grad_magnitude = fast::max(fwidth(d), 9.9999999747524270787835121154785e-07);
float d_n = d / grad_magnitude;
float h_n = in.f_half_feather / grad_magnitude;
float h_n = in.f_half_feather_ppx / grad_magnitude;
float2 uv_1 = (gl_FragCoord.xy * _108.inv_downsample_factor) * _108.inv_working_size;
float3 color_1 = blur_input_tex.sample(blur_input_texSmplr, uv_1).xyz;
float3 tinted = mix(color_1, color_1 * in.f_color.xyz, float3(in.f_color.w));
Binary file not shown.
+18 -18
View File
@@ -55,18 +55,18 @@ struct Uniforms
struct Gaussian_Blur_Primitive
{
float4 bounds;
float4 radii;
float2 half_size;
float half_feather;
float4 radii_ppx;
float2 half_size_ppx;
float half_feather_ppx;
uint color;
};
struct Gaussian_Blur_Primitive_1
{
float4 bounds;
float4 radii;
float2 half_size;
float half_feather;
float4 radii_ppx;
float2 half_size_ppx;
float half_feather_ppx;
uint color;
};
@@ -81,9 +81,9 @@ struct main0_out
{
float2 p_local [[user(locn0)]];
float4 f_color [[user(locn1)]];
float2 f_half_size [[user(locn2)]];
float4 f_radii [[user(locn3)]];
float f_half_feather [[user(locn4)]];
float2 f_half_size_ppx [[user(locn2)]];
float4 f_radii_ppx [[user(locn3)]];
float f_half_feather_ppx [[user(locn4)]];
float4 gl_Position [[position]];
};
@@ -96,26 +96,26 @@ vertex main0_out main0(constant Uniforms& _13 [[buffer(0)]], const device Gaussi
out.gl_Position = float4(ndc, 0.0, 1.0);
out.p_local = float2(0.0);
out.f_color = float4(0.0);
out.f_half_size = float2(0.0);
out.f_radii = float4(0.0);
out.f_half_feather = 0.0;
out.f_half_size_ppx = float2(0.0);
out.f_radii_ppx = float4(0.0);
out.f_half_feather_ppx = 0.0;
}
else
{
Gaussian_Blur_Primitive p;
p.bounds = _69.primitives[int(gl_InstanceIndex)].bounds;
p.radii = _69.primitives[int(gl_InstanceIndex)].radii;
p.half_size = _69.primitives[int(gl_InstanceIndex)].half_size;
p.half_feather = _69.primitives[int(gl_InstanceIndex)].half_feather;
p.radii_ppx = _69.primitives[int(gl_InstanceIndex)].radii_ppx;
p.half_size_ppx = _69.primitives[int(gl_InstanceIndex)].half_size_ppx;
p.half_feather_ppx = _69.primitives[int(gl_InstanceIndex)].half_feather_ppx;
p.color = _69.primitives[int(gl_InstanceIndex)].color;
float2 corner = _97[int(gl_VertexIndex)];
float2 world_pos = mix(p.bounds.xy, p.bounds.zw, corner);
float2 center = (p.bounds.xy + p.bounds.zw) * 0.5;
out.p_local = (world_pos - center) * _13.dpi_scale;
out.f_color = unpack_unorm4x8_to_float(p.color);
out.f_half_size = p.half_size;
out.f_radii = p.radii;
out.f_half_feather = p.half_feather;
out.f_half_size_ppx = p.half_size_ppx;
out.f_radii_ppx = p.radii_ppx;
out.f_half_feather_ppx = p.half_feather_ppx;
out.gl_Position = _13.projection * float4(world_pos * _13.dpi_scale, 0.0, 1.0);
}
return out;
Binary file not shown.
+24 -24
View File
@@ -107,57 +107,57 @@ fragment main0_out main0(main0_in in [[stage_in]], texture2d<float> tex [[textur
}
float d = 1000000015047466219876688855040.0;
float h = 0.5;
float2 half_size = in.f_params.xy;
float2 p_local = in.f_local_or_uv;
float2 half_size_ppx = in.f_params.xy;
float2 p_local_ppx = in.f_local_or_uv;
if (kind == 1u)
{
float4 corner_radii = float4(in.f_params.zw, in.f_params2.xy);
float4 corner_radii_ppx = float4(in.f_params.zw, in.f_params2.xy);
h = in.f_params2.z;
float2 param = p_local;
float2 param_1 = half_size;
float4 param_2 = corner_radii;
float2 param = p_local_ppx;
float2 param_1 = half_size_ppx;
float4 param_2 = corner_radii_ppx;
d = sdRoundedBox(param, param_1, param_2);
}
else
{
if (kind == 2u)
{
float radius = in.f_params.x;
float radius_ppx = in.f_params.x;
float sides = in.f_params.y;
h = in.f_params.z;
float2 param_3 = p_local;
float param_4 = radius;
float2 param_3 = p_local_ppx;
float param_4 = radius_ppx;
float param_5 = sides;
d = sdRegularPolygon(param_3, param_4, param_5);
half_size = float2(radius);
half_size_ppx = float2(radius_ppx);
}
else
{
if (kind == 3u)
{
float2 ab = in.f_params.xy;
float2 radii_ppx = in.f_params.xy;
h = in.f_params.z;
float2 param_6 = p_local;
float2 param_7 = ab;
float2 param_6 = p_local_ppx;
float2 param_7 = radii_ppx;
d = sdEllipseApprox(param_6, param_7);
half_size = ab;
half_size_ppx = radii_ppx;
}
else
{
if (kind == 4u)
{
float inner = in.f_params.x;
float outer = in.f_params.y;
float inner_radius_ppx = in.f_params.x;
float outer_radius_ppx = in.f_params.y;
float2 n_start = in.f_params.zw;
float2 n_end = in.f_params2.xy;
uint arc_bits = (flags >> 5u) & 3u;
h = in.f_params2.z;
float r = length(p_local);
d = fast::max(inner - r, r - outer);
float r = length(p_local_ppx);
d = fast::max(inner_radius_ppx - r, r - outer_radius_ppx);
if (arc_bits != 0u)
{
float d_start = dot(p_local, n_start);
float d_end = dot(p_local, n_end);
float d_start = dot(p_local_ppx, n_start);
float d_end = dot(p_local_ppx, n_end);
float _338;
if (arc_bits == 1u)
{
@@ -170,7 +170,7 @@ fragment main0_out main0(main0_in in [[stage_in]], texture2d<float> tex [[textur
float d_wedge = _338;
d = fast::max(d, d_wedge);
}
half_size = float2(outer);
half_size_ppx = float2(outer_radius_ppx);
}
}
}
@@ -185,7 +185,7 @@ fragment main0_out main0(main0_in in [[stage_in]], texture2d<float> tex [[textur
float4 gradient_end = unpack_unorm4x8_to_float(in.f_effects.x);
if ((flags & 4u) != 0u)
{
float t_1 = length(p_local / half_size);
float t_1 = length(p_local_ppx / half_size_ppx);
float4 param_8 = gradient_start;
float4 param_9 = gradient_end;
float param_10 = t_1;
@@ -194,7 +194,7 @@ fragment main0_out main0(main0_in in [[stage_in]], texture2d<float> tex [[textur
else
{
float2 direction = float2(as_type<half2>(in.f_effects.z));
float t_2 = (dot(p_local / half_size, direction) * 0.5) + 0.5;
float t_2 = (dot(p_local_ppx / half_size_ppx, direction) * 0.5) + 0.5;
float4 param_11 = gradient_start;
float4 param_12 = gradient_end;
float param_13 = t_2;
@@ -206,7 +206,7 @@ fragment main0_out main0(main0_in in [[stage_in]], texture2d<float> tex [[textur
if ((flags & 1u) != 0u)
{
float4 uv_rect = in.f_uv_rect;
float2 local_uv = ((p_local / half_size) * 0.5) + float2(0.5);
float2 local_uv = ((p_local_ppx / half_size_ppx) * 0.5) + float2(0.5);
float2 uv = mix(uv_rect.xy, uv_rect.zw, local_uv);
shape_color = in.f_color * tex.sample(texSmplr, uv);
}
Binary file not shown.
+32 -22
View File
@@ -60,32 +60,21 @@ struct main0_in
float4 v_color [[attribute(2)]];
};
vertex main0_out main0(main0_in in [[stage_in]], constant Uniforms& _12 [[buffer(0)]], const device Core_2D_Primitives& _75 [[buffer(1)]], uint gl_InstanceIndex [[instance_id]])
vertex main0_out main0(main0_in in [[stage_in]], constant Uniforms& _12 [[buffer(0)]], const device Core_2D_Primitives& _31 [[buffer(1)]], uint gl_InstanceIndex [[instance_id]])
{
main0_out out = {};
if (_12.mode == 0u)
{
out.f_color = in.v_color;
out.f_local_or_uv = in.v_uv;
out.f_params = float4(0.0);
out.f_params2 = float4(0.0);
out.f_flags = 0u;
out.f_uv_rect = float4(0.0);
out.f_effects = uint4(0u);
out.gl_Position = _12.projection * float4(in.v_position * _12.dpi_scale, 0.0, 1.0);
}
else
if (_12.mode == 1u)
{
Core_2D_Primitive p;
p.bounds = _75.primitives[int(gl_InstanceIndex)].bounds;
p.color = _75.primitives[int(gl_InstanceIndex)].color;
p.flags = _75.primitives[int(gl_InstanceIndex)].flags;
p.rotation_sc = _75.primitives[int(gl_InstanceIndex)].rotation_sc;
p._pad = _75.primitives[int(gl_InstanceIndex)]._pad;
p.params = _75.primitives[int(gl_InstanceIndex)].params;
p.params2 = _75.primitives[int(gl_InstanceIndex)].params2;
p.uv_rect = _75.primitives[int(gl_InstanceIndex)].uv_rect;
p.effects = _75.primitives[int(gl_InstanceIndex)].effects;
p.bounds = _31.primitives[int(gl_InstanceIndex)].bounds;
p.color = _31.primitives[int(gl_InstanceIndex)].color;
p.flags = _31.primitives[int(gl_InstanceIndex)].flags;
p.rotation_sc = _31.primitives[int(gl_InstanceIndex)].rotation_sc;
p._pad = _31.primitives[int(gl_InstanceIndex)]._pad;
p.params = _31.primitives[int(gl_InstanceIndex)].params;
p.params2 = _31.primitives[int(gl_InstanceIndex)].params2;
p.uv_rect = _31.primitives[int(gl_InstanceIndex)].uv_rect;
p.effects = _31.primitives[int(gl_InstanceIndex)].effects;
float2 corner = in.v_position;
float2 world_pos = mix(p.bounds.xy, p.bounds.zw, corner);
float2 center = (p.bounds.xy + p.bounds.zw) * 0.5;
@@ -105,6 +94,27 @@ vertex main0_out main0(main0_in in [[stage_in]], constant Uniforms& _12 [[buffer
out.f_effects = p.effects;
out.gl_Position = _12.projection * float4(world_pos * _12.dpi_scale, 0.0, 1.0);
}
else
{
out.f_color = in.v_color;
out.f_local_or_uv = in.v_uv;
out.f_params = float4(0.0);
out.f_params2 = float4(0.0);
out.f_flags = 0u;
out.f_uv_rect = float4(0.0);
out.f_effects = uint4(0u);
float2 _199;
if (_12.mode == 2u)
{
_199 = in.v_position;
}
else
{
_199 = in.v_position * _12.dpi_scale;
}
float2 pos = _199;
out.gl_Position = _12.projection * float4(pos, 0.0, 1.0);
}
return out;
}
Binary file not shown.
+6 -6
View File
@@ -40,9 +40,9 @@ const uint MAX_KERNEL_PAIRS = 32;
// --- Inputs from vertex shader ---
layout(location = 0) in vec2 p_local;
layout(location = 1) in mediump vec4 f_color;
layout(location = 2) flat in vec2 f_half_size;
layout(location = 3) flat in vec4 f_radii;
layout(location = 4) flat in float f_half_feather;
layout(location = 2) flat in vec2 f_half_size_ppx;
layout(location = 3) flat in vec4 f_radii_ppx;
layout(location = 4) flat in float f_half_feather_ppx;
// --- Output ---
layout(location = 0) out vec4 out_color;
@@ -123,15 +123,15 @@ void main() {
// ---- Mode 1: composite per-primitive.
// RRect SDF — early discard for fragments well outside the masked region.
float d = sdRoundedBox(p_local, f_half_size, f_radii);
if (d > f_half_feather) {
float d = sdRoundedBox(p_local, f_half_size_ppx, f_radii_ppx);
if (d > f_half_feather_ppx) {
discard;
}
// fwidth-based normalization for AA (matches main pipeline approach).
float grad_magnitude = max(fwidth(d), 1e-6);
float d_n = d / grad_magnitude;
float h_n = f_half_feather / grad_magnitude;
float h_n = f_half_feather_ppx / grad_magnitude;
// Sample the fully-blurred working-res texture. gl_FragCoord is full-res; convert to
// working-res UV via inv_downsample_factor. No kernel is applied — the H+V blur passes
+16 -16
View File
@@ -24,12 +24,12 @@
layout(location = 0) out vec2 p_local;
// f_color: tint, unpacked from primitive.color. Only meaningful in mode 1.
layout(location = 1) out mediump vec4 f_color;
// f_half_size: RRect half extents in physical pixels (mode 1 only).
layout(location = 2) flat out vec2 f_half_size;
// f_radii: per-corner radii in physical pixels (mode 1 only).
layout(location = 3) flat out vec4 f_radii;
// f_half_feather: SDF anti-aliasing feather (mode 1 only).
layout(location = 4) flat out float f_half_feather;
// f_half_size_ppx: RRect half extents in physical pixels (mode 1 only).
layout(location = 2) flat out vec2 f_half_size_ppx;
// f_radii_ppx: per-corner radii in physical pixels (mode 1 only).
layout(location = 3) flat out vec4 f_radii_ppx;
// f_half_feather_ppx: SDF anti-aliasing feather in physical pixels (mode 1 only).
layout(location = 4) flat out float f_half_feather_ppx;
// --- Uniforms (set 1) ---
// Backdrop pipeline's own uniform block — distinct from the main pipeline's
@@ -53,10 +53,10 @@ layout(set = 1, binding = 0) uniform Uniforms {
// edge effects (e.g. liquid-glass-style refraction outlines) would be a dedicated
// primitive type with its own pipeline rather than a flag bit here.
struct Gaussian_Blur_Primitive {
vec4 bounds; // 0-15: min_xy, max_xy (world-space)
vec4 radii; // 16-31: per-corner radii (physical px)
vec2 half_size; // 32-39: RRect half extents (physical px)
float half_feather; // 40-43: SDF anti-aliasing feather (physical px)
vec4 bounds; // 0-15: min_xy, max_xy (world-space, logical px)
vec4 radii_ppx; // 16-31: per-corner radii
vec2 half_size_ppx; // 32-39: RRect half extents
float half_feather_ppx; // 40-43: SDF anti-aliasing feather
uint color; // 44-47: tint, packed RGBA u8x4
};
@@ -78,9 +78,9 @@ void main() {
// Mode 0 doesn't read the per-primitive varyings; zero-init for safety.
p_local = vec2(0.0);
f_color = vec4(0.0);
f_half_size = vec2(0.0);
f_radii = vec4(0.0);
f_half_feather = 0.0;
f_half_size_ppx = vec2(0.0);
f_radii_ppx = vec4(0.0);
f_half_feather_ppx = 0.0;
} else {
// ---- Mode 1: V-composite instanced unit-quad over Gaussian_Blur_Primitive ----
Gaussian_Blur_Primitive p = primitives[gl_InstanceIndex];
@@ -101,9 +101,9 @@ void main() {
p_local = (world_pos - center) * dpi_scale;
f_color = unpackUnorm4x8(p.color);
f_half_size = p.half_size;
f_radii = p.radii;
f_half_feather = p.half_feather;
f_half_size_ppx = p.half_size_ppx;
f_radii_ppx = p.radii_ppx;
f_half_feather_ppx = p.half_feather_ppx;
gl_Position = projection * vec4(world_pos * dpi_scale, 0.0, 1.0);
}
+26 -26
View File
@@ -45,7 +45,7 @@ float sdRegularPolygon(vec2 p, float r, float n) {
return length(p) * cos(bn) - r;
}
// Coverage from SDF distance using half-feather width (feather_px * 0.5, pre-computed on CPU).
// Coverage from SDF distance using half-feather width (feather_ppx * 0.5, pre-computed on CPU).
// Produces a symmetric transition centered on d=0: smoothstep(-h, h, d).
float sdf_alpha(float d, float h) {
return 1.0 - smoothstep(-h, h, d);
@@ -80,56 +80,56 @@ void main() {
// SDF path — dispatch on kind
float d = 1e30;
float h = 0.5; // half-feather width; overwritten per shape kind
vec2 half_size = f_params.xy; // used by RRect and as reference size for gradients
float h = 0.5; // half-feather width (physical px); overwritten per shape kind
vec2 half_size_ppx = f_params.xy; // used by RRect and as reference size for gradients
vec2 p_local = f_local_or_uv; // arrives rotated; vertex shader handled .Rotated
vec2 p_local_ppx = f_local_or_uv; // arrives rotated; vertex shader handled .Rotated
if (kind == 1u) {
// RRect — half_feather in params2.z
vec4 corner_radii = vec4(f_params.zw, f_params2.xy);
// RRect — half_feather_ppx in params2.z
vec4 corner_radii_ppx = vec4(f_params.zw, f_params2.xy);
h = f_params2.z;
d = sdRoundedBox(p_local, half_size, corner_radii);
d = sdRoundedBox(p_local_ppx, half_size_ppx, corner_radii_ppx);
}
else if (kind == 2u) {
// NGon — half_feather in params.z
float radius = f_params.x;
// NGon — half_feather_ppx in params.z
float radius_ppx = f_params.x;
float sides = f_params.y;
h = f_params.z;
d = sdRegularPolygon(p_local, radius, sides);
half_size = vec2(radius); // for gradient UV computation
d = sdRegularPolygon(p_local_ppx, radius_ppx, sides);
half_size_ppx = vec2(radius_ppx); // for gradient UV computation
}
else if (kind == 3u) {
// Ellipse — half_feather in params.z
vec2 ab = f_params.xy;
// Ellipse — half_feather_ppx in params.z
vec2 radii_ppx = f_params.xy;
h = f_params.z;
d = sdEllipseApprox(p_local, ab);
half_size = ab; // for gradient UV computation
d = sdEllipseApprox(p_local_ppx, radii_ppx);
half_size_ppx = radii_ppx; // for gradient UV computation
}
else if (kind == 4u) {
// Ring_Arc — half_feather in params2.z
// Ring_Arc — half_feather_ppx in params2.z
// Arc mode from flag bits 5-6: 0 = full, 1 = narrow (≤π), 2 = wide (>π)
float inner = f_params.x;
float outer = f_params.y;
float inner_radius_ppx = f_params.x;
float outer_radius_ppx = f_params.y;
vec2 n_start = f_params.zw;
vec2 n_end = f_params2.xy;
uint arc_bits = (flags >> 5u) & 3u;
h = f_params2.z;
float r = length(p_local);
d = max(inner - r, r - outer);
float r = length(p_local_ppx);
d = max(inner_radius_ppx - r, r - outer_radius_ppx);
if (arc_bits != 0u) {
float d_start = dot(p_local, n_start);
float d_end = dot(p_local, n_end);
float d_start = dot(p_local_ppx, n_start);
float d_end = dot(p_local_ppx, n_end);
float d_wedge = (arc_bits == 1u)
? max(d_start, d_end) // arc ≤ π: intersect half-planes
: min(d_start, d_end); // arc > π: union half-planes
d = max(d, d_wedge);
}
half_size = vec2(outer); // for gradient UV computation
half_size_ppx = vec2(outer_radius_ppx); // for gradient UV computation
}
// --- fwidth-based normalization for correct AA and stroke width ---
@@ -146,18 +146,18 @@ void main() {
if ((flags & 4u) != 0u) {
// Radial gradient (bit 2): t from distance to center
mediump float t = length(p_local / half_size);
mediump float t = length(p_local_ppx / half_size_ppx);
shape_color = gradient_2color(gradient_start, gradient_end, t);
} else {
// Linear gradient: direction pre-computed on CPU as (cos, sin) f16 pair
vec2 direction = unpackHalf2x16(f_effects.z);
mediump float t = dot(p_local / half_size, direction) * 0.5 + 0.5;
mediump float t = dot(p_local_ppx / half_size_ppx, direction) * 0.5 + 0.5;
shape_color = gradient_2color(gradient_start, gradient_end, t);
}
} else if ((flags & 1u) != 0u) {
// Textured (bit 0)
vec4 uv_rect = f_uv_rect;
vec2 local_uv = p_local / half_size * 0.5 + 0.5;
vec2 local_uv = p_local_ppx / half_size_ppx * 0.5 + 0.5;
vec2 uv = mix(uv_rect.xy, uv_rect.zw, local_uv);
shape_color = f_color * texture(tex, uv);
} else {
+31 -14
View File
@@ -1,6 +1,6 @@
#version 450 core
// ---------- Vertex attributes (used in both modes) ----------
// ---------- Vertex attributes (used in all modes) ----------
layout(location = 0) in vec2 v_position;
layout(location = 1) in vec2 v_uv;
layout(location = 2) in vec4 v_color;
@@ -16,10 +16,18 @@ layout(location = 6) flat out vec4 f_uv_rect;
layout(location = 7) flat out uvec4 f_effects;
// ---------- Uniforms (single block — avoids spirv-cross reordering on Metal) ----------
// Mode values mirror Core_2D_Mode in core_2d.odin:
// 0 = Tessellated v_position is in logical pixels; shader scales by dpi_scale.
// 1 = SDF v_position is a unit-quad corner; world-space comes from
// primitives[gl_InstanceIndex].bounds (logical px). Shader
// scales by dpi_scale.
// 2 = Text v_position is in *physical* pixels already (the CPU baked
// the anchor snap and SDL_ttf glyph offsets, both physical).
// Shader must NOT rescale.
layout(set = 1, binding = 0) uniform Uniforms {
mat4 projection;
float dpi_scale;
uint mode; // 0 = tessellated, 1 = SDF
uint mode;
};
// ---------- SDF primitive storage buffer ----------
@@ -44,18 +52,7 @@ layout(std430, set = 0, binding = 0) readonly buffer Core_2D_Primitives {
// ---------- Entry point ----------
void main() {
if (mode == 0u) {
// ---- Mode 0: Tessellated (used for text and arbitrary user geometry) ----
f_color = v_color;
f_local_or_uv = v_uv;
f_params = vec4(0.0);
f_params2 = vec4(0.0);
f_flags = 0u;
f_uv_rect = vec4(0.0);
f_effects = uvec4(0);
gl_Position = projection * vec4(v_position * dpi_scale, 0.0, 1.0);
} else {
if (mode == 1u) {
// ---- Mode 1: SDF instanced quads ----
Core_2D_Primitive p = primitives[gl_InstanceIndex];
@@ -86,5 +83,25 @@ void main() {
f_effects = p.effects;
gl_Position = projection * vec4(world_pos * dpi_scale, 0.0, 1.0);
} else {
// ---- Mode 0 (Tessellated) and Mode 2 (Text) ----
// Both feed the raw-vertex pipeline (kind 0 in the fragment shader).
// They differ only in what coord space `v_position` is in:
// Mode 0 — logical pixels, scale here by dpi_scale.
// Mode 2 — physical pixels (CPU pre-scaled and snapped to integer
// physical pixels for atlas-aligned bilinear sampling).
// Do NOT rescale.
// `mode` is uniform across the workgroup, so the select compiles to a
// uniform-controlled branch with no SIMT divergence cost.
f_color = v_color;
f_local_or_uv = v_uv;
f_params = vec4(0.0);
f_params2 = vec4(0.0);
f_flags = 0u;
f_uv_rect = vec4(0.0);
f_effects = uvec4(0);
vec2 pos = (mode == 2u) ? v_position : (v_position * dpi_scale);
gl_Position = projection * vec4(pos, 0.0, 1.0);
}
}