summaryrefslogtreecommitdiff
path: root/src
diff options
context:
space:
mode:
Diffstat (limited to 'src')
-rw-r--r--src/3d/object.h5
-rw-r--r--src/3d/physics.cc2
-rw-r--r--src/3d/renderer.cc2
-rw-r--r--src/3d/renderer.h1
-rw-r--r--src/3d/renderer_draw.cc20
-rw-r--r--src/audio/fft.cc30
-rw-r--r--src/effects/scene2_effect.cc34
-rw-r--r--src/effects/scene2_effect.h19
-rw-r--r--src/gpu/texture_manager.cc154
-rw-r--r--src/gpu/texture_manager.h7
-rw-r--r--src/gpu/wgsl_effect.cc8
-rw-r--r--src/gpu/wgsl_effect.h5
12 files changed, 99 insertions, 188 deletions
diff --git a/src/3d/object.h b/src/3d/object.h
index a8eb98c..e2cd15a 100644
--- a/src/3d/object.h
+++ b/src/3d/object.h
@@ -9,7 +9,7 @@
#include <memory> // For std::shared_ptr
enum class ObjectType {
- CUBE,
+ CUBE, // Legacy alias for BOX (value 0, kept for binary scene compat)
SPHERE,
PLANE,
TORUS,
@@ -17,6 +17,7 @@ enum class ObjectType {
SKYBOX,
MESH
// Add more SDF types here
+ // NOTE: CUBE == BOX semantically. Use BOX for new code.
};
struct BoundingVolume {
@@ -46,7 +47,7 @@ class Object3D {
std::shared_ptr<void>
shared_user_data; // For tool-specific data managed with shared ownership
- Object3D(ObjectType t = ObjectType::CUBE)
+ Object3D(ObjectType t = ObjectType::BOX)
: position(0, 0, 0), rotation(0, 0, 0, 1), scale(1, 1, 1), type(t),
color(1, 1, 1, 1), velocity(0, 0, 0), mass(1.0f), restitution(0.5f),
is_static(false), mesh_asset_id((AssetId)0), local_extent(1, 1, 1),
diff --git a/src/3d/physics.cc b/src/3d/physics.cc
index db27e95..788246f 100644
--- a/src/3d/physics.cc
+++ b/src/3d/physics.cc
@@ -16,7 +16,7 @@ float PhysicsSystem::sample_sdf(const Object3D& obj, vec3 world_p) {
float d = 1000.0f;
if (obj.type == ObjectType::SPHERE) {
d = q.len() - 1.0f;
- } else if (obj.type == ObjectType::BOX || obj.type == ObjectType::CUBE) {
+ } else if (obj.type == ObjectType::BOX || obj.type == ObjectType::CUBE) { // CUBE is legacy alias
d = sdf::sdBox(q, vec3(1.0f, 1.0f, 1.0f));
} else if (obj.type == ObjectType::TORUS) {
d = sdf::sdTorus(q, vec2(1.0f, 0.4f));
diff --git a/src/3d/renderer.cc b/src/3d/renderer.cc
index 7f2f800..e3e8ce7 100644
--- a/src/3d/renderer.cc
+++ b/src/3d/renderer.cc
@@ -108,10 +108,12 @@ void Renderer3D::resize(int width, int height) {
void Renderer3D::set_noise_texture(WGPUTextureView noise_view) {
noise_texture_view_ = noise_view;
+ bind_group_dirty_ = true;
}
void Renderer3D::set_sky_texture(WGPUTextureView sky_view) {
sky_texture_view_ = sky_view;
+ bind_group_dirty_ = true;
}
void Renderer3D::add_debug_aabb(const vec3& min, const vec3& max,
diff --git a/src/3d/renderer.h b/src/3d/renderer.h
index 8f933b5..21192f3 100644
--- a/src/3d/renderer.h
+++ b/src/3d/renderer.h
@@ -125,6 +125,7 @@ class Renderer3D {
BVH cpu_bvh_; // Keep a CPU-side copy for building/uploading
bool bvh_enabled_ = true;
bool direct_render_ = false; // true = render to surface (no post-process flip)
+ bool bind_group_dirty_ = true; // Recreate bind group when textures change
std::map<AssetId, MeshGpuData> mesh_cache_;
const MeshGpuData* temp_mesh_override_ = nullptr; // HACK for test_mesh tool
diff --git a/src/3d/renderer_draw.cc b/src/3d/renderer_draw.cc
index dca7113..929f261 100644
--- a/src/3d/renderer_draw.cc
+++ b/src/3d/renderer_draw.cc
@@ -27,8 +27,8 @@ void Renderer3D::update_uniforms(const Scene& scene, const Camera& camera,
float type_id = 0.0f;
switch (obj.type) {
case ObjectType::SPHERE: type_id = 1.0f; break;
+ case ObjectType::CUBE: // fallthrough (legacy alias for BOX)
case ObjectType::BOX: type_id = 2.0f; break;
- case ObjectType::CUBE: type_id = 2.0f; break; // CUBE is same as BOX
case ObjectType::TORUS: type_id = 3.0f; break;
case ObjectType::PLANE: type_id = 4.0f; break;
case ObjectType::MESH: type_id = 5.0f; break;
@@ -63,7 +63,11 @@ void Renderer3D::draw(WGPURenderPassEncoder pass, const Scene& scene,
const Camera& camera, float time) {
update_uniforms(scene, camera, time);
- // Lazy Bind Group creation
+ // Recreate bind group only when textures or BVH mode change
+ if (!bind_group_dirty_) {
+ // Skip bind group rebuild — reuse existing
+ } else {
+ bind_group_dirty_ = false;
if (bind_group_)
wgpuBindGroupRelease(bind_group_);
@@ -115,11 +119,9 @@ void Renderer3D::draw(WGPURenderPassEncoder pass, const Scene& scene,
bg_entries.push_back(e);
}
- // Select the correct pipeline and bind group layout
- WGPURenderPipeline current_pipeline =
- bvh_enabled_ ? pipeline_ : pipeline_no_bvh_;
+ WGPURenderPipeline cp = bvh_enabled_ ? pipeline_ : pipeline_no_bvh_;
WGPUBindGroupLayout current_layout =
- wgpuRenderPipelineGetBindGroupLayout(current_pipeline, 0);
+ wgpuRenderPipelineGetBindGroupLayout(cp, 0);
WGPUBindGroupDescriptor bg_desc = {};
bg_desc.layout = current_layout;
@@ -129,10 +131,10 @@ void Renderer3D::draw(WGPURenderPassEncoder pass, const Scene& scene,
bind_group_ = wgpuDeviceCreateBindGroup(device_, &bg_desc);
wgpuBindGroupLayoutRelease(current_layout);
+ } // end dirty block
- wgpuRenderPassEncoderSetPipeline(pass, current_pipeline);
-
- wgpuRenderPassEncoderSetBindGroup(pass, 0, bind_group_, 0, nullptr);
+ WGPURenderPipeline current_pipeline =
+ bvh_enabled_ ? pipeline_ : pipeline_no_bvh_;
uint32_t instance_count =
(uint32_t)std::min((size_t)kMaxObjects, scene.objects.size());
diff --git a/src/audio/fft.cc b/src/audio/fft.cc
index 7523b42..982f35f 100644
--- a/src/audio/fft.cc
+++ b/src/audio/fft.cc
@@ -7,6 +7,10 @@
#include <cmath>
#include <cstring>
+// Max supported FFT size for stack-allocated temp buffers.
+// All callers use N <= 512 (DCT_SIZE). imdct needs 2*N = 1024.
+static const size_t kMaxFFTSize = 1024;
+
// Bit-reversal permutation (in-place)
// Reorders array elements by reversing their binary indices
static void bit_reverse_permute(float* real, float* imag, size_t N) {
@@ -102,9 +106,9 @@ void fft_inverse(float* real, float* imag, size_t N) {
void dct_fft(const float* input, float* output, size_t N) {
const float PI = 3.14159265358979323846f;
- // Allocate temporary arrays for N-point FFT
- float* real = new float[N];
- float* imag = new float[N];
+ // Stack-allocated temp arrays (N <= kMaxFFTSize)
+ float real[kMaxFFTSize];
+ float imag[kMaxFFTSize];
// Reorder input: even indices first, then odd indices reversed
// [x[0], x[2], x[4], ...] followed by [x[N-1], x[N-3], x[N-5], ...]
@@ -135,9 +139,6 @@ void dct_fft(const float* input, float* output, size_t N) {
output[k] = dct_value * sqrtf(2.0f / N);
}
}
-
- delete[] real;
- delete[] imag;
}
// IMDCT via FFT
@@ -149,8 +150,9 @@ void imdct_fft(const float* input, float* output, size_t N) {
const float PI = 3.14159265358979323846f;
const size_t M = 2 * N; // output length
- float* real = new float[M];
- float* imag = new float[M];
+ // Stack-allocated temp arrays (M = 2*N <= kMaxFFTSize)
+ float real[kMaxFFTSize];
+ float imag[kMaxFFTSize];
// Pre-multiply X[k] by exp(-j*pi*(2k+1)/(4N)), build 2N complex FFT input
// via standard IMDCT-via-FFT algorithm (N-point complex FFT)
@@ -180,9 +182,6 @@ void imdct_fft(const float* input, float* output, size_t N) {
const float angle = -PI * (2.0f * n + 1.0f) / (4.0f * N);
output[n] = gain * (real[n] * cosf(angle) - imag[n] * sinf(angle));
}
-
- delete[] real;
- delete[] imag;
}
// IDCT (DCT-III) via FFT - inverse of the DCT-II reordering method
@@ -190,9 +189,9 @@ void imdct_fft(const float* input, float* output, size_t N) {
void idct_fft(const float* input, float* output, size_t N) {
const float PI = 3.14159265358979323846f;
- // Allocate temporary arrays for N-point FFT
- float* real = new float[N];
- float* imag = new float[N];
+ // Stack-allocated temp arrays (N <= kMaxFFTSize)
+ float real[kMaxFFTSize];
+ float imag[kMaxFFTSize];
// Prepare FFT input with inverse phase correction
// FFT[k] = DCT[k] * exp(+j*pi*k/(2*N)) / normalization
@@ -226,7 +225,4 @@ void idct_fft(const float* input, float* output, size_t N) {
output[2 * i] = real[i]; // Even positions
output[2 * i + 1] = real[N - 1 - i]; // Odd positions (reversed)
}
-
- delete[] real;
- delete[] imag;
}
diff --git a/src/effects/scene2_effect.cc b/src/effects/scene2_effect.cc
deleted file mode 100644
index 92e5ecd..0000000
--- a/src/effects/scene2_effect.cc
+++ /dev/null
@@ -1,34 +0,0 @@
-// This file is part of the 64k demo project.
-// Scene2 effect - ShaderToy conversion (scene)
-// Generated by convert_shadertoy.py
-
-#include "effects/scene2_effect.h"
-#include "effects/shaders.h"
-#include "gpu/gpu.h"
-#include "gpu/post_process_helper.h"
-#include "util/fatal_error.h"
-
-Scene2Effect::Scene2Effect(const GpuContext& ctx,
- const std::vector<std::string>& inputs,
- const std::vector<std::string>& outputs,
- float start_time, float end_time)
- : Effect(ctx, inputs, outputs, start_time, end_time) {
- HEADLESS_RETURN_IF_NULL(ctx_.device);
- create_nearest_sampler();
- create_dummy_scene_texture();
- pipeline_.set(create_post_process_pipeline(
- ctx_.device, WGPUTextureFormat_RGBA8Unorm, scene2_shader_wgsl));
-}
-
-void Scene2Effect::render(WGPUCommandEncoder encoder,
- const UniformsSequenceParams& params,
- NodeRegistry& nodes) {
- WGPUTextureView output_view = nodes.get_view(output_nodes_[0]);
-
- // uniforms_buffer_ auto-updated by base class dispatch_render()
- pp_update_bind_group(ctx_.device, pipeline_.get(), bind_group_.get_address(),
- dummy_texture_view_.get(), uniforms_buffer_.get(),
- {nullptr, 0});
-
- run_fullscreen_pass(encoder, pipeline_.get(), bind_group_.get(), output_view);
-}
diff --git a/src/effects/scene2_effect.h b/src/effects/scene2_effect.h
index da4cf7e..0e26fc3 100644
--- a/src/effects/scene2_effect.h
+++ b/src/effects/scene2_effect.h
@@ -4,19 +4,14 @@
#pragma once
-#include "gpu/effect.h"
-#include "gpu/wgpu_resource.h"
+#include "effects/shaders.h"
+#include "gpu/wgsl_effect.h"
-class Scene2Effect : public Effect {
- public:
+struct Scene2Effect : public WgslEffect {
Scene2Effect(const GpuContext& ctx, const std::vector<std::string>& inputs,
const std::vector<std::string>& outputs, float start_time,
- float end_time);
-
- void render(WGPUCommandEncoder encoder, const UniformsSequenceParams& params,
- NodeRegistry& nodes) override;
-
- private:
- RenderPipeline pipeline_;
- BindGroup bind_group_;
+ float end_time)
+ : WgslEffect(ctx, inputs, outputs, start_time, end_time,
+ scene2_shader_wgsl, WGPULoadOp_Clear, {},
+ WgslSamplerType::Nearest) {}
};
diff --git a/src/gpu/texture_manager.cc b/src/gpu/texture_manager.cc
index bdeb508..20e215d 100644
--- a/src/gpu/texture_manager.cc
+++ b/src/gpu/texture_manager.cc
@@ -285,142 +285,76 @@ void TextureManager::dispatch_compute(const std::string& func_name,
wgpuTextureViewRelease(target_view);
}
-void TextureManager::create_gpu_noise_texture(
- const std::string& name, const GpuProceduralParams& params) {
- extern const char* gen_noise_compute_wgsl;
- get_or_create_compute_pipeline("gen_noise", gen_noise_compute_wgsl, 16);
-
- WGPUTextureDescriptor tex_desc = {};
- tex_desc.usage =
- WGPUTextureUsage_StorageBinding | WGPUTextureUsage_TextureBinding;
- tex_desc.dimension = WGPUTextureDimension_2D;
- tex_desc.size = {(uint32_t)params.width, (uint32_t)params.height, 1};
- tex_desc.format = WGPUTextureFormat_RGBA8Unorm;
- tex_desc.mipLevelCount = 1;
- tex_desc.sampleCount = 1;
- WGPUTexture texture = wgpuDeviceCreateTexture(device_, &tex_desc);
+void TextureManager::create_gpu_procedural(
+ const std::string& name, const std::string& func_name,
+ const char* shader_code, const GpuProceduralParams& params,
+ const void* uniform_data, size_t uniform_size) {
+ get_or_create_compute_pipeline(func_name, shader_code, uniform_size);
- struct NoiseParams {
- uint32_t width;
- uint32_t height;
- float seed;
- float frequency;
- };
- NoiseParams uniforms = {(uint32_t)params.width, (uint32_t)params.height,
- params.params[0], params.params[1]};
- dispatch_compute("gen_noise", texture, params, &uniforms,
- sizeof(NoiseParams));
+ TextureWithView tv = gpu_create_storage_texture_2d(
+ device_, (uint32_t)params.width, (uint32_t)params.height,
+ WGPUTextureFormat_RGBA8Unorm);
- WGPUTextureView view =
- gpu_create_texture_view_2d(texture, WGPUTextureFormat_RGBA8Unorm);
+ dispatch_compute(func_name, tv.texture, params, uniform_data, uniform_size);
GpuTexture gpu_tex;
- gpu_tex.texture = texture;
- gpu_tex.view = view;
+ gpu_tex.texture = tv.texture;
+ gpu_tex.view = tv.view;
gpu_tex.width = params.width;
gpu_tex.height = params.height;
textures_[name] = gpu_tex;
#if !defined(STRIP_ALL)
- printf("Generated GPU noise texture: %s (%dx%d)\n", name.c_str(),
- params.width, params.height);
+ printf("Generated GPU %s texture: %s (%dx%d)\n", func_name.c_str(),
+ name.c_str(), params.width, params.height);
#endif
}
+void TextureManager::create_gpu_noise_texture(
+ const std::string& name, const GpuProceduralParams& params) {
+ extern const char* gen_noise_compute_wgsl;
+ struct NoiseParams {
+ uint32_t width, height;
+ float seed, frequency;
+ };
+ NoiseParams u = {(uint32_t)params.width, (uint32_t)params.height,
+ params.params[0], params.params[1]};
+ create_gpu_procedural(name, "gen_noise", gen_noise_compute_wgsl, params, &u,
+ sizeof(u));
+}
+
void TextureManager::create_gpu_perlin_texture(
const std::string& name, const GpuProceduralParams& params) {
extern const char* gen_perlin_compute_wgsl;
- get_or_create_compute_pipeline("gen_perlin", gen_perlin_compute_wgsl, 32);
-
- WGPUTextureDescriptor tex_desc = {};
- tex_desc.usage =
- WGPUTextureUsage_StorageBinding | WGPUTextureUsage_TextureBinding;
- tex_desc.dimension = WGPUTextureDimension_2D;
- tex_desc.size = {(uint32_t)params.width, (uint32_t)params.height, 1};
- tex_desc.format = WGPUTextureFormat_RGBA8Unorm;
- tex_desc.mipLevelCount = 1;
- tex_desc.sampleCount = 1;
- WGPUTexture texture = wgpuDeviceCreateTexture(device_, &tex_desc);
-
struct PerlinParams {
- uint32_t width;
- uint32_t height;
- float seed;
- float frequency;
- float amplitude;
- float amplitude_decay;
+ uint32_t width, height;
+ float seed, frequency, amplitude, amplitude_decay;
uint32_t octaves;
float _pad0;
};
- PerlinParams uniforms = {(uint32_t)params.width,
- (uint32_t)params.height,
- params.params[0],
- params.params[1],
- params.num_params > 2 ? params.params[2] : 1.0f,
- params.num_params > 3 ? params.params[3] : 0.5f,
- params.num_params > 4 ? (uint32_t)params.params[4]
- : 4u,
- 0.0f};
- dispatch_compute("gen_perlin", texture, params, &uniforms,
- sizeof(PerlinParams));
-
- WGPUTextureView view =
- gpu_create_texture_view_2d(texture, WGPUTextureFormat_RGBA8Unorm);
-
- GpuTexture gpu_tex;
- gpu_tex.texture = texture;
- gpu_tex.view = view;
- gpu_tex.width = params.width;
- gpu_tex.height = params.height;
- textures_[name] = gpu_tex;
-
-#if !defined(STRIP_ALL)
- printf("Generated GPU perlin texture: %s (%dx%d)\n", name.c_str(),
- params.width, params.height);
-#endif
+ PerlinParams u = {(uint32_t)params.width,
+ (uint32_t)params.height,
+ params.params[0],
+ params.params[1],
+ params.num_params > 2 ? params.params[2] : 1.0f,
+ params.num_params > 3 ? params.params[3] : 0.5f,
+ params.num_params > 4 ? (uint32_t)params.params[4] : 4u,
+ 0.0f};
+ create_gpu_procedural(name, "gen_perlin", gen_perlin_compute_wgsl, params, &u,
+ sizeof(u));
}
void TextureManager::create_gpu_grid_texture(
const std::string& name, const GpuProceduralParams& params) {
extern const char* gen_grid_compute_wgsl;
- get_or_create_compute_pipeline("gen_grid", gen_grid_compute_wgsl, 16);
-
- WGPUTextureDescriptor tex_desc = {};
- tex_desc.usage =
- WGPUTextureUsage_StorageBinding | WGPUTextureUsage_TextureBinding;
- tex_desc.dimension = WGPUTextureDimension_2D;
- tex_desc.size = {(uint32_t)params.width, (uint32_t)params.height, 1};
- tex_desc.format = WGPUTextureFormat_RGBA8Unorm;
- tex_desc.mipLevelCount = 1;
- tex_desc.sampleCount = 1;
- WGPUTexture texture = wgpuDeviceCreateTexture(device_, &tex_desc);
-
struct GridParams {
- uint32_t width;
- uint32_t height;
- uint32_t grid_size;
- uint32_t thickness;
+ uint32_t width, height, grid_size, thickness;
};
- GridParams uniforms = {
- (uint32_t)params.width, (uint32_t)params.height,
- params.num_params > 0 ? (uint32_t)params.params[0] : 32u,
- params.num_params > 1 ? (uint32_t)params.params[1] : 2u};
- dispatch_compute("gen_grid", texture, params, &uniforms, sizeof(GridParams));
-
- WGPUTextureView view =
- gpu_create_texture_view_2d(texture, WGPUTextureFormat_RGBA8Unorm);
-
- GpuTexture gpu_tex;
- gpu_tex.texture = texture;
- gpu_tex.view = view;
- gpu_tex.width = params.width;
- gpu_tex.height = params.height;
- textures_[name] = gpu_tex;
-
-#if !defined(STRIP_ALL)
- printf("Generated GPU grid texture: %s (%dx%d)\n", name.c_str(), params.width,
- params.height);
-#endif
+ GridParams u = {(uint32_t)params.width, (uint32_t)params.height,
+ params.num_params > 0 ? (uint32_t)params.params[0] : 32u,
+ params.num_params > 1 ? (uint32_t)params.params[1] : 2u};
+ create_gpu_procedural(name, "gen_grid", gen_grid_compute_wgsl, params, &u,
+ sizeof(u));
}
#if !defined(STRIP_GPU_COMPOSITE)
diff --git a/src/gpu/texture_manager.h b/src/gpu/texture_manager.h
index ec30c7b..a5462ae 100644
--- a/src/gpu/texture_manager.h
+++ b/src/gpu/texture_manager.h
@@ -93,6 +93,13 @@ class TextureManager {
const GpuProceduralParams& params,
const void* uniform_data, size_t uniform_size);
+ // Shared helper: create pipeline + storage texture + dispatch + store result
+ void create_gpu_procedural(const std::string& name,
+ const std::string& func_name,
+ const char* shader_code,
+ const GpuProceduralParams& params,
+ const void* uniform_data, size_t uniform_size);
+
#if !defined(STRIP_GPU_COMPOSITE)
void dispatch_composite(const std::string& func_name, WGPUTexture target,
const GpuProceduralParams& params,
diff --git a/src/gpu/wgsl_effect.cc b/src/gpu/wgsl_effect.cc
index 1cb0ecb..4f658a5 100644
--- a/src/gpu/wgsl_effect.cc
+++ b/src/gpu/wgsl_effect.cc
@@ -10,13 +10,17 @@ WgslEffect::WgslEffect(const GpuContext& ctx,
const std::vector<std::string>& outputs,
float start_time, float end_time,
const char* shader_code, WGPULoadOp load_op,
- WgslEffectParams initial_params)
+ WgslEffectParams initial_params,
+ WgslSamplerType sampler_type)
: Effect(ctx, inputs, outputs, start_time, end_time),
effect_params(initial_params),
load_op_(load_op) {
HEADLESS_RETURN_IF_NULL(ctx_.device);
- create_linear_sampler();
+ if (sampler_type == WgslSamplerType::Nearest)
+ create_nearest_sampler();
+ else
+ create_linear_sampler();
params_buffer_.init(ctx_.device);
pipeline_.set(create_post_process_pipeline(ctx_.device,
diff --git a/src/gpu/wgsl_effect.h b/src/gpu/wgsl_effect.h
index 062f885..f487ef7 100644
--- a/src/gpu/wgsl_effect.h
+++ b/src/gpu/wgsl_effect.h
@@ -16,6 +16,8 @@ struct WgslEffectParams {
};
static_assert(sizeof(WgslEffectParams) == 32, "WgslEffectParams must be 32 bytes");
+enum class WgslSamplerType { Linear, Nearest };
+
class WgslEffect : public Effect {
public:
// Mutate per-frame for dynamic parameter modulation.
@@ -25,7 +27,8 @@ class WgslEffect : public Effect {
const std::vector<std::string>& outputs, float start_time,
float end_time, const char* shader_code,
WGPULoadOp load_op = WGPULoadOp_Clear,
- WgslEffectParams initial_params = {});
+ WgslEffectParams initial_params = {},
+ WgslSamplerType sampler_type = WgslSamplerType::Linear);
void render(WGPUCommandEncoder encoder, const UniformsSequenceParams& params,
NodeRegistry& nodes) override;
generated by cgit v1.2.3 (git 2.51.0) at 2026-05-29 23:29:56 +0000