fixed broken branches, updated README

Reviewed-on: #3

.gitignore

@@ -42,4 +42,3 @@ build
 debug
 .cache
 tmp
-screenshot*

README.md

@@ -1,6 +1,6 @@
 # polypartiCL
 
-Naive photon simulator with SYCL and [raylib](https://raylib.com)
+Naive photon simulator using [SYCL](https://khronos.org/sycl/) and [raylib](https://raylib.com)
 
 This project uses the [raylib-cpp](https://robloach.github.io/raylib-cpp) wrapper library and is provided in the /include directory.
 raylib-cpp is licensed under an unmodified zlib/libpng license. A copy of this license is provided at /include/LICENSE.
@@ -8,16 +8,23 @@ raylib-cpp is licensed under an unmodified zlib/libpng license. A copy of this l
 cmake assumes icpx and the [Intel OneAPI](https://www.intel.com/content/www/us/en/developer/tools/oneapi/overview.html) environment is installed.
 You'll need these even if you don't compile with cmake until SYCL gets native LLVM support.
 
-polypartiCL is licensed with the 3-clause BSD license.
+All simulation code uses single-precision floating point arithmetic to ensure compatability with (integrated) graphics packages that do not support 64-bit floating point.
+
+polypartiCL is licensed with the 3-clause BSD license. Initial development of GLSL shaders (./shaders/*.fs) was assisted by generative AI (Claude Sonnet).
 
 ## Todo
+- Reduce corner escaping
+    - Ability limited by f32 precision
 - Rewrite & optimize simulation code, store all points/velocites in one array and submit once
     - Consider modelling each particle and all its relevant data points individually
     - Submit each relevant data point by pointer offset, size of struct is irrelevant as long as it is constant, only necessary data will be submitted to kernel
 - Add linear beams
 - Add environment objects / multiple rooms per screen
 - Add timed events
+- Add MIDI support for real-time music visualization
+- Add compile option for 64-bit floating point simulation
 
-![Screenshot 1](https://alexlardner.com/img/1.png)
-![Screenshot 2](https://alexlardner.com/img/2.png)
-![Screenshot 3](https://alexlardner.com/img/3.png)
+![Screenshot 1](screenshots/1.png)
+![Screenshot 2](screenshots/2.png)
+![Screenshot 3](screenshots/3.png)
+![Screenshot 4](screenshots/4.png)

particles/bnc.prtc

@@ -0,0 +1,8 @@
+Center Delay
+count velocity x y theta_i theta_f color start end decayrate
+===================================================
+s
+20000 70 0.5 0.5 0 360 red 1 0 0
+20000 70 0.5 0.5 0 360 green 3.30769 0 0
+20000 70 0.5 0.5 0 360 blue 5.61538 0 0
+20000 70 0.5 0.5 0 360 white 7.92308 0 0

particles/load.prtc

@@ -2,6 +2,7 @@ Center Delay
 count velocity x y theta_i theta_f color start end decayrate
 ===================================================
 s
-16000 79 0.5 0.5 0 360 cyan 1 0 0
-16000 79 0.5 0.5 0 360 magenta 2.075 0 0
-16000 79 0.5 0.5 0 360 yellow 4.931 0 0
+10000 40 0.5 0.5 0 360 orange 1 0 0
+10000 40 0.5 0.5 0 360 cyan 3.30769 0 0
+10000 40 0.5 0.5 0 360 violet 5.61538 0 0
+10000 40 0.5 0.5 0 360 green 7.92308 0 0

rooms/load.room

@@ -1,11 +1,9 @@
-Big Hexagon (fixed 1080)
+Big Diamond (relative)
 x y
 ==================
-f
-960.0 1.303
-1426.525 270.652
-1426.525 809.348
-960.0 1078.697
-493.475 809.348
-493.475 270.652
-960.0 1.303
+r
+0.5 0.0
+0.78125 0.5
+0.5 1.0
+0.21875 0.5
+0.5 0.0

src/polypartiCL.cpp

@@ -30,9 +30,9 @@ struct Polyparti::ParticleField::ColCode {
 
         //Pointers to malloc on GPU VRAM for calculations. malloc_shared pointers are entry/exit 
         //point for data in CPU RAM
-        float *v_ptr = malloc_shared<float>(2 * len_points, q);
-        float *d_ptr = malloc_shared<float>(2 * len_points, q);
-        float *c_ptr = malloc_shared<float>(2 * len_points, q);
+        float *v_ptr = malloc_device<float>(2 * len_points, q);
+        float *d_ptr = malloc_device<float>(2 * len_points, q);
+        float *c_ptr = malloc_device<float>(2 * len_points, q);
         float *ray_ptr = malloc_device<float>(2 * len_points, q);
         float *det_ptr = malloc_device<float>(len_points, q);
         float *bestA_ptr = malloc_device<float>(2 * len_points, q);
@@ -170,9 +170,9 @@ struct Polyparti::ParticleField::ColCode {
     void moveParticles() {
         queue& q = q_shared();
         int len = positions.size();
-        float *v_ptr = malloc_shared<float>(2 * len, q);
-        float *p_ptr = malloc_shared<float>(2 * len, q);
-        float *t_ptr = malloc_shared<float>(1, q);
+        float *v_ptr = malloc_device<float>(2 * len, q);
+        float *p_ptr = malloc_device<float>(2 * len, q);
+        float *t_ptr = malloc_device<float>(1, q);
 
         q.submit([&](handler& h) {
             h.memcpy(p_ptr, &positions[0], len * 2 * sizeof(float));