diff --git a/Cargo.lock b/Cargo.lock
index b438387..e982548 100644
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -682,7 +682,7 @@ dependencies = [
 
 [[package]]
 name = "heat-wgpu"
-version = "0.2.0"
+version = "0.2.1"
 dependencies = [
  "bytemuck",
  "env_logger",
diff --git a/Cargo.toml b/Cargo.toml
index 554feb2..cfea81b 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -1,6 +1,6 @@
 [package]
 name = "heat-wgpu"
-version = "0.2.0"
+version = "0.2.1"
 edition = "2021"
 
 [dependencies]
diff --git a/README.md b/README.md
index da64338..6519412 100644
--- a/README.md
+++ b/README.md
@@ -52,5 +52,10 @@ cargo run --release
 - LeVeque, R. J. (2007). *Finite difference methods for ordinary and partial differential equations: steady-state and time-dependent problems. Society for Industrial and Applied Mathematics*.
 - Shewchuk, J. R. (1994). [*An introduction to the conjugate gradient method without the agonizing pain*](https://www.cs.cmu.edu/~quake-papers/painless-conjugate-gradient.pdf).
 - Bell, N., & Garland, M. (2008). *Efficient sparse matrix-vector multiplication on CUDA (Vol. 2, No. 5). Nvidia Technical Report NVR-2008-004, Nvidia Corporation*.
+- GPU Gems 2: Programming Techniques for High-Performance Graphics and General-Purpose Computation. 2005. Addison-Wesley Professional.
+  - Specifically [*Chapter 44: A GPU Framework for Solving Systems of Linear Equations*](https://developer.nvidia.com/gpugems/gpugems2/part-vi-simulation-and-numerical-algorithms/chapter-44-gpu-framework-solving), which also cites the following papers:
+    - Bolz, J., I. Farmer, E. Grinspun, and P. Schröder. 2003. "Sparse Matrix Solvers on the GPU: Conjugate Gradients and Multigrid." *ACM Transactions on Graphics (Proceedings of SIGGRAPH 2003)* 22(3), pp. 917–924.
+    - Krüger, Jens, and Rüdiger Westermann. 2003. "Linear Algebra Operators for GPU Implementation of Numerical Algorithms." *ACM Transactions on Graphics (Proceedings of SIGGRAPH 2003)* 22(3), pp. 908–916.
 - Harris, M. (2007). *Optimizing parallel reduction in CUDA. Nvidia developer technology, 2*(4), 70.
+- Mikhailov, A. (2019). [Turbo, An Improved Rainbow Colormap for Visualization](https://ai.googleblog.com/2019/08/turbo-improved-rainbow-colormap-for.html).
 - [WebGPU specification](https://gpuweb.github.io/gpuweb/).
diff --git a/src/app.rs b/src/app.rs
index 6cfbbe6..4241e88 100644
--- a/src/app.rs
+++ b/src/app.rs
@@ -61,6 +61,7 @@ impl App {
             .await
             .unwrap();
         println!("Adapter: {:?}", adapter.get_info());
+        println!("Surface: {:?}", surface.get_capabilities(&adapter));
         //device and queue
         let (device, queue) = adapter
             .request_device(
@@ -83,8 +84,10 @@ impl App {
             .get_default_config(&adapter, size.width, size.height)
             .expect("Surface isn't supported by the adapter.");
         config.present_mode = wgpu::PresentMode::Fifo;
+        config.format = wgpu::TextureFormat::Bgra8Unorm;
         let surface_view_format = config.format.add_srgb_suffix();
         config.view_formats.push(surface_view_format);
+        println!("Config: {:?}", config);
         surface.configure(&device, &config);
 
         // ------ GPU Compute config ------
diff --git a/src/shaders/render.wgsl b/src/shaders/render.wgsl
index 1ed383a..aa2784e 100644
--- a/src/shaders/render.wgsl
+++ b/src/shaders/render.wgsl
@@ -36,6 +36,8 @@ fn fs_main(in: VertexOutput) -> @location(0) vec4<f32> {
 
 // Turbo colormap (polynomial approximation)
 // reference: https://ai.googleblog.com/2019/08/turbo-improved-rainbow-colormap-for.html
+// Original LUT: https://gist.github.com/mikhailov-work/ee72ba4191942acecc03fe6da94fc73f
+// Authors: Anton Mikhailov (mikhailov@google.com), Ruofei Du (ruofei@google.com)
 fn TurboColormap(x: f32) -> vec3<f32> {
   let kRedVec4: vec4<f32> = vec4<f32>(0.13572138, 4.61539260, -42.66032258, 132.13108234);
   let kGreenVec4: vec4<f32> = vec4<f32>(0.09140261, 2.19418839, 4.84296658, -14.18503333);