diff --git a/assignment-2a/src/HW2a.cpp b/assignment-2a/src/HW2a.cpp
index a19e5f5..a83bf5e 100755
--- a/assignment-2a/src/HW2a.cpp
+++ b/assignment-2a/src/HW2a.cpp
@@ -2,13 +2,22 @@
 // Based on example code from: Interactive Computer Graphics: A Top-Down
 // Approach with Shader-Based OpenGL (6th Edition), by Ed Angel
 
-#include "GLFW/glfw3.h"
-#include "glad/glad.h"
-#include <iostream>
 #include <math.h>
-#include <sstream>
 #include <stdio.h>
 #include <stdlib.h>
+#include <x86intrin.h>
+#include <xmmintrin.h>
+
+#include <iostream>
+#include <istream>
+#include <optional>
+#include <sstream>
+
+// Unfortunately this must be included first because it does some annoying check
+// that vomits if GLFW has already been included (dumb)
+#include "glad/glad.h"
+
+#include "GLFW/glfw3.h"
 
 #define DEBUG_ON                                                               \
   0 // repetitive of the debug flag in the shader loading code, included here
@@ -18,6 +27,18 @@
 // compiles them
 #include "ShaderStuff.hpp"
 
+//----------------------------------------------------------------------------
+// Forward-declaring some functions for later implementation
+
+/// Multiplies two matrices and puts them into result.
+///
+/// - Left matrix must be ROW-order
+/// - Right matrix must be COLUMN-order
+///
+/// Result will be row-order
+void slow4x4MatrixMultiplyIntoRowOrder(GLfloat *left, GLfloat *right,
+                                       GLfloat *result);
+
 //----------------------------------------------------------------------------
 
 // initialize some basic structure types
@@ -90,54 +111,29 @@ void init(void) {
   FloatType2D vertices[NVERTICES];
   GLuint vao[1], buffer, program, location1, location2;
 
+  // clang-format off
   // set up some hard-coded colors and geometry
   // this part can be customized to read in an object description from a file
-  colors[0].r = 1;
-  colors[0].g = 1;
-  colors[0].b = 1; // white
-  colors[1].r = 1;
-  colors[1].g = 0;
-  colors[1].b = 0; // red
-  colors[2].r = 1;
-  colors[2].g = 0;
-  colors[2].b = 0; // red
-  colors[3].r = 1;
-  colors[3].g = 1;
-  colors[3].b = 1; // white
-  colors[4].r = 0;
-  colors[4].g = 0;
-  colors[4].b = 1; // blue
-  colors[5].r = 0;
-  colors[5].g = 0;
-  colors[5].b = 1; // blue
-  colors[6].r = 1;
-  colors[6].g = 1;
-  colors[6].b = 1; // white
-  colors[7].r = 0;
-  colors[7].g = 1;
-  colors[7].b = 1; // cyan
-  colors[8].r = 0;
-  colors[8].g = 1;
-  colors[8].b = 1; // cyan
+  colors[0].r = 1; colors[0].g = 1; colors[0].b = 1; // white
+  colors[1].r = 1; colors[1].g = 0; colors[1].b = 0; // red
+  colors[2].r = 1; colors[2].g = 0; colors[2].b = 0; // red
+  colors[3].r = 1; colors[3].g = 1; colors[3].b = 1; // white
+  colors[4].r = 0; colors[4].g = 0; colors[4].b = 1; // blue
+  colors[5].r = 0; colors[5].g = 0; colors[5].b = 1; // blue
+  colors[6].r = 1; colors[6].g = 1; colors[6].b = 1; // white
+  colors[7].r = 0; colors[7].g = 1; colors[7].b = 1; // cyan
+  colors[8].r = 0; colors[8].g = 1; colors[8].b = 1; // cyan
 
-  vertices[0].x = 0;
-  vertices[0].y = 0.25; // center
-  vertices[1].x = 0.25;
-  vertices[1].y = 0.5; // upper right
-  vertices[2].x = -0.25;
-  vertices[2].y = 0.5; // upper left
-  vertices[3].x = 0;
-  vertices[3].y = 0.25; // center (again)
-  vertices[4].x = 0.25;
-  vertices[4].y = -0.5; // low-lower right
-  vertices[5].x = 0.5;
-  vertices[5].y = -0.25; // mid-lower right
-  vertices[6].x = 0;
-  vertices[6].y = 0.25; // center (again)
-  vertices[7].x = -0.5;
-  vertices[7].y = -0.25; // low-lower left
-  vertices[8].x = -0.25;
-  vertices[8].y = -0.5; // mid-lower left
+  vertices[0].x = 0; vertices[0].y = 0.25; // center
+  vertices[1].x = 0.25; vertices[1].y = 0.5; // upper right
+  vertices[2].x = -0.25; vertices[2].y = 0.5; // upper left
+  vertices[3].x = 0; vertices[3].y = 0.25; // center (again)
+  vertices[4].x = 0.25; vertices[4].y = -0.5; // low-lower right
+  vertices[5].x = 0.5; vertices[5].y = -0.25; // mid-lower right
+  vertices[6].x = 0; vertices[6].y = 0.25; // center (again)
+  vertices[7].x = -0.5; vertices[7].y = -0.25; // low-lower left
+  vertices[8].x = -0.25; vertices[8].y = -0.5; // mid-lower left
+  // clang-format on
 
   // Create and bind a vertex array object
   glGenVertexArrays(1, vao);
@@ -277,3 +273,17 @@ int main(int argc, char **argv) {
   exit(EXIT_SUCCESS);
 
 } // end main
+
+void slow4x4MatrixMultiplyIntoRowOrder(GLfloat *left, GLfloat *right,
+                                       GLfloat *result) {
+  for (int i = 0; i < 4; ++i) {
+    for (int j = 0; j < 4; ++j) {
+      for (int k = 0; k < 4; ++k) {
+        const int resultIdx = i * 4 + j;
+        const GLfloat leftVal = left[i * 4 + k];
+        const GLfloat rightVal = right[j * 4 + k];
+        result[i * 4 + j] += leftVal * rightVal;
+      }
+    }
+  }
+}