shaderpipeline: Add `inverse()` function to Cg preamble

HLSL never offered it so glslangValidator rejects it (but it does have `determinant()`)

Sadly we can't neatly map this back to a matrix inverse op in the SPIR-V, but I don't think that really matters - there is probably no hardware support for it and maybe this way it can actually be optimized better if some component values are known statically

Plus, you really shouldn't be using it anyway - use a matrix inverse input instead

panda/src/shaderpipeline/cg_preamble.hlsl

@@ -196,3 +196,49 @@ uint bitfieldExtract(uint val, int off, int size) {
 #define floatToIntBits(x) (asint(x))
 #define floatToRawIntBits(x) (asint(x))
 #define intBitsToFloat(x) (asfloat(x))
+
+float2x2 inverse(float2x2 m) {
+  return float2x2(m[1][1], -m[0][1], -m[1][0], m[0][0]) * (1.0f / determinant(m));
+}
+
+float3x3 inverse(float3x3 m) {
+  float3 t = float3(m[1][1] * m[2][2] - m[1][2] * m[2][1], m[1][2] * m[2][0] - m[1][0] * m[2][2], m[1][0] * m[2][1] - m[1][1] * m[2][0]);
+  return float3x3(t[0],
+                  m[0][2] * m[2][1] - m[0][1] * m[2][2],
+                  m[0][1] * m[1][2] - m[0][2] * m[1][1],
+                  t[1],
+                  m[0][0] * m[2][2] - m[0][2] * m[2][0],
+                  m[0][2] * m[1][0] - m[0][0] * m[1][2],
+                  t[2],
+                  m[0][1] * m[2][0] - m[0][0] * m[2][1],
+                  m[0][0] * m[1][1] - m[0][1] * m[1][0]) * (1.0f / dot(m[0], t));
+}
+
+float4x4 inverse(float4x4 m) {
+  float4 t = float4(
+    m[2][1] * m[3][2] * m[1][3] - m[3][1] * m[2][2] * m[1][3] + m[3][1] * m[1][2] * m[2][3] - m[1][1] * m[3][2] * m[2][3] - m[2][1] * m[1][2] * m[3][3] + m[1][1] * m[2][2] * m[3][3],
+    m[3][0] * m[2][2] * m[1][3] - m[2][0] * m[3][2] * m[1][3] - m[3][0] * m[1][2] * m[2][3] + m[1][0] * m[3][2] * m[2][3] + m[2][0] * m[1][2] * m[3][3] - m[1][0] * m[2][2] * m[3][3],
+    m[2][0] * m[3][1] * m[1][3] - m[3][0] * m[2][1] * m[1][3] + m[3][0] * m[1][1] * m[2][3] - m[1][0] * m[3][1] * m[2][3] - m[2][0] * m[1][1] * m[3][3] + m[1][0] * m[2][1] * m[3][3],
+    m[3][0] * m[2][1] * m[1][2] - m[2][0] * m[3][1] * m[1][2] - m[3][0] * m[1][1] * m[2][2] + m[1][0] * m[3][1] * m[2][2] + m[2][0] * m[1][1] * m[3][2] - m[1][0] * m[2][1] * m[3][2]);
+  return float4x4(
+      t[0],
+      (m[3][1] * m[2][2] * m[0][3] - m[2][1] * m[3][2] * m[0][3] - m[3][1] * m[0][2] * m[2][3] + m[0][1] * m[3][2] * m[2][3] + m[2][1] * m[0][2] * m[3][3] - m[0][1] * m[2][2] * m[3][3]),
+      (m[1][1] * m[3][2] * m[0][3] - m[3][1] * m[1][2] * m[0][3] + m[3][1] * m[0][2] * m[1][3] - m[0][1] * m[3][2] * m[1][3] - m[1][1] * m[0][2] * m[3][3] + m[0][1] * m[1][2] * m[3][3]),
+      (m[2][1] * m[1][2] * m[0][3] - m[1][1] * m[2][2] * m[0][3] - m[2][1] * m[0][2] * m[1][3] + m[0][1] * m[2][2] * m[1][3] + m[1][1] * m[0][2] * m[2][3] - m[0][1] * m[1][2] * m[2][3]),
+
+      t[1],
+      (m[2][0] * m[3][2] * m[0][3] - m[3][0] * m[2][2] * m[0][3] + m[3][0] * m[0][2] * m[2][3] - m[0][0] * m[3][2] * m[2][3] - m[2][0] * m[0][2] * m[3][3] + m[0][0] * m[2][2] * m[3][3]),
+      (m[3][0] * m[1][2] * m[0][3] - m[1][0] * m[3][2] * m[0][3] - m[3][0] * m[0][2] * m[1][3] + m[0][0] * m[3][2] * m[1][3] + m[1][0] * m[0][2] * m[3][3] - m[0][0] * m[1][2] * m[3][3]),
+      (m[1][0] * m[2][2] * m[0][3] - m[2][0] * m[1][2] * m[0][3] + m[2][0] * m[0][2] * m[1][3] - m[0][0] * m[2][2] * m[1][3] - m[1][0] * m[0][2] * m[2][3] + m[0][0] * m[1][2] * m[2][3]),
+
+      t[2],
+      (m[3][0] * m[2][1] * m[0][3] - m[2][0] * m[3][1] * m[0][3] - m[3][0] * m[0][1] * m[2][3] + m[0][0] * m[3][1] * m[2][3] + m[2][0] * m[0][1] * m[3][3] - m[0][0] * m[2][1] * m[3][3]),
+      (m[1][0] * m[3][1] * m[0][3] - m[3][0] * m[1][1] * m[0][3] + m[3][0] * m[0][1] * m[1][3] - m[0][0] * m[3][1] * m[1][3] - m[1][0] * m[0][1] * m[3][3] + m[0][0] * m[1][1] * m[3][3]),
+      (m[2][0] * m[1][1] * m[0][3] - m[1][0] * m[2][1] * m[0][3] - m[2][0] * m[0][1] * m[1][3] + m[0][0] * m[2][1] * m[1][3] + m[1][0] * m[0][1] * m[2][3] - m[0][0] * m[1][1] * m[2][3]),
+
+      t[3],
+      (m[2][0] * m[3][1] * m[0][2] - m[3][0] * m[2][1] * m[0][2] + m[3][0] * m[0][1] * m[2][2] - m[0][0] * m[3][1] * m[2][2] - m[2][0] * m[0][1] * m[3][2] + m[0][0] * m[2][1] * m[3][2]),
+      (m[3][0] * m[1][1] * m[0][2] - m[1][0] * m[3][1] * m[0][2] - m[3][0] * m[0][1] * m[1][2] + m[0][0] * m[3][1] * m[1][2] + m[1][0] * m[0][1] * m[3][2] - m[0][0] * m[1][1] * m[3][2]),
+      (m[1][0] * m[2][1] * m[0][2] - m[2][0] * m[1][1] * m[0][2] + m[2][0] * m[0][1] * m[1][2] - m[0][0] * m[2][1] * m[1][2] - m[1][0] * m[0][1] * m[2][2] + m[0][0] * m[1][1] * m[2][2])
+    ) * (1.0f / dot(m[0], t));
+}