BLF: Optimize text rendering and caching

The current code allocates and transfers a lot of memory to the GPU,
but only a small portion of this memory is actually used.
In addition, the code calls many costly gl operations during the
caching process.

This commit significantly reduce the amount of memory by allocating
and transferring a flat array without pads to the GPU.
It also calls as little as possible the gl operations during the cache.

This code also simulate a billinear filter `GL_LINEAR` using a 1D texture.

**Average drawing time:**
|before:|0.00003184 sec
|now:|0.00001943 sec
|fac:|1.6385156675048407

**5 worst times:**
|before:|[0.001075, 0.001433, 0.002143, 0.002915, 0.003242]
|now:|[0.00094, 0.000993, 0.001502, 0.002284, 0.002328]

Differential Revision: https://developer.blender.org/D6886

1 files changed, 17 insertions, 4 deletions

diff --git a/source/blender/gpu/shaders/gpu_shader_text_vert.glsl b/source/blender/gpu/shaders/gpu_shader_text_vert.glsl
index 28437208e91..768638e5229 100644
--- a/source/blender/gpu/shaders/gpu_shader_text_vert.glsl
+++ b/source/blender/gpu/shaders/gpu_shader_text_vert.glsl
@@ -2,20 +2,33 @@
 uniform mat4 ModelViewProjectionMatrix;
 
 in vec4 pos; /* rect */
-in vec4 tex; /* rect */
 in vec4 col;
+in int offset;
+in ivec2 glyph_size;
 
 flat out vec4 color_flat;
 noperspective out vec2 texCoord_interp;
+flat out int glyph_offset;
+flat out ivec2 glyph_dim;
+flat out int interp_size;
 
 void main()
 {
+  color_flat = col;
+  glyph_offset = offset;
+  glyph_dim = abs(glyph_size);
+  interp_size = int(glyph_size.x < 0) + int(glyph_size.y < 0);
+
   /* Quad expension using instanced rendering. */
   float x = float(gl_VertexID % 2);
   float y = float(gl_VertexID / 2);
   vec2 quad = vec2(x, y);
 
-  gl_Position = ModelViewProjectionMatrix * vec4(mix(pos.xy, pos.zw, quad), 0.0, 1.0);
-  texCoord_interp = mix(abs(tex.xy), abs(tex.zw), quad) * sign(tex.xw);
-  color_flat = col;
+  vec2 interp_offset = float(interp_size) / abs(pos.zw - pos.xy);
+  texCoord_interp = mix(-interp_offset, 1.0 + interp_offset, quad);
+
+  vec2 final_pos = mix(
+      pos.xy + ivec2(-interp_size, interp_size), pos.zw + ivec2(interp_size, -interp_size), quad);
+
+  gl_Position = ModelViewProjectionMatrix * vec4(final_pos, 0.0, 1.0);
 }