Inline 2.0
UberCTS
In the course of working on more CI-related things for zink, I came across a series of troublesome tests (KHR-GL46.geometry_shader.rendering.rendering.triangles_*) that triggered a severe performance issue. Specifically, the LLVM optimizer spends absolute ages trying to optimize ubershaders like this one used in the tests:
#version 440
in vec4 position;
out vec4 vs_gs_color;
uniform bool is_lines_output;
uniform bool is_indexed_draw_call;
uniform bool is_instanced_draw_call;
uniform bool is_points_output;
uniform bool is_triangle_fan_input;
uniform bool is_triangle_strip_input;
uniform bool is_triangle_strip_adjacency_input;
uniform bool is_triangles_adjacency_input;
uniform bool is_triangles_input;
uniform bool is_triangles_output;
uniform ivec2 renderingTargetSize;
uniform ivec2 singleRenderingTargetSize;
void main()
{
gl_Position = position + vec4(float(gl_InstanceID) ) * vec4(0, float(singleRenderingTargetSize.y) / float(renderingTargetSize.y), 0, 0) * vec4(2.0);
vs_gs_color = vec4(1.0, 0.0, 0.0, 0.0);
if (is_lines_output)
{
if (!is_indexed_draw_call)
{
if (is_triangle_fan_input)
{
switch(gl_VertexID)
{
case 0: vs_gs_color = vec4(0.1, 0.2, 0.3, 0.4); break;
case 1:
case 5: vs_gs_color = vec4(0.2, 0.3, 0.4, 0.5); break;
case 2: vs_gs_color = vec4(0.3, 0.4, 0.5, 0.6); break;
case 3: vs_gs_color = vec4(0.4, 0.5, 0.6, 0.7); break;
case 4: vs_gs_color = vec4(0.5, 0.6, 0.7, 0.8); break;
default: vs_gs_color = vec4(1.0, 1.0, 1.0, 1.0); break;
}
}
else
if (is_triangle_strip_input)
{
switch(gl_VertexID)
{
case 1:
case 6: vs_gs_color = vec4(0.2, 0.3, 0.4, 0.5); break;
case 0:
case 4: vs_gs_color = vec4(0.1, 0.2, 0.3, 0.4); break;
case 2: vs_gs_color = vec4(0.3, 0.4, 0.5, 0.6); break;
case 3: vs_gs_color = vec4(0.4, 0.5, 0.6, 0.7); break;
case 5: vs_gs_color = vec4(0.5, 0.6, 0.7, 0.8); break;
default: vs_gs_color = vec4(1.0, 1.0, 1.0, 1.0); break;
}
}
else
if (is_triangle_strip_adjacency_input)
{
switch(gl_VertexID)
{
case 2:
case 12: vs_gs_color = vec4(0.2, 0.3, 0.4, 0.5); break;
case 0:
case 8: vs_gs_color = vec4(0.1, 0.2, 0.3, 0.4); break;
case 4: vs_gs_color = vec4(0.3, 0.4, 0.5, 0.6); break;
case 6: vs_gs_color = vec4(0.4, 0.5, 0.6, 0.7); break;
case 10: vs_gs_color = vec4(0.5, 0.6, 0.7, 0.8); break;
default: vs_gs_color = vec4(1.0, 1.0, 1.0, 1.0); break;
}
}
else
if (is_triangles_input)
{
switch(gl_VertexID)
{
case 0: vs_gs_color = vec4(0.1, 0.2, 0.3, 0.4); break;
case 1: vs_gs_color = vec4(0.2, 0.3, 0.4, 0.5); break;
case 2: vs_gs_color = vec4(0.3, 0.4, 0.5, 0.6); break;
case 3: vs_gs_color = vec4(0.1, 0.2, 0.3, 0.4); break;
case 4: vs_gs_color = vec4(0.3, 0.4, 0.5, 0.6); break;
case 5: vs_gs_color = vec4(0.4, 0.5, 0.6, 0.7); break;
case 6: vs_gs_color = vec4(0.1, 0.2, 0.3, 0.4); break;
case 7: vs_gs_color = vec4(0.4, 0.5, 0.6, 0.7); break;
case 8: vs_gs_color = vec4(0.5, 0.6, 0.7, 0.8); break;
case 9: vs_gs_color = vec4(0.1, 0.2, 0.3, 0.4); break;
case 10: vs_gs_color = vec4(0.5, 0.6, 0.7, 0.8); break;
case 11: vs_gs_color = vec4(0.2, 0.3, 0.4, 0.5); break;
}
}
else
if (is_triangles_adjacency_input)
{
vs_gs_color = vec4(1.0, 1.0, 1.0, 1.0);
switch(gl_VertexID)
{
case 0: vs_gs_color = vec4(0.1, 0.2, 0.3, 0.4); break;
case 2: vs_gs_color = vec4(0.2, 0.3, 0.4, 0.5); break;
case 4: vs_gs_color = vec4(0.3, 0.4, 0.5, 0.6); break;
case 6: vs_gs_color = vec4(0.1, 0.2, 0.3, 0.4); break;
case 8: vs_gs_color = vec4(0.3, 0.4, 0.5, 0.6); break;
case 10: vs_gs_color = vec4(0.4, 0.5, 0.6, 0.7); break;
case 12: vs_gs_color = vec4(0.1, 0.2, 0.3, 0.4); break;
case 14: vs_gs_color = vec4(0.4, 0.5, 0.6, 0.7); break;
case 16: vs_gs_color = vec4(0.5, 0.6, 0.7, 0.8); break;
case 18: vs_gs_color = vec4(0.1, 0.2, 0.3, 0.4); break;
case 20: vs_gs_color = vec4(0.5, 0.6, 0.7, 0.8); break;
case 22: vs_gs_color = vec4(0.2, 0.3, 0.4, 0.5); break;
}
}
}
else
{
if (is_triangles_input)
{
switch(gl_VertexID)
{
case 11: vs_gs_color = vec4(0.1, 0.2, 0.3, 0.4); break;
case 10: vs_gs_color = vec4(0.2, 0.3, 0.4, 0.5); break;
case 9: vs_gs_color = vec4(0.3, 0.4, 0.5, 0.6); break;
case 8: vs_gs_color = vec4(0.1, 0.2, 0.3, 0.4); break;
case 7: vs_gs_color = vec4(0.3, 0.4, 0.5, 0.6); break;
case 6: vs_gs_color = vec4(0.4, 0.5, 0.6, 0.7); break;
case 5: vs_gs_color = vec4(0.1, 0.2, 0.3, 0.4); break;
case 4: vs_gs_color = vec4(0.4, 0.5, 0.6, 0.7); break;
case 3: vs_gs_color = vec4(0.5, 0.6, 0.7, 0.8); break;
case 2: vs_gs_color = vec4(0.1, 0.2, 0.3, 0.4); break;
case 1: vs_gs_color = vec4(0.5, 0.6, 0.7, 0.8); break;
case 0: vs_gs_color = vec4(0.2, 0.3, 0.4, 0.5); break;
}
}
else
if (is_triangle_fan_input)
{
switch(gl_VertexID)
{
case 5: vs_gs_color = vec4(0.1, 0.2, 0.3, 0.4); break;
case 4:
case 0: vs_gs_color = vec4(0.2, 0.3, 0.4, 0.5); break;
case 3: vs_gs_color = vec4(0.3, 0.4, 0.5, 0.6); break;
case 2: vs_gs_color = vec4(0.4, 0.5, 0.6, 0.7); break;
case 1: vs_gs_color = vec4(0.5, 0.6, 0.7, 0.8); break;
default: vs_gs_color = vec4(1.0, 1.0, 1.0, 1.0); break;
}
}
else
if (is_triangle_strip_input)
{
switch (gl_VertexID)
{
case 5:
case 0: vs_gs_color = vec4(0.2, 0.3, 0.4, 0.5); break;
case 6:
case 2: vs_gs_color = vec4(0.1, 0.2, 0.3, 0.4); break;
case 4: vs_gs_color = vec4(0.3, 0.4, 0.5, 0.6); break;
case 3: vs_gs_color = vec4(0.4, 0.5, 0.6, 0.7); break;
case 1: vs_gs_color = vec4(0.5, 0.6, 0.7, 0.8); break;
default: vs_gs_color = vec4(1.0, 1.0, 1.0, 1.0); break;
}
}
else
if (is_triangle_strip_adjacency_input)
{
switch(gl_VertexID)
{
case 11:
case 1: vs_gs_color = vec4(0.2, 0.3, 0.4, 0.5); break;
case 13:
case 5: vs_gs_color = vec4(0.1, 0.2, 0.3, 0.4); break;
case 9: vs_gs_color = vec4(0.3, 0.4, 0.5, 0.6); break;
case 7: vs_gs_color = vec4(0.4, 0.5, 0.6, 0.7); break;
case 3: vs_gs_color = vec4(0.5, 0.6, 0.7, 0.8); break;
default: vs_gs_color = vec4(1.0, 1.0, 1.0, 1.0); break;
}
}
else
if (is_triangles_adjacency_input)
{
vs_gs_color = vec4(1.0, 1.0, 1.0, 1.0);
switch(gl_VertexID)
{
case 23: vs_gs_color = vec4(0.1, 0.2, 0.3, 0.4); break;
case 21: vs_gs_color = vec4(0.2, 0.3, 0.4, 0.5); break;
case 19: vs_gs_color = vec4(0.3, 0.4, 0.5, 0.6); break;
case 17: vs_gs_color = vec4(0.1, 0.2, 0.3, 0.4); break;
case 15: vs_gs_color = vec4(0.3, 0.4, 0.5, 0.6); break;
case 13: vs_gs_color = vec4(0.4, 0.5, 0.6, 0.7); break;
case 11: vs_gs_color = vec4(0.1, 0.2, 0.3, 0.4); break;
case 9: vs_gs_color = vec4(0.4, 0.5, 0.6, 0.7); break;
case 7: vs_gs_color = vec4(0.5, 0.6, 0.7, 0.8); break;
case 5: vs_gs_color = vec4(0.1, 0.2, 0.3, 0.4); break;
case 3: vs_gs_color = vec4(0.5, 0.6, 0.7, 0.8); break;
case 1: vs_gs_color = vec4(0.2, 0.3, 0.4, 0.5); break;
}
}
}
}
else
if (is_points_output)
{
if (!is_indexed_draw_call)
{
if (is_triangles_adjacency_input)
{
vs_gs_color = vec4(1.0, 1.0, 1.0, 1.0);
switch (gl_VertexID)
{
case 0:
case 6:
case 12:
case 18: vs_gs_color = vec4(0.4, 0.5, 0.6, 0.7); break;
case 2:
case 22: vs_gs_color = vec4(0.5, 0.6, 0.7, 0.8); break;
case 4:
case 8: vs_gs_color = vec4(0.1, 0.2, 0.3, 0.4); break;
case 10:
case 14: vs_gs_color = vec4(0.2, 0.3, 0.4, 0.5); break;
case 16:
case 20: vs_gs_color = vec4(0.3, 0.4, 0.5, 0.6); break;
}
}
else
if (is_triangle_fan_input)
{
switch(gl_VertexID)
{
case 0: vs_gs_color = vec4(0.4, 0.5, 0.6, 0.7); break;
case 1:
case 5: vs_gs_color = vec4(0.5, 0.6, 0.7, 0.8); break;
case 2: vs_gs_color = vec4(0.1, 0.2, 0.3, 0.4); break;
case 3: vs_gs_color = vec4(0.2, 0.3, 0.4, 0.5); break;
case 4: vs_gs_color = vec4(0.3, 0.4, 0.5, 0.6); break;
default: vs_gs_color = vec4(1.0, 1.0, 1.0, 1.0); break;
}
}
else
if (is_triangle_strip_input)
{
switch (gl_VertexID)
{
case 1:
case 4: vs_gs_color = vec4(0.4, 0.5, 0.6, 0.7); break;
case 0:
case 6: vs_gs_color = vec4(0.5, 0.6, 0.7, 0.8); break;
case 2: vs_gs_color = vec4(0.1, 0.2, 0.3, 0.4); break;
case 3: vs_gs_color = vec4(0.2, 0.3, 0.4, 0.5); break;
case 5: vs_gs_color = vec4(0.3, 0.4, 0.5, 0.6); break;
default: vs_gs_color = vec4(1.0, 1.0, 1.0, 1.0); break;
}
}
else
if (is_triangle_strip_adjacency_input)
{
switch (gl_VertexID)
{
case 2:
case 8: vs_gs_color = vec4(0.4, 0.5, 0.6, 0.7); break;
case 0:
case 12: vs_gs_color = vec4(0.5, 0.6, 0.7, 0.8); break;
case 4: vs_gs_color = vec4(0.1, 0.2, 0.3, 0.4); break;
case 6: vs_gs_color = vec4(0.2, 0.3, 0.4, 0.5); break;
case 10: vs_gs_color = vec4(0.3, 0.4, 0.5, 0.6); break;
default: vs_gs_color = vec4(1.0, 1.0, 1.0, 1.0); break;
}
}
else
if (is_triangles_input)
{
switch (gl_VertexID)
{
case 0:
case 3:
case 6:
case 9: vs_gs_color = vec4(0.4, 0.5, 0.6, 0.7); break;
case 1:
case 11: vs_gs_color = vec4(0.5, 0.6, 0.7, 0.8); break;
case 2:
case 4: vs_gs_color = vec4(0.1, 0.2, 0.3, 0.4); break;
case 5:
case 7: vs_gs_color = vec4(0.2, 0.3, 0.4, 0.5); break;
case 8:
case 10: vs_gs_color = vec4(0.3, 0.4, 0.5, 0.6); break;
}
}
}
else
{
if (is_triangle_fan_input)
{
switch (gl_VertexID)
{
case 5: vs_gs_color = vec4(0.4, 0.5, 0.6, 0.7); break;
case 4:
case 0: vs_gs_color = vec4(0.5, 0.6, 0.7, 0.8); break;
case 3: vs_gs_color = vec4(0.1, 0.2, 0.3, 0.4); break;
case 2: vs_gs_color = vec4(0.2, 0.3, 0.4, 0.5); break;
case 1: vs_gs_color = vec4(0.3, 0.4, 0.5, 0.6); break;
default: vs_gs_color = vec4(1.0, 1.0, 1.0, 1.0); break;
}
}
else
if (is_triangle_strip_input)
{
switch (gl_VertexID)
{
case 5:
case 2: vs_gs_color = vec4(0.4, 0.5, 0.6, 0.7); break;
case 6:
case 0: vs_gs_color = vec4(0.5, 0.6, 0.7, 0.8); break;
case 4: vs_gs_color = vec4(0.1, 0.2, 0.3, 0.4); break;
case 3: vs_gs_color = vec4(0.2, 0.3, 0.4, 0.5); break;
case 1: vs_gs_color = vec4(0.3, 0.4, 0.5, 0.6); break;
default: vs_gs_color = vec4(1.0, 1.0, 1.0, 1.0); break;
}
}
else
if (is_triangle_strip_adjacency_input)
{
switch (gl_VertexID)
{
case 11:
case 5: vs_gs_color = vec4(0.4, 0.5, 0.6, 0.7); break;
case 13:
case 1: vs_gs_color = vec4(0.5, 0.6, 0.7, 0.8); break;
case 9: vs_gs_color = vec4(0.1, 0.2, 0.3, 0.4); break;
case 7: vs_gs_color = vec4(0.2, 0.3, 0.4, 0.5); break;
case 3: vs_gs_color = vec4(0.3, 0.4, 0.5, 0.6); break;
default: vs_gs_color = vec4(1.0, 1.0, 1.0, 1.0); break;
}
}
else
if (is_triangles_adjacency_input)
{
vs_gs_color = vec4(1.0, 1.0, 1.0, 1.0);
switch (gl_VertexID)
{
case 23:
case 17:
case 11:
case 5: vs_gs_color = vec4(0.4, 0.5, 0.6, 0.7); break;
case 21:
case 1: vs_gs_color = vec4(0.5, 0.6, 0.7, 0.8); break;
case 19:
case 15: vs_gs_color = vec4(0.1, 0.2, 0.3, 0.4); break;
case 13:
case 9: vs_gs_color = vec4(0.2, 0.3, 0.4, 0.5); break;
case 7:
case 3: vs_gs_color = vec4(0.3, 0.4, 0.5, 0.6); break;
}
}
else
if (is_triangles_input)
{
switch (gl_VertexID)
{
case 11:
case 8:
case 5:
case 2: vs_gs_color = vec4(0.4, 0.5, 0.6, 0.7); break;
case 10:
case 0: vs_gs_color = vec4(0.5, 0.6, 0.7, 0.8); break;
case 9:
case 7: vs_gs_color = vec4(0.1, 0.2, 0.3, 0.4); break;
case 6:
case 4: vs_gs_color = vec4(0.2, 0.3, 0.4, 0.5); break;
case 3:
case 1: vs_gs_color = vec4(0.3, 0.4, 0.5, 0.6); break;
}
}
}
}
else
if (is_triangles_output)
{
int vertex_id = 0;
if (!is_indexed_draw_call && is_triangles_adjacency_input && (gl_VertexID % 2 == 0) )
{
vertex_id = gl_VertexID / 2 + 1;
}
else
{
vertex_id = gl_VertexID + 1;
}
vs_gs_color = vec4(float(vertex_id) / 48.0, float(vertex_id % 3) / 2.0, float(vertex_id % 4) / 3.0, float(vertex_id % 5) / 4.0);
}
}
By ages I mean upwards of 10 minutes per test.
Yikes.
When In Doubt, Inline
Fortunately, zink already has tools to combat exactly this problem: ZINK_INLINE_UNIFORMS.
This feature analyzes shaders to determine if inlining uniform values will be beneficial, and if so, it rewrites the shader with the uniform values as constants rather than loads. This brings the resulting NIR for the shader from 4000+ lines down to just under 300. The tests all become near-instant to run as well.
Uniform inlining has been in zink for a while, but it’s been disabled by default (except on zink-wip for testing) as this isn’t a feature that’s typically desirable when running apps/games; every time the uniforms are updated, a new shader must be compiled, and this causes (even more) stuttering, making games on zink (even more) unplayable.
On CPU-based drivers like lavapipe, however, the time to compile a shader is usually less than the time to actually run a shader, so the trade-off becomes worth doing.
Stay tuned for exciting announcements in the next few days.
Written on November 10, 2021