This moves the nir_lower_indirect_derefs() call into
brw_preprocess_nir() so thats is called by both OpenGL and Vulkan
and removes that call to the old GLSL IR pass
lower_variable_index_to_cond_assign()
We want to do this pass in nir to be able to move loop unrolling
to nir.
There is a increase of 1-3 instructions in a small number of shaders,
and 2 Kerbal Space program shaders that increase by 32 instructions.
Shader-db results BDW:
total instructions in shared programs: 8705873 -> 8706194 (0.00%)
instructions in affected programs: 32515 -> 32836 (0.99%)
helped: 3
HURT: 79
total cycles in shared programs:
74618120 ->
74583476 (-0.05%)
cycles in affected programs: 528104 -> 493460 (-6.56%)
helped: 47
HURT: 37
LOST: 2
GAINED: 0
nir_shader_gather_info(nir, entry_point->impl);
- nir_variable_mode indirect_mask = 0;
- if (compiler->glsl_compiler_options[stage].EmitNoIndirectInput)
- indirect_mask |= nir_var_shader_in;
- if (compiler->glsl_compiler_options[stage].EmitNoIndirectOutput)
- indirect_mask |= nir_var_shader_out;
- if (compiler->glsl_compiler_options[stage].EmitNoIndirectTemp)
- indirect_mask |= nir_var_local;
-
- nir_lower_indirect_derefs(nir, indirect_mask);
-
return nir;
}
do_copy_propagation(shader->ir);
- bool lowered_variable_indexing =
- lower_variable_index_to_cond_assign(shader->Stage, shader->ir,
- options->EmitNoIndirectInput,
- options->EmitNoIndirectOutput,
- options->EmitNoIndirectTemp,
- options->EmitNoIndirectUniform);
-
- if (unlikely(brw->perf_debug && lowered_variable_indexing)) {
- perf_debug("Unsupported form of variable indexing in %s; falling "
- "back to very inefficient code generation\n",
- _mesa_shader_stage_to_abbrev(shader->Stage));
- }
-
bool progress;
do {
progress = false;
/* Lower a bunch of stuff */
OPT_V(nir_lower_var_copies);
+ nir_variable_mode indirect_mask = 0;
+ if (compiler->glsl_compiler_options[nir->stage].EmitNoIndirectInput)
+ indirect_mask |= nir_var_shader_in;
+ if (compiler->glsl_compiler_options[nir->stage].EmitNoIndirectOutput)
+ indirect_mask |= nir_var_shader_out;
+ if (compiler->glsl_compiler_options[nir->stage].EmitNoIndirectTemp)
+ indirect_mask |= nir_var_local;
+
+ nir_lower_indirect_derefs(nir, indirect_mask);
+
/* Get rid of split copies */
nir = nir_optimize(nir, is_scalar);