[Mesa-dev] [PATCH] i965/nir/vec4: fill the type of the dst and src when loading an uniform

[Alejandro Piñeiro]

Until know, nir_intrinsic_load_uniform was using a default type. This
caused some type mismatch between movs and alu operations, so copy
propagation optimization was not applied to remove unneeded movs if
negate modifier was involved. This was first detected on minus
(negate+add) operations with uniforms involved.

This patch is equivalent to commit 4de86, but that one only affected
inputs, which information, included the type, was already being stored.
So this patch includes saving the type on nir_setup_uniforms.

Shader DB results (taking into account only vec4):

total instructions in shared programs: 1754416 -> 1742146 (-0.70%)
instructions in affected programs:     677491 -> 665221 (-1.81%)
helped:                                5381
HURT:                                  0
---
 src/mesa/drivers/dri/i965/brw_vec4.h           | 1 +
 src/mesa/drivers/dri/i965/brw_vec4_nir.cpp     | 4 ++++
 src/mesa/drivers/dri/i965/brw_vec4_visitor.cpp | 1 +
 3 files changed, 6 insertions(+)

diff --git a/src/mesa/drivers/dri/i965/brw_vec4.h b/src/mesa/drivers/dri/i965/brw_vec4.h
index 01c6e84..f6d2c82 100644
--- a/src/mesa/drivers/dri/i965/brw_vec4.h
+++ b/src/mesa/drivers/dri/i965/brw_vec4.h
@@ -163,6 +163,7 @@ public:
    int *uniform_vector_size;
    int uniform_array_size; /*< Size of uniform_[vector_]size arrays */
    int uniforms;
+   brw_reg_type *uniform_type;
 
    src_reg shader_start_time;
 
diff --git a/src/mesa/drivers/dri/i965/brw_vec4_nir.cpp b/src/mesa/drivers/dri/i965/brw_vec4_nir.cpp
index 175d92b..0b624fa 100644
--- a/src/mesa/drivers/dri/i965/brw_vec4_nir.cpp
+++ b/src/mesa/drivers/dri/i965/brw_vec4_nir.cpp
@@ -143,6 +143,7 @@ vec4_visitor::nir_setup_uniforms(nir_shader *shader)
 
          assert(uniforms < uniform_array_size);
          this->uniform_size[uniforms] = type_size_vec4(var->type);
+         this->uniform_type[uniforms] = brw_type_for_base_type(var->type);
 
          if (strncmp(var->name, "gl_", 3) == 0)
             nir_setup_builtin_uniform(var);
@@ -553,6 +554,9 @@ vec4_visitor::nir_emit_intrinsic(nir_intrinsic_instr *instr)
       src = src_reg(dst_reg(UNIFORM, instr->const_index[0]));
       src.reg_offset = instr->const_index[1];
 
+      assert(instr->const_index[0] < uniform_array_size);
+      dest.type = src.type = this->uniform_type[instr->const_index[0]];
+
       if (has_indirect) {
          src_reg tmp = get_nir_src(instr->src[0], BRW_REGISTER_TYPE_D, 1);
          src.reladdr = new(mem_ctx) src_reg(tmp);
diff --git a/src/mesa/drivers/dri/i965/brw_vec4_visitor.cpp b/src/mesa/drivers/dri/i965/brw_vec4_visitor.cpp
index 0465770..8e00612 100644
--- a/src/mesa/drivers/dri/i965/brw_vec4_visitor.cpp
+++ b/src/mesa/drivers/dri/i965/brw_vec4_visitor.cpp
@@ -3747,6 +3747,7 @@ vec4_visitor::vec4_visitor(const struct brw_compiler *compiler,
 
    this->uniform_size = rzalloc_array(mem_ctx, int, this->uniform_array_size);
    this->uniform_vector_size = rzalloc_array(mem_ctx, int, this->uniform_array_size);
+   this->uniform_type = rzalloc_array(mem_ctx, brw_reg_type, this->uniform_array_size);
 }
 
 vec4_visitor::~vec4_visitor()
-- 
2.1.4