[Mesa-dev] [PATCH 1/2] nir: fill outputs_read field and add patch outputs read

[Dave Airlie]

From: Dave Airlie <airlied at redhat.com>

This is to be used for TCS optimisations on radv.
---
 src/compiler/nir/nir_gather_info.c | 29 ++++++++++++++++++++++-------
 src/compiler/shader_info.h         |  2 ++
 2 files changed, 24 insertions(+), 7 deletions(-)

diff --git a/src/compiler/nir/nir_gather_info.c b/src/compiler/nir/nir_gather_info.c
index 13cdae3..ab2d519 100644
--- a/src/compiler/nir/nir_gather_info.c
+++ b/src/compiler/nir/nir_gather_info.c
@@ -25,7 +25,8 @@
 #include "nir.h"
 
 static void
-set_io_mask(nir_shader *shader, nir_variable *var, int offset, int len)
+set_io_mask(nir_shader *shader, nir_variable *var, int offset, int len,
+            bool is_output_read)
 {
    for (int i = 0; i < len; i++) {
       assert(var->data.location != -1);
@@ -64,6 +65,14 @@ set_io_mask(nir_shader *shader, nir_variable *var, int offset, int len)
             shader->info.outputs_written |= bitfield;
          }
 
+         if (is_output_read) {
+            if (is_patch_generic) {
+               shader->info.patch_outputs_read |= bitfield;
+            } else {
+               shader->info.outputs_read |= bitfield;
+            }
+         }
+
          if (var->data.fb_fetch_output)
             shader->info.outputs_read |= bitfield;
       }
@@ -75,7 +84,7 @@ set_io_mask(nir_shader *shader, nir_variable *var, int offset, int len)
  * represents a shader input or output.
  */
 static void
-mark_whole_variable(nir_shader *shader, nir_variable *var)
+mark_whole_variable(nir_shader *shader, nir_variable *var, bool is_output_read)
 {
    const struct glsl_type *type = var->type;
 
@@ -88,7 +97,7 @@ mark_whole_variable(nir_shader *shader, nir_variable *var)
       var->data.compact ? DIV_ROUND_UP(glsl_get_length(type), 4)
                         : glsl_count_attribute_slots(type, false);
 
-   set_io_mask(shader, var, 0, slots);
+   set_io_mask(shader, var, 0, slots, is_output_read);
 }
 
 static unsigned
@@ -124,7 +133,7 @@ get_io_offset(nir_deref_var *deref)
  * occurs, then nothing will be marked and false will be returned.
  */
 static bool
-try_mask_partial_io(nir_shader *shader, nir_deref_var *deref)
+try_mask_partial_io(nir_shader *shader, nir_deref_var *deref, bool is_output_read)
 {
    nir_variable *var = deref->var;
    const struct glsl_type *type = var->type;
@@ -186,7 +195,7 @@ try_mask_partial_io(nir_shader *shader, nir_deref_var *deref)
       return false;
    }
 
-   set_io_mask(shader, var, offset, elem_width);
+   set_io_mask(shader, var, offset, elem_width, is_output_read);
    return true;
 }
 
@@ -209,8 +218,13 @@ gather_intrinsic_info(nir_intrinsic_instr *instr, nir_shader *shader)
 
       if (var->data.mode == nir_var_shader_in ||
           var->data.mode == nir_var_shader_out) {
-         if (!try_mask_partial_io(shader, instr->variables[0]))
-            mark_whole_variable(shader, var);
+         bool is_output_read = false;
+         if (var->data.mode == nir_var_shader_out &&
+             instr->intrinsic == nir_intrinsic_load_var)
+            is_output_read = true;
+
+         if (!try_mask_partial_io(shader, instr->variables[0], is_output_read))
+            mark_whole_variable(shader, var, is_output_read);
 
          /* We need to track which input_reads bits correspond to a
           * dvec3/dvec4 input attribute */
@@ -339,6 +353,7 @@ nir_shader_gather_info(nir_shader *shader, nir_function_impl *entrypoint)
    shader->info.inputs_read = 0;
    shader->info.outputs_written = 0;
    shader->info.outputs_read = 0;
+   shader->info.patch_outputs_read = 0;
    shader->info.double_inputs_read = 0;
    shader->info.patch_inputs_read = 0;
    shader->info.patch_outputs_written = 0;
diff --git a/src/compiler/shader_info.h b/src/compiler/shader_info.h
index 5f14ad1..bcb3f0f 100644
--- a/src/compiler/shader_info.h
+++ b/src/compiler/shader_info.h
@@ -66,6 +66,8 @@ typedef struct shader_info {
    uint32_t patch_inputs_read;
    /* Which patch outputs are actually written */
    uint32_t patch_outputs_written;
+   /* Which patch outputs are read */
+   uint32_t patch_outputs_read;
 
    /* Whether or not this shader ever uses textureGather() */
    bool uses_texture_gather;
-- 
2.9.5