[Mesa-dev] [PATCH v2 09/15] i965/fs: calculate first non-payload GRF using attrib slots

[Antia Puentes]

From: "Juan A. Suarez Romero" <jasuarez at igalia.com>

When computing where the first non-payload GRF starts, we can't rely on
the number of attributes, as each attribute can be using 1 or 2 slots
depending on whether they are a dvec3/4 or other.

Instead, we need to use the number of slots used by the attributes.

Reviewed-by: Kenneth Graunke <kenneth at whitecape.org>
---
 src/mesa/drivers/dri/i965/brw_compiler.h | 1 +
 src/mesa/drivers/dri/i965/brw_fs.cpp     | 2 +-
 src/mesa/drivers/dri/i965/brw_vec4.cpp   | 1 +
 3 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/src/mesa/drivers/dri/i965/brw_compiler.h b/src/mesa/drivers/dri/i965/brw_compiler.h
index 5807305..446c609 100644
--- a/src/mesa/drivers/dri/i965/brw_compiler.h
+++ b/src/mesa/drivers/dri/i965/brw_compiler.h
@@ -607,6 +607,7 @@ struct brw_vs_prog_data {
    GLbitfield64 inputs_read;
 
    unsigned nr_attributes;
+   unsigned nr_attribute_slots;
 
    bool uses_vertexid;
    bool uses_instanceid;
diff --git a/src/mesa/drivers/dri/i965/brw_fs.cpp b/src/mesa/drivers/dri/i965/brw_fs.cpp
index e2a87a7..970846c 100644
--- a/src/mesa/drivers/dri/i965/brw_fs.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs.cpp
@@ -1875,7 +1875,7 @@ fs_visitor::assign_vs_urb_setup()
    assert(stage == MESA_SHADER_VERTEX);
 
    /* Each attribute is 4 regs. */
-   this->first_non_payload_grf += 4 * vs_prog_data->nr_attributes;
+   this->first_non_payload_grf += 4 * vs_prog_data->nr_attribute_slots;
 
    assert(vs_prog_data->base.urb_read_length <= 15);
 
diff --git a/src/mesa/drivers/dri/i965/brw_vec4.cpp b/src/mesa/drivers/dri/i965/brw_vec4.cpp
index b144fe8..88d9317 100644
--- a/src/mesa/drivers/dri/i965/brw_vec4.cpp
+++ b/src/mesa/drivers/dri/i965/brw_vec4.cpp
@@ -2120,6 +2120,7 @@ brw_compile_vs(const struct brw_compiler *compiler, void *log_data,
          DIV_ROUND_UP(MAX2(nr_attribute_slots, 1), 2);
 
    prog_data->nr_attributes = nr_attributes;
+   prog_data->nr_attribute_slots = nr_attribute_slots;
 
    /* Since vertex shaders reuse the same VUE entry for inputs and outputs
     * (overwriting the original contents), we need to make sure the size is
-- 
2.7.4