[Mesa-dev] [PATCH] i965/vs: Fix matNxM vertex attributes where M != 4.

[Kenneth Graunke]

Matrix vertex attributes have their columns padded out to vec4s, which
I was failing to account for.  Scalar NIR expects them to be packed,
however.

Cc: mesa-stable at lists.freedesktop.org
Signed-off-by: Kenneth Graunke <kenneth at whitecape.org>
---
 src/mesa/drivers/dri/i965/brw_fs_nir.cpp | 15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

I still need to write proper Piglit tests for this.  We have basically a single
test for matrix vertex attributes, and that's a mat4 (which worked).

But I figure we probably shouldn't hold up the bugfix on that.

diff --git a/src/mesa/drivers/dri/i965/brw_fs_nir.cpp b/src/mesa/drivers/dri/i965/brw_fs_nir.cpp
index caf1300..37b1ed7 100644
--- a/src/mesa/drivers/dri/i965/brw_fs_nir.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs_nir.cpp
@@ -91,12 +91,19 @@ fs_visitor::nir_setup_inputs(nir_shader *shader)
           * So, we need to copy from fs_reg(ATTR, var->location) to
           * offset(nir_inputs, var->data.driver_location).
           */
-         unsigned components = var->type->without_array()->components();
+         const glsl_type *const t = var->type->without_array();
+         const unsigned components = t->components();
+         const unsigned cols = t->matrix_columns;
+         const unsigned elts = t->vector_elements;
          unsigned array_length = var->type->is_array() ? var->type->length : 1;
          for (unsigned i = 0; i < array_length; i++) {
-            for (unsigned j = 0; j < components; j++) {
-               bld.MOV(retype(offset(input, bld, components * i + j), type),
-                       offset(fs_reg(ATTR, var->data.location + i, type), bld, j));
+            for (unsigned j = 0; j < cols; j++) {
+               for (unsigned k = 0; k < elts; k++) {
+                  bld.MOV(offset(retype(input, type), bld,
+                                 components * i + elts * j + k),
+                          offset(fs_reg(ATTR, var->data.location + i, type),
+                                 bld, 4 * j + k));
+               }
             }
          }
          break;
-- 
2.4.4