4 files changed, 17 insertions, 2 deletions
diff --git a/src/mesa/drivers/dri/i965/brw_fs.cpp b/src/mesa/drivers/dri/i965/brw_fs.cpp
index 629fbbdf01b..ad94fa479e2 100644
--- a/src/mesa/drivers/dri/i965/brw_fs.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs.cpp
@@ -514,6 +514,19 @@ type_size_scalar(const struct glsl_type *type)
 }
 
 /**
+ * Returns the number of scalar components needed to store type, assuming
+ * that vectors are padded out to vec4.
+ *
+ * This has the packing rules of type_size_vec4(), but counts components
+ * similar to type_size_scalar().
+ */
+extern "C" int
+type_size_vec4_times_4(const struct glsl_type *type)
+{
+   return 4 * type_size_vec4(type);
+}
+
+/**
  * Create a MOV to read the timestamp register.
  *
  * The caller is responsible for emitting the MOV.  The return value is
diff --git a/src/mesa/drivers/dri/i965/brw_fs_nir.cpp b/src/mesa/drivers/dri/i965/brw_fs_nir.cpp
index b6f4c52c50f..261518605b7 100644
--- a/src/mesa/drivers/dri/i965/brw_fs_nir.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs_nir.cpp
@@ -104,7 +104,7 @@ fs_visitor::nir_setup_outputs()
       switch (stage) {
       case MESA_SHADER_VERTEX:
       case MESA_SHADER_GEOMETRY:
-         for (unsigned int i = 0; i < ALIGN(type_size_scalar(var->type), 4) / 4; i++) {
+         for (int i = 0; i < type_size_vec4(var->type); i++) {
             int output = var->data.location + i;
             this->outputs[output] = offset(reg, bld, 4 * i);
             this->output_components[output] = vector_elements;
diff --git a/src/mesa/drivers/dri/i965/brw_nir.c b/src/mesa/drivers/dri/i965/brw_nir.c
index a7a5eb511cd..dece208233f 100644
--- a/src/mesa/drivers/dri/i965/brw_nir.c
+++ b/src/mesa/drivers/dri/i965/brw_nir.c
@@ -150,7 +150,8 @@ brw_nir_lower_outputs(nir_shader *nir, bool is_scalar)
    case MESA_SHADER_GEOMETRY:
       if (is_scalar) {
          nir_assign_var_locations(&nir->outputs, &nir->num_outputs,
-                                  type_size_scalar);
+                                  type_size_vec4_times_4);
+         nir_lower_io(nir, nir_var_shader_out, type_size_vec4_times_4);
       } else {
          nir_foreach_variable(var, &nir->outputs)
             var->data.driver_location = var->data.location;
diff --git a/src/mesa/drivers/dri/i965/brw_shader.h b/src/mesa/drivers/dri/i965/brw_shader.h
index 6a2dfc9bbb6..29baebf0cc1 100644
--- a/src/mesa/drivers/dri/i965/brw_shader.h
+++ b/src/mesa/drivers/dri/i965/brw_shader.h
@@ -277,6 +277,7 @@ bool brw_cs_precompile(struct gl_context *ctx,
 
 int type_size_scalar(const struct glsl_type *type);
 int type_size_vec4(const struct glsl_type *type);
+int type_size_vec4_times_4(const struct glsl_type *type);
 
 bool is_scalar_shader_stage(const struct brw_compiler *compiler, int stage);