nir: Add a "compact array" flag and IO lowering code.
Certain built-in arrays, such as gl_ClipDistance[], gl_CullDistance[], gl_TessLevelInner[], and gl_TessLevelOuter[] are specified as scalar arrays. Normal scalar arrays are sparse - each array element usually occupies a whole vec4 slot. However, most hardware assumes these built-in arrays are tightly packed. The new var->data.compact flag indicates that a scalar array should be tightly packed, so a float[4] array would take up a single vec4 slot, and a float[8] array would take up two slots. They are still arrays, not vec4s, however. nir_lower_io will generate intrinsics using ARB_enhanced_layouts style component qualifiers. v2: Add nir_validate code to enforce type restrictions. Signed-off-by: Kenneth Graunke <kenneth@whitecape.org> Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
This commit is contained in:
@@ -94,8 +94,11 @@ mark_whole_variable(nir_shader *shader, nir_variable *var)
|
||||
var->data.mode == nir_var_shader_in)
|
||||
is_vertex_input = true;
|
||||
|
||||
set_io_mask(shader, var, 0,
|
||||
glsl_count_attribute_slots(type, is_vertex_input));
|
||||
const unsigned slots =
|
||||
var->data.compact ? DIV_ROUND_UP(glsl_get_length(type), 4)
|
||||
: glsl_count_attribute_slots(type, is_vertex_input);
|
||||
|
||||
set_io_mask(shader, var, 0, slots);
|
||||
}
|
||||
|
||||
static unsigned
|
||||
@@ -150,7 +153,7 @@ try_mask_partial_io(nir_shader *shader, nir_deref_var *deref)
|
||||
* here marking the entire variable as used.
|
||||
*/
|
||||
if (!(glsl_type_is_matrix(type) ||
|
||||
(glsl_type_is_array(type) &&
|
||||
(glsl_type_is_array(type) && !var->data.compact &&
|
||||
(glsl_type_is_numeric(glsl_without_array(type)) ||
|
||||
glsl_type_is_boolean(glsl_without_array(type)))))) {
|
||||
|
||||
|
Reference in New Issue
Block a user