diff options
| -rw-r--r-- | src/glsl/linker.cpp | 64 |
1 files changed, 36 insertions, 28 deletions
diff --git a/src/glsl/linker.cpp b/src/glsl/linker.cpp index bc5e55b4b21..01554bc2ad7 100644 --- a/src/glsl/linker.cpp +++ b/src/glsl/linker.cpp @@ -2339,6 +2339,7 @@ assign_attribute_or_color_locations(gl_shader_program *prog, */ unsigned used_locations = (max_index >= 32) ? ~0 : ~((1 << max_index) - 1); + unsigned double_storage_locations = 0; assert((target_index == MESA_SHADER_VERTEX) || (target_index == MESA_SHADER_FRAGMENT)); @@ -2452,34 +2453,6 @@ assign_attribute_or_color_locations(gl_shader_program *prog, const unsigned slots = var->type->count_attribute_slots(); - /* From GL4.5 core spec, section 11.1.1 (Vertex Attributes): - * - * "A program with more than the value of MAX_VERTEX_ATTRIBS active - * attribute variables may fail to link, unless device-dependent - * optimizations are able to make the program fit within available - * hardware resources. For the purposes of this test, attribute variables - * of the type dvec3, dvec4, dmat2x3, dmat2x4, dmat3, dmat3x4, dmat4x3, - * and dmat4 may count as consuming twice as many attributes as equivalent - * single-precision types. While these types use the same number of - * generic attributes as their single-precision equivalents, - * implementations are permitted to consume two single-precision vectors - * of internal storage for each three- or four-component double-precision - * vector." - * Until someone has a good reason in Mesa, enforce that now. - */ - if (target_index == MESA_SHADER_VERTEX) { - total_attribs_size += slots; - if (var->type->without_array() == glsl_type::dvec3_type || - var->type->without_array() == glsl_type::dvec4_type || - var->type->without_array() == glsl_type::dmat2x3_type || - var->type->without_array() == glsl_type::dmat2x4_type || - var->type->without_array() == glsl_type::dmat3_type || - var->type->without_array() == glsl_type::dmat3x4_type || - var->type->without_array() == glsl_type::dmat4x3_type || - var->type->without_array() == glsl_type::dmat4_type) - total_attribs_size += slots; - } - /* If the variable is not a built-in and has a location statically * assigned in the shader (presumably via a layout qualifier), make sure * that it doesn't collide with other assigned locations. Otherwise, @@ -2594,6 +2567,38 @@ assign_attribute_or_color_locations(gl_shader_program *prog, } used_locations |= (use_mask << attr); + + /* From the GL 4.5 core spec, section 11.1.1 (Vertex Attributes): + * + * "A program with more than the value of MAX_VERTEX_ATTRIBS + * active attribute variables may fail to link, unless + * device-dependent optimizations are able to make the program + * fit within available hardware resources. For the purposes + * of this test, attribute variables of the type dvec3, dvec4, + * dmat2x3, dmat2x4, dmat3, dmat3x4, dmat4x3, and dmat4 may + * count as consuming twice as many attributes as equivalent + * single-precision types. While these types use the same number + * of generic attributes as their single-precision equivalents, + * implementations are permitted to consume two single-precision + * vectors of internal storage for each three- or four-component + * double-precision vector." + * + * Mark this attribute slot as taking up twice as much space + * so we can count it properly against limits. According to + * issue (3) of the GL_ARB_vertex_attrib_64bit behavior, this + * is optional behavior, but it seems preferable. + */ + const glsl_type *type = var->type->without_array(); + if (type == glsl_type::dvec3_type || + type == glsl_type::dvec4_type || + type == glsl_type::dmat2x3_type || + type == glsl_type::dmat2x4_type || + type == glsl_type::dmat3_type || + type == glsl_type::dmat3x4_type || + type == glsl_type::dmat4x3_type || + type == glsl_type::dmat4_type) { + double_storage_locations |= (use_mask << attr); + } } continue; @@ -2605,6 +2610,9 @@ assign_attribute_or_color_locations(gl_shader_program *prog, } if (target_index == MESA_SHADER_VERTEX) { + unsigned total_attribs_size = + _mesa_bitcount(used_locations & ((1 << max_index) - 1)) + + _mesa_bitcount(double_storage_locations); if (total_attribs_size > max_index) { linker_error(prog, "attempt to use %d vertex attribute slots only %d available ", |