[Mesa-dev] [PATCH 01/17] glsl/nir: add new num_packed_components field

Edward O'Callaghan funfunctor at folklore1984.net
Fri Jul 8 02:42:08 UTC 2016


Patches 7, 8, 10-13 & 15-17 are simple enough,

Reviewed-by: Edward O'Callaghan <funfunctor at folklore1984.net>

I would perhaps suggest squashing 16+17 together, up to you.

Kind Regards,
Edward.

On 07/08/2016 10:38 AM, Timothy Arceri wrote:
> On Thu, 2016-07-07 at 17:50 +1000, Edward O'Callaghan wrote:
>> Hi,
>>
>> There is a typing issue in this patch in that, you are converting
>> ‘gl_linked_shader*’ to ‘gl_shader*’ for the first argument to
>> function
>> ‘void set_num_packed_components(gl_shader*, ir_variable_mode,
>> unsigned
>> int)’ at the various call sites.
> 
> Whoops, not sure how I missed that when rebasing. Fix pushed to the
> branch in my repo. Thanks.
> 
>>
>> Cheers,
>> Edward.
>>
>>
>> On 07/07/2016 11:58 AM, Timothy Arceri wrote:
>>> This will be used to store the total number of components used at
>>> this location
>>> when packing via ARB_enhanced_layouts.
>>> ---
>>>  src/compiler/glsl/glsl_to_nir.cpp   |  1 +
>>>  src/compiler/glsl/ir.h              |  5 +++
>>>  src/compiler/glsl/link_varyings.cpp | 74
>>> ++++++++++++++++++++++++++++++++++++-
>>>  src/compiler/glsl/linker.cpp        |  2 +
>>>  src/compiler/glsl/linker.h          |  4 ++
>>>  src/compiler/nir/nir.h              |  5 +++
>>>  6 files changed, 89 insertions(+), 2 deletions(-)
>>>
>>> diff --git a/src/compiler/glsl/glsl_to_nir.cpp
>>> b/src/compiler/glsl/glsl_to_nir.cpp
>>> index 20302e3..baba624 100644
>>> --- a/src/compiler/glsl/glsl_to_nir.cpp
>>> +++ b/src/compiler/glsl/glsl_to_nir.cpp
>>> @@ -375,6 +375,7 @@ nir_visitor::visit(ir_variable *ir)
>>>     var->data.explicit_binding = ir->data.explicit_binding;
>>>     var->data.has_initializer = ir->data.has_initializer;
>>>     var->data.location_frac = ir->data.location_frac;
>>> +   var->data.num_packed_components = ir-
>>>> data.num_packed_components;
>>>  
>>>     switch (ir->data.depth_layout) {
>>>     case ir_depth_layout_none:
>>> diff --git a/src/compiler/glsl/ir.h b/src/compiler/glsl/ir.h
>>> index 1325e35..637b53c 100644
>>> --- a/src/compiler/glsl/ir.h
>>> +++ b/src/compiler/glsl/ir.h
>>> @@ -770,6 +770,11 @@ public:
>>>        unsigned location_frac:2;
>>>  
>>>        /**
>>> +       * The total number of components packed into this location.
>>> +       */
>>> +      unsigned num_packed_components:4;
>>> +
>>> +      /**
>>>         * Layout of the matrix.  Uses glsl_matrix_layout values.
>>>         */
>>>        unsigned matrix_layout:2;
>>> diff --git a/src/compiler/glsl/link_varyings.cpp
>>> b/src/compiler/glsl/link_varyings.cpp
>>> index 76d0be1..35f97a9 100644
>>> --- a/src/compiler/glsl/link_varyings.cpp
>>> +++ b/src/compiler/glsl/link_varyings.cpp
>>> @@ -1975,6 +1975,70 @@ reserved_varying_slot(struct
>>> gl_linked_shader *stage,
>>>     return slots;
>>>  }
>>>  
>>> +void
>>> +set_num_packed_components(struct gl_shader *shader,
>>> ir_variable_mode io_mode,
>>> +                          unsigned base_offset)
>>> +{
>>> +   /* Find the max number of components used at this location */
>>> +   unsigned num_components[MAX_VARYINGS_INCL_PATCH] = { 0 };
>>> +
>>> +   foreach_in_list(ir_instruction, node, shader->ir) {
>>> +      ir_variable *const var = node->as_variable();
>>> +
>>> +      if (var == NULL || var->data.mode != io_mode ||
>>> +          !var->data.explicit_location)
>>> +         continue;
>>> +
>>> +      int idx = var->data.location - base_offset;
>>> +      if (idx < 0 || idx >= MAX_VARYINGS_INCL_PATCH ||
>>> +          var->type->without_array()->is_record() ||
>>> +          var->type->without_array()->is_matrix())
>>> +         continue;
>>> +
>>> +      if (var->type->is_array()) {
>>> +         const glsl_type *type = get_varying_type(var, shader-
>>>> Stage);
>>> +         unsigned array_components = type->without_array()-
>>>> vector_elements +
>>> +            var->data.location_frac;
>>> +         assert(type->arrays_of_arrays_size() + idx <=
>>> +                ARRAY_SIZE(num_components));
>>> +         for (unsigned i = idx; i < type->arrays_of_arrays_size(); 
>>> i++) {
>>> +            num_components[i] = MAX2(array_components,
>>> num_components[i]);
>>> +         }
>>> +      } else {
>>> +         unsigned comps = var->type->vector_elements +
>>> +            var->data.location_frac;
>>> +         num_components[idx] = MAX2(comps, num_components[idx]);
>>> +      }
>>> +   }
>>> +
>>> +   foreach_in_list(ir_instruction, node, shader->ir) {
>>> +      ir_variable *const var = node->as_variable();
>>> +
>>> +      if (var == NULL || var->data.mode != io_mode ||
>>> +          !var->data.explicit_location)
>>> +         continue;
>>> +
>>> +      int idx = var->data.location - base_offset;
>>> +      if (idx < 0 || idx >= MAX_VARYINGS_INCL_PATCH ||
>>> +          var->type->without_array()->is_record() ||
>>> +          var->type->without_array()->is_matrix())
>>> +         continue;
>>> +
>>> +      /* For arrays we need to check all elements in order to find
>>> the max
>>> +       * number of components used.
>>> +       */
>>> +      unsigned c = 0;
>>> +      if (var->type->is_array()) {
>>> +         const glsl_type *type = get_varying_type(var, shader-
>>>> Stage);
>>> +         for (unsigned i = idx; i < type->arrays_of_arrays_size(); 
>>> i++) {
>>> +            c = MAX2(c, num_components[i]);
>>> +         }
>>> +      } else {
>>> +         c = num_components[idx];
>>> +      }
>>> +      var->data.num_packed_components = c;
>>> +   }
>>> +}
>>>  
>>>  /**
>>>   * Assign locations for all variables that are produced in one
>>> pipeline stage
>>> @@ -2091,11 +2155,17 @@ assign_varying_locations(struct gl_context
>>> *ctx,
>>>      * 4. Mark input variables in the consumer that do not have
>>> locations as
>>>      *    not being inputs.  This lets the optimizer eliminate
>>> them.
>>>      */
>>> -   if (consumer)
>>> +   if (consumer) {
>>>        canonicalize_shader_io(consumer->ir, ir_var_shader_in);
>>> +      set_num_packed_components(consumer, ir_var_shader_in,
>>> +                                VARYING_SLOT_VAR0);
>>> +   }
>>>  
>>> -   if (producer)
>>> +   if (producer) {
>>>        canonicalize_shader_io(producer->ir, ir_var_shader_out);
>>> +      set_num_packed_components(producer, ir_var_shader_out,
>>> +                                VARYING_SLOT_VAR0);
>>> +   }
>>>  
>>>     if (consumer)
>>>        linker::populate_consumer_input_sets(mem_ctx, consumer->ir,
>>> diff --git a/src/compiler/glsl/linker.cpp
>>> b/src/compiler/glsl/linker.cpp
>>> index d963f54..d8bb58b 100644
>>> --- a/src/compiler/glsl/linker.cpp
>>> +++ b/src/compiler/glsl/linker.cpp
>>> @@ -2625,6 +2625,8 @@
>>> assign_attribute_or_color_locations(gl_shader_program *prog,
>>>        (target_index == MESA_SHADER_VERTEX)
>>>        ? ir_var_shader_in : ir_var_shader_out;
>>>  
>>> +   set_num_packed_components(sh, direction, generic_base);
>>> +
>>>  
>>>     /* Temporary storage for the set of attributes that need
>>> locations assigned.
>>>      */
>>> diff --git a/src/compiler/glsl/linker.h
>>> b/src/compiler/glsl/linker.h
>>> index e1a53d2..056ce97 100644
>>> --- a/src/compiler/glsl/linker.h
>>> +++ b/src/compiler/glsl/linker.h
>>> @@ -86,6 +86,10 @@ extern void
>>>  link_check_atomic_counter_resources(struct gl_context *ctx,
>>>                                      struct gl_shader_program
>>> *prog);
>>>  
>>> +void
>>> +set_num_packed_components(struct gl_shader *shader,
>>> ir_variable_mode io_mode,
>>> +                          unsigned base_offset);
>>> +
>>>  /**
>>>   * Class for processing all of the leaf fields of a variable that
>>> corresponds
>>>   * to a program resource.
>>> diff --git a/src/compiler/nir/nir.h b/src/compiler/nir/nir.h
>>> index a7921ee..2bfedb2 100644
>>> --- a/src/compiler/nir/nir.h
>>> +++ b/src/compiler/nir/nir.h
>>> @@ -227,6 +227,11 @@ typedef struct nir_variable {
>>>        unsigned location_frac:2;
>>>  
>>>        /**
>>> +       * The total number of components packed into this location.
>>> +       */
>>> +      unsigned num_packed_components:4;
>>> +
>>> +      /**
>>>         * \brief Layout qualifier for gl_FragDepth.
>>>         *
>>>         * This is not equal to \c ir_depth_layout_none if and only
>>> if this
>>>
>>

-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 819 bytes
Desc: OpenPGP digital signature
URL: <https://lists.freedesktop.org/archives/mesa-dev/attachments/20160708/f7656cf4/attachment.sig>


More information about the mesa-dev mailing list