i965/fs: Allow copy propagation on ATTR file registers.

This especially helps with NIR because we currently emit MOVs at the top
of the shader to copy from various ATTR registers to a giant VGRF array
of all inputs.  (This could potentially be done better, but since
there's only ever one write to each register, it should be trivial to
copy propagate away...)

With NIR - only vertex shaders:
total instructions in shared programs: 3129373 -> 2889581 (-7.66%)
instructions in affected programs:     3119717 -> 2879925 (-7.69%)
helped:                                20833

Without NIR - only vertex shaders:
total instructions in shared programs: 2745901 -> 2724483 (-0.78%)
instructions in affected programs:     693426 -> 672008 (-3.09%)
helped:                                3516

Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Reviewed-by: Jason Ekstrand <jason.ekstrand@intel.com>

diff --git a/src/mesa/drivers/dri/i965/brw_fs_copy_propagation.cpp b/src/mesa/drivers/dri/i965/brw_fs_copy_propagation.cpp
index c0f0119..52bfa92 100644 (file)
--- a/src/mesa/drivers/dri/i965/brw_fs_copy_propagation.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs_copy_propagation.cpp
@@ -293,7 +293,8 @@ fs_visitor::try_copy_propagate(fs_inst *inst, int arg, acp_entry *entry)
 
    if (entry->src.file == IMM)
       return false;
-   assert(entry->src.file == GRF || entry->src.file == UNIFORM);
+   assert(entry->src.file == GRF || entry->src.file == UNIFORM ||
+          entry->src.file == ATTR);
 
    if (entry->opcode == SHADER_OPCODE_LOAD_PAYLOAD &&
        inst->opcode == SHADER_OPCODE_LOAD_PAYLOAD)
@@ -394,6 +395,7 @@ fs_visitor::try_copy_propagate(fs_inst *inst, int arg, acp_entry *entry)
       inst->src[arg].reg_offset = entry->src.reg_offset;
       inst->src[arg].subreg_offset = entry->src.subreg_offset;
       break;
+   case ATTR:
    case GRF:
       {
          assert(entry->src.width % inst->src[arg].width == 0);
@@ -634,6 +636,7 @@ can_propagate_from(fs_inst *inst)
            ((inst->src[0].file == GRF &&
              (inst->src[0].reg != inst->dst.reg ||
               inst->src[0].reg_offset != inst->dst.reg_offset)) ||
+            inst->src[0].file == ATTR ||
             inst->src[0].file == UNIFORM ||
             inst->src[0].file == IMM) &&
            inst->src[0].type == inst->dst.type &&