i965/fs: Enable CSE on uniform pull constant loads.

Improves on a major performance regression for the dolphin wii emulator
from its move to using UBOs.  Performance in the UBO codepath (as
replayed through apitrace) is up 21.1% +/- 2.3% (n=26/29).

Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>

diff --git a/src/mesa/drivers/dri/i965/brw_fs_cse.cpp b/src/mesa/drivers/dri/i965/brw_fs_cse.cpp
index a13ca362699a9402fd7d639bbea72a0db6c30fcc..44479d8e9ffef2286450ccb757aee6df246b556f 100644 (file)
--- a/src/mesa/drivers/dri/i965/brw_fs_cse.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs_cse.cpp
@@ -66,6 +66,7 @@ is_expression(const fs_inst *const inst)
    case BRW_OPCODE_LINE:
    case BRW_OPCODE_PLN:
    case BRW_OPCODE_MAD:
+   case FS_OPCODE_UNIFORM_PULL_CONSTANT_LOAD:
    case FS_OPCODE_CINTERP:
    case FS_OPCODE_LINTERP:
       return true;
@@ -136,8 +137,10 @@ fs_visitor::opt_cse_local(bblock_t *block, exec_list *aeb)
            }
 
            /* dest <- temp */
+            assert(inst->dst.type == entry->tmp.type);
            fs_inst *copy = new(ralloc_parent(inst))
               fs_inst(BRW_OPCODE_MOV, inst->dst, entry->tmp);
+            copy->force_writemask_all = inst->force_writemask_all;
            inst->replace_with(copy);
 
            /* Appending an instruction may have changed our bblock end. */