ac: eliminate duplicated VS exports

Only very few shaders have them (from 48486 shaders):

shaders/private/left_4_dead_2/765.shader_test - ac: 1 matches 2
shaders/private/left_4_dead_2/877.shader_test - ac: 1 matches 6
shaders/private/left_4_dead_2/2141.shader_test - ac: 1 matches 6
shaders/private/ue4_effects_cave/11.shader_test - ac: 4 matches 5
shaders/private/ue4_effects_cave/14.shader_test - ac: 5 matches 6
shaders/private/ue4_effects_cave/46.shader_test - ac: 5 matches 6
shaders/private/ue4_effects_cave/42.shader_test - ac: 4 matches 5
shaders/private/ue4_effects_cave/104.shader_test - ac: 4 matches 5
shaders/private/f1-2015/336.shader_test - ac: 3 matches 4
shaders/private/f1-2015/948.shader_test - ac: 6 matches 7
shaders/private/f1-2015/602.shader_test - ac: 0 matches 3
shaders/private/f1-2015/600.shader_test - ac: 0 matches 3
shaders/private/f1-2015/1214.shader_test - ac: 0 matches 1
shaders/private/f1-2015/988.shader_test - ac: 4 matches 5
shaders/private/ue4_elemental/149.shader_test - ac: 3 matches 4
shaders/private/ue4_elemental/346.shader_test - ac: 4 matches 5
shaders/private/ue4_elemental/178.shader_test - ac: 3 matches 4
shaders/private/ue4_elemental/136.shader_test - ac: 4 matches 5
shaders/private/ue4_elemental/168.shader_test - ac: 4 matches 5
shaders/private/ue4_elemental/690.shader_test - ac: 3 matches 4
shaders/private/ue4_elemental/19.shader_test - ac: 5 matches 6
shaders/private/dota2/1901.shader_test - ac: 0 matches 5
shaders/private/dota2/1357.shader_test - ac: 0 matches 5
shaders/private/dota2/1375.shader_test - ac: 0 matches 5
shaders/private/dota2/1369.shader_test - ac: 0 matches 5
shaders/private/dota2/1583.shader_test - ac: 0 matches 5
shaders/private/dota2/1811.shader_test - ac: 0 matches 5
shaders/private/dota2/1893.shader_test - ac: 0 matches 5
shaders/private/dota2/1533.shader_test - ac: 0 matches 5
shaders/private/dota2/1951.shader_test - ac: 0 matches 5
shaders/private/dota2/1361.shader_test - ac: 0 matches 5
shaders/private/mad_max/2792.shader_test - ac: 0 matches 1
shaders/private/mad_max/2794.shader_test - ac: 0 matches 1
shaders/private/mad_max/2780.shader_test - ac: 0 matches 1
shaders/private/mad_max/2902.shader_test - ac: 0 matches 1
shaders/private/bioshock-infinite/3050.shader_test - ac: 3 matches 7
shaders/private/bioshock-infinite/2544.shader_test - ac: 3 matches 6
shaders/private/bioshock-infinite/3062.shader_test - ac: 3 matches 8
shaders/private/bioshock-infinite/2012.shader_test - ac: 3 matches 7
shaders/private/bioshock-infinite/3058.shader_test - ac: 3 matches 7
shaders/private/bioshock-infinite/3270.shader_test - ac: 3 matches 7
shaders/private/bioshock-infinite/732.shader_test - ac: 3 matches 7
shaders/private/bioshock-infinite/3026.shader_test - ac: 3 matches 7
shaders/private/bioshock-infinite/3258.shader_test - ac: 3 matches 6
shaders/private/bioshock-infinite/3198.shader_test - ac: 3 matches 6
shaders/private/bioshock-infinite/3046.shader_test - ac: 3 matches 7
shaders/private/bioshock-infinite/3168.shader_test - ac: 3 matches 6
shaders/private/bioshock-infinite/2550.shader_test - ac: 3 matches 6
shaders/private/bioshock-infinite/3210.shader_test - ac: 3 matches 6
shaders/private/bioshock-infinite/3032.shader_test - ac: 3 matches 6
shaders/private/bioshock-infinite/668.shader_test - ac: 3 matches 7

Reviewed-by: Dave Airlie <airlied@redhat.com>
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>

diff --git a/src/amd/common/ac_llvm_build.c b/src/amd/common/ac_llvm_build.c
index 26ade111177254c93c08687499cc9d85c5e92ece..c89633f923cb4b7d1da350ca0659c3fdc3a61e2f 100644 (file)
--- a/src/amd/common/ac_llvm_build.c
+++ b/src/amd/common/ac_llvm_build.c
@@ -1320,6 +1320,80 @@ static bool ac_eliminate_const_output(uint8_t *vs_output_param_offset,
        return true;
 }
 
+static bool ac_eliminate_duplicated_output(uint8_t *vs_output_param_offset,
+                                          uint32_t num_outputs,
+                                          struct ac_vs_exports *processed,
+                                          struct ac_vs_exp_inst *exp)
+{
+       unsigned p, copy_back_channels = 0;
+
+       /* See if the output is already in the list of processed outputs.
+        * The LLVMValueRef comparison relies on SSA.
+        */
+       for (p = 0; p < processed->num; p++) {
+               bool different = false;
+
+               for (unsigned j = 0; j < 4; j++) {
+                       struct ac_vs_exp_chan *c1 = &processed->exp[p].chan[j];
+                       struct ac_vs_exp_chan *c2 = &exp->chan[j];
+
+                       /* Treat undef as a match. */
+                       if (c2->type == AC_IR_UNDEF)
+                               continue;
+
+                       /* If c1 is undef but c2 isn't, we can copy c2 to c1
+                        * and consider the instruction duplicated.
+                        */
+                       if (c1->type == AC_IR_UNDEF) {
+                               copy_back_channels |= 1 << j;
+                               continue;
+                       }
+
+                       /* Test whether the channels are not equal. */
+                       if (c1->type != c2->type ||
+                           (c1->type == AC_IR_CONST &&
+                            c1->const_float != c2->const_float) ||
+                           (c1->type == AC_IR_VALUE &&
+                            c1->value != c2->value)) {
+                               different = true;
+                               break;
+                       }
+               }
+               if (!different)
+                       break;
+
+               copy_back_channels = 0;
+       }
+       if (p == processed->num)
+               return false;
+
+       /* If a match was found, but the matching export has undef where the new
+        * one has a normal value, copy the normal value to the undef channel.
+        */
+       struct ac_vs_exp_inst *match = &processed->exp[p];
+
+       while (copy_back_channels) {
+               unsigned chan = u_bit_scan(&copy_back_channels);
+
+               assert(match->chan[chan].type == AC_IR_UNDEF);
+               LLVMSetOperand(match->inst, AC_EXP_OUT0 + chan,
+                              exp->chan[chan].value);
+               match->chan[chan] = exp->chan[chan];
+       }
+
+       /* The PARAM export is duplicated. Kill it. */
+       LLVMInstructionEraseFromParent(exp->inst);
+
+       /* Change OFFSET to the matching export. */
+       for (unsigned i = 0; i < num_outputs; i++) {
+               if (vs_output_param_offset[i] == exp->offset) {
+                       vs_output_param_offset[i] = match->offset;
+                       break;
+               }
+       }
+       return true;
+}
+
 void ac_optimize_vs_outputs(struct ac_llvm_context *ctx,
                            LLVMValueRef main_fn,
                            uint8_t *vs_output_param_offset,
@@ -1389,9 +1463,12 @@ void ac_optimize_vs_outputs(struct ac_llvm_context *ctx,
                                }
                        }
 
-                       /* Eliminate constant value PARAM exports. */
+                       /* Eliminate constant and duplicated PARAM exports. */
                        if (ac_eliminate_const_output(vs_output_param_offset,
-                                                     num_outputs, &exp)) {
+                                                     num_outputs, &exp) ||
+                           ac_eliminate_duplicated_output(vs_output_param_offset,
+                                                          num_outputs, &exports,
+                                                          &exp)) {
                                removed_any = true;
                        } else {
                                exports.exp[exports.num++] = exp;