aco: add framework for unit testing

[mesa.git] / src / amd / compiler / aco_reduce_assign.cpp

diff --git a/src/amd/compiler/aco_reduce_assign.cpp b/src/amd/compiler/aco_reduce_assign.cpp
index 28a779580a26f7f52cea75e037861973730b2e6a..7bf7a6c3b685b9d8ddcf756782100f2200a08c0e 100644 (file)
--- a/src/amd/compiler/aco_reduce_assign.cpp
+++ b/src/amd/compiler/aco_reduce_assign.cpp
@@ -120,10 +120,15 @@ void setup_reduce_temp(Program* program)
                           op == fmin64 || op == fmax64 || op == umin64 ||
                           op == umax64 || op == imin64 || op == imax64 ||
                           op == imul64;
+         bool gfx10_need_vtmp = op == imul8 || op == imax8 || op == imin8 || op == umin8 ||
+                                op == imul16 || op == imax16 || op == imin16 || op == umin16 ||
+                                op == iadd64;
 
-         if (program->chip_class >= GFX10 && cluster_size == 64 && op != gfx10_wave64_bpermute)
+         if (program->chip_class >= GFX10 && cluster_size == 64)
             need_vtmp = true;
-         if (program->chip_class >= GFX10 && op == iadd64)
+         if (program->chip_class >= GFX10 && gfx10_need_vtmp)
+            need_vtmp = true;
+         if (program->chip_class <= GFX7)
             need_vtmp = true;
 
          need_vtmp |= cluster_size == 32;
@@ -153,12 +158,14 @@ void setup_reduce_temp(Program* program)
          instr->definitions[1] = bld.def(s2);
 
          /* scalar identity temporary */
-         bool need_sitmp = program->chip_class >= GFX10 && cluster_size == 64;
+         bool need_sitmp = (program->chip_class <= GFX7 || program->chip_class >= GFX10) && instr->opcode != aco_opcode::p_reduce;
          if (instr->opcode == aco_opcode::p_exclusive_scan) {
             need_sitmp |=
-               (op == imin32 || op == imin64 || op == imax32 || op == imax64 ||
-                op == fmin32 || op == fmin64 || op == fmax32 || op == fmax64 ||
-                op == fmul64);
+               (op == imin8 || op == imin16 || op == imin32 || op == imin64 ||
+                op == imax8 || op == imax16 || op == imax32 || op == imax64 ||
+                op == fmin16 || op == fmin32 || op == fmin64 ||
+                op == fmax16 || op == fmax32 || op == fmax64 ||
+                op == fmul16 || op == fmul64);
          }
          if (need_sitmp) {
             instr->definitions[2] = bld.def(RegClass(RegType::sgpr, instr->operands[0].size()));
@@ -172,7 +179,7 @@ void setup_reduce_temp(Program* program)
             clobber_vcc = true;
 
          if (clobber_vcc)
-            instr->definitions[4] = Definition(vcc, s2);
+            instr->definitions[4] = Definition(vcc, bld.lm);
       }
    }
 }