[Mesa-dev] [PATCH 2/2] nvir/gm107: consider FILE_FLAGS dependencies in SchedDataCalculatorGM107

[Karol Herbst]

currently while insterting barriers, writes and reads to FILE_FLAGS aren't
considered. This can lead to WaR hazards in some situations.

Fixes OpenCL CTS tests on Maxwell+:
basic/test_basic.intmath_long.LONG_MAD
basic/test_basic.intmath_long2.LONG_MAD
basic/test_basic.intmath_long4.LONG_MAD

Signed-off-by: Karol Herbst <kherbst at redhat.com>
---
 src/gallium/drivers/nouveau/codegen/nv50_ir_emit_gm107.cpp | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_gm107.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_gm107.cpp
index db1585818c..cd75d531df 100644
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_gm107.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_emit_gm107.cpp
@@ -3949,6 +3949,7 @@ SchedDataCalculatorGM107::needWrDepBar(const Instruction *insn) const
 
    for (int d = 0; insn->defExists(d); ++d) {
       if (insn->def(d).getFile() == FILE_GPR ||
+          insn->def(d).getFile() == FILE_FLAGS ||
           insn->def(d).getFile() == FILE_PREDICATE)
          return true;
    }
@@ -3988,6 +3989,9 @@ SchedDataCalculatorGM107::findFirstUse(const Instruction *bari) const
                   continue;
                return insn;
             }
+            if (bari->def(d).getFile() == FILE_FLAGS) {
+               return insn;
+            }
          }
       }
    }
@@ -4007,7 +4011,8 @@ SchedDataCalculatorGM107::findFirstDef(const Instruction *bari) const
 
       for (int d = 0; insn->defExists(d); ++d) {
          const Value *def = insn->def(d).rep();
-         if (insn->def(d).getFile() != FILE_GPR)
+         if (insn->def(d).getFile() != FILE_GPR &&
+             insn->def(d).getFile() != FILE_FLAGS)
             continue;
 
          minGPR = def->reg.data.id;
@@ -4015,7 +4020,11 @@ SchedDataCalculatorGM107::findFirstDef(const Instruction *bari) const
 
          for (int s = 0; bari->srcExists(s); ++s) {
             const Value *src = bari->src(s).rep();
+            if (bari->src(s).getFile() == FILE_FLAGS &&
+                insn->def(d).getFile() == FILE_FLAGS)
+               return insn;
             if (bari->src(s).getFile() != FILE_GPR ||
+                insn->def(d).getFile() != FILE_GPR ||
                 src->reg.data.id + src->reg.size / 4 - 1 < minGPR ||
                 src->reg.data.id > maxGPR)
                continue;
-- 
2.14.3