[Mesa-dev] [PATCH v2 3/7] nv50/ir: optimize neg(and(set, 1)) to set

[Karol Herbst]

From: Karol Herbst <git at karolherbst.de>

helps shaders in saints row IV, bioshock infinite and shadow warrior

total instructions in shared programs : 1921966 -> 1910935 (-0.57%)
total gprs used in shared programs    : 251863 -> 251728 (-0.05%)
total local used in shared programs   : 5673 -> 5673 (0.00%)
total bytes used in shared programs   : 17622728 -> 17521824 (-0.57%)

                local        gpr       inst      bytes
    helped           0         137         719         719
      hurt           0          12           0           0

v2: remove this opt for OP_SLCT and check against float for OP_SET
Signed-off-by: Karol Herbst <nouveau at karolherbst.de>
---
 .../drivers/nouveau/codegen/nv50_ir_peephole.cpp   | 29 ++++++++++++++++++++++
 1 file changed, 29 insertions(+)

diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
index 7b51ce0..eb43f6c 100644
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
@@ -1510,6 +1510,7 @@ private:
    void handleCVT_CVT(Instruction *);
    void handleCVT_EXTBF(Instruction *);
    void handleSUCLAMP(Instruction *);
+   void handleNEG(Instruction *);
 
    BuildUtil bld;
 };
@@ -1982,6 +1983,31 @@ AlgebraicOpt::handleSUCLAMP(Instruction *insn)
    insn->setSrc(0, add->getSrc(s));
 }
 
+// NEG(AND(SET, 1)) -> SET
+void
+AlgebraicOpt::handleNEG(Instruction *i) {
+   Instruction *src = i->getSrc(0)->getInsn();
+   if (src->op == OP_AND) {
+      ImmediateValue imm;
+      int b = 1;
+      if (src->src(0).getImmediate(imm))
+         b = 1;
+      else if (src->src(1).getImmediate(imm))
+         b = 0;
+      else
+         return;
+
+      if (imm.isInteger(1)) {
+         Value *srcAnd = src->getSrc(b);
+         Instruction *set = srcAnd->getInsn();
+         if (set->op == OP_SET && !isFloatType(set->dType)) {
+            i->def(0).replace(srcAnd->getInsn()->getDef(0), false);
+            return;
+         }
+      }
+   }
+}
+
 bool
 AlgebraicOpt::visit(BasicBlock *bb)
 {
@@ -2019,6 +2045,9 @@ AlgebraicOpt::visit(BasicBlock *bb)
       case OP_SUCLAMP:
          handleSUCLAMP(i);
          break;
+      case OP_NEG:
+         handleNEG(i);
+         break;
       default:
          break;
       }
-- 
2.7.0