[Mesa-dev] [PATCH 1/3] nv50/ir: optimize slct(b, c, set(a, 0)) to slct(b, c, a)

[Karol Herbst]

From: Karol Herbst <karolherbst at gmail.com>

helps mainly feral ported games

shader-db changes:
total instructions in shared programs : 5751418 -> 5730139 (-0.37%)
total gprs used in shared programs    : 664007 -> 663206 (-0.12%)
total shared used in shared programs  : 548832 -> 548832 (0.00%)
total local used in shared programs   : 20956 -> 20956 (0.00%)
total bytes used in shared programs   : 61439848 -> 61212472 (-0.37%)

                local     shared        gpr       inst      bytes
    helped           0           0         673        3746        3746
      hurt           0           0          49           8           8

Signed-off-by: Karol Herbst <kherbst at redhat.com>
---
 .../nouveau/codegen/nv50_ir_peephole.cpp      | 47 +++++++++++++++++--
 1 file changed, 44 insertions(+), 3 deletions(-)

diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
index 39177bd044b..32c6f9ee7af 100644
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
@@ -1664,7 +1664,8 @@ private:
    bool tryADDToMADOrSAD(Instruction *, operation toOp);
    void handleMINMAX(Instruction *);
    void handleRCP(Instruction *);
-   void handleSLCT(Instruction *);
+   void handleSLCT(CmpInstruction *);
+   bool tryMergeSLCTSET(CmpInstruction *slct, CmpInstruction *set);
    void handleLOGOP(Instruction *);
    void handleCVT_NEG(Instruction *);
    void handleCVT_CVT(Instruction *);
@@ -1847,8 +1848,12 @@ AlgebraicOpt::handleRCP(Instruction *rcp)
 }
 
 void
-AlgebraicOpt::handleSLCT(Instruction *slct)
+AlgebraicOpt::handleSLCT(CmpInstruction *slct)
 {
+   Instruction *insn = slct->getSrc(2)->getInsn();
+   while(insn && insn->op == OP_SET && tryMergeSLCTSET(slct, insn->asCmp())) {
+      insn = slct->getSrc(2)->getInsn();
+   }
    if (slct->getSrc(2)->reg.file == FILE_IMMEDIATE) {
       if (slct->getSrc(2)->asImm()->compare(slct->asCmp()->setCond, 0.0f))
          slct->setSrc(0, slct->getSrc(1));
@@ -1861,6 +1866,42 @@ AlgebraicOpt::handleSLCT(Instruction *slct)
    slct->setSrc(2, NULL);
 }
 
+bool
+AlgebraicOpt::tryMergeSLCTSET(CmpInstruction *slct, CmpInstruction *set)
+{
+   assert(slct->op == OP_SLCT && set->op == OP_SET);
+
+   if (typeSizeof(set->sType) != 4)
+      return false;
+
+   CondCode setCC = set->getCondition();
+   CondCode slctCC = slct->getCondition();
+   CondCode newCC = setCC;
+
+   if (slctCC != CC_NE && slctCC != CC_EQ)
+      return false;
+
+   ImmediateValue imm0;
+   int s;
+
+   if (set->src(0).getImmediate(imm0) && imm0.isInteger(0))
+      s = 1;
+   else if (set->src(1).getImmediate(imm0) && imm0.isInteger(0))
+      s = 0;
+   else
+      return false;
+
+   slct->setSrc(2, set->getSrc(s));
+   if (s)
+      newCC = reverseCondCode(newCC);
+   if (slctCC == CC_EQ)
+      newCC = inverseCondCode(newCC);
+
+   slct->sType = set->sType;
+   slct->setCondition(newCC);
+   return true;
+}
+
 void
 AlgebraicOpt::handleLOGOP(Instruction *logop)
 {
@@ -2196,7 +2237,7 @@ AlgebraicOpt::visit(BasicBlock *bb)
          handleMINMAX(i);
          break;
       case OP_SLCT:
-         handleSLCT(i);
+         handleSLCT(i->asCmp());
          break;
       case OP_AND:
       case OP_OR:
-- 
2.17.1