nv50/ir: optimize mad/fma with third argument 0 to mul

Very modest effect, but it's clearly the right thing to do.

total instructions in shared programs : 6131491 -> 6131398 (-0.00%)
total gprs used in shared programs    : 910157 -> 910131 (-0.00%)
total local used in shared programs   : 15328 -> 15328 (0.00%)

                local        gpr       inst      bytes
    helped           0          55          85          85
      hurt           0          26          20          20

Signed-off-by: Karol Herbst <nouveau@karolherbst.de>
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>

diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
index bda9c7d..eb790d0 100644 (file)
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
@@ -336,6 +336,7 @@ private:
    void expr(Instruction *, ImmediateValue&, ImmediateValue&);
    void expr(Instruction *, ImmediateValue&, ImmediateValue&, ImmediateValue&);
    void opnd(Instruction *, ImmediateValue&, int s);
+   void opnd3(Instruction *, ImmediateValue&);
 
    void unary(Instruction *, const ImmediateValue&);
 
@@ -388,6 +389,8 @@ ConstantFolding::visit(BasicBlock *bb)
       else
       if (i->srcExists(1) && i->src(1).getImmediate(src1))
          opnd(i, src1, 1);
+      if (i->srcExists(2) && i->src(2).getImmediate(src2))
+         opnd3(i, src2);
    }
    return true;
 }
@@ -873,6 +876,24 @@ ConstantFolding::tryCollapseChainedMULs(Instruction *mul2,
 }
 
 void
+ConstantFolding::opnd3(Instruction *i, ImmediateValue &imm2)
+{
+   switch (i->op) {
+   case OP_MAD:
+   case OP_FMA:
+      if (imm2.isInteger(0)) {
+         i->op = OP_MUL;
+         i->setSrc(2, NULL);
+         foldCount++;
+         return;
+      }
+      break;
+   default:
+      return;
+   }
+}
+
+void
 ConstantFolding::opnd(Instruction *i, ImmediateValue &imm0, int s)
 {
    const int t = !s;