nv50/ir: prefer to color mad def and src2 with the same color

This allows us to use the short encoding, and potentially fold
immediates in later on.

total instructions in shared programs : 6379731 -> 6367861 (-0.19%)
total gprs used in shared programs    : 728502 -> 728683 (0.02%)
total local used in shared programs   : 9904 -> 9904 (0.00%)
total bytes used in shared programs   : 44661008 -> 44154976 (-1.13%)

                local        gpr       inst      bytes
    helped           0          51        7267       20306
      hurt           0         232         125         274

Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>

diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_ra.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_ra.cpp
index a7d81774a8307242502ba3529c3cc7431d8671db..b32bc13f755e9fad96c0c690df53ecdcdb1501fc 100644 (file)
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_ra.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_ra.cpp
@@ -1465,6 +1465,20 @@ GCRA::allocateRegisters(ArrayList& insns)
       if (lval) {
          nodes[i].init(regs, lval);
          RIG.insert(&nodes[i]);
+
+         if (lval->inFile(FILE_GPR) && lval->defs.size() > 0 &&
+             prog->getTarget()->getChipset() < 0xc0) {
+            Instruction *insn = lval->getInsn();
+            if (insn->op == OP_MAD || insn->op == OP_SAD)
+               // Short encoding only possible if they're all GPRs, no need to
+               // affect them otherwise.
+               if (insn->flagsDef < 0 &&
+                   isFloatType(insn->dType) &&
+                   insn->src(0).getFile() == FILE_GPR &&
+                   insn->src(1).getFile() == FILE_GPR &&
+                   insn->src(2).getFile() == FILE_GPR)
+                  nodes[i].addRegPreference(getNode(insn->getSrc(2)->asLValue()));
+         }
       }
    }