nv50/ir: also do PostRaLoadPropagation for FMA

Helps Feral-ported games, due to their use of fma()

shader-db changes:
total instructions in shared programs : 3934925 -> 3934327 (-0.02%)
total gprs used in shared programs    : 481563 -> 481563 (0.00%)
total local used in shared programs   : 27469 -> 27469 (0.00%)
total bytes used in shared programs   : 36061888 -> 36056504 (-0.01%)

                local        gpr       inst      bytes
    helped           0           0         228         228
      hurt           0           0           0           0

Signed-off-by: Karol Herbst <karolherbst@gmail.com>
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 7cf0166..4c92a1e 100644 (file)
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
@@ -3307,6 +3307,7 @@ bool
 PostRaLoadPropagation::visit(Instruction *i)
 {
    switch (i->op) {
+   case OP_FMA:
    case OP_MAD:
       if (prog->getTarget()->getChipset() < 0xc0)
          handleMADforNV50(i);

diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_ra.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_ra.cpp
index d36c853..193628c 100644 (file)
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_ra.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_ra.cpp
@@ -1471,7 +1471,7 @@ GCRA::allocateRegisters(ArrayList& insns)
          if (lval->inFile(FILE_GPR) && lval->getInsn() != NULL &&
              prog->getTarget()->getChipset() < 0xc0) {
             Instruction *insn = lval->getInsn();
-            if (insn->op == OP_MAD || insn->op == OP_SAD)
+            if (insn->op == OP_MAD || insn->op == OP_FMA || insn->op == OP_SAD)
                // Short encoding only possible if they're all GPRs, no need to
                // affect them otherwise.
                if (insn->flagsDef < 0 &&