[Mesa-dev] [PATCH 2/2] nv50/ir: improve POW lowering

[Karol Herbst]

If the exponent is a small integer immediate value, we can lower POW to
MULs instead to save a few instructions. Also MUL instructions execute
faster than what we lower POW in the default case to.

score change for GpuTest /test=pixmark_piano /benchmark /no_scorebox
/msaa=0 /benchmark_duration_ms=60000 /width=1024 /height=640:
1045 -> 1060

changes in shader-db:
total instructions in shared programs : 4350261 -> 4349451 (-0.02%)
total gprs used in shared programs    : 525853 -> 525861 (0.00%)
total local used in shared programs   : 30081 -> 30081 (0.00%)
total bytes used in shared programs   : 39865176 -> 39857712 (-0.02%)

                local        gpr       inst      bytes
    helped           0           4         313         313
      hurt           0          12           1           1

Signed-off-by: Karol Herbst <karolherbst at gmail.com>
---
 .../drivers/nouveau/codegen/nv50_ir_build_util.cpp | 49 ++++++++++++++++++++++
 1 file changed, 49 insertions(+)

diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_build_util.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_build_util.cpp
index 5756e1b4d4..b31dcec1ab 100644
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_build_util.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_build_util.cpp
@@ -640,6 +640,55 @@ bool
 BuildUtil::lowerPOW(Instruction *i)
 {
    LValue *val = getScratch();
+   ImmediateValue imm;
+
+   if (i->src(1).getImmediate(imm)) {
+      Value *src = i->getSrc(0);
+      if (imm.isInteger(0)) {
+         i->op = OP_MOV;
+         i->setSrc(0, loadImm(NULL, 1));
+         i->setSrc(1, NULL);
+         return true;
+      } else
+      if (imm.isInteger(1)) {
+         i->op = OP_MOV;
+         i->setSrc(1, NULL);
+         return true;
+      } else
+      if (imm.isInteger(2)) {
+         i->op = OP_MUL;
+         i->setSrc(1, src);
+         return true;
+      } else
+      if (imm.isInteger(3)) {
+         mkOp2(OP_MUL, i->dType, val, src, src);
+         i->op = OP_MUL;
+         i->setSrc(1, val);
+         return true;
+      } else
+      if (imm.isInteger(4)) {
+         mkOp2(OP_MUL, i->dType, val, src, src);
+         i->op = OP_MUL;
+         i->setSrc(0, val);
+         i->setSrc(1, val);
+         return true;
+      } else
+      if (imm.isInteger(5)) {
+         mkOp2(OP_MUL, i->dType, val, src, src);
+         mkOp2(OP_MUL, i->dType, val, val, val);
+         i->op = OP_MUL;
+         i->setSrc(1, val);
+         return true;
+      } else
+      if (imm.isInteger(8)) {
+         mkOp2(OP_MUL, i->dType, val, src, src);
+         mkOp2(OP_MUL, i->dType, val, val, val);
+         i->op = OP_MUL;
+         i->setSrc(0, val);
+         i->setSrc(1, val);
+         return true;
+      }
+   }
 
    mkOp1(OP_LG2, TYPE_F32, val, i->getSrc(0));
    mkOp2(OP_MUL, TYPE_F32, val, i->getSrc(1), val)->dnz = 1;
-- 
2.13.1