gm200/ir: optimize rcp(sqrt) to rsq

mitigates hurt shaders after adding sqrt:
total instructions in shared programs : 5456166 -> 5454825 (-0.02%)
total gprs used in shared programs    : 647522 -> 647551 (0.00%)
total shared used in shared programs  : 389120 -> 389120 (0.00%)
total local used in shared programs   : 21064 -> 21064 (0.00%)
total bytes used in shared programs   : 58288696 -> 58274448 (-0.02%)

                local     shared        gpr       inst      bytes
    helped           0           0           0         516         516
      hurt           0           0          27           2           2

Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
Signed-off-by: Karol Herbst <kherbst@redhat.com>

diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
index 16022e6..2f7cc20 100644 (file)
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
@@ -1848,15 +1848,24 @@ AlgebraicOpt::handleMINMAX(Instruction *minmax)
    }
 }
 
+// rcp(rcp(a)) = a
+// rcp(sqrt(a)) = rsq(a)
 void
 AlgebraicOpt::handleRCP(Instruction *rcp)
 {
    Instruction *si = rcp->getSrc(0)->getUniqueInsn();
 
-   if (si && si->op == OP_RCP) {
+   if (!si)
+      return;
+
+   if (si->op == OP_RCP) {
       Modifier mod = rcp->src(0).mod * si->src(0).mod;
       rcp->op = mod.getOp();
       rcp->setSrc(0, si->getSrc(0));
+   } else if (si->op == OP_SQRT) {
+      rcp->op = OP_RSQ;
+      rcp->setSrc(0, si->getSrc(0));
+      rcp->src(0).mod = rcp->src(0).mod * si->src(0).mod;
    }
 }