From: Ilia Mirkin <imirkin@alum.mit.edu>
Date: Fri, 4 Dec 2015 20:21:11 +0000 (-0500)
Subject: nv50/ir: propagate indirect loads into instructions
X-Git-Url: https://git.libre-soc.org/?a=commitdiff_plain;h=abd326e81b06f58797be94bd655ee06b17a34f0c;p=mesa.git

nv50/ir: propagate indirect loads into instructions

This way $r1 = $r0 + 4; c1[$r1] becomes c1[$r0+4].

On SM35:

total instructions in shared programs : 6206257 -> 6185058 (-0.34%)
total gprs used in shared programs    : 911045 -> 910722 (-0.04%)
total local used in shared programs   : 39072 -> 39072 (0.00%)

                local        gpr       inst      bytes
    helped           0         417        4195        4195
      hurt           0         280           0           0

Signed-off-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 9e49c19b8e1..0d74f725bd1 100644
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
@@ -265,6 +265,57 @@ LoadPropagation::visit(BasicBlock *bb)
 
 // =============================================================================
 
+class IndirectPropagation : public Pass
+{
+private:
+   virtual bool visit(BasicBlock *);
+};
+
+bool
+IndirectPropagation::visit(BasicBlock *bb)
+{
+   const Target *targ = prog->getTarget();
+   Instruction *next;
+
+   for (Instruction *i = bb->getEntry(); i; i = next) {
+      next = i->next;
+
+      for (int s = 0; i->srcExists(s); ++s) {
+         Instruction *insn;
+         ImmediateValue imm;
+         if (!i->src(s).isIndirect(0))
+            continue;
+         insn = i->getIndirect(s, 0)->getInsn();
+         if (!insn)
+            continue;
+         if (insn->op == OP_ADD && !isFloatType(insn->dType)) {
+            if (insn->src(0).getFile() != targ->nativeFile(FILE_ADDRESS) ||
+                !insn->src(1).getImmediate(imm))
+               continue;
+            i->setIndirect(s, 0, insn->getSrc(0));
+            i->setSrc(s, cloneShallow(func, i->getSrc(s)));
+            i->src(s).get()->reg.data.offset += imm.reg.data.u32;
+         } else if (insn->op == OP_SUB && !isFloatType(insn->dType)) {
+            if (insn->src(0).getFile() != targ->nativeFile(FILE_ADDRESS) ||
+                !insn->src(1).getImmediate(imm))
+               continue;
+            i->setIndirect(s, 0, insn->getSrc(0));
+            i->setSrc(s, cloneShallow(func, i->getSrc(s)));
+            i->src(s).get()->reg.data.offset -= imm.reg.data.u32;
+         } else if (insn->op == OP_MOV) {
+            if (!insn->src(0).getImmediate(imm))
+               continue;
+            i->setIndirect(s, 0, NULL);
+            i->setSrc(s, cloneShallow(func, i->getSrc(s)));
+            i->src(s).get()->reg.data.offset += imm.reg.data.u32;
+         }
+      }
+   }
+   return true;
+}
+
+// =============================================================================
+
 // Evaluate constant expressions.
 class ConstantFolding : public Pass
 {
@@ -3135,6 +3186,7 @@ Program::optimizeSSA(int level)
    RUN_PASS(2, ModifierFolding, run); // before load propagation -> less checks
    RUN_PASS(1, ConstantFolding, foldAll);
    RUN_PASS(1, LoadPropagation, run);
+   RUN_PASS(1, IndirectPropagation, run);
    RUN_PASS(2, MemoryOpt, run);
    RUN_PASS(2, LocalCSE, run);
    RUN_PASS(0, DeadCodeElim, buryAll);