nv50/ir: handle SHLADD in IndirectPropagation

An alternative solution to the problem fixed in
0bd83d0 ("nv50/ir: move LateAlgebraicOpt to the very end").

total instructions in shared programs : 5481195 -> 5480808 (-0.01%)
total gprs used in shared programs    : 647535 -> 647530 (-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   : 58555784 -> 58551648 (-0.01%)

                local     shared        gpr       inst      bytes
    helped           0           0           2          34          34
      hurt           0           0           0           0           0

diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
index 520cbee7c1adce6f6845baf6f26620b477d397a3..aaa6cacbe60d53d9b9e11a9bfc31468f1fa8b31e 100644 (file)
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
@@ -283,6 +283,8 @@ class IndirectPropagation : public Pass
 {
 private:
    virtual bool visit(BasicBlock *);
+
+   BuildUtil bld;
 };
 
 bool
@@ -294,6 +296,8 @@ IndirectPropagation::visit(BasicBlock *bb)
    for (Instruction *i = bb->getEntry(); i; i = next) {
       next = i->next;
 
+      bld.setPosition(i, false);
+
       for (int s = 0; i->srcExists(s); ++s) {
          Instruction *insn;
          ImmediateValue imm;
@@ -325,6 +329,14 @@ IndirectPropagation::visit(BasicBlock *bb)
             i->setIndirect(s, 0, NULL);
             i->setSrc(s, cloneShallow(func, i->getSrc(s)));
             i->src(s).get()->reg.data.offset += imm.reg.data.u32;
+         } else if (insn->op == OP_SHLADD) {
+            if (!insn->src(2).getImmediate(imm) ||
+                !targ->insnCanLoadOffset(i, s, imm.reg.data.s32))
+               continue;
+            i->setIndirect(s, 0, bld.mkOp2v(
+               OP_SHL, TYPE_U32, bld.getSSA(), insn->getSrc(0), insn->getSrc(1)));
+            i->setSrc(s, cloneShallow(func, i->getSrc(s)));
+            i->src(s).get()->reg.data.offset += imm.reg.data.u32;
          }
       }
    }