[Mesa-dev] [PATCH v2 1/2] nv50/ir: handle SHLADD in IndirectPropagation

[Rhys Perry]

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

total instructions in shared programs : 5265148 -> 5264804 (-0.01%)
total gprs used in shared programs    : 624346 -> 624341 (-0.00%)
total shared used in shared programs  : 360704 -> 360704 (0.00%)
total local used in shared programs   : 20952 -> 20952 (0.00%)

                local     shared        gpr       inst      bytes
    helped           0           0           2          31          31
      hurt           0           0           0           0           0

Signed-off-by: Rhys Perry <pendingchaos02 at gmail.com>
---
 src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
index 39177bd044..83fb15ca34 100644
--- 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;
          }
       }
    }
-- 
2.14.4