[Mesa-dev] [PATCH] nv50/ir: avoid messing up arg1 of PFETCH

[Ilia Mirkin]

There can be scenarios where the "indirect" arg of a PFETCH becomes
known, and so the code will attempt to propagate it. Use this
opportunity to just fold it into the first argument, and prevent the
load propagation pass from touching PFETCH further.

This fixes gs-input-array-vec4-index-rd.shader_test and
vs-output-array-vec4-index-wr-before-gs.shader_test on nvc0 at least.

Signed-off-by: Ilia Mirkin <imirkin at alum.mit.edu>
Cc: "10.5 10.6" <mesa-stable at lists.freedesktop.org>
---
 src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
index 72dd31e..98e3d1f 100644
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
@@ -236,6 +236,9 @@ LoadPropagation::visit(BasicBlock *bb)
       if (i->op == OP_CALL) // calls have args as sources, they must be in regs
          continue;
 
+      if (i->op == OP_PFETCH) // pfetch expects arg1 to be a reg
+         continue;
+
       if (i->srcExists(1))
          checkSwapSrc01(i);
 
@@ -581,6 +584,11 @@ ConstantFolding::expr(Instruction *i,
    case OP_POPCNT:
       res.data.u32 = util_bitcount(a->data.u32 & b->data.u32);
       break;
+   case OP_PFETCH:
+      // The two arguments to pfetch are logically added together. Normally
+      // the second argument will not be constant, but that can happen.
+      res.data.u32 = a->data.u32 + b->data.u32;
+      break;
    default:
       return;
    }
@@ -610,6 +618,8 @@ ConstantFolding::expr(Instruction *i,
          bld.setPosition(i, false);
          i->setSrc(1, bld.loadImm(NULL, res.data.u32));
       }
+   } else if (i->op == OP_PFETCH) {
+      // Leave PFETCH alone... we just folded its 2 args into 1.
    } else {
       i->op = i->saturate ? OP_SAT : OP_MOV; /* SAT handled by unary() */
    }
-- 
2.3.6