[Mesa-dev] [PATCH 3/3] nv50/ir: convert slct with boolean result to set

[Ilia Mirkin]

On Fri, Dec 14, 2018 at 6:12 PM Karol Herbst <kherbst at redhat.com> wrote:
>
> From: Karol Herbst <karolherbst at gmail.com>
>
> helps mainly feral ported games
>
> changes in shader-db:
> total instructions in shared programs     : 7565661 -> 7545812 (-0.26%)
> total gprs used in shared programs        : 797213 -> 797088 (-0.02%)
> total shared used in shared programs      : 639636 -> 639636 (0.00%)
> total local used in shared programs       : 24648 -> 24648 (0.00%)
> total bytes used in shared programs       : 80806160 -> 80594056 (-0.26%)
>
>                 local     shared        gpr       inst      bytes
>     helped          0          0        103       5049       5049
>       hurt          0          0         29          0          0
>
> Signed-off-by: Karol Herbst <kherbst at redhat.com>
> ---
>  .../nouveau/codegen/nv50_ir_peephole.cpp      | 50 +++++++++++++++++++
>  1 file changed, 50 insertions(+)
>
> diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
> index 37e9edc49f4..b62dee675ce 100644
> --- a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
> +++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
> @@ -372,6 +372,8 @@ private:
>     void expr(Instruction *, ImmediateValue&, ImmediateValue&, ImmediateValue&);
>     /* true if i was deleted */
>     bool opnd(Instruction *i, ImmediateValue&, int s);
> +   /* 3 srcs where 1st and 2nd are immediates */
> +   void opnd(Instruction *, ImmediateValue&, ImmediateValue&);
>     void opnd3(Instruction *, ImmediateValue&);
>
>     void unary(Instruction *, const ImmediateValue&);
> @@ -432,6 +434,10 @@ ConstantFolding::visit(BasicBlock *bb)
>        }
>        if (i->srcExists(2) && i->src(2).getImmediate(src2))
>           opnd3(i, src2);
> +      else
> +      if (i->srcExists(2) &&
> +          i->src(0).getImmediate(src0) && i->src(1).getImmediate(src1))
> +         opnd(i, src0, src1);
>     }
>     return true;
>  }
> @@ -935,6 +941,50 @@ ConstantFolding::tryCollapseChainedMULs(Instruction *mul2,
>     }
>  }
>
> +void
> +ConstantFolding::opnd(Instruction *i, ImmediateValue &imm0, ImmediateValue &imm1)
> +{
> +   const Storage &a = imm0.reg;
> +   const Storage &b = imm1.reg;
> +
> +   switch (i->op) {
> +   case OP_SLCT: {
> +      CmpInstruction *slct = i->asCmp();
> +      if (a.data.u32 == 0xffffffff && b.data.u32 == 0x0) {
> +         slct->setSrc(0, slct->getSrc(2));
> +         slct->setSrc(2, NULL);
> +         slct->dType = TYPE_U32;
> +         slct->op = OP_SET;
> +      }
> +      else if (a.data.u32 == 0x3f800000 && b.data.u32 == 0x0) {
> +         slct->setSrc(0, slct->getSrc(2));
> +         slct->setSrc(2, NULL);
> +         slct->dType = TYPE_F32;
> +         slct->op = OP_SET;
> +      }
> +      else if (a.data.u32 == 0x0 && b.data.u32 == 0xffffffff) {
> +         slct->swapSources(0, 1);
> +         slct->setSrc(0, slct->getSrc(2));
> +         slct->setSrc(2, NULL);
> +         slct->dType = TYPE_U32;
> +         slct->setCondition(inverseCondCode(slct->getCondition()));
> +         slct->op = OP_SET;
> +      }
> +      else if (a.data.u32 == 0x0 && b.data.u32 == 0x3f800000) {
> +         slct->swapSources(0, 1);
> +         slct->setSrc(0, slct->getSrc(2));
> +         slct->setSrc(2, NULL);
> +         slct->dType = TYPE_F32;
> +         slct->setCondition(inverseCondCode(slct->getCondition()));
> +         slct->op = OP_SET;
> +      }

You could make the code a little less repetitive by doing something like:

bool swap = false;
if (a.data.u32 == 0x0) {
  std::swap(a, b);
  swap = true;
}
if (b.data.u32 != 0x0)
  break;

if (a.data.f32 == 1.0)
  slct->dType = TYPE_F32
else if (a.data.u32 == 0xffffffff)
  slct->dType = TYPE_U32;
else
  break;

if (swap)
  slct->swapSources(0, 1);
slct->setSrc(0, ...);
slct->setSrc(2, NULL);
if (swap)
  slct->setCondition(...);

slct->op = OP_SET;

Your call.

> +      break;
> +   }
> +   default:
> +      break;
> +   }
> +}
> +
>  void
>  ConstantFolding::opnd3(Instruction *i, ImmediateValue &imm2)
>  {
> --
> 2.19.2
>