On Mon, Jun 11, 2018 at 2:39 PM, Rhys Perry <pendingchao...@gmail.com> wrote:
> An alternative solution to the problem fixed in
> 0bd83d0 ("nv50/ir: move LateAlgebraicOpt to the very end"). Should be
> useful in the future and seems to make dolphin ubershaders a bit smaller.
>
> total instructions in shared programs : 226722 -> 226464 (-0.11%)
> total gprs used in shared programs : 19378 -> 19378 (0.00%)
> total shared used in shared programs : 0 -> 0 (0.00%)
> total local used in shared programs : 0 -> 0 (0.00%)
>
> local shared gpr inst bytes
> helped 0 0 0 51 51
> hurt 0 0 0 0 0
>
> Signed-off-by: Rhys Perry <pendingchao...@gmail.com>
> ---
> src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp | 14 +++++++++++++-
> 1 file changed, 13 insertions(+), 1 deletion(-)
>
> diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
> b/src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
> index 39177bd044..4d0589214d 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;
> }
> }
> }
> @@ -3797,11 +3809,11 @@ Program::optimizeSSA(int level)
> RUN_PASS(2, AlgebraicOpt, run);
> RUN_PASS(2, ModifierFolding, run); // before load propagation -> less
> checks
> RUN_PASS(1, ConstantFolding, foldAll);
> + RUN_PASS(2, LateAlgebraicOpt, run);
> RUN_PASS(1, Split64BitOpPreRA, run);
> RUN_PASS(1, LoadPropagation, run);
> RUN_PASS(1, IndirectPropagation, run);
> RUN_PASS(2, MemoryOpt, run);
> - RUN_PASS(2, LateAlgebraicOpt, run);
> RUN_PASS(2, LocalCSE, run);
> RUN_PASS(0, DeadCodeElim, buryAll);
well no, it is late for a good reason actually. those opts have the
potential to increase instruction count in other shaders. This should
be tested on more shaders than just the default shader-db ones.
>
> --
> 2.14.4
>
> _______________________________________________
> mesa-dev mailing list
> mesa-dev@lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/mesa-dev
_______________________________________________
mesa-dev mailing list
mesa-dev@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/mesa-dev
