Ping.
> On 15 Nov 2024, at 17:04, Kyrylo Tkachov <ktkac...@nvidia.com> wrote:
>
> Hi all,
>
> This is a patch submission following-up from the RFC at:
> https://gcc.gnu.org/pipermail/gcc/2024-November/245076.html
> The patch is rebased and retested against current trunk, some debugging code
> removed, comments improved and some fixes added as I've we've done more
> testing.
>
> ------------------------>8-----------------------------------------------------
> Implement partitioning and cloning in the callgraph to help locality.
> A new -flto-partition=locality flag is used to enable this.
> The majority of the logic is in the new IPA pass in ipa-locality-cloning.cc
> The optimization has two components:
> * Partitioning the callgraph so as to group callers and callees that
> frequently
> call each other in the same partition
> * Cloning functions that straddle multiple callchains and allowing each clone
> to be local to the partition of its callchain.
>
> The majority of the logic is in the new IPA pass in ipa-locality-cloning.cc.
> It creates a partitioning plan and does the prerequisite cloning.
> The partitioning is then implemented during the existing LTO partitioning
> pass.
>
> To guide these locality heuristics we use PGO data.
> In the absence of PGO data we use a static heuristic that uses the accumulated
> estimated edge frequencies of the callees for each function to guide the
> reordering.
> We are investigating some more elaborate static heuristics, in particular
> using
> the demangled C++ names to group template instantiatios together.
> This is promising but we are working out some kinks in the implementation
> currently and want to send that out as a follow-up once we're more confident
> in it.
>
> A new bootstrap-lto-locality bootstrap config is added that allows us to test
> this on GCC itself with either static or PGO heuristics.
> GCC bootstraps with both (normal LTO bootstrap and profiledbootstrap).
>
> With this optimization we are seeing good performance gains on some large
> internal workloads that stress the parts of the processor that is sensitive
> to code locality, but we'd appreciate wider performance evaluation.
>
> Bootstrapped and tested on aarch64-none-linux-gnu.
> Ok for mainline?
> Thanks,
> Kyrill
>
> Signed-off-by: Prachi Godbole <pgodb...@nvidia.com>
> Co-authored-by: Kyrylo Tkachov <ktkac...@nvidia.com>
>
> config/ChangeLog:
> * bootstrap-lto-locality.mk: New file.
>
> gcc/ChangeLog:
> * Makefile.in (OBJS): Add ipa-locality-cloning.o
> (GTFILES): Add ipa-locality-cloning.cc dependency.
> * common.opt (lto_partition_model): Add locality value.
> * flag-types.h (lto_partition_model): Add LTO_PARTITION_LOCALITY
> value.
> (enum lto_locality_cloning_model): Define.
> * lto-cgraph.cc (lto_set_symtab_encoder_in_partition): Add dumping
> of node
> and index.
> * params.opt (lto_locality_cloning_model): New enum.
> (lto-partition-locality-cloning): New param.
> (lto-partition-locality-frequency-cutoff): Likewise.
> (lto-partition-locality-size-cutoff): Likewise.
> (lto-max-locality-partition): Likewise.
> * passes.def: Add pass_ipa_locality_cloning.
> * timevar.def (TV_IPA_LC): New timevar.
> * tree-pass.h (make_pass_ipa_locality_cloning): Declare.
> * ipa-locality-cloning.cc: New file.
> * ipa-locality-cloning.h: New file.
>
> gcc/lto/ChangeLog:
> * lto-partition.cc: Include ipa-locality-cloning.h
> (add_node_references_to_partition): Define.
> (create_partition): Likewise.
> (lto_locality_map): Likewise.
> (lto_promote_cross_file_statics): Add extra dumping.
> * lto-partition.h (lto_locality_map): Declare.
> * lto.cc (do_whole_program_analysis): Handle
> LTO_PARTITION_LOCALITY.
>
> <0001-Introduce-flto-partition-locality.patch>
