From 9bd1ee6d330b0441c165d889b6b25a5c85caf427 Mon Sep 17 00:00:00 2001 From: Jan Hubicka Date: Thu, 27 Jul 2023 16:17:59 +0200 Subject: Fix profile update in tree_transform_and_unroll_loop Fixe profile update in tree_transform_and_unroll_loop which is used by predictive comming. I stared by attempt to fix gcc.dg/tree-ssa/update-unroll-1.c I xfailed last week, but it turned to be harder job. Unrolling was never fixed for changes in duplicate_loop_body_to_header_edge which is now smarter on getting profile right when some exists are eliminated. A lot of manual profile can thus now be done using existing infrastructure. I also noticed that scale_dominated_blocks_in_loop does job identical to loop I wrote in scale_loop_profile and thus I commonized the implementaiton and removed recursion. I also extended duplicate_loop_body_to_header_edge to handle flat profiles same way as we do in vectorizer. Without it we end up with less then 0 iteration count in gcc.dg/tree-ssa/update-unroll-1.c (it is unrolled 32times but predicted to iterated fewer times) and added missing code to update loop_info. gcc/ChangeLog: * cfgloopmanip.cc (scale_dominated_blocks_in_loop): Move here from tree-ssa-loop-manip.cc and avoid recursion. (scale_loop_profile): Use scale_dominated_blocks_in_loop. (duplicate_loop_body_to_header_edge): Add DLTHE_FLAG_FLAT_PROFILE flag. * cfgloopmanip.h (DLTHE_FLAG_FLAT_PROFILE): Define. (scale_dominated_blocks_in_loop): Declare. * predict.cc (dump_prediction): Do not ICE on uninitialized probability. (change_edge_frequency): Remove. * predict.h (change_edge_frequency): Remove. * tree-ssa-loop-manip.cc (scale_dominated_blocks_in_loop): Move to cfgloopmanip.cc. (niter_for_unrolled_loop): Remove. (tree_transform_and_unroll_loop): Fix profile update. gcc/testsuite/ChangeLog: * gcc.dg/pr102385.c: Check for no profile mismatches. * gcc.dg/pr96931.c: Check for no profile mismatches. * gcc.dg/tree-ssa/predcom-1.c: Check for no profile mismatches. * gcc.dg/tree-ssa/predcom-2.c: Check for no profile mismatches. * gcc.dg/tree-ssa/predcom-3.c: Check for no profile mismatches. * gcc.dg/tree-ssa/predcom-4.c: Check for no profile mismatches. * gcc.dg/tree-ssa/predcom-5.c: Check for no profile mismatches. * gcc.dg/tree-ssa/predcom-7.c: Check for one profile mismatch. * gcc.dg/tree-ssa/predcom-8.c: Check for no profile mismatches. * gcc.dg/tree-ssa/predcom-dse-1.c: Check for no profile mismatches. * gcc.dg/tree-ssa/predcom-dse-10.c: Check for no profile mismatches. * gcc.dg/tree-ssa/predcom-dse-11.c: Check for no profile mismatches. * gcc.dg/tree-ssa/predcom-dse-12.c: Check for no profile mismatches. * gcc.dg/tree-ssa/predcom-dse-2.c: Check for no profile mismatches. * gcc.dg/tree-ssa/predcom-dse-3.c: Check for no profile mismatches. * gcc.dg/tree-ssa/predcom-dse-4.c: Check for no profile mismatches. * gcc.dg/tree-ssa/predcom-dse-5.c: Check for no profile mismatches. * gcc.dg/tree-ssa/predcom-dse-6.c: Check for no profile mismatches. * gcc.dg/tree-ssa/predcom-dse-7.c: Check for no profile mismatches. * gcc.dg/tree-ssa/predcom-dse-8.c: Check for no profile mismatches. * gcc.dg/tree-ssa/predcom-dse-9.c: Check for no profile mismatches. * gcc.dg/tree-ssa/update-unroll-1.c: Unxfail. --- gcc/cfgloopmanip.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'gcc/cfgloopmanip.h') diff --git a/gcc/cfgloopmanip.h b/gcc/cfgloopmanip.h index 75b2a5e..af6a29f 100644 --- a/gcc/cfgloopmanip.h +++ b/gcc/cfgloopmanip.h @@ -32,6 +32,8 @@ enum field of newly create BB. */ #define DLTHE_FLAG_COMPLETTE_PEEL 4 /* Update frequencies expecting a complete peeling. */ +#define DLTHE_FLAG_FLAT_PROFILE 8 /* Profile is flat; do not reduce + count by unroll factor. */ extern edge mfb_kj_edge; extern bool remove_path (edge, bool * = NULL, bitmap = NULL); @@ -64,5 +66,7 @@ class loop * loop_version (class loop *, void *, profile_probability, profile_probability, profile_probability, profile_probability, bool); void adjust_loop_info_after_peeling (class loop *loop, int npeel, bool precise); +void scale_dominated_blocks_in_loop (class loop *loop, basic_block bb, + profile_count num, profile_count den); #endif /* GCC_CFGLOOPMANIP_H */ -- cgit v1.1