public inbox for gcc-bugs@sourceware.org help / color / mirror / Atom feed
From: "matz at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org> To: gcc-bugs@gcc.gnu.org Subject: [Bug middle-end/53852] -ftree-loop-linear: large compile time / memory usage Date: Wed, 04 Jul 2012 12:11:00 -0000 [thread overview] Message-ID: <bug-53852-4-OnTn6kX7jc@http.gcc.gnu.org/bugzilla/> (raw) In-Reply-To: <bug-53852-4@http.gcc.gnu.org/bugzilla/> http://gcc.gnu.org/bugzilla/show_bug.cgi?id=53852 --- Comment #2 from Michael Matz <matz at gcc dot gnu.org> 2012-07-04 12:11:10 UTC --- ISL generally has speed problems. For instance graphite/interchange-8.c needs quite long to compile (well, several seconds), and _all_ of the runtime is basically in malloc/free/copy activity of isl_int's. It does 10 million calls to malloc/free, 51 million to gmpz_set, 15 million to gmpz_addmul, 9 million to gmpz_mul, 51 million gmpn_copi, and so on. Huge causes for this excessive gmp activity is compute_deps -> isl_union_map_compute_flow. Three calls of the latter are responsible for 76% compile time, and it's all in gmp activity. It's then doing 16x isl_access_info_compute_flow, 210x isl_map_partial_lexmax, 307x isl_map_apply_range and isl_map_intersect, which do 10000x isl_basic_map_intersect and 7400x isl_basic_map_apply_range. That causes 25000x isl_basic_map_simplify and 61000x isl_basic_map_alloc_space. That results in 82000x isl_blk_alloc, which ultimately does the excessive number of malloc and gmp_init calls. And it results in several million calls to the simplify primitives (isl_seq_elim->isl_seq_combine->gmp_addmul/mul/set, isl_seq_copy, and isl_seq_abs_min_non_zero).
next prev parent reply other threads:[~2012-07-04 12:11 UTC|newest] Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top 2012-07-04 11:19 [Bug middle-end/53852] New: " Joost.VandeVondele at mat dot ethz.ch 2012-07-04 11:54 ` [Bug middle-end/53852] " rguenth at gcc dot gnu.org 2012-07-04 12:11 ` matz at gcc dot gnu.org [this message] 2012-07-04 12:18 ` Joost.VandeVondele at mat dot ethz.ch 2012-07-04 12:44 ` [Bug tree-optimization/53852] [4.8 Regression] " rguenth at gcc dot gnu.org 2012-08-22 11:58 ` Joost.VandeVondele at mat dot ethz.ch 2012-12-06 16:25 ` rguenth at gcc dot gnu.org 2012-12-13 13:00 ` rguenth at gcc dot gnu.org 2013-02-07 9:05 ` Joost.VandeVondele at mat dot ethz.ch 2013-02-19 20:48 ` law at redhat dot com 2013-03-22 14:43 ` [Bug tree-optimization/53852] [4.8/4.9 " jakub at gcc dot gnu.org 2013-05-31 10:58 ` jakub at gcc dot gnu.org 2013-10-16 9:51 ` jakub at gcc dot gnu.org 2014-01-23 7:30 ` law at redhat dot com 2014-05-22 9:02 ` [Bug tree-optimization/53852] [4.8/4.9/4.10 " rguenth at gcc dot gnu.org 2014-12-19 13:41 ` [Bug tree-optimization/53852] [4.8/4.9/5 " jakub at gcc dot gnu.org 2015-06-23 8:23 ` [Bug tree-optimization/53852] [4.8/4.9/5/6 " rguenth at gcc dot gnu.org 2015-06-26 20:13 ` [Bug tree-optimization/53852] [4.9/5/6 " jakub at gcc dot gnu.org 2015-06-26 20:37 ` jakub at gcc dot gnu.org 2015-08-28 4:28 ` Joost.VandeVondele at mat dot ethz.ch 2015-08-28 14:29 ` spop at gcc dot gnu.org 2015-09-02 22:38 ` spop at gcc dot gnu.org 2015-09-09 4:23 ` spop at gcc dot gnu.org
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=bug-53852-4-OnTn6kX7jc@http.gcc.gnu.org/bugzilla/ \ --to=gcc-bugzilla@gcc.gnu.org \ --cc=gcc-bugs@gcc.gnu.org \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions for how to clone and mirror all data and code used for this inbox; as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).