public inbox for gcc-bugs@sourceware.org help / color / mirror / Atom feed
From: "tkoenig at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org> To: gcc-bugs@gcc.gnu.org Subject: [Bug libgcc/108279] Improved speed for float128 routines Date: Tue, 03 Jan 2023 21:02:09 +0000 [thread overview] Message-ID: <bug-108279-4-oisHkanNUQ@http.gcc.gnu.org/bugzilla/> (raw) In-Reply-To: <bug-108279-4@http.gcc.gnu.org/bugzilla/> https://gcc.gnu.org/bugzilla/show_bug.cgi?id=108279 --- Comment #1 from Thomas Koenig <tkoenig at gcc dot gnu.org> --- Created attachment 54183 --> https://gcc.gnu.org/bugzilla/attachment.cgi?id=54183&action=edit Example patch with Michael S's code just pasted over the libgcc implementation, for a test A benchmarks: Just pasting over the code from the github repo yields an improvement of gfortran's matmul by almost a factor of two, so significant speedups are possible: module tick interface function rdtsc() bind(C,name="rdtsc") use iso_c_binding integer(kind=c_long) :: rdtsc end function rdtsc end interface end module tick program main use tick use iso_c_binding implicit none integer, parameter :: wp = selected_real_kind(30) ! integer, parameter :: n=5000, p=4000, m=3666 integer, parameter :: n = 1000, p = 1000, m = 1000 real (kind=wp) :: c(n,p), a(n,m), b(m, p) character(len=80) :: line integer(c_long) :: t1, t2, t3 real (kind=wp) :: fl = 2.d0*n*m*p integer :: i,j print *,wp line = '10 10' call random_number(a) call random_number(b) t1 = rdtsc() t2 = rdtsc() t3 = t2-t1 print *,t3 t1 = rdtsc() c = matmul(a,b) t2 = rdtsc() print *,1/(fl/(t2-t1-t3)),"Cycles per operation" read (unit=line,fmt=*) i,j write (unit=line,fmt=*) c(i,j) end program main showed tkoenig@gcc188:~> ./original 16 32 ^C tkoenig@gcc188:~> time ./original 16 32 90.5696151959999999999999999999999997 Cycles per operation real 1m2,148s user 1m2,123s sys 0m0,008s tkoenig@gcc188:~> time ./modified 16 32 52.8148391719999999999999999999999957 Cycles per operation real 0m36,296s user 0m36,278s sys 0m0,008s where "original" is the current libgcc soft-float implementation, and "modified" is with the code from the repro. It does not handle exceptions, so this causes a few regressions, but certainly shows the potential
next prev parent reply other threads:[~2023-01-03 21:02 UTC|newest] Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top 2023-01-03 20:55 [Bug libgcc/108279] New: " tkoenig at gcc dot gnu.org 2023-01-03 21:02 ` tkoenig at gcc dot gnu.org [this message] 2023-01-04 10:43 ` [Bug libgcc/108279] " jakub at gcc dot gnu.org 2023-01-04 17:14 ` tkoenig at gcc dot gnu.org 2023-01-04 22:19 ` already5chosen at yahoo dot com 2023-01-11 23:06 ` already5chosen at yahoo dot com 2023-01-12 23:24 ` tkoenig at gcc dot gnu.org 2023-01-13 0:34 ` already5chosen at yahoo dot com 2023-01-13 1:29 ` already5chosen at yahoo dot com 2023-01-14 9:21 ` tkoenig at gcc dot gnu.org 2023-01-14 10:22 ` tkoenig at gcc dot gnu.org 2023-01-14 23:52 ` already5chosen at yahoo dot com 2023-01-15 0:20 ` already5chosen at yahoo dot com 2023-01-15 15:13 ` tkoenig at gcc dot gnu.org 2023-01-15 19:17 ` tkoenig at gcc dot gnu.org 2023-01-15 19:28 ` jakub at gcc dot gnu.org 2023-01-15 22:27 ` already5chosen at yahoo dot com 2023-01-16 22:16 ` joseph at codesourcery dot com 2023-01-18 19:02 ` wilco at gcc dot gnu.org 2023-01-18 19:20 ` jakub at gcc dot gnu.org 2023-01-18 19:26 ` jakub at gcc dot gnu.org 2023-01-18 20:10 ` wilco at gcc dot gnu.org 2023-01-18 22:28 ` already5chosen at yahoo dot com 2023-01-18 23:31 ` already5chosen at yahoo dot com 2023-02-10 13:38 ` already5chosen at yahoo dot com
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-108279-4-oisHkanNUQ@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).