public inbox for gcc-bugs@sourceware.org help / color / mirror / Atom feed
From: "chip.kerchner at ibm dot com" <gcc-bugzilla@gcc.gnu.org> To: gcc-bugs@gcc.gnu.org Subject: [Bug tree-optimization/108757] We do not simplify (a - (N*M)) / N + M -> a / N Date: Mon, 13 Feb 2023 20:13:04 +0000 [thread overview] Message-ID: <bug-108757-4-CtvLjzNecJ@http.gcc.gnu.org/bugzilla/> (raw) In-Reply-To: <bug-108757-4@http.gcc.gnu.org/bugzilla/> https://gcc.gnu.org/bugzilla/show_bug.cgi?id=108757 --- Comment #12 from Chip Kerchner <chip.kerchner at ibm dot com> --- Here is an example of the original problem #define EIGEN_ALWAYS_INLINE __attribute__((always_inline)) inline typedef __vector float Packet4f; typedef size_t Index; EIGEN_ALWAYS_INLINE Packet4f ploadu(const float* from) { return vec_xl(0, const_cast<float*>(from)); } EIGEN_ALWAYS_INLINE void pstoreu(float* to, const Packet4f &from) { vec_xst(from, 0, to); } void convert(Index rows, float*src, float *result) { for(Index i = 0; i + 4 <= rows; i+=4) { Packet4f r32_0 = ploadu(src + i + 0); pstoreu(result + i + 0, r32_0); } } And the output (with notation on the lines in question) cmpldi 0,3,3 blelr 0 addi 3,3,-4 <- i = rows - 4 li 9,0 srdi 3,3,2 <- i >>= 2 addi 8,3,1 <- i = i + 1 andi. 7,8,0x3 mr 10,8 beq 0,.L10 cmpdi 0,7,1 beq 0,.L14 cmpdi 0,7,2 beq 0,.L15 lxv 0,0(4) mr 8,3 li 9,16 stxv 0,0(5) .L15: lxvx 0,4,9 addi 8,8,-1 stxvx 0,5,9 addi 9,9,16 .L14: lxvx 0,4,9 cmpdi 0,8,1 stxvx 0,5,9 addi 9,9,16 beqlr 0 .L10: srdi 10,10,2 mtctr 10 .L3: lxvx 0,4,9 addi 10,9,16 addi 7,9,32 addi 8,9,48 stxvx 0,5,9 lxvx 0,4,10 addi 9,9,64 stxvx 0,5,10 lxvx 0,4,7 stxvx 0,5,7 lxvx 0,4,8 stxvx 0,5,8 bdnz .L3 blr In this case the 3 lines notated can be replaced a simple `srdi 8,3,2`
next prev parent reply other threads:[~2023-02-13 20:13 UTC|newest] Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top 2023-02-10 22:26 [Bug tree-optimization/108757] New: " bergner at gcc dot gnu.org 2023-02-10 22:28 ` [Bug tree-optimization/108757] " bergner at gcc dot gnu.org 2023-02-10 22:33 ` pinskia at gcc dot gnu.org 2023-02-10 22:40 ` pinskia at gcc dot gnu.org 2023-02-11 13:14 ` anlauf at gcc dot gnu.org 2023-02-11 16:38 ` segher at gcc dot gnu.org 2023-02-11 17:32 ` bergner at gcc dot gnu.org 2023-02-11 17:55 ` segher at gcc dot gnu.org 2023-02-11 18:05 ` bergner at gcc dot gnu.org 2023-02-11 18:15 ` segher at gcc dot gnu.org 2023-02-11 19:45 ` chip.kerchner at ibm dot com 2023-02-11 21:55 ` chip.kerchner at ibm dot com 2023-02-11 22:03 ` chip.kerchner at ibm dot com 2023-02-13 20:13 ` chip.kerchner at ibm dot com [this message] 2023-02-13 20:20 ` pinskia at gcc dot gnu.org 2023-02-13 20:27 ` [Bug rtl-optimization/108757] " pinskia at gcc dot gnu.org 2023-02-13 20:36 ` chip.kerchner at ibm dot com 2023-02-13 20:37 ` chip.kerchner at ibm dot com 2023-02-13 20:58 ` [Bug tree-optimization/108757] " pinskia at gcc dot gnu.org 2023-02-13 20:59 ` pinskia at gcc dot gnu.org 2023-02-13 21:01 ` pinskia at gcc dot gnu.org 2023-05-11 13:15 ` guojiufu at gcc dot gnu.org 2023-05-11 17:32 ` pinskia at gcc dot gnu.org 2023-05-12 1:52 ` guojiufu at gcc dot gnu.org 2023-05-12 6:25 ` guojiufu at gcc dot gnu.org 2023-05-12 9:35 ` guojiufu at gcc dot gnu.org 2023-09-04 2:46 ` cvs-commit at gcc dot gnu.org 2023-09-04 3:26 ` guojiufu 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-108757-4-CtvLjzNecJ@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).