public inbox for gcc-bugs@sourceware.org help / color / mirror / Atom feed
From: "klepikov.alex+bugs at gmail dot com" <gcc-bugzilla@gcc.gnu.org> To: gcc-bugs@gcc.gnu.org Subject: [Bug target/49263] SH Target: underutilized "TST #imm, R0" instruction Date: Wed, 24 May 2023 13:34:00 +0000 [thread overview] Message-ID: <bug-49263-4-PdcUyg9RTJ@http.gcc.gnu.org/bugzilla/> (raw) In-Reply-To: <bug-49263-4@http.gcc.gnu.org/bugzilla/> https://gcc.gnu.org/bugzilla/show_bug.cgi?id=49263 --- Comment #37 from Alexander Klepikov <klepikov.alex+bugs at gmail dot com> --- > Can you also compile for little endian, and most of all, use -O2 > optimization level. Some optimizations are not done below -O2. Here's source file, I added functions with non-constant shifts $ cat f.c #define ADDR 0xFFFF0000 #define P ((unsigned char *)ADDR) #define FLAG 0x40 #define S 7 unsigned char f_char_var(char v){ return (v & FLAG) == FLAG; } unsigned char f_unsigned_char_var(unsigned char v){ return (v & FLAG) == FLAG; } unsigned char f_symbol(void){ return (*P & FLAG) == FLAG; } unsigned char f_symbol_zero(void){ return (*P & FLAG) == 0; } unsigned char f_symbol_non_zero(void){ return (*P & FLAG) != 0; } unsigned int dyn_lshift (unsigned int x, unsigned int y) { return x << (y & 31); } unsigned int dyn_rshift (unsigned int x, unsigned int y) { return x >> (y & 31); } unsigned int really_dyn_lshift (unsigned int x, unsigned int y) { return x << y; } unsigned int really_dyn_rshift (unsigned int x, unsigned int y) { return x >> y; } With patch disabled, -O2 -mb: $ cat f.s .file "f.c" .text .text .align 1 .align 2 .global _f_char_var .type _f_char_var, @function _f_char_var: mov.l .L4,r1 sts.l pr,@-r15 jsr @r1 exts.b r4,r4 mov r4,r0 and #1,r0 lds.l @r15+,pr rts nop .L5: .align 2 .L4: .long ___ashiftrt_r4_6 .size _f_char_var, .-_f_char_var .align 1 .align 2 .global _f_unsigned_char_var .type _f_unsigned_char_var, @function _f_unsigned_char_var: mov.l .L8,r1 sts.l pr,@-r15 jsr @r1 exts.b r4,r4 mov r4,r0 and #1,r0 lds.l @r15+,pr rts nop .L9: .align 2 .L8: .long ___ashiftrt_r4_6 .size _f_unsigned_char_var, .-_f_unsigned_char_var .align 1 .align 2 .global _f_symbol .type _f_symbol, @function _f_symbol: mov.l .L12,r1 sts.l pr,@-r15 mov.b @r1,r4 mov.l .L13,r1 jsr @r1 nop mov r4,r0 and #1,r0 lds.l @r15+,pr rts nop .L14: .align 2 .L12: .long -65536 .L13: .long ___ashiftrt_r4_6 .size _f_symbol, .-_f_symbol .align 1 .align 2 .global _f_symbol_zero .type _f_symbol_zero, @function _f_symbol_zero: mov.l .L16,r1 mov.b @r1,r0 tst #64,r0 rts movt r0 .L17: .align 2 .L16: .long -65536 .size _f_symbol_zero, .-_f_symbol_zero .align 1 .align 2 .global _f_symbol_non_zero .type _f_symbol_non_zero, @function _f_symbol_non_zero: mov.l .L20,r1 sts.l pr,@-r15 mov.b @r1,r4 mov.l .L21,r1 jsr @r1 nop mov r4,r0 and #1,r0 lds.l @r15+,pr rts nop .L22: .align 2 .L20: .long -65536 .L21: .long ___ashiftrt_r4_6 .size _f_symbol_non_zero, .-_f_symbol_non_zero .align 1 .align 2 .global _dyn_lshift .type _dyn_lshift, @function _dyn_lshift: mov.l .L25,r1 sts.l pr,@-r15 jsr @r1 mov r5,r0 lds.l @r15+,pr rts nop .L26: .align 2 .L25: .long ___ashlsi3_r0 .size _dyn_lshift, .-_dyn_lshift .align 1 .align 2 .global _dyn_rshift .type _dyn_rshift, @function _dyn_rshift: mov.l .L29,r1 sts.l pr,@-r15 jsr @r1 mov r5,r0 lds.l @r15+,pr rts nop .L30: .align 2 .L29: .long ___lshrsi3_r0 .size _dyn_rshift, .-_dyn_rshift .align 1 .align 2 .global _really_dyn_lshift .type _really_dyn_lshift, @function _really_dyn_lshift: mov.l .L33,r1 sts.l pr,@-r15 jsr @r1 mov r5,r0 lds.l @r15+,pr rts nop .L34: .align 2 .L33: .long ___ashlsi3_r0 .size _really_dyn_lshift, .-_really_dyn_lshift .align 1 .align 2 .global _really_dyn_rshift .type _really_dyn_rshift, @function _really_dyn_rshift: mov.l .L37,r1 sts.l pr,@-r15 jsr @r1 mov r5,r0 lds.l @r15+,pr rts nop .L38: .align 2 .L37: .long ___lshrsi3_r0 .size _really_dyn_rshift, .-_really_dyn_rshift .ident "GCC: (GNU) 12.3.0" With patch disabled, -O2 -ml $ cat f.s .file "f.c" .text .little .text .align 1 .align 2 .global _f_char_var .type _f_char_var, @function _f_char_var: mov.l .L4,r1 sts.l pr,@-r15 jsr @r1 exts.b r4,r4 mov r4,r0 and #1,r0 lds.l @r15+,pr rts nop .L5: .align 2 .L4: .long ___ashiftrt_r4_6 .size _f_char_var, .-_f_char_var .align 1 .align 2 .global _f_unsigned_char_var .type _f_unsigned_char_var, @function _f_unsigned_char_var: mov.l .L8,r1 sts.l pr,@-r15 jsr @r1 exts.b r4,r4 mov r4,r0 and #1,r0 lds.l @r15+,pr rts nop .L9: .align 2 .L8: .long ___ashiftrt_r4_6 .size _f_unsigned_char_var, .-_f_unsigned_char_var .align 1 .align 2 .global _f_symbol .type _f_symbol, @function _f_symbol: mov.l .L12,r1 sts.l pr,@-r15 mov.b @r1,r4 mov.l .L13,r1 jsr @r1 nop mov r4,r0 and #1,r0 lds.l @r15+,pr rts nop .L14: .align 2 .L12: .long -65536 .L13: .long ___ashiftrt_r4_6 .size _f_symbol, .-_f_symbol .align 1 .align 2 .global _f_symbol_zero .type _f_symbol_zero, @function _f_symbol_zero: mov.l .L16,r1 mov.b @r1,r0 tst #64,r0 rts movt r0 .L17: .align 2 .L16: .long -65536 .size _f_symbol_zero, .-_f_symbol_zero .align 1 .align 2 .global _f_symbol_non_zero .type _f_symbol_non_zero, @function _f_symbol_non_zero: mov.l .L20,r1 sts.l pr,@-r15 mov.b @r1,r4 mov.l .L21,r1 jsr @r1 nop mov r4,r0 and #1,r0 lds.l @r15+,pr rts nop .L22: .align 2 .L20: .long -65536 .L21: .long ___ashiftrt_r4_6 .size _f_symbol_non_zero, .-_f_symbol_non_zero .align 1 .align 2 .global _dyn_lshift .type _dyn_lshift, @function _dyn_lshift: mov.l .L25,r1 sts.l pr,@-r15 jsr @r1 mov r5,r0 lds.l @r15+,pr rts nop .L26: .align 2 .L25: .long ___ashlsi3_r0 .size _dyn_lshift, .-_dyn_lshift .align 1 .align 2 .global _dyn_rshift .type _dyn_rshift, @function _dyn_rshift: mov.l .L29,r1 sts.l pr,@-r15 jsr @r1 mov r5,r0 lds.l @r15+,pr rts nop .L30: .align 2 .L29: .long ___lshrsi3_r0 .size _dyn_rshift, .-_dyn_rshift .align 1 .align 2 .global _really_dyn_lshift .type _really_dyn_lshift, @function _really_dyn_lshift: mov.l .L33,r1 sts.l pr,@-r15 jsr @r1 mov r5,r0 lds.l @r15+,pr rts nop .L34: .align 2 .L33: .long ___ashlsi3_r0 .size _really_dyn_lshift, .-_really_dyn_lshift .align 1 .align 2 .global _really_dyn_rshift .type _really_dyn_rshift, @function _really_dyn_rshift: mov.l .L37,r1 sts.l pr,@-r15 jsr @r1 mov r5,r0 lds.l @r15+,pr rts nop .L38: .align 2 .L37: .long ___lshrsi3_r0 .size _really_dyn_rshift, .-_really_dyn_rshift .ident "GCC: (GNU) 12.3.0" With patch enabled -O2 -mb $ cat f.s .file "f.c" .text .text .align 1 .align 2 .global _f_char_var .type _f_char_var, @function _f_char_var: mov r4,r0 tst #64,r0 mov #-1,r0 rts negc r0,r0 .size _f_char_var, .-_f_char_var .align 1 .align 2 .global _f_unsigned_char_var .type _f_unsigned_char_var, @function _f_unsigned_char_var: mov r4,r0 tst #64,r0 mov #-1,r0 rts negc r0,r0 .size _f_unsigned_char_var, .-_f_unsigned_char_var .align 1 .align 2 .global _f_symbol .type _f_symbol, @function _f_symbol: mov.l .L5,r1 mov.b @r1,r0 tst #64,r0 mov #-1,r0 rts negc r0,r0 .L6: .align 2 .L5: .long -65536 .size _f_symbol, .-_f_symbol .align 1 .align 2 .global _f_symbol_zero .type _f_symbol_zero, @function _f_symbol_zero: mov.l .L8,r1 mov.b @r1,r0 tst #64,r0 rts movt r0 .L9: .align 2 .L8: .long -65536 .size _f_symbol_zero, .-_f_symbol_zero .align 1 .align 2 .global _f_symbol_non_zero .type _f_symbol_non_zero, @function _f_symbol_non_zero: mov.l .L11,r1 mov.b @r1,r0 tst #64,r0 mov #-1,r0 rts negc r0,r0 .L12: .align 2 .L11: .long -65536 .size _f_symbol_non_zero, .-_f_symbol_non_zero .align 1 .align 2 .global _dyn_lshift .type _dyn_lshift, @function _dyn_lshift: mov.l .L15,r1 sts.l pr,@-r15 jsr @r1 mov r5,r0 lds.l @r15+,pr rts nop .L16: .align 2 .L15: .long ___ashlsi3_r0 .size _dyn_lshift, .-_dyn_lshift .align 1 .align 2 .global _dyn_rshift .type _dyn_rshift, @function _dyn_rshift: mov.l .L19,r1 sts.l pr,@-r15 jsr @r1 mov r5,r0 lds.l @r15+,pr rts nop .L20: .align 2 .L19: .long ___lshrsi3_r0 .size _dyn_rshift, .-_dyn_rshift .align 1 .align 2 .global _really_dyn_lshift .type _really_dyn_lshift, @function _really_dyn_lshift: mov.l .L23,r1 sts.l pr,@-r15 jsr @r1 mov r5,r0 lds.l @r15+,pr rts nop .L24: .align 2 .L23: .long ___ashlsi3_r0 .size _really_dyn_lshift, .-_really_dyn_lshift .align 1 .align 2 .global _really_dyn_rshift .type _really_dyn_rshift, @function _really_dyn_rshift: mov.l .L27,r1 sts.l pr,@-r15 jsr @r1 mov r5,r0 lds.l @r15+,pr rts nop .L28: .align 2 .L27: .long ___lshrsi3_r0 .size _really_dyn_rshift, .-_really_dyn_rshift .ident "GCC: (GNU) 12.3.0" With patch enabled, -O2 -ml $ cat f.s .file "f.c" .text .little .text .align 1 .align 2 .global _f_char_var .type _f_char_var, @function _f_char_var: mov r4,r0 tst #64,r0 mov #-1,r0 rts negc r0,r0 .size _f_char_var, .-_f_char_var .align 1 .align 2 .global _f_unsigned_char_var .type _f_unsigned_char_var, @function _f_unsigned_char_var: mov r4,r0 tst #64,r0 mov #-1,r0 rts negc r0,r0 .size _f_unsigned_char_var, .-_f_unsigned_char_var .align 1 .align 2 .global _f_symbol .type _f_symbol, @function _f_symbol: mov.l .L5,r1 mov.b @r1,r0 tst #64,r0 mov #-1,r0 rts negc r0,r0 .L6: .align 2 .L5: .long -65536 .size _f_symbol, .-_f_symbol .align 1 .align 2 .global _f_symbol_zero .type _f_symbol_zero, @function _f_symbol_zero: mov.l .L8,r1 mov.b @r1,r0 tst #64,r0 rts movt r0 .L9: .align 2 .L8: .long -65536 .size _f_symbol_zero, .-_f_symbol_zero .align 1 .align 2 .global _f_symbol_non_zero .type _f_symbol_non_zero, @function _f_symbol_non_zero: mov.l .L11,r1 mov.b @r1,r0 tst #64,r0 mov #-1,r0 rts negc r0,r0 .L12: .align 2 .L11: .long -65536 .size _f_symbol_non_zero, .-_f_symbol_non_zero .align 1 .align 2 .global _dyn_lshift .type _dyn_lshift, @function _dyn_lshift: mov.l .L15,r1 sts.l pr,@-r15 jsr @r1 mov r5,r0 lds.l @r15+,pr rts nop .L16: .align 2 .L15: .long ___ashlsi3_r0 .size _dyn_lshift, .-_dyn_lshift .align 1 .align 2 .global _dyn_rshift .type _dyn_rshift, @function _dyn_rshift: mov.l .L19,r1 sts.l pr,@-r15 jsr @r1 mov r5,r0 lds.l @r15+,pr rts nop .L20: .align 2 .L19: .long ___lshrsi3_r0 .size _dyn_rshift, .-_dyn_rshift .align 1 .align 2 .global _really_dyn_lshift .type _really_dyn_lshift, @function _really_dyn_lshift: mov.l .L23,r1 sts.l pr,@-r15 jsr @r1 mov r5,r0 lds.l @r15+,pr rts nop .L24: .align 2 .L23: .long ___ashlsi3_r0 .size _really_dyn_lshift, .-_really_dyn_lshift .align 1 .align 2 .global _really_dyn_rshift .type _really_dyn_rshift, @function _really_dyn_rshift: mov.l .L27,r1 sts.l pr,@-r15 jsr @r1 mov r5,r0 lds.l @r15+,pr rts nop .L28: .align 2 .L27: .long ___lshrsi3_r0 .size _really_dyn_rshift, .-_really_dyn_rshift .ident "GCC: (GNU) 12.3.0" > '-mdisable-dynshift-libcall' would be more appropriate for what it tries to > do, I think. Although that is a whole different issue ... but what is it > going to do for real dynamic shifts on SH2? > > What kind of code is it supposed to emit for things like > > unsigned int dyn_shift (unsigned int x, unsigned int y) > { > return x << (y & 31); > } As far as I understand from GCC sources, function I patched 'expand_ashiftrt' process only constant values of shift. As you can see earlier, I added your and other examples to tests. It looks like really dynamic shifts translate to library calls. Should I test more exotic situations? If so, could you please help me with really exotic or weired examples?
next prev parent reply other threads:[~2023-05-24 13:34 UTC|newest] Thread overview: 46+ messages / expand[flat|nested] mbox.gz Atom feed top 2011-06-01 20:17 [Bug target/49263] New: " oleg.endo@t-online.de 2011-06-01 20:42 ` [Bug target/49263] " oleg.endo@t-online.de 2011-06-12 23:12 ` kkojima at gcc dot gnu.org 2011-06-19 16:42 ` oleg.endo@t-online.de 2011-06-22 22:34 ` kkojima at gcc dot gnu.org 2011-06-26 22:31 ` oleg.endo@t-online.de 2011-06-27 5:15 ` kkojima at gcc dot gnu.org 2011-10-09 23:35 ` oleg.endo@t-online.de 2011-10-10 1:32 ` kkojima at gcc dot gnu.org 2011-10-10 23:48 ` oleg.endo@t-online.de 2011-10-11 1:47 ` kkojima at gcc dot gnu.org 2011-10-13 22:55 ` oleg.endo@t-online.de 2011-10-14 23:06 ` kkojima at gcc dot gnu.org 2011-10-15 2:33 ` kkojima at gcc dot gnu.org 2011-11-20 14:20 ` oleg.endo@t-online.de 2011-12-29 1:09 ` oleg.endo@t-online.de 2012-02-26 16:28 ` olegendo at gcc dot gnu.org 2012-02-26 23:29 ` olegendo at gcc dot gnu.org 2012-08-27 19:52 ` olegendo at gcc dot gnu.org 2012-10-28 22:02 ` olegendo at gcc dot gnu.org 2012-10-31 13:47 ` olegendo at gcc dot gnu.org 2013-12-08 13:47 ` olegendo at gcc dot gnu.org 2013-12-17 12:37 ` olegendo at gcc dot gnu.org 2014-12-30 18:45 ` olegendo at gcc dot gnu.org 2015-01-24 13:05 ` olegendo at gcc dot gnu.org 2015-01-26 23:57 ` olegendo at gcc dot gnu.org 2023-05-12 11:46 ` klepikov.alex+bugs at gmail dot com 2023-05-23 12:34 ` klepikov.alex+bugs at gmail dot com 2023-05-23 12:35 ` klepikov.alex+bugs at gmail dot com 2023-05-23 19:05 ` olegendo at gcc dot gnu.org 2023-05-24 11:40 ` klepikov.alex+bugs at gmail dot com 2023-05-24 11:57 ` olegendo at gcc dot gnu.org 2023-05-24 13:34 ` klepikov.alex+bugs at gmail dot com [this message] 2023-05-24 15:00 ` olegendo at gcc dot gnu.org 2023-05-25 17:53 ` klepikov.alex+bugs at gmail dot com 2023-05-25 21:32 ` olegendo at gcc dot gnu.org 2023-05-26 12:03 ` klepikov.alex+bugs at gmail dot com 2023-05-26 17:44 ` olegendo at gcc dot gnu.org 2023-05-28 10:24 ` klepikov.alex+bugs at gmail dot com 2023-05-28 10:48 ` olegendo at gcc dot gnu.org 2023-05-29 14:54 ` klepikov.alex+bugs at gmail dot com 2023-05-30 1:48 ` egallager at gcc dot gnu.org 2023-05-30 1:56 ` olegendo at gcc dot gnu.org 2023-05-30 12:42 ` klepikov.alex+bugs at gmail dot com 2023-05-30 19:57 ` olegendo at gcc dot gnu.org 2023-05-30 20:00 ` olegendo 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-49263-4-PdcUyg9RTJ@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).