From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <gcc-bugzilla@gcc.gnu.org>
Received: by sourceware.org (Postfix, from userid 48)
	id 7D5CF385843A; Wed,  6 Mar 2024 10:01:33 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 7D5CF385843A
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org;
	s=default; t=1709719293;
	bh=DhHJzkxggA2nYOylQrjER0I6NQ7bmot2tu0F5N56Ifk=;
	h=From:To:Subject:Date:From;
	b=Ug1jGoFMd9qsHnNoKTm0DMQcvMPcMa0FLq7PGDYERR9d019MzQKiMI42Cy9aL25qV
	 8NMhxyrokCsmIx13w8++Znz+Fojw7cknA9fhSaGuG5C1uXr+OoCEFMYEfX5YyULmlu
	 c41HUukEnWSzNGgqUr7UgXrW6ryNNsyOIJADDUxQ=
From: "gjl at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug tree-optimization/114252] New: Introducing bswapsi reduces code
 performance
Date: Wed, 06 Mar 2024 10:01:32 +0000
X-Bugzilla-Reason: CC
X-Bugzilla-Type: new
X-Bugzilla-Watch-Reason: None
X-Bugzilla-Product: gcc
X-Bugzilla-Component: tree-optimization
X-Bugzilla-Version: 14.0
X-Bugzilla-Keywords: 
X-Bugzilla-Severity: normal
X-Bugzilla-Who: gjl at gcc dot gnu.org
X-Bugzilla-Status: UNCONFIRMED
X-Bugzilla-Resolution: 
X-Bugzilla-Priority: P3
X-Bugzilla-Assigned-To: unassigned at gcc dot gnu.org
X-Bugzilla-Target-Milestone: ---
X-Bugzilla-Flags: 
X-Bugzilla-Changed-Fields: bug_id short_desc product version bug_status
 bug_severity priority component assigned_to reporter target_milestone
 attachments.created
Message-ID: <bug-114252-4@http.gcc.gnu.org/bugzilla/>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
X-Bugzilla-URL: http://gcc.gnu.org/bugzilla/
Auto-Submitted: auto-generated
MIME-Version: 1.0
List-Id: <gcc-bugs.sourceware.org>

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=3D114252

            Bug ID: 114252
           Summary: Introducing bswapsi reduces code performance
           Product: gcc
           Version: 14.0
            Status: UNCONFIRMED
          Severity: normal
          Priority: P3
         Component: tree-optimization
          Assignee: unassigned at gcc dot gnu.org
          Reporter: gjl at gcc dot gnu.org
  Target Milestone: ---

Created attachment 57628
  --> https://gcc.gnu.org/bugzilla/attachment.cgi?id=3D57628&action=3Dedit
GNU-C test case

typedef __UINT8_TYPE__ uint8_t;
typedef __UINT32_TYPE__ uint32_t;

typedef uint8_t __attribute__((vector_size(4))) v4u8_t;

uint32_t func1 (const uint8_t *buf) {
    v4u8_t v4 =3D { buf[1], buf[0], buf[3], buf[2] };

    return (uint32_t) v4;
}

Compile the code with

$ avr-gcc code.c -S -Os -dp

with v13 the result is:


func1:
        mov r30,r24      ;  37  [c=3D4 l=3D1]  movqi_insn/0
        mov r31,r25      ;  38  [c=3D4 l=3D1]  movqi_insn/0
        ldd r22,Z+1      ;  39  [c=3D4 l=3D1]  movqi_insn/3
        ld r23,Z                 ;  40  [c=3D4 l=3D1]  movqi_insn/3
        ldd r24,Z+3      ;  41  [c=3D4 l=3D1]  movqi_insn/3
        ldd r25,Z+2      ;  42  [c=3D4 l=3D1]  movqi_insn/3
/* epilogue start */
        ret              ;  45  [c=3D0 l=3D1]  return

which is good code: insn 37, 38 move the address to pointer register Z, and
then follow 4 loads, one for each byte.

When compiled with v14 however:

func1:
        mov r30,r24      ;  23  [c=3D4 l=3D2]  *movhi/0
        mov r31,r25
        ld r22,Z         ;  24  [c=3D16 l=3D4]  *movsi/2
        ldd r23,Z+1
        ldd r24,Z+2
        ldd r25,Z+3
        rcall __bswapsi2         ;  25  [c=3D16 l=3D1]  *bswapsi2.libgcc
        mov r31,r23      ;  32  [c=3D4 l=3D1]  movqi_insn/0
        mov r23,r25      ;  33  [c=3D4 l=3D1]  movqi_insn/0
        mov r25,r31      ;  34  [c=3D4 l=3D1]  movqi_insn/0
        mov r31,r22      ;  35  [c=3D4 l=3D1]  movqi_insn/0
        mov r22,r24      ;  36  [c=3D4 l=3D1]  movqi_insn/0
        mov r24,r31      ;  37  [c=3D4 l=3D1]  movqi_insn/0
/* epilogue start */
        ret              ;  40  [c=3D0 l=3D1]  return


Target: avr
Configured with: ../../source/gcc-master/configure --target=3Davr --disable=
-nls
--with-dwarf2 --with-gnu-as --with-gnu-ld --disable-shared
--enable-languages=3Dc,c++
Thread model: single
Supported LTO compression algorithms: zlib
gcc version 14.0.1 20240303 (experimental) (GCC)=