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 38AD43858C66; Mon, 23 Oct 2023 03:36:04 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 38AD43858C66
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org;
	s=default; t=1698032164;
	bh=bv/+Bn2ZUNEvFaev0aCEm7At6bAw9O5mC049PvFEIWU=;
	h=From:To:Subject:Date:From;
	b=nYBH50kxvvNepvQ1jSEMw8AYPoOo7Uevm3KuN3Az9lHxLyIrohhUs0Qij5bL0vZtL
	 7sa8swIb4lItad6lg0WbPcy59uPPUPOLqkvMg7WwyO2hjDu6iCfgJbvw6pz5A4ytwK
	 XLrD2nQ4ShEGwyzitdagzwSdqvVSi1h+J51r5gdA=
From: "lehua.ding at rivai dot ai" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug target/111926] New: RISC-V: Use vsetvl insn replace csrr vlenb
 insn
Date: Mon, 23 Oct 2023 03:36:03 +0000
X-Bugzilla-Reason: CC
X-Bugzilla-Type: new
X-Bugzilla-Watch-Reason: None
X-Bugzilla-Product: gcc
X-Bugzilla-Component: target
X-Bugzilla-Version: 14.0
X-Bugzilla-Keywords: 
X-Bugzilla-Severity: normal
X-Bugzilla-Who: lehua.ding at rivai dot ai
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
Message-ID: <bug-111926-4@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=3D111926

            Bug ID: 111926
           Summary: RISC-V: Use vsetvl insn replace csrr vlenb insn
           Product: gcc
           Version: 14.0
            Status: UNCONFIRMED
          Severity: normal
          Priority: P3
         Component: target
          Assignee: unassigned at gcc dot gnu.org
          Reporter: lehua.ding at rivai dot ai
  Target Milestone: ---

We can use:=20
        vsetvl a5, zero, e8, mf8, ta, ta
replace:
        csrr    a4,vlenb
        srli    a4,a4,3

The reason for this is that the performance of the vsetvl instruction tends=
 to
be better optimised than the csrr instruction.

#include <riscv_vector.h>

#define exhaust_vector_regs()=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=
=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=
=20=20=20=20=20=20=20=20=20
\
  asm volatile("#" ::=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=
=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=
=20=20=20=20=20=20=20=20=20=20=20=20=20=20
\
                 : "v0", "v1", "v2", "v3", "v4", "v5", "v6", "v7", "v8", "v=
9",
\
                   "v10", "v11", "v12", "v13", "v14", "v15", "v16", "v17",=
=20=20=20=20
\
                   "v18", "v19", "v20", "v21", "v22", "v23", "v24", "v25",=
=20=20=20=20
\
                   "v26", "v27", "v28", "v29", "v30", "v31");

void
spill_1 (int8_t *in, int8_t *out)
{
  vint8mf8_t v1 =3D *(vint8mf8_t*)in;
  exhaust_vector_regs ();
  *(vint8mf8_t*)out =3D v1;
}

spill_1(signed char*, signed char*):
        csrr    a4,vlenb
        srli    a4,a4,3
        csrr    t0,vlenb
        slli    a3,a4,3
        sub     sp,sp,t0
        sub     a3,a3,a4
        add     a3,a3,sp
        vsetvli a5,zero,e8,mf8,ta,ma
        vle8.v  v1,0(a0)
        vse8.v  v1,0(a3)
        csrr    a4,vlenb
        srli    a4,a4,3
        slli    a3,a4,3
        sub     a3,a3,a4
        add     a3,a3,sp
        vle8.v  v1,0(a3)
        csrr    t0,vlenb
        vse8.v  v1,0(a1)
        add     sp,sp,t0
        jr      ra


https://godbolt.org/z/TcKxbjnoh=