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 2B7AF3858C53; Tue, 29 Nov 2022 14:54:13 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 2B7AF3858C53
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org;
	s=default; t=1669733653;
	bh=nnDzrtwMgrIOvCTsbf2fiOB9XdKfCNOi9nGZoKQkeLU=;
	h=From:To:Subject:Date:In-Reply-To:References:From;
	b=w9v/A5XZrUPSV+cRdW6DCE/ozywf/ArkICvLKPBvwudCq87k031UV0/t2XuFjfpMc
	 65le5t7mSEoI4W9XkaTPVwcklMPrqdu1/2xlw81HH4E4pcRe22iM3CB3iB3RjyjTeQ
	 +1ZAxaFGW7jGqRYDKBdN9qTQSj8A7HsL+s119aFE=
From: "pinskia at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug middle-end/107916] vector_size(32) is inefficient for VSX on
 powerpc64
Date: Tue, 29 Nov 2022 14:54:12 +0000
X-Bugzilla-Reason: CC
X-Bugzilla-Type: changed
X-Bugzilla-Watch-Reason: None
X-Bugzilla-Product: gcc
X-Bugzilla-Component: middle-end
X-Bugzilla-Version: unknown
X-Bugzilla-Keywords: missed-optimization
X-Bugzilla-Severity: enhancement
X-Bugzilla-Who: pinskia at gcc dot gnu.org
X-Bugzilla-Status: NEW
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: keywords short_desc component
Message-ID: <bug-107916-4-dLD5sB93sy@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-107916-4@http.gcc.gnu.org/bugzilla/>
References: <bug-107916-4@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=3D107916

Andrew Pinski <pinskia at gcc dot gnu.org> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
           Keywords|                            |missed-optimization
            Summary|PPC VSX code generation for |vector_size(32) is
                   |OpenZFS                     |inefficient for VSX on
                   |                            |powerpc64
          Component|target                      |middle-end

--- Comment #2 from Andrew Pinski <pinskia at gcc dot gnu.org> ---
Reduced testcase:
```
#include <stdint.h>

typedef uint32_t u32x4 __attribute__ ((vector_size (16)));

typedef uint32_t u32x8 __attribute__ ((vector_size (32)));
typedef uint64_t u64x4 __attribute__ ((vector_size (32)));

#pragma GCC push_options

#if defined(__x86_64__)

#ifdef __clang_major__
#pragma clang attribute push(__attribute__((target("avx2"))), \
  apply_to =3D function)
#else
#pragma GCC target ("avx2")
#endif

#elif defined(__powerpc64__)
#ifdef __clang_major__
#pragma clang attribute
push(__attribute__((target("vsx,block-ops-unaligned-vsx,power8-vector"))), \
  apply_to =3D function)
#else
#pragma GCC target ("vsx,block-ops-unaligned-vsx,power8-vector,power9-vecto=
r")
#endif

#endif

void f(int n, u32x8 *a, u32x8 *b)
{
  u32x8 c =3D {0};
  for(int i =3D 0; i < n; i++)
     c+=3D*a;
  *b +=3D c;
}
#ifdef __clang_major__
#if defined(__x86_64__) || defined(__powerpc64__)
#pragma clang attribute pop
#endif
#else
#pragma GCC pop_options
#endif
```
Basically what is going wrong is that c is being pushed to the stack. But
really I had expected c's phi node to be split during vector lowering.=