From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from st43p00im-ztbu10063701.me.com (st43p00im-ztbu10063701.me.com [17.58.63.178]) by sourceware.org (Postfix) with ESMTPS id D105A3857708 for ; Mon, 15 May 2023 20:13:37 +0000 (GMT) DMARC-Filter: OpenDMARC Filter v1.4.2 sourceware.org D105A3857708 Authentication-Results: sourceware.org; dmarc=pass (p=quarantine dis=none) header.from=icloud.com Authentication-Results: sourceware.org; spf=pass smtp.mailfrom=icloud.com DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=icloud.com; s=1a1hai; t=1684181617; bh=IHwqSn/D2RdWWPXF2OyNv/NsttZsBywMU7yIHm5NH28=; h=From:Message-Id:Content-Type:Mime-Version:Subject:Date:To; b=Ap91EBQvJWiKQbLj72ozbwD8b2YQCbE5/x0uH6OtCOvV+A8tibvedhsdxETiGaVHh Quh5rqNyIx8h2G8UrxbNfqdVeb8D36ubnA/aY95Z/nJUF0kSkVEULDEbvJrXHf/JgF LFRkt8Rv6XsBfPUBvTgW5z/SC1pBDWSqk31+rcr1lbybOKkBKvQMdhGEkSUihoIfCp nV38LEd6u6ay2DiS+1hs01NzVpQsS1sf8sonUUjIlqMa5BnjABMx+J+kWNCpZRu5Sf 3+iCPS1g0SHxIGiHo3KzcbhloSQR/rFGTSU6ESOPgdhdBvuLCw1MN8ZtxvJex3Ynew hCIiiNd0A182g== Received: from smtpclient.apple (st43p00im-dlb-asmtp-mailmevip.me.com [17.42.251.41]) by st43p00im-ztbu10063701.me.com (Postfix) with ESMTPSA id 9DAFFD002C1; Mon, 15 May 2023 20:13:36 +0000 (UTC) From: Evandro Menezes Message-Id: <691ED2DC-333C-4E3D-AB54-B84519673C75@icloud.com> Content-Type: multipart/alternative; boundary="Apple-Mail=_1EB73652-8713-42B5-9132-A727865D446C" Mime-Version: 1.0 (Mac OS X Mail 16.0 \(3731.500.231\)) Subject: Re: [PATCH] aarch64: Add SVE instruction types Date: Mon, 15 May 2023 15:13:05 -0500 In-Reply-To: Cc: Richard Sandiford , Evandro Menezes via Gcc-patches , "evandro+gcc@gcc.gnu.org" , Tamar Christina To: Kyrylo Tkachov References: <1D567E08-9EBB-4EF7-9626-BA95D8E0EB36@icloud.com> X-Mailer: Apple Mail (2.3731.500.231) X-Proofpoint-ORIG-GUID: C5PcnyOe0fUpGR1bESNDb0J2WplQf9eJ X-Proofpoint-GUID: C5PcnyOe0fUpGR1bESNDb0J2WplQf9eJ X-Proofpoint-Virus-Version: =?UTF-8?Q?vendor=3Dfsecure_engine=3D1.1.170-22c6f66c430a71ce266a39bfe25bc?= =?UTF-8?Q?2903e8d5c8f:6.0.425,18.0.572,17.0.605.474.0000000_definitions?= =?UTF-8?Q?=3D2022-01-14=5F01:2022-01-14=5F01,2020-02-14=5F11,2020-01-23?= =?UTF-8?Q?=5F02_signatures=3D0?= X-Proofpoint-Spam-Details: rule=notspam policy=default score=0 clxscore=1011 adultscore=0 suspectscore=0 phishscore=0 mlxscore=0 malwarescore=0 spamscore=0 bulkscore=0 mlxlogscore=999 classifier=spam adjust=0 reason=mlx scancount=1 engine=8.12.0-2212070000 definitions=main-2305150167 X-Spam-Status: No, score=-3.2 required=5.0 tests=BAYES_00,DKIM_SIGNED,DKIM_VALID,DKIM_VALID_AU,DKIM_VALID_EF,FREEMAIL_FROM,HTML_MESSAGE,KAM_SHORT,RCVD_IN_DNSWL_LOW,SPF_HELO_NONE,SPF_PASS,TXREP,T_SCC_BODY_TEXT_LINE autolearn=unavailable autolearn_force=no version=3.4.6 X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on server2.sourceware.org List-Id: --Apple-Mail=_1EB73652-8713-42B5-9132-A727865D446C Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset=utf-8 Hi, Kyrill. I wasn=E2=80=99t aware of your previous patch. Could you clarify why you c= onsidered creating an SVE specific type attribute instead of reusing the co= mmon one? I really liked the iterators that you created; I=E2=80=99d like = to use them. Do you have specific examples which you might want to mention with regards = to granularity? Yes, my intent for this patch is to enable modeling the SVE instructions on= N1. The patch that implements it brings up some performance improvements,= but it=E2=80=99s mostly flat, as expected. Thank you, --=20 Evandro Menezes > Em 15 de mai. de 2023, =C3=A0(s) 04:49, Kyrylo Tkachov escreveu: >=20 >=20 >=20 >> -----Original Message----- >> From: Richard Sandiford > >> Sent: Monday, May 15, 2023 10:01 AM >> To: Evandro Menezes via Gcc-patches > >> Cc: evandro+gcc@gcc.gnu.org ; Evandro Me= nezes >; >> Kyrylo Tkachov >;= Tamar Christina >> > >> Subject: Re: [PATCH] aarch64: Add SVE instruction types >>=20 >> Evandro Menezes via Gcc-patches writes: >>> This patch adds the attribute `type` to most SVE1 instructions, as in t= he >> other >>> instructions. >>=20 >> Thanks for doing this. >>=20 >> Could you say what criteria you used for picking the granularity? Other >> maintainers might disagree, but personally I'd prefer to distinguish two >> instructions only if: >>=20 >> (a) a scheduling description really needs to distinguish them or >> (b) grouping them together would be very artificial (because they're >> logically unrelated) >>=20 >> It's always possible to split types later if new scheduling descriptions >> require it. Because of that, I don't think we should try to predict ahe= ad >> of time what future scheduling descriptions will need. >>=20 >> Of course, this depends on having results that show that scheduling >> makes a significant difference on an SVE core. I think one of the >> problems here is that, when a different scheduling model changes the >> performance of a particular test, it's difficult to tell whether >> the gain/loss is caused by the model being more/less accurate than >> the previous one, or if it's due to important "secondary" effects >> on register live ranges. Instinctively, I'd have expected these >> secondary effects to dominate on OoO cores. >=20 > I agree with Richard on these points. The key here is getting the granula= rity right without having too maintain too many types that aren't useful in= the models. > FWIW I had posted https://gcc.gnu.org/pipermail/gcc-patches/2022-November= /607101.html in November. It adds annotations to SVE2 patterns as well as f= or base SVE. > Feel free to reuse it if you'd like. > I see you had posted a Neoverse V1 scheduling model. Does that give an im= provement on SVE code when combined with the scheduling attributes somehow? > Thanks, > Kyrill --Apple-Mail=_1EB73652-8713-42B5-9132-A727865D446C--