This is the mail archive of the
libc-alpha@sourceware.org
mailing list for the glibc project.
Re: [PATCH] aarch64: Optimized implementation of pthread_spin_lock and unlock
- From: Wilco Dijkstra <Wilco dot Dijkstra at arm dot com>
- To: Szabolcs Nagy <Szabolcs dot Nagy at arm dot com>, Andrew Pinski <pinskia at gmail dot com>, Xuelei Zhang <zhangxuelei4 at huawei dot com>
- Cc: nd <nd at arm dot com>, GNU C Library <libc-alpha at sourceware dot org>, Siddhesh Poyarekar <siddhesh at gotplt dot org>, "jiangyikun at huawei dot com" <jiangyikun at huawei dot com>, "yikunkero at gmail dot com" <yikunkero at gmail dot com>
- Date: Tue, 29 Oct 2019 11:54:34 +0000
- Subject: Re: [PATCH] aarch64: Optimized implementation of pthread_spin_lock and unlock
- Arc-authentication-results: i=1; mx.microsoft.com 1; spf=pass smtp.mailfrom=arm.com; dmarc=pass action=none header.from=arm.com; dkim=pass header.d=arm.com; arc=none
- Arc-message-signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=microsoft.com; s=arcselector9901; h=From:Date:Subject:Message-ID:Content-Type:MIME-Version:X-MS-Exchange-SenderADCheck; bh=1VVN/4K/fAGNGSnBlJA5D1lP0j8j2T3JPcwIHKz64QI=; b=CxxFm+RFVo6XdIazcDiGVa3/Nz1cRPZvA8F5B7l1YY4XdE2rrS78c1KgbFS7OJx5kWd7UZIWYklzBN3k3xSR+wCvZTwT3ZABzH8XqmjUUIqN4QU7WOc19IguViUlH/vuSC8pGeytcRmyu1/p57WXqQIcn3pN5piwP/FSA9Qp3L6OiR0khYZsmBE5SJhf3pQF7+HKHlnT6AKn4mFIijHMEi/b4B5lKXvWSbYG09Ndj5Y2W9chP6KGup8SKgJLfgt/lra2jtehHn34Wo+JsJ07z6f5X77wZSKynbg0fLx9/HYSVUlGuv6apvljHkiFreTRySd2kCe6mTCOtmk+g2pryQ==
- Arc-seal: i=1; a=rsa-sha256; s=arcselector9901; d=microsoft.com; cv=none; b=HKVEiWlfL9UgjsG+ybR6roXDSF1Mcq7gPinYjAYZTjnM9ComICSNoLB0wqMaqKsSIvPfQ+o1VSJmc42QmucmNYOPkt5qkBd4wDdTh0aL3wTU1YHy1Q6WKQdg2JI7dkUKt8SnB+AtNmAuieuXgFJ6ju/MPeNsJjeQsbi+WZX/Mc+bwRolKcsWHqh8VuSNjWafFolnt8igmakjF3AKt33VLuCbmVABmvz6jA+7FfEjCLQG1kDveU6BTIe6/NQGYkrDGbX+50SjTcX5KYzcUllG5E3mKoAF2cu2WDL522am/4yECtUg3DCpQpaHuOe0s8tSaHQIoXEOKuYY4RdMh2prgQ==
- Original-authentication-results: spf=none (sender IP is ) smtp.mailfrom=Wilco dot Dijkstra at arm dot com;
- References: <20191028133911.8612-1-zhangxuelei4@huawei.com> <CA+=Sn1mO8cSN3JLrAsSWDQZSLRiSyyw5_U81XWecEJk_BRstNQ@mail.gmail.com>,<6b9d4ded-64a5-769b-2701-e15b1fdf43d7@arm.com>
Hi,
> i'd prefer to improve the generic c code if
> possible instead of using asm.
Agreed, there isn't really anything performance critical that assembler
could speed up. It's more about what strategy to use if there is any
contention.
But we really need representative benchmarks first. Without that it's
impossible to decide whether a new spinlock implementation is faster.
Cheers,
Wilco