Message ID | 6d9dea6e-5595-477e-b049-6992623f13fc@codesourcery.com |
---|---|
State | New |
Headers |
Return-Path: <newlib-bounces+patchwork=sourceware.org@sourceware.org> X-Original-To: patchwork@sourceware.org Delivered-To: patchwork@sourceware.org Received: from server2.sourceware.org (localhost [IPv6:::1]) by sourceware.org (Postfix) with ESMTP id E18B83858422 for <patchwork@sourceware.org>; Fri, 20 Oct 2023 11:54:34 +0000 (GMT) X-Original-To: newlib@sourceware.org Delivered-To: newlib@sourceware.org Received: from esa2.mentor.iphmx.com (esa2.mentor.iphmx.com [68.232.141.98]) by sourceware.org (Postfix) with ESMTPS id 49ED43858D20 for <newlib@sourceware.org>; Fri, 20 Oct 2023 11:54:24 +0000 (GMT) DMARC-Filter: OpenDMARC Filter v1.4.2 sourceware.org 49ED43858D20 Authentication-Results: sourceware.org; dmarc=none (p=none dis=none) header.from=codesourcery.com Authentication-Results: sourceware.org; spf=pass smtp.mailfrom=mentor.com ARC-Filter: OpenARC Filter v1.0.0 sourceware.org 49ED43858D20 Authentication-Results: server2.sourceware.org; arc=none smtp.remote-ip=68.232.141.98 ARC-Seal: i=1; a=rsa-sha256; d=sourceware.org; s=key; t=1697802865; cv=none; b=HnBDlDqVGeXL4PxtlQaxqqSbsfTZI/fJPwjAjtJFJeVPgoXvpm6QhfejxyGzw3BNAuRyz4jDq1aLgbHB7MJ879YqMnr1/asUkAh2mwofuQ3yGXqkG0bd0OuhkwlrnnOOvMxXJihLLPx/m6ctkmkopGfVcOr6c5BINnxMJhNG7Tg= ARC-Message-Signature: i=1; a=rsa-sha256; d=sourceware.org; s=key; t=1697802865; c=relaxed/simple; bh=i3Sn0qFvCXjZ7UMepYd6xRZpyU0StFNqSHv+cpGxXd4=; h=Message-ID:Date:MIME-Version:To:From:Subject; b=GQoA/PZ4m81Q/JxasdCEvdd1Eji2RrZvtodVdEkcqq5e/rtfQ/UHmyj1DeFcj2SOkhlKBfWVpUbfqUkUJop35/KjIJN6UZeHe6ySAZoe51iZ61+UWNH4Xi2o85jz29GtA33c4F8ENk5VbkEwT2r59W9H7b5lw0JBxxNWoOLc3rI= ARC-Authentication-Results: i=1; server2.sourceware.org X-CSE-ConnectionGUID: JSzHunQvSsGMR0XpAxJLtg== X-CSE-MsgGUID: dXSNLjoxTe2V9HAunf252w== X-IronPort-AV: E=Sophos;i="6.03,238,1694764800"; d="scan'208";a="22661231" Received: from orw-gwy-01-in.mentorg.com ([192.94.38.165]) by esa2.mentor.iphmx.com with ESMTP; 20 Oct 2023 03:54:22 -0800 IronPort-SDR: bu7bKgqeTTfQSj9vHUetJuqw7k/190ckcl5RyLI5LQcoiq5QO1G8o+woNhhKQCZwDGR6j12CYy dDA0SniJHExEKq0751dJWhFmEcskjndh56NyCwakhuEmCdzVUxbanDqEFzs6NKWPzW7+VnYYJ1 sXCxa7/Df3uUlna5Fa1Xs8L6ftWrys5E/3UMxyalMQO4YY6Gh1XP3JnO/LWMQJLZJRxjKRR8p9 bpWhmfKHKDKSskD9ScriZPjwcgjd+pPflbevcYw3cqjhuza/j3Xfn4CfHjjj/RwE1hmg4sle/l lag= Content-Type: multipart/mixed; boundary="------------nlo5XGbbFR5lPl1z1JeDosJ5" Message-ID: <6d9dea6e-5595-477e-b049-6992623f13fc@codesourcery.com> Date: Fri, 20 Oct 2023 12:54:17 +0100 MIME-Version: 1.0 User-Agent: Mozilla Thunderbird Content-Language: en-GB To: <newlib@sourceware.org> From: Andrew Stubbs <ams@codesourcery.com> Subject: [PATCH] amdgcn: remove unnecessary scalar cache flush X-Originating-IP: [137.202.0.90] X-ClientProxiedBy: svr-ies-mbx-13.mgc.mentorg.com (139.181.222.13) To svr-ies-mbx-11.mgc.mentorg.com (139.181.222.11) X-Spam-Status: No, score=-12.0 required=5.0 tests=BAYES_00, GIT_PATCH_0, HEADER_FROM_DIFFERENT_DOMAINS, KAM_DMARC_STATUS, SPF_HELO_PASS, SPF_PASS, TXREP autolearn=ham autolearn_force=no version=3.4.6 X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on server2.sourceware.org X-BeenThere: newlib@sourceware.org X-Mailman-Version: 2.1.30 Precedence: list List-Id: Newlib mailing list <newlib.sourceware.org> List-Unsubscribe: <https://sourceware.org/mailman/options/newlib>, <mailto:newlib-request@sourceware.org?subject=unsubscribe> List-Archive: <https://sourceware.org/pipermail/newlib/> List-Post: <mailto:newlib@sourceware.org> List-Help: <mailto:newlib-request@sourceware.org?subject=help> List-Subscribe: <https://sourceware.org/mailman/listinfo/newlib>, <mailto:newlib-request@sourceware.org?subject=subscribe> Errors-To: newlib-bounces+patchwork=sourceware.org@sourceware.org |
Series |
amdgcn: remove unnecessary scalar cache flush
|
|
Commit Message
Andrew Stubbs
Oct. 20, 2023, 11:54 a.m. UTC
Hi, This patch is necessary to support AMD RDNA2 GPUs that don't have a writable scalar cache. However, the write back isn't actually doing anything useful on any GPU any more, so we can remove it. Andrew amdgcn: remove unnecessary scalar cache flush The exit code isn't actually written via the scalar cache so the cache flush is not actually needed.
Comments
Ping. On 20/10/2023 12:54, Andrew Stubbs wrote: > Hi, > > This patch is necessary to support AMD RDNA2 GPUs that don't have a > writable scalar cache. However, the write back isn't actually doing > anything useful on any GPU any more, so we can remove it. > > Andrew
On Oct 20 12:54, Andrew Stubbs wrote: > Hi, > > This patch is necessary to support AMD RDNA2 GPUs that don't have a writable > scalar cache. However, the write back isn't actually doing anything useful > on any GPU any more, so we can remove it. > > Andrew > amdgcn: remove unnecessary scalar cache flush > > The exit code isn't actually written via the scalar cache so the cache flush > is not actually needed. > > diff --git a/newlib/libc/machine/amdgcn/exit-value.h b/newlib/libc/machine/amdgcn/exit-value.h > index 7aa2508bb..6b9d2411b 100644 > --- a/newlib/libc/machine/amdgcn/exit-value.h > +++ b/newlib/libc/machine/amdgcn/exit-value.h > @@ -32,7 +32,6 @@ exit_with_int (int val) > *return_value = val; > > /* Terminate the current kernel. */ > - asm ("s_dcache_wb"); > asm ("s_endpgm"); > __builtin_unreachable (); > } Pushed. Thanks, Corinna
diff --git a/newlib/libc/machine/amdgcn/exit-value.h b/newlib/libc/machine/amdgcn/exit-value.h index 7aa2508bb..6b9d2411b 100644 --- a/newlib/libc/machine/amdgcn/exit-value.h +++ b/newlib/libc/machine/amdgcn/exit-value.h @@ -32,7 +32,6 @@ exit_with_int (int val) *return_value = val; /* Terminate the current kernel. */ - asm ("s_dcache_wb"); asm ("s_endpgm"); __builtin_unreachable (); }