From stuart.monteith at arm.com Thu Jul 16 19:29:51 2020 From: stuart.monteith at arm.com (Stuart Monteith) Date: Thu, 16 Jul 2020 20:29:51 +0100 Subject: RFR(S): 8246373 AArch64: Refactor register spilling code in ZGC barriers Message-ID: Hello, There is an opportunity to spill/load fewer registers in ZGC barriers. This is targetting JDK 16 jdk/jdk. JIRA: https://bugs.openjdk.java.net/browse/JDK-8246373 Webrev: http://cr.openjdk.java.net/~smonteith/8246373/webrev.0/ Tested with JTReg, SPECjbb2015, and other workloads. Thanks, Stuart From aph at redhat.com Fri Jul 17 07:42:17 2020 From: aph at redhat.com (Andrew Haley) Date: Fri, 17 Jul 2020 08:42:17 +0100 Subject: RFR(S): 8246373 AArch64: Refactor register spilling code in ZGC barriers In-Reply-To: References: Message-ID: <80ad8cb8-fe7e-dce7-d04f-2ff81cd9d548@redhat.com> Hi, On 16/07/2020 20:29, Stuart Monteith wrote: > Hello, > There is an opportunity to spill/load fewer registers in ZGC barriers. This is targetting JDK 16 jdk/jdk. > > JIRA: > https://bugs.openjdk.java.net/browse/JDK-8246373 > Webrev: > http://cr.openjdk.java.net/~smonteith/8246373/webrev.0/ > > Tested with JTReg, SPECjbb2015, and other workloads. Looks reasonable, but please keep push_call_clobbered_registers(). If you need to do this, add push_call_clobbered_registers_except(RegSet). Of course the former can call the latter. -- Andrew Haley (he/him) Java Platform Lead Engineer Red Hat UK Ltd. https://keybase.io/andrewhaley EAC8 43EB D3EF DB98 CC77 2FAD A5CD 6035 332F A671 From erik.osterlund at oracle.com Tue Jul 21 07:59:34 2020 From: erik.osterlund at oracle.com (=?UTF-8?Q?Erik_=c3=96sterlund?=) Date: Tue, 21 Jul 2020 09:59:34 +0200 Subject: RFR(S): 8246373 AArch64: Refactor register spilling code in ZGC barriers In-Reply-To: <80ad8cb8-fe7e-dce7-d04f-2ff81cd9d548@redhat.com> References: <80ad8cb8-fe7e-dce7-d04f-2ff81cd9d548@redhat.com> Message-ID: <1c08cd73-ef1e-43b4-8cd2-cf4801ce5c08@oracle.com> Looks good, given Andrew's suggestion. Don't need another webrev for that. Thanks, /Erik On 2020-07-17 09:42, Andrew Haley wrote: > Hi, > > On 16/07/2020 20:29, Stuart Monteith wrote: >> Hello, >> There is an opportunity to spill/load fewer registers in ZGC barriers. This is targetting JDK 16 jdk/jdk. >> >> JIRA: >> https://bugs.openjdk.java.net/browse/JDK-8246373 >> Webrev: >> http://cr.openjdk.java.net/~smonteith/8246373/webrev.0/ >> >> Tested with JTReg, SPECjbb2015, and other workloads. > Looks reasonable, but please keep push_call_clobbered_registers(). If > you need to do this, add push_call_clobbered_registers_except(RegSet). > Of course the former can call the latter. > From stumon01 at arm.com Wed Jul 22 15:47:57 2020 From: stumon01 at arm.com (Stuart Monteith) Date: Wed, 22 Jul 2020 16:47:57 +0100 Subject: RFR(S): 8246373 AArch64: Refactor register spilling code in ZGC barriers In-Reply-To: <1c08cd73-ef1e-43b4-8cd2-cf4801ce5c08@oracle.com> References: <80ad8cb8-fe7e-dce7-d04f-2ff81cd9d548@redhat.com> <1c08cd73-ef1e-43b4-8cd2-cf4801ce5c08@oracle.com> Message-ID: <2ddf7b16-ffe2-e0f4-2d8f-3ad7bf2257d2@arm.com> Thanks Eric, I've got a new webrev that'll hopefully be satisfactory: http://cr.openjdk.java.net/~smonteith/8246373/webrev.1/ Thanks, Stuart On 21/07/2020 08:59, Erik ?sterlund wrote: > Looks good, given Andrew's suggestion. Don't need another webrev for that. > > Thanks, > /Erik > > On 2020-07-17 09:42, Andrew Haley wrote: >> Hi, >> >> On 16/07/2020 20:29, Stuart Monteith wrote: >>> Hello, >>> There is an opportunity to spill/load fewer registers in ZGC barriers. This is targetting JDK 16 jdk/jdk. >>> >>> JIRA: >>> https://bugs.openjdk.java.net/browse/JDK-8246373 >>> Webrev: >>> http://cr.openjdk.java.net/~smonteith/8246373/webrev.0/ >>> >>> Tested with JTReg, SPECjbb2015, and other workloads. >> Looks reasonable, but please keep push_call_clobbered_registers(). If >> you need to do this, add push_call_clobbered_registers_except(RegSet). >> Of course the former can call the latter. >> > IMPORTANT NOTICE: The contents of this email and any attachments are confidential and may also be privileged. If you are not the intended recipient, please notify the sender immediately and do not disclose the contents to any other person, use it for any purpose, or store or copy the information in any medium. Thank you. From erik.osterlund at oracle.com Wed Jul 22 16:37:22 2020 From: erik.osterlund at oracle.com (=?UTF-8?Q?Erik_=c3=96sterlund?=) Date: Wed, 22 Jul 2020 18:37:22 +0200 Subject: RFR(S): 8246373 AArch64: Refactor register spilling code in ZGC barriers In-Reply-To: <2ddf7b16-ffe2-e0f4-2d8f-3ad7bf2257d2@arm.com> References: <80ad8cb8-fe7e-dce7-d04f-2ff81cd9d548@redhat.com> <1c08cd73-ef1e-43b4-8cd2-cf4801ce5c08@oracle.com> <2ddf7b16-ffe2-e0f4-2d8f-3ad7bf2257d2@arm.com> Message-ID: Hi Stuart, Looks good. Thanks, /Erik On 2020-07-22 17:47, Stuart Monteith wrote: > Thanks Eric, > ?????? I've got a new webrev that'll hopefully be satisfactory: > http://cr.openjdk.java.net/~smonteith/8246373/webrev.1/ > > > Thanks, > ?????? Stuart > > On 21/07/2020 08:59, Erik ?sterlund wrote: >> Looks good, given Andrew's suggestion. Don't need another webrev for >> that. >> >> Thanks, >> /Erik >> >> On 2020-07-17 09:42, Andrew Haley wrote: >>> Hi, >>> >>> On 16/07/2020 20:29, Stuart Monteith wrote: >>>> Hello, >>>> ???? There is an opportunity to spill/load fewer registers in ZGC >>>> barriers. This is targetting JDK 16 jdk/jdk. >>>> >>>> JIRA: >>>> https://bugs.openjdk.java.net/browse/JDK-8246373 >>>> Webrev: >>>> http://cr.openjdk.java.net/~smonteith/8246373/webrev.0/ >>>> >>>> Tested with JTReg, SPECjbb2015, and other workloads. >>> Looks reasonable, but please keep push_call_clobbered_registers(). If >>> you need to do this, add push_call_clobbered_registers_except(RegSet). >>> Of course the former can call the latter. >>> >> > > IMPORTANT NOTICE: The contents of this email and any attachments are > confidential and may also be privileged. If you are not the intended > recipient, please notify the sender immediately and do not disclose > the contents to any other person, use it for any purpose, or store or > copy the information in any medium. Thank you. From ningsheng.jian at arm.com Fri Jul 24 01:02:34 2020 From: ningsheng.jian at arm.com (Ningsheng Jian) Date: Fri, 24 Jul 2020 09:02:34 +0800 Subject: RFR(S): 8246373 AArch64: Refactor register spilling code in ZGC barriers In-Reply-To: References: <80ad8cb8-fe7e-dce7-d04f-2ff81cd9d548@redhat.com> <1c08cd73-ef1e-43b4-8cd2-cf4801ce5c08@oracle.com> <2ddf7b16-ffe2-e0f4-2d8f-3ad7bf2257d2@arm.com> Message-ID: <13b76c61-446d-6042-aac9-95aab626bcfe@arm.com> Hi Stuart, Looks good to me and pushed. Thanks, Ningsheng On 7/23/20 12:37 AM, Erik ?sterlund wrote: > Hi Stuart, > > Looks good. > > Thanks, > /Erik > > On 2020-07-22 17:47, Stuart Monteith wrote: >> Thanks Eric, >> ?????? I've got a new webrev that'll hopefully be satisfactory: >> http://cr.openjdk.java.net/~smonteith/8246373/webrev.1/ >> >> >> Thanks, >> ?????? Stuart >> >> On 21/07/2020 08:59, Erik ?sterlund wrote: >>> Looks good, given Andrew's suggestion. Don't need another webrev for >>> that. >>> >>> Thanks, >>> /Erik >>> >>> On 2020-07-17 09:42, Andrew Haley wrote: >>>> Hi, >>>> >>>> On 16/07/2020 20:29, Stuart Monteith wrote: >>>>> Hello, >>>>> ???? There is an opportunity to spill/load fewer registers in ZGC >>>>> barriers. This is targetting JDK 16 jdk/jdk. >>>>> >>>>> JIRA: >>>>> https://bugs.openjdk.java.net/browse/JDK-8246373 >>>>> Webrev: >>>>> http://cr.openjdk.java.net/~smonteith/8246373/webrev.0/ >>>>> >>>>> Tested with JTReg, SPECjbb2015, and other workloads. >>>> Looks reasonable, but please keep push_call_clobbered_registers(). If >>>> you need to do this, add push_call_clobbered_registers_except(RegSet). >>>> Of course the former can call the latter. >>>> >>> >> >> IMPORTANT NOTICE: The contents of this email and any attachments are >> confidential and may also be privileged. If you are not the intended >> recipient, please notify the sender immediately and do not disclose >> the contents to any other person, use it for any purpose, or store or >> copy the information in any medium. Thank you. >