From mboxrd@z Thu Jan 1 00:00:00 1970 From: Pekka Paalanen Subject: Re: [PATCH 1/3] vulkan: Define new VK_MESA_query_timestamp extension [v2] Date: Wed, 11 Jul 2018 10:31:10 +0300 Message-ID: <20180711103110.333b1523@eldfell> References: <20180623151521.8306-1-keithp@keithp.com> <20180623151521.8306-2-keithp@keithp.com> <1642da34868.27ad.c6988b7ea6112e3e892765a0d4287e0c@jlekstrand.net> <20180710101615.610c7966@eldfell> <87fu0rklzk.fsf@keithp.com> Mime-Version: 1.0 Content-Type: multipart/mixed; boundary="===============2078767744==" Return-path: In-Reply-To: <87fu0rklzk.fsf@keithp.com> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: mesa-dev-bounces@lists.freedesktop.org Sender: "mesa-dev" To: Keith Packard Cc: mesa-dev@lists.freedesktop.org, dri-devel@lists.freedesktop.org List-Id: dri-devel@lists.freedesktop.org --===============2078767744== Content-Type: multipart/signed; micalg=pgp-sha256; boundary="Sig_/h_s_elgy2Hnmv1CzvVGAN70"; protocol="application/pgp-signature" --Sig_/h_s_elgy2Hnmv1CzvVGAN70 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: quoted-printable On Tue, 10 Jul 2018 11:02:23 -0700 "Keith Packard" wrote: > Pekka Paalanen writes: >=20 > > On Sat, 23 Jun 2018 12:13:53 -0500 > > Jason Ekstrand wrote: > > =20 > >> I haven't thought through this comment all that hard but would it make= =20 > >> sense to have three timestamps, CPU, GPU, CPU so that you have error b= ars=20 > >> on the GPU timestamp? At the very least, two timestamps would be bett= er=20 > >> than one so that, when we pull it into the kernel, it can provide some= thing=20 > >> more accurate than userspace trying to grab a snapshot. =20 > > > > Hi, > > > > three timestamps sounds like a good idea to me, but you might want to > > reach out to media developers (e.g. gstreamer) who have experience in > > synchronizing different clocks and what that will actually take. =20 >=20 > Oh, I know that's really hard, and I don't want to solve that problem > here. I explicitly *don't* solve it though -- I simply expose the > ability to get correlated values in the two application-visible time > domains that the Vulkan API already exposes (surface time and GPU > time). How to synchronize the application as those two clocks drift > around is outside the domain of this extension. Hi Keith, I did not mean you would be solving that problem. I meant that it would be good to figure out what people actually want from the API to be able to solve the problem themselves. Thanks, pq --Sig_/h_s_elgy2Hnmv1CzvVGAN70 Content-Type: application/pgp-signature Content-Description: OpenPGP digital signature -----BEGIN PGP SIGNATURE----- iQIzBAEBCAAdFiEEJQjwWQChkWOYOIONI1/ltBGqqqcFAltFsj4ACgkQI1/ltBGq qqcCVQ//QvK9R2NYqYEgfNnF6xoqOMW+33THa4mQBuCm1IMwv/x6FvknQNLKE3gZ ZjJJWReeeya7wisG1ru2uQ6c6nG/t6qBIk9JH+QgnhxnsFcvFrTxWJo03ZDLjHJt mNmqrpCT0tXrpqBxVy4fVmVD9ov0ayP43GKabXF5IFRDpsr53vcpR5m1uiwigZNm eRPJOuP+X8RKJNZXKsnudsSglH5sio6Q35+Xwfyi712/iNANMtdJGA3o48ICKz0n 8sahv1bzkl0SgvRTU+WVshomQE+qt3RtcDkmfmgeYXSHqB/ilTlN0coyQ3yvj9GI 9UPd+XZToVtwZQ3boGm7kfiWA17IPYvscFlCy7TRU0b68YPHD/bln+VqQ843bSUN H7I402zPd3lkUGkYyGrLUaB2QAD7dhglAfDdcAYclz3uvrRjFE2+2xDHlMZG/CqE jsjZqcwF2pzbjOY/TTG6ioIkGFGtenucUhrW1vSmiCqWgQ2sJ3bKRg7MFDbaXS3N Ubp1NBvsUkIOvkA32R0dpDEXV7pTYt4mDPcCL9tvVepg7NJHCIk/TWCVYwnAgY+N GnrD1UZo3oxNFQdFZA5ZGN2QIlZvpDtfmOnQP6tC/3NQDtYfrMVe2jmT3BW2vlQY L7nsfv/QSU4H5jtNdU+NUHy4BpRKJMCChgYw1tYpYW1E04QnNxA= =RbRg -----END PGP SIGNATURE----- --Sig_/h_s_elgy2Hnmv1CzvVGAN70-- --===============2078767744== Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: base64 Content-Disposition: inline X19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX18KbWVzYS1kZXYg bWFpbGluZyBsaXN0Cm1lc2EtZGV2QGxpc3RzLmZyZWVkZXNrdG9wLm9yZwpodHRwczovL2xpc3Rz LmZyZWVkZXNrdG9wLm9yZy9tYWlsbWFuL2xpc3RpbmZvL21lc2EtZGV2Cg== --===============2078767744==--