From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:35626) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1fbFLj-0001Qc-BS for qemu-devel@nongnu.org; Thu, 05 Jul 2018 21:15:54 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1fbFLi-0000QK-56 for qemu-devel@nongnu.org; Thu, 05 Jul 2018 21:15:51 -0400 Date: Fri, 6 Jul 2018 11:03:15 +1000 From: David Gibson Message-ID: <20180706010315.GI3450@umbus.fritz.box> References: <20180703151732.29843-1-richard.henderson@linaro.org> <20180703151732.29843-8-richard.henderson@linaro.org> <128b92a6-7b0e-5e27-2bad-63da14bb3a6a@linaro.org> <1106207A-1C28-4146-9F94-F9747BF8B345@gmail.com> MIME-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha256; protocol="application/pgp-signature"; boundary="WHz+neNWvhIGAO8A" Content-Disposition: inline In-Reply-To: <1106207A-1C28-4146-9F94-F9747BF8B345@gmail.com> Subject: Re: [Qemu-devel] [PATCH 7/7] target/ppc: Use non-arithmetic conversions for fp load/store List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Programmingkid Cc: Richard Henderson , qemu-devel@nongnu.org, qemu-ppc@nongnu.org --WHz+neNWvhIGAO8A Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Thu, Jul 05, 2018 at 12:51:00PM -0400, Programmingkid wrote: >=20 > > On Jul 5, 2018, at 12:48 PM, Richard Henderson wrote: > >=20 > > On 07/05/2018 09:31 AM, Programmingkid wrote: > >>> On Jul 3, 2018, at 11:17 AM, Richard Henderson wrote: > >>>=20 > >>> Memory operations have no side effects on fp state. > >>> The use of a "real" conversions between float64 and float32 > >>> would raise exceptions for SNaN and out-of-range inputs. > >>=20 > >> Would you have any documentation that tells us about converting > >> between 64 bit and 32 bit floating points? > >=20 > > Spelled out right at the beginning of sections 4.6 (load) and 4.7 (stor= e) of > > Book 1 of the Power ISA manual (version 3.0B) [0]. > >=20 > > I've double-checked vs RISU[1] testing of LFS and STFS, with master tra= ces > > generated on Power 8 ppc64le, so I don't see anything immediately wrong= with > > the patch. But I haven't had time to look further than that. > >=20 > >=20 > > r~ > >=20 > >=20 > > [0] https://openpowerfoundation.org/?resource_lib=3Dpower-isa-version-3= -0 > > [1] https://git.linaro.org/people/peter.maydell/risu.git >=20 > Thank you for the documentation. My guess is there are differences > between the PowerPC and Power 8 implementations. That seems very, very unlikely to me. > PowerPC is big > endian. Would you be able to do your testing again with your Power 8 > CPU in big endian mode? >=20 >=20 --=20 David Gibson | I'll have my music baroque, and my code david AT gibson.dropbear.id.au | minimalist, thank you. NOT _the_ _other_ | _way_ _around_! http://www.ozlabs.org/~dgibson --WHz+neNWvhIGAO8A Content-Type: application/pgp-signature; name="signature.asc" -----BEGIN PGP SIGNATURE----- iQIzBAEBCAAdFiEEdfRlhq5hpmzETofcbDjKyiDZs5IFAls+v9EACgkQbDjKyiDZ s5Jwqw//U+65dZ2+DHx6/4nlAAT5Dp2vopAP1wYgqp8juUuP3ouoCesitcqSQaEi 8GhdmckGWgQjDp0E800hhyFDBg7ypxyvN7zIlKwQRvvCxj0mTmKUyLjKABEhz3nk YqdyfkuoKVR2Tnyx4lO7xHD4mRGaS9uvxgbZhjIltmV41WVtHUJcV0fFjIT58lHF mN81YuZm8kYgkSHst5AFGndFn6ewsRQCKAuyqUp0ALL8iGJAtRUWhv6UkP3/pXkt j0w8ok1yYKVC1/QlZHkSP1oiRSsdbIqYylXz2WdGHULOYsH1WoQBLUoWOBAA26lD 756GAT/U0vZctFj1zmbSL/sP7zLxRMLEVDcmJE6mVxF+2tvz1vPSyVWvwc2QH6qY WkUtAcxO/BsQLeXQEN6lVS1FXlYWFlgKzk/jdB/xRCc89ueukzEY4pJQtVwieBXS mYE8YzL4D+B94o0KdFIz6c6UM5L2yh3mZchH6y1YULKWJlgnZ9JTJoowqCoYUeGq pqAE/djjDofLiJIt54+YsloUX5assmWMWXgxRvrTwrE3dOjtrUKpSmhZrmdSCJBN C/xnWHR/KnyB+jY4X9sAoG+SyctF+5L1U/m0Jc5EHuY1WA4HSjmVz7p044rdY4Bp LEkmT1/asx/y8N9AIh9uv0+nrMFpd5OSoh+MLbdlJRXIR8xCyh0= =zh7W -----END PGP SIGNATURE----- --WHz+neNWvhIGAO8A--