Re: [RFC] Deprecate AGP GART support for Radeon/Nouveau/TTM
On Fri, May 22, 2020 at 6:41 AM Christian König wrote: > > Am 20.05.20 um 18:18 schrieb Alex Deucher: > > On Wed, May 20, 2020 at 10:43 AM Christian König > > wrote: > >> Am 13.05.20 um 13:03 schrieb Christian König: > >>> Unfortunately AGP is still to widely used as we could just drop support > >>> for using its GART. > >>> > >>> Not using the AGP GART also doesn't mean a loss in functionality since > >>> drivers will just fallback to the driver specific PCI GART. > >>> > >>> For now just deprecate the code and don't enable the AGP GART in TTM even > >>> when general AGP support is available. > >> So I've used an ancient system (32bit) to setup a test box for this. > >> > >> > >> The first GPU I could test is an RV280 (Radeon 9200 PRO) which is easily > >> 15 years old. > >> > >> What happens in AGP mode is that glxgears shows artifacts during > >> rendering on this system. > >> > >> In PCI mode those rendering artifacts are gone and glxgears seems to > >> draw everything correctly now. > >> > >> Performance is obviously not comparable, cause in AGP we don't render > >> all triangles correctly. > >> > >> > >> The second GPU I could test is an RV630 PRO (Radeon HD 2600 PRO AGP) > >> which is more than 10 years old. > >> > >> As far as I can tell this one works in both AGP and PCIe mode perfectly > >> fine. > >> > >> Since this is only a 32bit system I couldn't really test any OpenGL game > >> that well. > >> > >> But for glxgears switching from AGP to PCIe mode seems to result in a > >> roughly 5% performance drop. > >> > >> The surprising reason for this is not the better TLB performance, but > >> the lack of USWC support for the PCIe GART in radeon. > >> > >> > >> So if anybody wants to get his hands dirty and squeeze a bit more > >> performance out of the old hardware, porting USWC from amdgpu to radeon > >> shouldn't be to much of a problem. > > We do support USWC on radeon, although I think we had separate flags > > for cached and WC. That said we had a lot of problems with WC on 32 > > bit (see radeon_bo_create()). The other problem is that, at least on > > the really old radeons, the PCI gart didn't support snooped and > > unsnooped. It was always snooped. It wasn't until pcie that the gart > > hw got support for both. For AGP, the expectation was that AGP > > provided the uncached memory. > > Oh, indeed. I didn't remembered that. > > Interesting is that in this case I have no idea where the performance > difference is coming from. > > > > >> > >> Summing it up I'm still leaning towards disabling AGP completely by > >> default for radeon and deprecate it in TTM as well. > >> > >> Thoughts? Especially Alex what do you think. > > Works for me. > > I will take that as an rb and commit at least the first patch. Yeah, Reviewed-by: Alex Deucher > > Thanks, > Christian. > > > > > Alex > ___ dri-devel mailing list dri-devel@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/dri-devel
Re: [RFC] Deprecate AGP GART support for Radeon/Nouveau/TTM
On 2020-05-22 12:40 p.m., Christian König wrote: > Am 20.05.20 um 18:25 schrieb Michel Dänzer: >> On 2020-05-20 4:43 p.m., Christian König wrote: >>> Am 13.05.20 um 13:03 schrieb Christian König: Unfortunately AGP is still to widely used as we could just drop support for using its GART. Not using the AGP GART also doesn't mean a loss in functionality since drivers will just fallback to the driver specific PCI GART. For now just deprecate the code and don't enable the AGP GART in TTM even when general AGP support is available. >>> So I've used an ancient system (32bit) to setup a test box for this. >>> >>> >>> The first GPU I could test is an RV280 (Radeon 9200 PRO) which is easily >>> 15 years old. >>> >>> What happens in AGP mode is that glxgears shows artifacts during >>> rendering on this system. >>> >>> In PCI mode those rendering artifacts are gone and glxgears seems to >>> draw everything correctly now. >>> >>> Performance is obviously not comparable, cause in AGP we don't render >>> all triangles correctly. >>> >>> >>> The second GPU I could test is an RV630 PRO (Radeon HD 2600 PRO AGP) >>> which is more than 10 years old. >>> >>> As far as I can tell this one works in both AGP and PCIe mode perfectly >>> fine. >>> >>> Since this is only a 32bit system I couldn't really test any OpenGL game >>> that well. >>> >>> But for glxgears switching from AGP to PCIe mode seems to result in a >>> roughly 5% performance drop. >>> >>> The surprising reason for this is not the better TLB performance, but >>> the lack of USWC support for the PCIe GART in radeon. >> I suspect the main reason it's only 5% is that PCIe GART page tables are >> stored in VRAM, so they don't need to be fetched across the PCIe link >> (and presumably it has more than one TLB entry as well). The difference >> is much bigger with native AGP ASICs with PCI GART. > > Do you have some hardware you could give that a try on? As I mentioned before, I tested this many times on my AGP PowerBooks back in the day. The result was always a similar, big hit with PCI GART vs AGP (even just 1x). I haven't seen any reason to believe this has changed. > While I agree that it means a performance regression, this is a rather > high motivation to go ahead with at least the first patch. I totally agree with the benefits, I just want everyone to be honest and clear about the performance hit with native AGP Radeons, which already have very weak performance by today's standards even with AGP. -- Earthling Michel Dänzer | https://redhat.com Libre software enthusiast | Mesa and X developer ___ dri-devel mailing list dri-devel@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/dri-devel
Re: [RFC] Deprecate AGP GART support for Radeon/Nouveau/TTM
Am 20.05.20 um 18:18 schrieb Alex Deucher: On Wed, May 20, 2020 at 10:43 AM Christian König wrote: Am 13.05.20 um 13:03 schrieb Christian König: Unfortunately AGP is still to widely used as we could just drop support for using its GART. Not using the AGP GART also doesn't mean a loss in functionality since drivers will just fallback to the driver specific PCI GART. For now just deprecate the code and don't enable the AGP GART in TTM even when general AGP support is available. So I've used an ancient system (32bit) to setup a test box for this. The first GPU I could test is an RV280 (Radeon 9200 PRO) which is easily 15 years old. What happens in AGP mode is that glxgears shows artifacts during rendering on this system. In PCI mode those rendering artifacts are gone and glxgears seems to draw everything correctly now. Performance is obviously not comparable, cause in AGP we don't render all triangles correctly. The second GPU I could test is an RV630 PRO (Radeon HD 2600 PRO AGP) which is more than 10 years old. As far as I can tell this one works in both AGP and PCIe mode perfectly fine. Since this is only a 32bit system I couldn't really test any OpenGL game that well. But for glxgears switching from AGP to PCIe mode seems to result in a roughly 5% performance drop. The surprising reason for this is not the better TLB performance, but the lack of USWC support for the PCIe GART in radeon. So if anybody wants to get his hands dirty and squeeze a bit more performance out of the old hardware, porting USWC from amdgpu to radeon shouldn't be to much of a problem. We do support USWC on radeon, although I think we had separate flags for cached and WC. That said we had a lot of problems with WC on 32 bit (see radeon_bo_create()). The other problem is that, at least on the really old radeons, the PCI gart didn't support snooped and unsnooped. It was always snooped. It wasn't until pcie that the gart hw got support for both. For AGP, the expectation was that AGP provided the uncached memory. Oh, indeed. I didn't remembered that. Interesting is that in this case I have no idea where the performance difference is coming from. Summing it up I'm still leaning towards disabling AGP completely by default for radeon and deprecate it in TTM as well. Thoughts? Especially Alex what do you think. Works for me. I will take that as an rb and commit at least the first patch. Thanks, Christian. Alex ___ dri-devel mailing list dri-devel@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/dri-devel
Re: [RFC] Deprecate AGP GART support for Radeon/Nouveau/TTM
Am 20.05.20 um 18:25 schrieb Michel Dänzer: On 2020-05-20 4:43 p.m., Christian König wrote: Am 13.05.20 um 13:03 schrieb Christian König: Unfortunately AGP is still to widely used as we could just drop support for using its GART. Not using the AGP GART also doesn't mean a loss in functionality since drivers will just fallback to the driver specific PCI GART. For now just deprecate the code and don't enable the AGP GART in TTM even when general AGP support is available. So I've used an ancient system (32bit) to setup a test box for this. The first GPU I could test is an RV280 (Radeon 9200 PRO) which is easily 15 years old. What happens in AGP mode is that glxgears shows artifacts during rendering on this system. In PCI mode those rendering artifacts are gone and glxgears seems to draw everything correctly now. Performance is obviously not comparable, cause in AGP we don't render all triangles correctly. The second GPU I could test is an RV630 PRO (Radeon HD 2600 PRO AGP) which is more than 10 years old. As far as I can tell this one works in both AGP and PCIe mode perfectly fine. Since this is only a 32bit system I couldn't really test any OpenGL game that well. But for glxgears switching from AGP to PCIe mode seems to result in a roughly 5% performance drop. The surprising reason for this is not the better TLB performance, but the lack of USWC support for the PCIe GART in radeon. I suspect the main reason it's only 5% is that PCIe GART page tables are stored in VRAM, so they don't need to be fetched across the PCIe link (and presumably it has more than one TLB entry as well). The difference is much bigger with native AGP ASICs with PCI GART. Do you have some hardware you could give that a try on? I mean the first card I put into the system obviously only worked correctly with AGP disabled. While I agree that it means a performance regression, this is a rather high motivation to go ahead with at least the first patch. Christian. ___ dri-devel mailing list dri-devel@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/dri-devel
Re: [RFC] Deprecate AGP GART support for Radeon/Nouveau/TTM
Hi, Christian, On Wed, 20 May 2020 at 16:00, Christian König wrote: > > So I've used an ancient system (32bit) to setup a test box for this. > > > The first GPU I could test is an RV280 (Radeon 9200 PRO) which is easily > 15 years old. Oh, I have one of those in box somewhere, but no AGP machine to install it (yet). > What happens in AGP mode is that glxgears shows artifacts during > rendering on this system. > > In PCI mode those rendering artifacts are gone and glxgears seems to > draw everything correctly now. > > Performance is obviously not comparable, cause in AGP we don't render > all triangles correctly. I agree, correctness before performance, always. > The second GPU I could test is an RV630 PRO (Radeon HD 2600 PRO AGP) > which is more than 10 years old. > > As far as I can tell this one works in both AGP and PCIe mode perfectly > fine. > > Since this is only a 32bit system I couldn't really test any OpenGL game > that well. I usually test with my distro's (Debian or Ubuntu, in my case) games. For example, I used Nexuiz when wiring up the shader cache on r300g. > But for glxgears switching from AGP to PCIe mode seems to result in a > roughly 5% performance drop. > > The surprising reason for this is not the better TLB performance, but > the lack of USWC support for the PCIe GART in radeon. > > So if anybody wants to get his hands dirty and squeeze a bit more > performance out of the old hardware, porting USWC from amdgpu to radeon > shouldn't be to much of a problem. Well, FWIW, I would argue that a regression in performance, if avoidable, should be avoided. I have not nearly enough knowledge of the driver to do it myself, but I'll glady test any patches, on both x86-64 (Radeon Xpress 1250) and ppc32 (Mobility Radeon 9550). Cheers, Rui ___ dri-devel mailing list dri-devel@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/dri-devel
Re: [RFC] Deprecate AGP GART support for Radeon/Nouveau/TTM
On 2020-05-20 4:43 p.m., Christian König wrote: > Am 13.05.20 um 13:03 schrieb Christian König: >> Unfortunately AGP is still to widely used as we could just drop >> support for using its GART. >> >> Not using the AGP GART also doesn't mean a loss in functionality since >> drivers will just fallback to the driver specific PCI GART. >> >> For now just deprecate the code and don't enable the AGP GART in TTM >> even when general AGP support is available. > > So I've used an ancient system (32bit) to setup a test box for this. > > > The first GPU I could test is an RV280 (Radeon 9200 PRO) which is easily > 15 years old. > > What happens in AGP mode is that glxgears shows artifacts during > rendering on this system. > > In PCI mode those rendering artifacts are gone and glxgears seems to > draw everything correctly now. > > Performance is obviously not comparable, cause in AGP we don't render > all triangles correctly. > > > The second GPU I could test is an RV630 PRO (Radeon HD 2600 PRO AGP) > which is more than 10 years old. > > As far as I can tell this one works in both AGP and PCIe mode perfectly > fine. > > Since this is only a 32bit system I couldn't really test any OpenGL game > that well. > > But for glxgears switching from AGP to PCIe mode seems to result in a > roughly 5% performance drop. > > The surprising reason for this is not the better TLB performance, but > the lack of USWC support for the PCIe GART in radeon. I suspect the main reason it's only 5% is that PCIe GART page tables are stored in VRAM, so they don't need to be fetched across the PCIe link (and presumably it has more than one TLB entry as well). The difference is much bigger with native AGP ASICs with PCI GART. -- Earthling Michel Dänzer | https://redhat.com Libre software enthusiast | Mesa and X developer ___ dri-devel mailing list dri-devel@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/dri-devel
Re: [RFC] Deprecate AGP GART support for Radeon/Nouveau/TTM
On Wed, May 20, 2020 at 10:43 AM Christian König wrote: > > Am 13.05.20 um 13:03 schrieb Christian König: > > Unfortunately AGP is still to widely used as we could just drop support for > > using its GART. > > > > Not using the AGP GART also doesn't mean a loss in functionality since > > drivers will just fallback to the driver specific PCI GART. > > > > For now just deprecate the code and don't enable the AGP GART in TTM even > > when general AGP support is available. > > So I've used an ancient system (32bit) to setup a test box for this. > > > The first GPU I could test is an RV280 (Radeon 9200 PRO) which is easily > 15 years old. > > What happens in AGP mode is that glxgears shows artifacts during > rendering on this system. > > In PCI mode those rendering artifacts are gone and glxgears seems to > draw everything correctly now. > > Performance is obviously not comparable, cause in AGP we don't render > all triangles correctly. > > > The second GPU I could test is an RV630 PRO (Radeon HD 2600 PRO AGP) > which is more than 10 years old. > > As far as I can tell this one works in both AGP and PCIe mode perfectly > fine. > > Since this is only a 32bit system I couldn't really test any OpenGL game > that well. > > But for glxgears switching from AGP to PCIe mode seems to result in a > roughly 5% performance drop. > > The surprising reason for this is not the better TLB performance, but > the lack of USWC support for the PCIe GART in radeon. > > > So if anybody wants to get his hands dirty and squeeze a bit more > performance out of the old hardware, porting USWC from amdgpu to radeon > shouldn't be to much of a problem. We do support USWC on radeon, although I think we had separate flags for cached and WC. That said we had a lot of problems with WC on 32 bit (see radeon_bo_create()). The other problem is that, at least on the really old radeons, the PCI gart didn't support snooped and unsnooped. It was always snooped. It wasn't until pcie that the gart hw got support for both. For AGP, the expectation was that AGP provided the uncached memory. > > > Summing it up I'm still leaning towards disabling AGP completely by > default for radeon and deprecate it in TTM as well. > > Thoughts? Especially Alex what do you think. Works for me. Alex ___ dri-devel mailing list dri-devel@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/dri-devel
Re: [RFC] Deprecate AGP GART support for Radeon/Nouveau/TTM
Am 13.05.20 um 13:03 schrieb Christian König: Unfortunately AGP is still to widely used as we could just drop support for using its GART. Not using the AGP GART also doesn't mean a loss in functionality since drivers will just fallback to the driver specific PCI GART. For now just deprecate the code and don't enable the AGP GART in TTM even when general AGP support is available. So I've used an ancient system (32bit) to setup a test box for this. The first GPU I could test is an RV280 (Radeon 9200 PRO) which is easily 15 years old. What happens in AGP mode is that glxgears shows artifacts during rendering on this system. In PCI mode those rendering artifacts are gone and glxgears seems to draw everything correctly now. Performance is obviously not comparable, cause in AGP we don't render all triangles correctly. The second GPU I could test is an RV630 PRO (Radeon HD 2600 PRO AGP) which is more than 10 years old. As far as I can tell this one works in both AGP and PCIe mode perfectly fine. Since this is only a 32bit system I couldn't really test any OpenGL game that well. But for glxgears switching from AGP to PCIe mode seems to result in a roughly 5% performance drop. The surprising reason for this is not the better TLB performance, but the lack of USWC support for the PCIe GART in radeon. So if anybody wants to get his hands dirty and squeeze a bit more performance out of the old hardware, porting USWC from amdgpu to radeon shouldn't be to much of a problem. Summing it up I'm still leaning towards disabling AGP completely by default for radeon and deprecate it in TTM as well. Thoughts? Especially Alex what do you think. Regards, Christian. ___ dri-devel mailing list dri-devel@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/dri-devel
