Re: [R300][PATCH] Add/fix COS SIN + FP fixes
Rune Petersen Ok commited. I didn't look too closely at this but I've a couple of comments. - COS looks too complicated broken. If you'd want to get 2 with a LOG2, you'd need 0.25 as source. But even using RCP instead, that's 5 instructions before performing the sine, for something you can easily do in two, using another constant (just 1 add + 1 cmp needed, if you use the right constants for the add). Maybe it's not that bad though, I don't know how many rgb and a slots it will actually consume, but still, are constant slots that rare? Second, you'd really need to do range reduction of the input, otherwise results will be very wrong for inputs outside [-pi, pi]. This would be true for taylor approximation too, of course, unless you do an infinite series :-). You wouldn't need to do that for SCS. Roland - Using Tomcat but need to do more? Need to support web services, security? Get stuff done quickly with pre-integrated technology to make your job easier. Download IBM WebSphere Application Server v.1.0.1 based on Apache Geronimo http://sel.as-us.falkag.net/sel?cmd=lnkkid=120709bid=263057dat=121642 -- ___ Dri-devel mailing list Dri-devel@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/dri-devel
Re: [R300][PATCH] Add/fix COS SIN + FP fixes
Roland Scheidegger wrote: Rune Petersen Ok commited. I didn't look too closely at this but I've a couple of comments. - COS looks too complicated broken. If you'd want to get 2 with a LOG2, you'd need 0.25 as source. But even using RCP instead, that's 5 instructions before performing the sine, for something you can easily do in two, using another constant (just 1 add + 1 cmp needed, if you use the right constants for the add). Maybe it's not that bad though, I don't know how many rgb and a slots it will actually consume, but still, are constant slots that rare? Second, you'd really need to do range reduction of the input, otherwise results will be very wrong for inputs outside [-pi, pi]. This would be true for taylor approximation too, of course, unless you do an infinite series :-). You wouldn't need to do that for SCS. Oh, and forgot to mention, you probably really want to use the higher precision variant by default. 12% max relative error (and even absolute it's still 6%) will likely be visible in some cases depending what the shader is doing. Even the enhanced version seems to miss opengl conformance (accurate to about 1 part in 10^5) by roughly a factor of 10, which stretches the meaning of about a bit probably already. You could also rely on the precision hint for fragment programs to switch to the faster version instead of a dri conf option (note though the spec explicitly states implementations are discouraged even in this case to perform optimizations which could have significant impact on the output). Roland - Using Tomcat but need to do more? Need to support web services, security? Get stuff done quickly with pre-integrated technology to make your job easier. Download IBM WebSphere Application Server v.1.0.1 based on Apache Geronimo http://sel.as-us.falkag.net/sel?cmd=lnkkid=120709bid=263057dat=121642 -- ___ Dri-devel mailing list Dri-devel@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/dri-devel
Re: Hown compile and install linux-agp-compat
On Tue, 2007-02-06 at 21:46 +, Sergio Monteiro Basto wrote: Does your kernel config enable agpgart and intel-agp as modules? no , is compiled into kernel CONFIG_AGP=y CONFIG_AGP_ALI=y CONFIG_AGP_ATI=y CONFIG_AGP_AMD=y CONFIG_AGP_AMD64=y CONFIG_AGP_INTEL=y CONFIG_AGP_NVIDIA=y CONFIG_AGP_SIS=y CONFIG_AGP_SWORKS=y CONFIG_AGP_VIA=y CONFIG_AGP_EFFICEON=y is required be compiled has module ? I use fedora stock kernels, which are more than updated (devel ones) , so I need to know If I need recompile all kernel with agpgart and intel-agp as modules ? Thanks, PS: I just finish to read yours README - Using Tomcat but need to do more? Need to support web services, security? Get stuff done quickly with pre-integrated technology to make your job easier. Download IBM WebSphere Application Server v.1.0.1 based on Apache Geronimo http://sel.as-us.falkag.net/sel?cmd=lnkkid=120709bid=263057dat=121642 -- ___ Dri-devel mailing list Dri-devel@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/dri-devel
Re: Hown compile and install linux-agp-compat
Sergio Monteiro Basto wrote: On Tue, 2007-02-06 at 21:46 +, Sergio Monteiro Basto wrote: Does your kernel config enable agpgart and intel-agp as modules? no , is compiled into kernel CONFIG_AGP=y CONFIG_AGP_ALI=y CONFIG_AGP_ATI=y CONFIG_AGP_AMD=y CONFIG_AGP_AMD64=y CONFIG_AGP_INTEL=y CONFIG_AGP_NVIDIA=y CONFIG_AGP_SIS=y CONFIG_AGP_SWORKS=y CONFIG_AGP_VIA=y CONFIG_AGP_EFFICEON=y is required be compiled has module ? I use fedora stock kernels, which are more than updated (devel ones) , so I need to know If I need recompile all kernel with agpgart and intel-agp as modules ? Yes, currently you need to do that. /Thomas Thanks, PS: I just finish to read yours README - Using Tomcat but need to do more? Need to support web services, security? Get stuff done quickly with pre-integrated technology to make your job easier. Download IBM WebSphere Application Server v.1.0.1 based on Apache Geronimo http://sel.as-us.falkag.net/sel?cmd=lnkkid=120709bid=263057dat=121642 -- ___ Dri-devel mailing list Dri-devel@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/dri-devel
Re: [R300][PATCH] Add/fix COS SIN + FP fixes
Roland Scheidegger wrote: Roland Scheidegger wrote: Rune Petersen Ok commited. I didn't look too closely at this but I've a couple of comments. - COS looks too complicated broken. If you'd want to get 2 with a LOG2, you'd need 0.25 as source. But even using RCP instead, that's 5 instructions before performing the sine, for something you can easily do in two, using another constant (just 1 add + 1 cmp needed, if you use the right constants for the add). Maybe it's not that bad though, I don't know how many rgb and a slots it will actually consume, but still, are constant slots that rare? Second, you'd really need to do range reduction of the input, otherwise results will be very wrong for inputs outside [-pi, pi]. This would be true for taylor approximation too, of course, unless you do an infinite series :-). You wouldn't need to do that for SCS. The mess of trying to get 2 from RCP was a brain fart on my part. And since I forgot the range reduction, I'll add PI*0.5 and then do the range reduction. And this time I will need a constant more (r300 has 16). Oh, and forgot to mention, you probably really want to use the higher precision variant by default. 12% max relative error (and even absolute it's still 6%) will likely be visible in some cases depending what the shader is doing. Even the enhanced version seems to miss opengl conformance (accurate to about 1 part in 10^5) by roughly a factor of 10, which stretches the meaning of about a bit probably already. You could also rely on the precision hint for fragment programs to switch to the faster version instead of a dri conf option (note though the spec explicitly states implementations are discouraged even in this case to perform optimizations which could have significant impact on the output). it helps to have the numbers. when making these decisions. Thank you for your feedback. Rune Petersen - Using Tomcat but need to do more? Need to support web services, security? Get stuff done quickly with pre-integrated technology to make your job easier. Download IBM WebSphere Application Server v.1.0.1 based on Apache Geronimo http://sel.as-us.falkag.net/sel?cmd=lnkkid=120709bid=263057dat=121642 -- ___ Dri-devel mailing list Dri-devel@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/dri-devel
