Re: [Pixman] New separable filter generator

2014-06-18 20:50 GMT+02:00 Bill Spitzak : > This patch is for Cairo but I now feel the correct solution is to place > this in pixman (and thus into XRender). Although the patch is for Cairo > it primarily consists of a replacement for pixman_generate_separable_filter > and changes to how it is call

Re: [Pixman] Prototype JIT compiler

2014-02-10 19:45 GMT+01:00 Søren Sandmann : > Potential downsides is that it's a huge template based C++ library, and > last time I looked at it (which was a long time ago), the SIMD support > wasn't that convincing. I also suspect that it will be difficult to > generate really top-notch code with

Re: [Pixman] Latest GIT source for 'pixman-sse2.c'

2013/10/5 John Emmas : > From experience, I STRONGLY SUSPECT that the error is caused by these lines > at the top of macro #2:- > > #define BILINEAR_INTERPOLATE_ONE_PIXEL_HELPER(pix, phase) \ > do {\ > __m128i xmm_wh, xmm_a, xmm_

Re: [Pixman] Image resampling [PATCH 0/6]

2012/11/27 Bill Spitzak : > Cairo may want to pre-scale the source surface by an integer factor using a > box filter so that the sampling filters are not so large. It would then have > to keep this scaled image around until either the source image is dirtied or > a transform requiring a different s

Re: [Pixman] Image resampling [PATCH 0/6]

2012/11/24 Søren Sandmann : > Hi, > > Reviewing the supersampling patch here: > >http://cgit.freedesktop.org/~ajohnson/pixman/log/?h=supersampling > > I wasn't happy with either the performance and image quality, and I > realized that the whole supersampling approach just isn't going to > fly.

Re: [Pixman] Image downscaling

W dniu 22 lipca 2011 21:45 użytkownik Bill Spitzak napisał: > The ideal/slow solution is this: > [SNIP] Thanks, this cleared things up a lot for me. I'll have a shot at implementing this after GSoC (if no one else does it by then). Regards, Krzysztof _

Re: [Pixman] Image downscaling

W dniu 22 lipca 2011 14:44 użytkownik Jonathan Morton napisał: > On Fri, 2011-07-22 at 04:51 +0200, Krzysztof Kosiński wrote: > 1) Trilinear or tricubic filtering on a mipmapped image.  The mipmaps > are generated by box-filtering 2x2 pixels at a time, which is trivial to > compute.  

[Pixman] Image downscaling

Hello Since Inkscape trunk switched to Cairo for all rendering, the lack of real image downscaling in Pixman is starting to affect users. https://bugs.launchpad.net/inkscape/+bug/804162 Some time ago I tried implementing supersampling in Pixman. The approach I took was to automatically increase

Re: [Pixman] [PATCH] sse2: Skip src pixels that are zero in sse2_composite_over_8888_n_8888()

2010/12/22 Rodrigo Kumpera : > This patch doesn't handle cases where alpha is zero but components are not. > Not sure > if this is either possible or frequent. Pixman uses premultiplied alpha so such values are not possible. Regards, Krzysztof ___ Pixma

Re: [Pixman] How pixman_implementation_t is getting free

2010/10/29 kb pachauri : > Hi, > I am going through pixman code for developing pixman with opencl > implementation. > I have made a little success i.e. will submit a patch sometime next week for > review. > But i am not getting how pixman_implementation_t is getting free..(where?) > Thanks in advan

Re: [Pixman] [cairo] Cairo roadmap

W dniu 28 września 2010 02:16 użytkownik Andrea Canciani napisał: > On Tue, Sep 28, 2010 at 1:27 AM, Krzysztof Kosiński > wrote: >> W dniu 27 września 2010 23:42 użytkownik Andrea Canciani >> napisał: >>>> 1. Floating point coordinates in Pixman. >>>

Re: [Pixman] [cairo] Cairo roadmap

W dniu 27 września 2010 23:42 użytkownik Andrea Canciani napisał: >> 1. Floating point coordinates in Pixman. > Do you mean in the API? Or for internal computations? Both are required to avoid the rendering corruptions seen with large gradients. >> 2. Gradient precision improvements. > I have a

Re: [Pixman] [PATCH 0/4] Meet the FPU-based implementation of the core pixel pipeline

2010/9/21 Dmitri Vorobiev : > Recently, there was a debate about using floating-point hardware > for a Pixman implementation instead of the fixed point code. In > our company, we have developed an FPU-based implementation of the > core pixel pipeline, including support for all pixel formats and > c

Re: [Pixman] [cairo] Supersampling - 2nd attempt

2010/8/16 Bill Spitzak : > The problem I am having is that this does not match how filtering of > transforms is done in any image processing software I am familiar with. > > This is how all software I am familiar with works, this replaces the three > steps you show above: > >        - Figure out th

Re: [Pixman] [cairo] Floating point API in Pixman

So what is the bottom line? Should we have two versions of all code, one using float and one using pixman_fixed_t, or is replacing pixman_fixed_t with float sufficient? How much slower is softfloat - a factor of 5, 15 or 500? Another thing we have to take into account is that new versions of Cair

Re: [Pixman] [cairo] Supersampling - 2nd attempt

2010/8/13 Arjen Nienhuis : > I think any algorithm will show some sort of aliasing for some images. Look > at this page for some comparisons: > http://www.xs4all.nl/~bvdwolf/main/foto/down_sample/down_sample.htm > > The algorithm that he implemented is certainly not the best, but its > certainly be

[Pixman] Supersampling - 2nd attempt

Hello This is the second attempt at bitmap supersampling in Pixman. Changes: 1. There is a new fast path flag called FAST_PATH_NO_SUPERSAMPLING (self-explanatory) 2. No divisions in inner loops, but this causes a proliferation of variables. Note: using float or double for transformation matrices

Re: [Pixman] [cairo] Floating point API in Pixman

W dniu 12 sierpnia 2010 00:50 użytkownik Arjen Nienhuis napisał: > The gradients in your test case > (https://bugs.freedesktop.org/show_bug.cgi?id=29470) can be rendered fine > with just 16.16 fixed point math. It's just that the implementation in > pixman is not very accurate. I guess it's accumu

Re: [Pixman] [cairo] Floating point API in Pixman

W dniu 11 sierpnia 2010 04:06 użytkownik Soeren Sandmann napisał: > How large are the images that inkscape needs to deal with? There is > currently a limitation in cairo of +/- 2^23, which is about +/- 8.3 > million. This is also about the approximate range of integers that can > be stored exactly

Re: [Pixman] [cairo] Supersampling - 1st attempt

W dniu 11 sierpnia 2010 03:18 użytkownik Soeren Sandmann napisał: >> 2. Shouldn't we use nearest-neighbor sampling to obtain subpixels? > > That's determined by what filter is being used in the call > bits_fetch_pixel_filtered(). So if you call > >        pixman_image_set_filter() > > with FILTER_

Re: [Pixman] [cairo] Gradient rendering seriously broken

W dniu 10 sierpnia 2010 07:56 użytkownik Soeren Sandmann napisał: > And then Krzysztof asks for more details about the algorithm and which > file interpolation happens in. > > Frankly, I'm not impressed. I did not receive the mail you've mentioned, because I subscribed to the list only after it w

Re: [Pixman] [cairo] Better quality downsampling in cairo/pixman

Trying to resurrect this topic again... Can someone tell me in what file is the interpolation code? Regards, Krzysztof ___ Pixman mailing list Pixman@lists.freedesktop.org http://lists.freedesktop.org/mailman/listinfo/pixman

Re: [Pixman] [cairo] Better quality downsampling in cairo/pixman

use Cairo bitmap scaling not good enough for Inkscape's needs. In particular, I want to use it when resizing intermediate renderings before applying fixed resolution filters. Regards, Krzysztof Kosiński ___ Pixman mailing list Pixman@lists.freede