Path: ...!news.mixmin.net!eternal-september.org!feeder3.eternal-september.org!news.eternal-september.org!.POSTED!not-for-mail From: Tim Rentsch Newsgroups: comp.lang.c Subject: Re: filling area by color atack safety - worst memory size Date: Thu, 11 Apr 2024 22:09:51 -0700 Organization: A noiseless patient Spider Lines: 56 Message-ID: <86o7afyxnk.fsf@linuxsc.com> References: <86h6h3nvyz.fsf@linuxsc.com> <865xxiok09.fsf@linuxsc.com> <20240319131842.00002138@yahoo.com> <86o7b9ms7d.fsf@linuxsc.com> <20240320115416.00001ab5@yahoo.com> <86zfusltwp.fsf@linuxsc.com> <20240324193352.000062e9@yahoo.com> <86jzlrk0f6.fsf@linuxsc.com> <20240405173033.00006145@yahoo.com> <868r1k1uq8.fsf@linuxsc.com> <20240411152033.00007173@yahoo.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Injection-Date: Fri, 12 Apr 2024 07:09:53 +0200 (CEST) Injection-Info: dont-email.me; posting-host="c97bd3546ab5d223656b076d0b7c627f"; logging-data="2301891"; mail-complaints-to="abuse@eternal-september.org"; posting-account="U2FsdGVkX19JfxVZVLbEUm0vVZdbMiSD6FluonZ0toY=" User-Agent: Gnus/5.11 (Gnus v5.11) Emacs/22.4 (gnu/linux) Cancel-Lock: sha1:C06UOlm2dypCDKbnG11rpKKD8to= sha1:ULBWMkwzBjxm6NkHu1CBy6c2XF4= Bytes: 3163 Michael S writes: > On Wed, 10 Apr 2024 19:47:11 -0700 > Tim Rentsch wrote: > >> Stack-based methods tend to do well on long skinny patterns and >> tend to do not as well on fatter patterns such as circles or >> squares. The fractal pattern is ideal for a stack-based method. >> Conversely, patterns that are mostly solid shapes don't fare as >> well under stack-based methods, at least not the ones that have >> been posted in this thread, and also they tend to use more memory >> in those cases. > > Indeed, with solid shapes it uses more memory. But at least in my > tests on my hardware with this sort of shapes it is easily faster > than anything else. The difference vs the best of the rest is > especially big at 4K images on AMD Zen3 based hardware, but even on > Intel Skylake which generally serves as equalizer between different > algorithms, the speed advantage of 2x2 stack is significant. This comment makes me wonder if I should post my timing results. Maybe I will (and including an appropriate disclaimer). I do timings over these sizes: 25 x 19 19 x 25 200 x 200 1280 x 760 760 x 1280 1920 x 1080 1080 x 1920 3840 x 2160 2160 x 3840 4096 x 4096 38400 x 21600 21600 x 38400 32767 x 32767 32768 x 32768 with these patterns: fractal slalom rotated slalom horizontal snake and vertical snake cross in cross donut aka ellipse with hole entire field starting from center If you have other patterns to suggest that would be great, I can try to incorporate them (especially if there is code to generate the pattern). Patterns are allowed to include a nominal start point, otherwise I can make an arbitrary choice and assign one.