BuddhaShader, branch master First steps with OpenGL: A compute shader that renders a BuddhaBrot to an SSBO. Can also save the result to PNG for future viewing pleasure. https://git.grois.info/BuddhaShader/atom/?h=master 2018-03-25T10:23:40Z Increase image area slightly 2018-03-25T10:23:40Z Andreas Grois andi@grois.info 2018-03-25T10:23:40Z urn:sha1:06c38f755d6aca9a2c43e206f640422c477322bc More excluded circles. 2018-03-23T08:13:29Z Andreas Grois andi@grois.info 2018-03-23T08:13:29Z urn:sha1:f60384e1306cb66b0460ed46a38fe010ff6c427a Initial benchmark support. 2018-03-21T22:16:20Z Andreas Grois andi@grois.info 2018-03-21T22:16:20Z urn:sha1:cca3254becdf793b9335a1f21bcda2c0909f4d1a Finally no more manual stopwatch usage... Fix build error regarding debug log clock 2018-03-18T21:37:49Z Andreas Grois andi@grois.info 2018-03-18T21:37:49Z urn:sha1:0c7b45b4e84aa197ada7391007f7d1610c92476c Undo splitting of buffers in three. Makes buffer access much faster 2018-03-18T20:11:39Z Andreas Grois andi@grois.info 2018-03-18T20:11:39Z urn:sha1:dc193156a82a80cc8d2321cf065019035855516f Not kidding here. For the default parameters this increased the maximum pixel brightness in the image by a factor of 2.25. This has the drawback that the maximum possible image size got reduced, but hey, there's a command line switch to ignore all size limits ;-) Move totaliterations calculation to CPU. This frees 4 VGPRs. 2018-03-18T19:45:26Z Andreas Grois andi@grois.info 2018-03-18T19:45:26Z urn:sha1:db2ea861c688aadf59fc35ff6cfca69149a1a94c Now the code is back to the limit of 32 VGPRs without the need to directly operate on the state buffer. This means that now it's bound by memory access. Undo change to directly work on buffer. Causes about 30% slowdown... 2018-03-18T16:19:33Z Andreas Grois andi@grois.info 2018-03-18T16:19:33Z urn:sha1:c6ba30d76aca396ce5a3975f4625e05e8cf915ee Add option to skip short orbits. Add option to print debug output. 2018-03-18T15:24:50Z Andreas Grois andi@grois.info 2018-03-18T15:24:50Z urn:sha1:385dd0dcf8fd003db604355341b00baa1fe1c1a0 Adjust default workgroup sizes to better match recommended values. 2018-03-17T21:39:45Z Andreas Grois andi@grois.info 2018-03-17T21:39:45Z urn:sha1:f3f67518d7eb74c868b523851ec482cd2177c3ce AMD recommends a local workgroup size of 256. Remove layout specifier from struct. Seems it's not allowed after all. 2018-03-17T19:52:50Z Andreas Grois andi@grois.info 2018-03-17T19:52:50Z urn:sha1:c2018354129a4a6eff1649eaba4d99756b537ed3