Steven Robertson
e106524701
Fix code in comment
2011-12-08 13:24:10 -05:00
Steven Robertson
e006ec1915
Slight tweak to clamp thresholds
2011-12-08 12:13:58 -05:00
Steven Robertson
b73461132c
Use consts for image size instead of immediates.
...
This saves us from having to recompile if the frame size changes.
2011-12-08 12:07:22 -05:00
Steven Robertson
084a65c615
Go back to using global accum for now
2011-12-08 11:50:46 -05:00
Steven Robertson
df8100d1f4
Use new mad.cc instruction in MWC
2011-12-08 11:49:31 -05:00
Steven Robertson
094df0ae21
Name the variation templates for debugging
2011-12-08 11:48:38 -05:00
Steven Robertson
e79d9a58fd
Fix cschden, cothden variations
2011-12-07 13:41:45 -05:00
erik
5ce5763da7
changed sense (and name) of values for affine xforms to match smoulder renders.
2011-11-23 07:54:48 -07:00
Steven Robertson
22fdc98128
Fix point swapping.
2011-11-20 10:08:13 -05:00
erik
efd261bd5b
fixes related to interpolation of palettes; hsv interpolation now goes
...
the 'short way' around the hue circle, and the correct palette is now
chosen when > 2 palettes are present in the knots.
2011-11-14 19:12:41 -07:00
Steven Robertson
0f848b8bb8
Dither color when packing for deferred write.
2011-11-12 11:06:44 -05:00
Steven Robertson
6d1c81486c
Don't inline catmull_rom for much faster compiles.
2011-11-12 11:05:44 -05:00
Steven Robertson
24c0c8ee56
Fix some color foibles (more yet remain)
2011-11-12 10:42:02 -05:00
Steven Robertson
9ef5363652
Fix dumb overflow bug
2011-11-11 17:54:33 -05:00
Steven Robertson
eb43b151dc
Deferred writeback.
2011-11-11 17:37:27 -05:00
Steven Robertson
05e1d08681
Add -1-skipping to sort.
2011-11-11 17:34:43 -05:00
Steven Robertson
54f411878b
Experiments with multi-pass sort (still has bugs)
2011-11-10 10:49:35 -05:00
Steven Robertson
13842196ea
Generalize the sort.
2011-11-09 12:00:59 -05:00
Steven Robertson
3147fd40d2
Support CUDA 4.1. Split filtering into new module.
...
The new toolkit generates code for filtering which uses too many
registers, so this change splits filtering into its own module so that
it can have separate register usage limits during compiling. As a bonus,
this should improve startup time in general, since the filtering code
is now fixed and does not need to be recompiled.
2011-11-08 14:38:45 -05:00
Steven Robertson
cea91d75bf
A very fast key-only radix sort.
2011-11-07 23:23:20 -05:00
Steven Robertson
7815c13ba4
Fix camera offset WRT flam3
2011-11-06 10:01:26 -05:00
erik
5179c98254
fixed flawed lazysusan variation. added whorl variation.
2011-11-03 13:31:32 -06:00
erik
3badf0f826
Merge branch 'master' of git://github.com/stevenrobertson/cuburn
...
Conflicts:
cuburn/code/filtering.py
2011-11-03 13:27:31 -06:00
erik
8ea057ff96
fixed highlight_power functionality difference between cuburn and smoulder
2011-11-03 13:18:43 -06:00
Erik Reckase
d382e0f14a
Fix highlight power
2011-10-31 17:20:13 -04:00
Steven Robertson
b240fc8459
Use custom "cross" filtering.
...
Sobel was giving too many false positives. This cross seems to detect
the kinds of edges we care about and avoids the rest of the image, and
it does so on pretty much everything I've tried it on. Very satisfying.
2011-10-29 17:36:06 -04:00
Steven Robertson
0936e34b88
Fix cards stalling out on degenerate flames
2011-10-29 11:14:11 -04:00
Steven Robertson
6204f36ebc
Fix spline derivative calculation.
2011-10-29 10:51:33 -04:00
Steven Robertson
bfff915b7e
Two very obvious spline bugs fixed.
2011-10-28 21:34:42 -04:00
Steven Robertson
28e73d08ee
Add derivative support to SplWrap.
2011-10-28 18:51:33 -04:00
Steven Robertson
a2c4c90cb2
Upgrade fuse, because, well, why not?
2011-10-28 08:41:20 -04:00
Steven Robertson
a6177edc0d
Drop the RNG mult shuffle.
...
It's surprisingly time-consuming, and until I have data showing that we
need it, I'm going to leave this bit of extra randomness voodoo out.
2011-10-28 08:36:27 -04:00
Steven Robertson
185823ad55
Rearrange the main render loop... again.
...
Using one stream with two pagelocked host buffers allows us to keep the
GPU work queue full without pegging the CPU, and also reduces the
incidences where a host buffer will get overwritten before it can be
written. devtid() was flaky, so this patch also introduces a ringbuffer
to handle the 'slots' concept. It also introduces an adaptive number of
temporal samples, which improves efficiency but also killed the
assumption that (ntemporal_samples % 256 == 0), which required some
additional fixes.
2011-10-28 08:30:36 -04:00
Steven Robertson
15f88383b1
Experimental: real Sobel gradient detection
2011-10-28 08:25:00 -04:00
Steven Robertson
9b2b3ba011
Fix buffer overrun in filtering
2011-10-28 08:24:16 -04:00
Steven Robertson
6b2cb024ac
Expand max filter radius to 21 pixels
2011-10-28 08:23:33 -04:00
Steven Robertson
f3a79b200c
New badvals mechanism.
2011-10-27 12:59:58 -04:00
Steven Robertson
cac9b691a8
Add a missing semicolin in disc2
2011-10-27 10:37:12 -04:00
Steven Robertson
77daf5e639
Correct blur radius after Box-Muller
2011-10-27 10:36:44 -04:00
Steven Robertson
1faffa1d14
'fill_dptr' instead of 'zero_dptr'
2011-10-27 10:35:01 -04:00
Steven Robertson
3c1dac530b
Updates to run_job.py
2011-10-27 10:26:30 -04:00
Steven Robertson
5368a9254a
Clamp DE radius further.
...
The maximum standard deviation pushes far too hard into the limits of
the filter width, giving discrete points a weird boxy blur. The filter
slice width needs to be expanded, but that's a whole lot of coeffecient
debugging, and I'm putting it off by just reducing the maximum DE width
for now.
2011-10-27 08:58:51 -04:00
Steven Robertson
9049902b4f
Add a crap gradient detect to make DE less bad.
...
Use the vertical and horizontal gradients to "detect" when a pixel is
part of an edge that has been softened by grid-shift AA, and avoid
blurring it further. This causes occasional 1px artifacts in stills, but
fixes the truly grotesque DE bleed-out for a net win. A better edge
detector is still needed.
2011-10-27 08:51:40 -04:00
Steven Robertson
7c84c6a7a9
Final xform color *is* used after all
2011-10-27 08:46:55 -04:00
Steven Robertson
f650844cb9
Fix two variations
2011-10-26 08:11:10 -04:00
Steven Robertson
a8528a9e1d
Fix rgb2hsv
2011-10-26 08:10:57 -04:00
Steven Robertson
376cd752d6
Palette interpolation on device
2011-10-25 22:56:19 -04:00
Steven Robertson
e793527c29
A few harmless const modifiers
2011-10-25 22:49:26 -04:00
Steven Robertson
3436291eb6
Improve spline loading
2011-10-25 19:03:35 -04:00
Steven Robertson
fb5bdc2a9f
Remove now-unused pyflam3_hacks
2011-10-25 19:03:10 -04:00
Steven Robertson
8939a6343a
New genome representation, and device interp.
2011-10-25 15:44:39 -04:00
Steven Robertson
be31708c09
Fix memory corruption bug (overshoot in colorclip)
2011-10-25 15:43:05 -04:00
Steven Robertson
efc2ac23e2
Fix rendering at insane resolutions
2011-10-19 14:17:01 -04:00
Steven Robertson
20520d2f69
Open primes.bin in binary mode.
2011-10-17 19:31:09 -04:00
Steven Robertson
6c2df777b0
Remove a TODO
2011-10-16 13:52:01 -04:00
Steven Robertson
8ce2470dfb
Relax FUSE a little (no visible impact so far)
2011-10-16 13:45:27 -04:00
Steven Robertson
c4ce3cf4c2
Don't crash on empty render(times)
2011-10-16 13:44:22 -04:00
Steven Robertson
0cc904c4f1
Do post affine transforms. How did I miss this?
2011-10-16 13:43:46 -04:00
Steven Robertson
5111a0f05c
Eliminate needless pre_ var separation
2011-10-16 13:42:37 -04:00
Steven Robertson
9bafbda81a
Refactor host rendering code for better load
2011-10-15 22:22:43 -04:00
Steven Robertson
9ff018de87
Actually fix dithering. (I've seen this before...)
2011-10-15 19:08:16 -04:00
Steven Robertson
63483480d0
Bias the radius to avoid very large dither offsets
2011-10-15 00:50:24 -04:00
Steven Robertson
3be14547ea
Use 3*256 instead of 2*512 blocks; faster on GF104
2011-10-15 00:33:37 -04:00
Steven Robertson
c7728d3507
Add faster no-L1 accum
2011-10-15 00:32:30 -04:00
Steven Robertson
dd645bcbf6
Use one dither offset per block.
2011-10-15 00:29:22 -04:00
Steven Robertson
83670df2c7
Fix random seeds.
2011-10-14 11:56:58 -04:00
Steven Robertson
b168a2431e
32-bit compatibility (I think?)
2011-10-13 16:56:20 -04:00
Steven Robertson
14872ee6ed
Add --sleep for slightly more usable system
2011-10-13 16:55:26 -04:00
Steven Robertson
e6e2c4a8d7
Add --sync option.
2011-10-13 07:53:55 -04:00
Steven Robertson
4834c9fdfa
Change synchronization model.
2011-10-12 14:08:13 -04:00
Steven Robertson
81f61d4d5d
Improve asynchrony; improve palette interp perf.
2011-10-12 14:07:28 -04:00
Steven Robertson
7b9bb165ac
Change the way compile options are handled
2011-10-12 14:02:32 -04:00
Steven Robertson
f04ad7ab68
Performance improvements in Genome.__init__()
2011-10-12 13:57:43 -04:00
Steven Robertson
0f615bd98b
Performance improvements in affine helpers
2011-10-12 13:56:34 -04:00
Steven Robertson
d409f02e4a
Precompile accessors.
...
This improves packing speed by 8x, which is visible on small or
low-quality frames.
2011-10-12 11:50:07 -04:00
Steven Robertson
a12714f4c4
Fix MWC test
2011-10-12 07:36:07 -04:00
Steven Robertson
9b03f557c2
Fix missing control points in async version.
...
The allocation pool was reallocating the same frame as soon as it had
left the current scope, before it had been copied. We just reallocate
the same chunks. I don't think this has any real performance impact but
this can be verified.
2011-10-11 20:54:33 -04:00
Steven Robertson
b081bc9378
Remove a sync from iter.
...
A small but consistent improvement.
2011-10-11 14:56:23 -04:00
Steven Robertson
095936666e
Actually asynchronous rendering.
...
This change didn't affect GPU performance at all, but it did improve CPU
startup time, and should also improve time for long-running animations.
2011-10-11 11:27:40 -04:00
Steven Robertson
8c7e86c7c7
Fixed fraction to not exceed range
2011-10-11 11:26:38 -04:00
Steven Robertson
618b51b1b1
Speed enhancement: alpha packing.
...
When the alpha channel is used in a color palette, the code now replaces
the blue channel in the accumulation buffer with a pair of two U16s,
which encode the values of the blue and alpha channels as a fraction of
the value of the density. When the alpha channel is always 1.0, the blue
channel works as normal. Density is now always the last element in the
accumulation buffer.
Eliminating the separate IO operations improved total runtime by more
than 30% on my card, while the extra calculations reduced that to 20%
when alpha was present (though that can be optimized further).
2011-10-11 09:57:37 -04:00
Steven Robertson
46c6074b92
Use C++ pass-by-reference to explicitly share.
2011-10-03 16:53:29 -04:00
Erik Reckase
851980f682
mobius d params were missing
2011-07-06 12:47:03 -06:00
Steven Robertson
18a60ec066
Major bugfix. Also include thread-swapping that works.
2011-06-25 20:37:08 -04:00
Erik Reckase
44f897f28e
fixed enable/disable chaos 'if chain' in iter kernel function
2011-06-24 09:59:14 -06:00
Erik Reckase
b732a3c244
now the chaos 'if chain' is only used if there are non-unity chaos entries in the genome.
2011-06-24 08:18:08 -06:00
Erik Reckase
50b664b1f9
chaos support \0/
2011-06-24 06:09:04 -06:00
Erik Reckase
bc2aa00e2a
removed stray debug printfs
2011-06-21 11:24:06 -06:00
Erik Reckase
addad052b1
closes 11 - all black pixels with non-zero density were not being handled properly.
2011-06-21 11:22:20 -06:00
Erik Reckase
981de94be5
added <stdio.h> for printf support in cuda code
2011-06-21 11:17:11 -06:00
Erik Reckase
746185ce4d
added support for pre_blur. all variations that start with 'pre_' will be applied to the
...
output of the affine transform before the other variation contributions are calculated.
2011-06-20 14:05:00 -06:00
Steven Robertson
c66cb463d4
Add background color support, and tentatively disable density blurring.
2011-06-19 00:30:54 -04:00
Steven Robertson
883de380fc
Did check. It is right.
2011-06-18 22:30:09 -04:00
Erik Reckase
98fb376545
fixed extra ) in var59
2011-06-17 16:36:27 -06:00
Erik Reckase
f684f90956
fixed a few more variations
2011-06-17 13:00:57 -06:00
Erik Reckase
3ee437d9b2
more fixes for variations...just about have all of the written ones validated.
2011-06-17 10:24:13 -06:00
Erik Reckase
6cd4f328f0
fixes for various variations
2011-06-16 21:25:06 -06:00
Steven Robertson
9e74ff57ce
Fix julia variation. Closes issue 10.
2011-06-16 13:42:17 -04:00
Erik Reckase
8a3365712c
fixed super_shape
2011-06-16 10:23:47 -06:00
Erik Reckase
e05d43fc57
fixed pie variation.
2011-06-16 06:50:26 -06:00
Erik Reckase
e83e67b440
fixed waves variation.
2011-06-16 05:34:46 -06:00
Erik Reckase
842efb6317
more variation fixes, syntax errors and so on.
2011-06-15 20:21:40 -06:00
Steven Robertson
702e303509
Gaussian dither
2011-06-13 23:20:39 -04:00
Steven Robertson
e579c837ce
Missed a double in the filtering
2011-06-13 00:50:41 -04:00
Steven Robertson
5ebf62b1a3
Reduce some double-precision constants
2011-06-13 00:48:31 -04:00
Erik Reckase
131ce96263
fixed some missing ; in the variation code.
2011-06-12 21:53:33 -06:00
Steven Robertson
ae914d0b81
Fix some animation bugs
2011-06-12 20:20:36 -04:00
Steven Robertson
89b6732752
Skip the final xform when (re)joining the attractor
2011-06-12 19:29:10 -04:00
Steven Robertson
9a8e57cbc6
Fix a type error when gamma linearization == 0
2011-06-12 19:18:47 -04:00
Steven Robertson
9f2bc49009
Clean up some leftover debugging code in filtering
2011-06-12 19:17:02 -04:00
Steven Robertson
f872baf844
Use much more accurate filtsum estimation polynomials
2011-06-12 17:37:57 -04:00
Steven Robertson
e9998c28da
Re-add a hard clamp for an estimator minimum.
...
The value 0.4 is above what it should be (0.3 is the theoretical minimum), and
having the harder clamp threshold causes some problems, but fixes others.
There's a deeper bug here.
2011-06-11 23:39:51 -04:00
Steven Robertson
299b5d5dab
Fix filtering - or at least make it less broken
2011-06-11 23:28:32 -04:00
Steven Robertson
6b09e162a3
Make DE use current center CP instead of anim-wide CP; start debugging color
2011-06-11 22:51:16 -04:00
Steven Robertson
7ff0b65d81
Fix improper gutter offset in camera computation
2011-06-11 17:58:08 -04:00
Steven Robertson
38fbc391e8
Add gamma linearization (may be incorrect)
2011-06-11 17:50:15 -04:00
Steven Robertson
5b67ed7c33
Fix gutter-trim and compilation keeping
2011-06-11 17:23:29 -04:00
Steven Robertson
6c7d0270ad
A few variation fixups
2011-06-11 17:21:34 -04:00
Steven Robertson
e79df46c66
Refactor API
...
--HG--
rename : cuburn/code/filter.py => cuburn/code/filtering.py
2011-06-11 15:59:10 -04:00
Steven Robertson
6f3c27007a
Remove outdated MemBench stuff
2011-06-11 15:58:37 -04:00
Steven Robertson
94c453d153
Filter adjustments (density prefilter, gutter)
2011-06-11 15:58:15 -04:00
Steven Robertson
cd1f905ca3
Fix assembly (don't think this bug ever bit, but it could)
2011-05-29 15:20:58 -04:00
Steven Robertson
daf56ffc53
Split thread group up along warp boundary (this is useful later)
2011-05-29 15:15:06 -04:00
Steven Robertson
923d471e0e
Merge memory transaction for slightly less smashing
2011-05-29 15:06:57 -04:00
Steven Robertson
78835085e8
A few trivial syntax corrections in the vars
2011-05-29 14:52:10 -04:00
Steven Robertson
7556d79ae5
Merge Erik's variations (TY!)
2011-05-05 23:36:40 -04:00
Steven Robertson
3d94c256a9
Another non-working checkin
2011-05-05 23:35:54 -04:00
Erik Reckase
0d88608b16
vars basically done. whew. a few are missing, but they're a pain and
...
i don't feel like doing them right now ;)
2011-05-05 21:16:47 -06:00
Erik Reckase
7d46b0d1db
Done with 77. Will pick and choose the rest.
2011-05-05 18:09:23 -06:00
Erik Reckase
ec01cbfc43
up through var 69!
2011-05-05 13:44:12 -06:00
Steven Robertson
fac6f838a4
Saving unsuccessful separable filtering code
2011-05-05 10:40:22 -04:00
Erik Reckase
4f5d7efe27
vars up to 67 complete
2011-05-05 05:48:53 -06:00
Erik Reckase
9f78f5225a
vars done through 57
2011-05-04 16:18:29 -06:00
Erik Reckase
d0084aab17
vars done through 49. skipping twintrian for now.
2011-05-04 14:43:17 -06:00
Erik Reckase
645222af47
added some blur variations, up to 36.
2011-05-04 12:05:51 -06:00
Erik Reckase
7a680efa1b
added a few more vars, also fixed waves since it was referring to
...
precalc'd parameters
2011-05-04 11:51:04 -06:00
Steven Robertson
1aafe4a93c
Some light performance optimizations
2011-05-04 09:52:20 -04:00
Steven Robertson
be66f80641
Final xforms
2011-05-04 08:13:39 -04:00
Erik Reckase
85ef8e7005
vars added up to 29.
2011-05-04 05:48:50 -06:00
Steven Robertson
e8a31bb4a5
Arbitrary camera, part 2
2011-05-04 01:30:22 -04:00
Steven Robertson
b2ee583b08
Arbitrary camera, part 1
2011-05-04 01:06:18 -04:00
Erik Reckase
765cf6b2e0
up to var22 (fan) completed.
2011-05-03 21:49:14 -06:00
Erik Reckase
d1137e8e89
lots more f's added. vars up to 19 complete.
2011-05-03 21:34:24 -06:00
Erik Reckase
f599685676
added missing f's and removed EPS 1e-20 thingies
2011-05-03 21:19:56 -06:00
Erik Reckase
8b6c6f462e
added variations up to #16 . 1/6 done!
2011-05-03 21:16:02 -06:00
Steven Robertson
c605815130
Make code more portable
2011-05-03 17:12:12 -04:00
Steven Robertson
eeff0a4d4f
Oh, missed some 'f' suffixes on numbers
2011-05-03 16:15:16 -04:00
Steven Robertson
9d969476ec
Be a little more particular about how mwc_11 is implemented
2011-05-03 15:26:44 -04:00
Steven Robertson
28c3c72bb8
Dithering
2011-05-03 15:26:05 -04:00
Steven Robertson
8ee5d3edd8
Add a few vars, and support for rendering single flames
2011-05-03 14:36:20 -04:00
