mirror of
https://github.com/gomson/TimothyLottes.github.io.git
synced 2026-08-04 14:48:49 +00:00
Add files via upload
This commit is contained in:
TimothyLottes
GitHub
+194
@@ -0,0 +1,194 @@
|
||||
<html><head><link rel="stylesheet" href="style.css"></head><body><div class="page">
|
||||
<h1>20150709 - GPU Unchained ASCII Notes</h1>
|
||||
<br>
|
||||
|
||||
<a href="20150328.html">Posted stills prior</a>, here are the notes, hopefull the "pre" tag works for everyone...<br>
|
||||
<br>
|
||||
<pre>
|
||||
================================================================================
|
||||
|
||||
|
||||
.
|
||||
##X=--=X## ##X=--=X## ## ##
|
||||
## __ ## ## ##
|
||||
. ## -=## ## ## ## ##
|
||||
. ## ## ##X=--=X## ## ## .
|
||||
##X=--=X## ## ##X=--=X##
|
||||
. _ .
|
||||
# # .
|
||||
. . # # #=-=# #=-=# #=-=# #=-=# -=# #=-=# #=-=# #=-=# .
|
||||
.:... .. # # # # # # # ___ # # # # # __# # # ... :::..:.
|
||||
:::::::::::.# . # # . # # .:. # : # # # . = . # . # # ... # . #.::::::::::::::
|
||||
|||||||'||| #=-=# # : # #=-=# # | # #=-=# #=-=# # : # #=-=# #=-=# ||||.|||||||||
|
||||
!!!''!;!!!!!.....!..!..!.....!.!!!.!.....!.....!.!!!.!.....!.....!!!!!!!!!'''!!!
|
||||
:/:::/::::::::::::::::::::::::::'''''''''':::''::::::::::::::::::::/:::::::.::::
|
||||
''''/ ''''';' ' ' ' ';' '' ' ''''''''';''
|
||||
/ ' / ___ . ''' /
|
||||
|imothy Lottes
|
||||
|
||||
|
||||
|
||||
================================================================================
|
||||
VISUALIZING ALIASING IN MOTION - STILL VS SCROLLING FONTS [a]
|
||||
================================================================================
|
||||
|
||||
"Evaluation criteria for correct sharpness
|
||||
should be different for stills and video"
|
||||
|
||||
SPATIAL PRECISION VS SHARPNESS
|
||||
------------------------------
|
||||
- In motion, sharpess must be reduced to have good spatial precision
|
||||
|
||||
LIVE EXAMPLE OF FONT RENDERING
|
||||
------------------------------
|
||||
- 1/4 x 1/4 resolution rendering
|
||||
- Render via stylized even field aperture grille (arcade Trinitron)
|
||||
- Font designed on pixel grid
|
||||
- Font rendered via function of min 1D distance to capsules (for lines)
|
||||
|
||||
|
||||
================================================================================
|
||||
FILTERING DIGITAL ORIGAMI [b]
|
||||
================================================================================
|
||||
|
||||
"Filtering is critical
|
||||
to convince the skeptical mind that a scene is believable"
|
||||
|
||||
LIVE EXAMPLE OF SIMPLE SDF SCENE
|
||||
--------------------------------
|
||||
- 1/2 x 1/2 resolution tracing
|
||||
- Full resolution reconstruction
|
||||
- Lots of high frequency sub-pixel sized content
|
||||
|
||||
PROGRESSION TO SIMPLE SAMPLE JITTERED TEMPORAL FILTERING
|
||||
--------------------------------------------------------
|
||||
- Simple gaussian resolve kernel (not enough samples/pix for negative lobes)
|
||||
- Temporal feedback also weights samples by rcp of reprojected luma difference
|
||||
|
||||
|
||||
================================================================================
|
||||
LIMITS OF PER-PIXEL SEARCH AND SDF LOD [c]
|
||||
================================================================================
|
||||
|
||||
"Highly variable frame timing is a poison for high refresh rates"
|
||||
|
||||
RAY HIT?
|
||||
--------
|
||||
- Standard termination,
|
||||
if(abs(distanceToSurface) <= distanceAlongRay * coneRadius) hit
|
||||
- LOD termination,
|
||||
... <= distanceAlongRay * (coneRadius + steps * lodFactor)) hit
|
||||
- Expands surfaces as ray march gets progressively more expensive
|
||||
|
||||
CHOOSING A GOOD FILTER KERNEL
|
||||
-----------------------------
|
||||
- Biased:
|
||||
1/(1 + abs(a-b) * const)
|
||||
- Still not great:
|
||||
1/(1 + (abs(a-b) / max(minimum,min(a,b))) * const)
|
||||
- Better:
|
||||
square(1 - abs(a-b) / max(a,b,minimum))
|
||||
|
||||
|
||||
================================================================================
|
||||
1/4 AREA TRACE+FEEDBACK + FULL AREA RECONSTRUCTION [d]
|
||||
================================================================================
|
||||
|
||||
"Maintaining higher spatial precision
|
||||
without increasing shading rate for higher quality visual"
|
||||
|
||||
VISUAL EXAMPLE
|
||||
--------------
|
||||
- Still tracing at sample-jittered half resolution (1/4 area).
|
||||
- Still sampling reprojection at half resolution.
|
||||
- But sampling reprojection from full resolution source.
|
||||
- And running reconstruction at full resolution.
|
||||
|
||||
|
||||
================================================================================
|
||||
HIERARCHICAL TRAVERSAL IN SINGLE KERNEL [e]
|
||||
================================================================================
|
||||
|
||||
"Reorder work to keep ALUs fully loaded,
|
||||
ok to leverage poor data access patterns if ALU bound"
|
||||
|
||||
THREAD TO WORK MAPPING
|
||||
----------------------
|
||||
- Not pixel to thread -> too much ALU under utilization after rays hit surf
|
||||
- Rather fixed distance estimator iterations per thread
|
||||
|
||||
SHADER
|
||||
------
|
||||
- Fetch ray
|
||||
- For fixed traversal iterations
|
||||
- Distance estimation
|
||||
- Walk forward
|
||||
- If ray hit (aka "close enough")
|
||||
- Store result
|
||||
- Start on another ray
|
||||
|
||||
--------------------------------------------------------------------------------
|
||||
BREAD CRUMBS [e]
|
||||
--------------------------------------------------------------------------------
|
||||
|
||||
"When working in parallel, don't wait, if data isn't ready, just compute it"
|
||||
|
||||
TRAVERSAL ORDERING
|
||||
------------------
|
||||
- Order rays by parent cones first in space filling curve,
|
||||
|
||||
0 -> 12 -> 4589 -> and so on
|
||||
34 67ab
|
||||
cdgh
|
||||
efij
|
||||
|
||||
ACCELERATION
|
||||
------------
|
||||
- Cones end by writing their stop depth into memory.
|
||||
- Child cones will check for completed parent result,
|
||||
otherwise will start from scratch.
|
||||
|
||||
--------------------------------------------------------------------------------
|
||||
IN THE NOISE [e]
|
||||
--------------------------------------------------------------------------------
|
||||
|
||||
"Degrade to pleasing noise when out of time"
|
||||
|
||||
TRADE RELATIVELY FIXED TIME FOR NOISE
|
||||
-------------------------------------
|
||||
- Fixed maximum DE iterations -> not always going to traverse full scene
|
||||
- Ok fine, lets not require tracing all rays
|
||||
|
||||
RAY ORDERING FOR FULL RESOLUTION
|
||||
--------------------------------
|
||||
- Fill ordering,
|
||||
|
||||
0 7 E 5 0 . . . 0 7 . 5 0 7 . 5
|
||||
C 3 A 1 . 3 . 1 . 3 . 1 . 3 A 1
|
||||
8 F 6 D . . . . . . 6 . 8 . 6 .
|
||||
4 B 2 9 . . 2 . 4 . 2 . 4 B 2 9
|
||||
|
||||
- Pattern defined by math (fast but perhaps not ideal)
|
||||
- Each frame gets different fill order (holes not always in same place)
|
||||
|
||||
|
||||
================================================================================
|
||||
FILTERED RECONSTRUCTION FROM DIFFERENT DOMAIN [f]
|
||||
================================================================================
|
||||
|
||||
360 DEG FISHEYE EXAMPLE
|
||||
-----------------------
|
||||
- Rendering into an octahedron map
|
||||
- Each sample writes out {x,y} projected screen position
|
||||
- Distortion finds the nearest texel in the octahedron map
|
||||
- Then samples a neighborhood around the texel
|
||||
- Then uses the difference in pixel center and sample {x,y} to filter
|
||||
- Reprojection samples from the warped reconstructed frame
|
||||
- Ideally adjust the filter kernel based on domain distortion
|
||||
- Showing simple adjustment of kernel size here (anisotropic is better)
|
||||
</pre>
|
||||
|
||||
</div></body></html>
|
||||
|
||||
|
||||
|
||||
@@ -87,6 +87,7 @@ Below this is active random migration (416 prior posts still to filter through)
|
||||
<a href="20150910.html">20150910 - September Trip to Iceland</a><br>
|
||||
<a href="20150829.html">20150829 - Ketogenic Diet Working on Year 2</a><br>
|
||||
<a href="20150719.html">20150719 - CRT Shadow Masks vs LCD</a><br>
|
||||
<a href="20150709.html">20150709 - GPU Unchained ASCII Notes</a><br>
|
||||
<a href="20150630.html">20150630 - Sugar Free Peppermint Chocolate Chip Custard Ice Cream</a><br>
|
||||
<a href="20150522.html">20150522 - The Other Project Cleaned Up</a><br>
|
||||
<a href="20150430.html">20150430 - The Other Project Getting Wired</a><br>
|
||||
|
||||
Reference in New Issue
Block a user