This patch allows for an unlimited number of textures in Cycles where the hardware allows. It replaces a number static arrays with dynamic arrays and changes the way the flat_slot indices are calculated. Eventually, I'd like to get to a point where there are only flat slots left and textures off all kinds are stored in a single array.
Note that the arrays in DeviceScene are changed from containing device_vector<T> objects to device_vector<T>* pointers. Ideally, I'd like to store objects, but dynamic resizing of a std:vector in pre-C++11 calls the copy constructor, which for a good reason is not implemented for device_vector. Once we require C++11 for Cycles builds, we can implement a move constructor for device_vector and store objects again.
The limits for CUDA Fermi hardware still apply.
Reviewers: tod_baudais, InsigMathK, dingto, #cycles
Reviewed By: dingto, #cycles
Subscribers: dingto, smellslikedonkey
Differential Revision: https://developer.blender.org/D2650
The final goal to reach is to make vectorized types much easier to maintain
and the previous design had following issues:
- Having all types and methods implementation made the source file rather
bloated and unfun to navigate in.
- It was not possible to quickly glance available API for the type you are
interested in.
- Adding more vectorization types will bloat the file even more, making
things even more tricky to follow.
Ever since we merged the extra texture types (half etc) and spit kernel the compile time for cycles_kernel has been going out of control.
It's currently sitting at a cool 1295.762 seconds with our standard compiler (2013/x64/release)
I'm not entirely sure why msvc gets upset with it, but the inlining of matrix near the bottom of the tri-cubic 3d interpolator is the source of the issue, this patch excludes it from being inlined.
This patch bring it back down to a manageable 186 seconds. (7x faster!!)
with the attached bzzt.blend that @sergey kindly provided i got the following results with builds with identical hashes
58:51.73 buildbot
58:04.23 Patched
it's really close, the slight speedup could be explained by the switch instead of having multiple if's (switches do generate more optimal code than a chain of if/else/if/else statements) but in all honesty it might just have been pure luck (dev box,very polluted, bad for benchmarks) regardless, this patch doesn't seem to slow down anything with my limited testing.
{F532336}
{F532337}
Reviewers: brecht, lukasstockner97, juicyfruit, dingto, sergey
Reviewed By: brecht, dingto, sergey
Subscribers: InsigMathK, sergey
Tags: #cycles
Differential Revision: https://developer.blender.org/D2595
The idea is to make include statements more explicit and obvious where the
file is coming from, additionally reducing chance of wrong header being
picked up.
For example, it was not obvious whether bvh.h was refferring to builder
or traversal, whenter node.h is a generic graph node or a shader node
and cases like that.
Surely this might look obvious for the active developers, but after some
time of not touching the code it becomes less obvious where file is coming
from.
This was briefly mentioned in T50824 and seems @brecht is fine with such
explicitness, but need to agree with all active developers before committing
this.
Please note that this patch is lacking changes related on GPU/OpenCL
support. This will be solved if/when we all agree this is a good idea to move
forward.
Reviewers: brecht, lukasstockner97, maiself, nirved, dingto, juicyfruit, swerner
Reviewed By: lukasstockner97, maiself, nirved, dingto
Subscribers: brecht
Differential Revision: https://developer.blender.org/D2586
The intention of this commit it to address issues mentioned in the
reports T43865,T50164 and T50452.
The code is based on Embree code with some extra vectorization
to speed up single ray to single triangle intersection.
Unfortunately, such a fix is not coming for free. There is some
slowdown for AVX2 processors, mainly due to different vectorization
code, which caused different number of instructions to be executed
and different instructions-per-cycle counters. But on another hand
this commit makes pre-AVX2 platforms such as AVX and SSE4.1 a bit
faster. The prerformance goes as following:
2.78c AVX2 2.78c AVX Patch AVX2 Patch AVX
BMW 05:21.09 06:05.34 05:32.97 (+3.5%) 05:34.97 (-8.5%)
Classroom 16:55.36 18:24.51 17:10.41 (+1.4%) 17:15.87 (-6.3%)
Fishy Cat 08:08.49 08:36.26 08:09.19 (+0.2%) 08:12.25 (-4.7%
Koro 11:22.54 11:45.24 11:13.25 (-1.5%) 11:43.81 (-0.3%)
Barcelone 14:18.32 16:09.46 14:15.20 (-0.4%) 14:25.15 (-10.8%)
On GPU the performance is about 1.5-2% slower in my tests on GTX1080
but afraid we can't do much as a part of this chaneg here and
consider it a price to pay for more proper intersection check.
Made in collaboration with Maxym Dmytrychenko, big thanks to him!
Reviewers: brecht, juicyfruit, lukasstockner97, dingto
Differential Revision: https://developer.blender.org/D1574
Use fast-math friendly version of this function.
We should probably avoid unsafe fast math, but this is to be done with
real care with all the benchmarks properly done.
For now comitting much safer fix.
It is unused now and if we want similar function we should use
Pluecker intersection which is same performance with SSE optimization
but which is more watertight.
Avoid construction of temporary array and make utility function force-inlined.
Additionally avoid calling float4_to_float3 twice.
This brings render times to the same values as before current patch series.
This is a preparation work for the followup commit which wil l move
remaining parts of Woop intersection logic to an utility file.
Doing it as a separate commit to keep changes more atomic and easier
to bisect when/if needed.
There are following benefits:
- Modifying intersection algorithm will not cause so much re-compilation.
- It works around header dependency hell and allows us to use vectorization
types much easier in there.
Single program generally compiles kernels faster (2-3 times), loads faster,
takes less drive space (2-3 times), and reduces the number of cached kernels.
This does a few things at once:
- Refactors host side split kernel logic into a new device
agnostic class `DeviceSplitKernel`.
- Removes tile splitting, a new work pool implementation takes its place and
allows as many threads as will fit in memory regardless of tile size, which
can give performance gains.
- Refactors split state buffers into one buffer, as well as reduces the
number of arguments passed to kernels. Means there's less code to deal
with overall.
- Moves kernel logic out of OpenCL kernel files so they can later be used by
other device types.
- Replaced OpenCL specific APIs with new generic versions
- Tiles can now be seen updating during rendering
