Jason Ekstrand
dd4db84640
We have a performance problem with dynamic buffer descriptors. Because
we are currently implementing them by pushing an offset into the shader
and adding that offset onto the already existing offset for the UBO/SSBO
operation, all UBO/SSBO operations on dynamic descriptors are indirect.
The back-end compiler implements indirect pull constant loads using what
basically amounts to a texelFetch instruction. For pull constant loads
with constant offsets, however, we use an oword block read message which
goes through the constant cache and reads a whole cache line at a time.
Because of these two things, direct pull constant loads are much faster
than indirect pull constant loads. Because all loads from dynamically
bound buffers are indirect, the user takes a substantial performance
penalty when using this "performance" feature.
There are two potential solutions I have seen for this problem. The
alternate solution is to continue pushing offsets into the shader but
wire things up in the back-end compiler so that we use the oword block
read messages anyway. The only reason we can do this because we know a
priori that the dynamic offsets are uniform and 16-byte aligned.
Unfortunately, thanks to the 16-byte alignment requirement of the oword
messages, we can't do some general "if the indirect offset is uniform,
use an oword message" sort of thing.
This solution, however, is recommended for a few of reasons:
1. Surface states are relatively cheap. We've been using on-the-fly
surface state setup for some time in GL and it works well. Also,
dynamic offsets with on-the-fly surface state should still be
cheaper than allocating new descriptor sets every time you want to
change a buffer offset which is really the only requirement of the
dynamic offsets feature.
2. This requires substantially less compiler plumbing. Not only can we
delete the entire apply_dynamic_offsets pass but we can also avoid
having to add architecture for passing dynamic offsets to the back-
end compiler in such a way that it can continue using oword messages.
3. We get robust buffer access range-checking for free. Because the
offset and range are baked into the surface state, we no longer need
to pass ranges around and do bounds-checking in the shader.
4. Once we finally get UBO pushing implemented, it will be much easier
to handle pushing chunks of dynamic descriptors if the compiler
remains blissfully unaware of dynamic descriptors.
This commit improves performance of The Talos Principle on ULTRA
settings by around 50% and brings it nicely into line with OpenGL
performance.
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
File: docs/README.WIN32 Last updated: 21 June 2013 Quick Start ----- ----- Windows drivers are build with SCons. Makefiles or Visual Studio projects are no longer shipped or supported. Run scons libgl-gdi to build gallium based GDI driver. This will work both with MSVS or Mingw. Windows Drivers ------- ------- At this time, only the gallium GDI driver is known to work. Source code also exists in the tree for other drivers in src/mesa/drivers/windows, but the status of this code is unknown. Recipe ------ Building on windows requires several open-source packages. These are steps that work as of this writing. - install python 2.7 - install scons (latest) - install mingw, flex, and bison - install pywin32 from here: http://www.lfd.uci.edu/~gohlke/pythonlibs get pywin32-218.4.win-amd64-py2.7.exe - install git - download mesa from git see https://www.mesa3d.org/repository.html - run scons General ------- After building, you can copy the above DLL files to a place in your PATH such as $SystemRoot/SYSTEM32. If you don't like putting things in a system directory, place them in the same directory as the executable(s). Be careful about accidentially overwriting files of the same name in the SYSTEM32 directory. The DLL files are built so that the external entry points use the stdcall calling convention. Static LIB files are not built. The LIB files that are built with are the linker import files associated with the DLL files. The si-glu sources are used to build the GLU libs. This was done mainly to get the better tessellator code. If you have a Windows-related build problem or question, please post to the mesa-dev or mesa-users list.