If there is relative addressing of temporaries, we cannot change register
indices, so skip register allocation entirely. To utilize register allocation
at least partially, we need separate indexable and non-indexable register
files in both TGSI and Mesa IR.
Previously, uniform initializers were handled by ir_to_mesa as it made
its Parameters list. However, uniform values are global to all
shaders, and the value set in one Parameters list wasn't propagated to
the other gl_program->Parameters lists. By going back through the
general Mesa uniform handling, we make sure that all gl_programs get
updated values, and also successfully separate uniform initializer
handling from ir_to_mesa gl_program generation.
Fixes:
glsl-uniform-initializer-5.
With MSVC it seems that this class and its constructor is colliding
with the one in ir_variable_refcount.cpp. Rename the class here to
avoid the collision.
This is a bit of a hack. Can the two variable_entry classes be merged
and shared?
A variable_entry after construction should have its referenced_count
member set to 0. However, occassionally this isn't the case and
entry->referenced_count has been observed to be a garbage value. This
leads to crashes of several tests in the Piglit test suite.
This patch adds an assert to check that a variable_entry instance has
its referenced_count member initialized to 0 after construction.
drm_driver_descriptor::driver_name is defined to be the name of the
kernel module. We should check against drm_driver_descriptor::name
instead of drm_driver_descriptor::driver_name.
st/egl/x11/x11_screen.c requests a driver named r300 not radeon
KNOWN ISSUE: breaks st/egl/kms/
st/egl/kms requests a pipe named "radeon"
that will not be found now
so why not leaving pipe_radeon there?
that was possible as long we have only r300g.
now there is also r600g for which st/egl/kms also
requests a pipe named "radeon"
(possible solution in later commit)
core.h is the public header of core mesa. GLX, WGL, and GLSL are
supposed to include this header file. It should be noted that headers
included by core.h must not perform feature tests (#if FEATURE_xxx).
Otherwise, we cannot, for example, mix a FEATURE_ES2 libmesagallium.a
with a FEATURE_GL libglsl.a.
Because the static types talloc their names at dlopen time,
talloc_freeing the types at DRI driver screen teardown means that if
the screen gets brought back up again, the names will point at freed
memory. talloc_autofree_context() exists to do just what we want
here: Free memory referenced across the program's lifetime so that we
avoid noise in memory leak checkers.
Fixes: bug #29722 (assertion failure in unigine).
This prevents assertion failures or cascading errors after we've
logged the fact that we were unable to handle the initializer.
Fixes unsized-array-non-const-index-2.vert
The previous any() implementation would generate arg0.x || arg0.y ||
arg0.z. Having an expression operation for this makes it easy for the
backend to generate something easier (DPn + SNE for 915 FS, .any
predication on 965 VS)
