This is an invasive set of changes. Each user shader tracks a set of other
shaders that contain built-in functions. During compilation, function
prototypes are imported from these shaders. During linking, the
shaders are linked with these built-in-function shaders just like with
any other shader.
some of the ALU instructions are different on r6xx vs r7xx,
separate the alu translation to separate files, and use family
to pick which compile stage to use.
Depth clamping seems to be implicit if clipping is disabled.
It's not perfect, but it's good enough for wine and passes
the corresponding piglit tests.
In both the preprocessor and in the compiler proper, we use a custom
yyltype struct to allow tracking the source-string number in addition
to line and column. However, we were previously relying on bison's
default initialization of the yyltype struct which of course is not
aware of the source field and leaves it uninitialized.
We fix this by defining our own YYLLOC_DEFAULT macro expanding on the
default version (as appears in the bison manual) and adding
initialization of yylloc.source.
This quiets a compiler warning, (and ensures a segmentation fault rather
than memory corruption if this variable is written through before being
initialized elsewhere).
While bootstrapping the dependencies, make will see the "include depend"
directive before the depend file has been created. To avoid a spurious
warning in this case we use "-include" instead, (which differs precisely
in the fact that it will not emit a diagnostic if the named file does
not exist).
This avoids two "function defined but not used" warnings. For the yyinput
function we define YY_NO_INPUT which tells flex to simply not generate this
function.
For unput, we add a call to this function, but inside a while(0) so
that it will quiet the warning without actually changing any
functionality.
Add declarations for two functions generated in the flex ouput. It
would be nicer if flex simply declared these generated functions as
static, but for now we can at least avoid the warning this way.
Previously, any occurence of the unary plus operator would trigger a
bogus type mismatch error. Fix this by making the ast_plus case look
more like the ast_neg case as far as type-checking is concerned.
With this change the shaders/CorrectPreprocess8.frag test in piglit
now passes.
Instead of one big boolean indicating indirect addressing, use a
bitfield indicating which register files are accessed with indirect
addressing.
Most shaders that use indirect addressing only use it to access the
constant buffer. So no need to use an array for temporary registers
in this case.
The previous code assumed that all elements of the address register
were the same. But it can vary from pixel to pixel or vertex to
vertex so we must use a gather operation when dynamically indexing
the constant buffer.
Still need to fix this for the temporary register file...
This is quite a large patch because breaking it into smaller pieces
would result in the tree being intermitently broken. The big changes
are:
* Add the ir_var_temporary variable mode
* Change the ir_variable constructor to take the mode as a
parameter and correctly specify the mode for all ir_varables.
* Change the linker to not cross validate ir_var_temporary
variables.
* Change the linker to pull all ir_var_temporary variables from
global scope into 'main'.
