Since the types are singletons across the lifetime of the compiler,
repeatedly compiling a program with the same structure type defined
would drop a copy of the array on the floor per compile.
This is a bit tricky because the static GLSL types are not called with
the talloc-based new, so we have to use the global type context, which
may not be initialized yet.
We regularly do lookups on the field names of the structure to find
the types within the struct, so returning a structure type with bad
names will lead to lots of error types being found.
Fixes piglit test glsl-array-length, and provides proper error messages
for negative piglit tests array-length-110.frag, array-length-unsized.frag,
and array-length-args.frag.
This assertion is triggered by method calls (i.e. array.length()), where
subexpressions[1] is an ast_function_call expression. Since the
assertion itself had a comment saying it could be removed eventually,
simply do so.
Causes negative glslparser tests array-length-110.frag,
array-length-args.frag, and array-length-unsized.frag to pass, but only
because the length() method is not supported yet.
The constant_expression_wrapper was already the only external API, and
much of the internal code used it anyway. Also, it wouldn't ever visit
non-rvalue ir_instructions, so using a visitor seemed a bit unnecessary.
This uses "ir_foo *ir = this;" lines to avoid code churn. These should
be removed.
Consider this test case:
#define EMPTY
int foo = 1+EMPTY+4;
The expression should compile as the sequence of tokens 1, PLUS,
UNARY_POSITIVE, 4. But glcpp has been failing for this case since it
results in the string "1++4" which a compiler correctly sees as a
syntax error, (1, POST_INCREMENT, 4).
We fix this by changing any macro with an empty definition to result
in a single SPACE token rather than nothing. This then gives "1+ +4"
which compiles correctly.
This commit does touch up the two existing test cases which already
have empty macros, (to add the space to the expected result).
It also adds a new test case to exercise the above scenario.
We define the YY_NO_INPUT macro to avoid one needless function being
generated.
for the other needless functions, (yyunput and yy_top_state), we add a
new UNREACHABLE start condition and call these functions from an
action there. This doesn't change functionality at all, (since we
never enter the UNREACHABLE start condition), but makes the compiler
stop complaining about these two functions being defined but not used.
It's really a bug in flex that these functions are generated with neither
a declaration nor the 'static' keyword, but we can at least avoid the
warnings this way.
Previously, if the outer #ifdef/#ifndef evaluated to false, the inner
directive would not be parsed correctly, (the identifier as the subject
of the #ifdef/#ifndef would inadvertently be skipped along with the other
content correctly being skipped).
We fix this by setting the lexing_if state in each case here.
We also add a new test to the test suite to ensure that this case is tested.
As it turns out, 4 of our current tests are not valgrind clean,
(use after free errors or so), so this will be helpful for
investigating and fixing those.
These were only ever intended to exist in the original, standalone
implementation of glcpp, (with the idea of dropping them as soon as
the code moved into mesa). The current build system wasn't compiling
this C file, but the presence of the header files could cause problems
if the two copies diverge in the future.
We head those problems off by deleting al of these redundant files.
The parameters[i] is our inlined variables representing the
parameters, so they are always ir_var_auto. Walk the signature params
in handling "out" values like we do for "in" values to find the mode.
Fixes (with the previous 2 commits):
glsl1-function call with in, out params
glsl1-function call with inout params
If they have a return value, this means putting it into a temporary
and making a deref of the temp be the rvalue, since we don't know if
the rvalue will be used or not.
I'd flipped around the order of two operations in paren-balancing
adventures, and left out the multiply by sign(x) required for negative x.
Fixes:
glsl1-acos(vec4) function
glsl1-asin(vec4) function
glsl1-atan(vec4) function
I hadn't noticed you could do this, but glsl1 tests caught it. Fixes:
glsl1-Swizzled writemask
glsl1-Swizzled writemask (2)
glsl1-Swizzled writemask (rgba)
glsl1-Swizzled writemask (stpq)
If max_index=0xffffffff and elt_bias > 0 the test for
elt_bias + max_index >= DRAW_PIPE_MAX_VERTICES
was wrong. Check earlier if max_index=0xffffffff and do the
"fail" case.
This fixes the piglit draw-elements-base-vertex test (and probably
some other things).
When defining mipmap level 'L' and level L-1 exists and the new level's
internalFormat matches level L-1's internalFormat, then use the same hw
format. Otherwise, do the regular ctx->Driver.ChooseTextureFormat() call.
This avoids a problem where we end up choosing different hw formats for
different mipmap levels depending on how the levels are defined (glTexImage
vs. glCopyTexImage vs. glGenerateMipmap, etc).
The root problem is the ChooseTextureFormat() implementation in some
drivers uses the user's glTexImage format/type parameters in the choosing
heuristic. Later mipmap levels might be generated with different calls
(ex: glCopyTexImage()) so we don't always have format/type info and the
driver may choose a different format.
For more background info see the July 2010 mesa-dev thread "Bug in
_mesa_meta_GenerateMipmap"
