The Intel Compiler 14.0.0 claims version GCC 4.7.3 compatibility
via __GNUC__/__GNUC__MINOR__ macros, but does not provide the same
level of GCC vector extensions support as the original GCC compiler:
http://gcc.gnu.org/onlinedocs/gcc/Vector-Extensions.html
Which results in the following compilation failure:
In file included from ../test/utils.h(7),
from ../test/utils.c(3):
../test/utils-prng.h(138): error: expression must have integral type
uint32x4 e = x->a - ((x->b << 27) + (x->b >> (32 - 27)));
^
The problem is fixed by doing a special check in configure for
this feature.
The call_test_function() contains some assembly that deliberately
causes the stack to be aligned to 32 bits rather than 128 bits on
x86-32. The intention is to catch bugs that surface when pixman is
called from code that only uses a 32 bit alignment.
However, recent versions of GCC apparently make the assumption (either
accidentally or deliberately) that that the incoming stack is aligned
to 128 bits, where older versions only seemed to make this assumption
when compiling with -msse2. This causes the vector code in the PRNG to
now segfault when called from call_test_function() on x86-32.
This patch fixes that by only making the stack unaligned on 32 bit
Windows, where it would definitely be incorrect for GCC to assume that
the incoming stack is aligned to 128 bits.
V2: Put "defined(...)" around __GNUC__
Reviewed-and-Tested-by: Matt Turner <mattst88@gmail.com>
Bugzilla: https://bugs.gentoo.org/show_bug.cgi?id=491110
(cherry picked from commit f473fd1e75)
GCC when compiling with -msse2 and -mssse3 will assume that the stack
is aligned to 16 bytes even on x86-32 and accordingly issue movdqa
instructions for stack allocated variables.
But despite what GCC thinks, the standard ABI on x86-32 only requires
a 4-byte aligned stack. This is true at least on Windows, but there
also was (and maybe still is) Linux code in the wild that assumed
this. When such code calls into pixman and hits something compiled
with -msse2, we get a segfault from the unaligned movdqas.
Pixman has worked around this issue in the past with the gcc attribute
"force_align_arg_pointer" but the problem has resurfaced now in
https://bugs.freedesktop.org/show_bug.cgi?id=68300
because pixman_composite_glyphs() is missing this attribute.
This patch makes fuzzer_test_main() call the test_function through a
trampoline, which, on x86-32, has a bit of assembly that deliberately
avoids aligning the stack to 16 bytes as GCC normally expects. The
result is that glyph-test now crashes.
V2: Mark caller-save registers as clobbered, rather than using
noinline on the trampoline.
For superluminescent destinations, the old code could underflow in
uint32_t r = (ad - d) * as / s;
when (ad - d) was negative. The new code avoids this problem (and
therefore causes changes in the checksums of thread-test and
blitters-test), but it is likely still buggy due to the use of
unsigned variables and other issues in the blend mode code.
Change blend_color_dodge() to follow the math in the comment more
closely.
Note, the new code here is in some sense worse than the old code
because it can now underflow the unsigned variables when the source is
superluminescent and (as - s) is therefore negative. The old code was
careful to clamp to 0.
But for superluminescent variables we really need the ability for the
blend function to become negative, and so the solution the underflow
problem is to just use signed variables. The use of unsigned variables
is a general problem in all of the blend mode code that will have to
be solved later.
The CRC32 values in thread-test and blitters-test are updated to
account for the changes in output.
The non-reentrant versions of prng_* functions are thread-safe only in
OpenMP-enabled builds.
Fixes thread-test failing when compiled with Clang (both on Linux and
on MacOS).
Fixes
check-formats.obj : error LNK2019: unresolved external symbol
_strcasecmp referenced in function _format_from_string
check-formats.obj : error LNK2019: unresolved external symbol
_snprintf referenced in function _list_operators
In d1434d112c the benchmarks have been
extended to include other programs as well and the variable names have
been updated accordingly in the autotools-based build system, but not
in the MSVC one.
This test program allocates an array of 16 * 7 uint32_ts and spawns 16
threads that each use 7 of the allocated uint32_ts as a destination
image for a large number of composite operations. Each thread then
computes and returns a checksum for the image. Finally, the main
thread computes a checksum of the checksums and verifies that it
matches expectations.
The purpose of this test is catch errors where memory outside images
is read and then written back. Such out-of-bounds accesses are broken
when multiple threads are involved, because the threads will race to
read and write the shared memory.
V2:
- Incorporate fixes from Siarhei for endianness and undefined behavior
regarding argument evaluation
- Make the images 7 pixels wide since the bug only happens when the
composite width is greater than 4.
- Compute a checksum of the checksums so that you don't have to
update 16 values if something changes.
V3: Remove stray dollar sign
Use a temporary variable s containing the absolute value of the stride
as the upper bound in the inner loops.
V2: Do this for the bpp == 16 case as well
Commit 4312f07736 claimed to have made
print_image() work with negative strides, but it didn't actually
work. When the stride was negative, the image buffer would be accessed
as if the stride were positive.
Fix the bug by not changing the stride variable and instead using a
temporary, s, that contains the absolute value of stride.
Pixman supports negative strides, but up until now they haven't been
tested outside of stress-test. This commit adds testing of negative
strides to blitters-test, scaling-test, affine-test, rotate-test, and
composite-traps-test.
The affine-test, blitters-test, and scaling-test all have the ability
to print out the bytes of the destination image. Share this code by
moving it to utils.c.
At the same time make the code work correctly with negative strides.
The calloc call from pixman_image_create_bits may still
rely on http://en.wikipedia.org/wiki/Copy-on-write
Explicitly initializing the destination image results in
a more predictable behaviour.
V2:
- allocate 16 bytes aligned buffer with aligned stride instead
of delegating this to pixman_image_create_bits
- use memset for the allocated buffer instead of pixman solid fill
- repeat tests 3 times and select best results in order to filter
out even more measurement noise
The default has been 7-bit for a while now, and the quality
improvement with 8-bit precision is not enough to justify keeping the
code around as a compile-time option.
This new benchmark scales a 320 x 240 test a8r8g8b8 image by all
ratios from 0.1, 0.2, ... up to 10.0 and reports the time it to took
to do each of the scaling operations, and the time spent per
destination pixel.
The times reported for the scaling operations are given in
milliseconds, the times-per-pixel are in nanoseconds.
V2: Format output better
The MSVC compiler is very strict about variable declarations after
statements.
Move all the declarations of each block before any statement in the
same block to fix multiple instances of:
alpha-loop.c(XX) : error C2275: 'pixman_image_t' : illegal use of this
type as an expression
Add necessary support to lowlevel-blt benchmark for benchmarking pixbuf and
rpixbuf fast paths. bench_composite function now checks for pixbuf string in
testname, and if that is detected, use same bits for src and mask images.
Current blitters-test program had difficulties detecting a bug in
over_n_8888_8888_ca implementation for MIPS DSPr2:
http://lists.freedesktop.org/archives/pixman/2013-March/002645.html
In order to hit the buggy code path, two consecutive mask values had
to be equal to 0xFFFFFFFF because of loop unrolling. The current
blitters-test generates random images in such a way that each byte
has 25% probability for having 0xFF value. Hence each 32-bit mask
value has ~0.4% probability for 0xFFFFFFFF. Because we are testing
many compositing operations with many pixels, encountering at least
one 0xFFFFFFFF mask value reasonably fast is not a problem. If a
bug related to 0xFFFFFFFF mask value is artificialy introduced into
over_n_8888_8888_ca generic C function, it gets detected on 675591
iteration in blitters-test (out of 2000000).
However two consecutive 0xFFFFFFFF mask values are much less likely
to be generated, so the bug was missed by blitters-test.
This patch addresses the problem by also randomly setting the 32-bit
values in images to either 0xFFFFFFFF or 0x00000000 (also with 25%
probability). It allows to have larger clusters of consecutive 0x00
or 0xFF bytes in images which may have special shortcuts for handling
them in unrolled or SIMD optimized code.
This benchmark renders one of the radial gradients used in the
swfdec-youtube cairo trace 500 times and reports the average time it
took.
V2: Update .gitignore
The source, mask and destination buffers are initialised to 0xCC just after
they are allocated. Between each benchmark, there are a pair of memcpys,
from the destination buffer to the source buffer and back again (there are
no explanatory comments, but presumably this is an effort to flush the
caches). However, it has an unintended consequence, which is to change the
contents of the buffers on entry to subsequent benchmarks. This means it is
not a fair test: for example, with over_n_8888 (featured in the following
patches) it reports L2 and even M tests as being faster than the L1 test,
because after the L1 test, the source buffer is filled with fully opaque
pixels, for which over_n_8888 has a shortcut.
The fix here is simply to reverse the order of the memcpys, so src and
destination are both filled with 0xCC on entry to all tests.
The check-formats programs reveals that the 8 bit pipeline cannot meet
the current 0.004 acceptable deviation specified in utils.c, so we
have to increase it. Some of the failing pixels were captured in
pixel-test, which with this commit now passes.
== a4r4g4b4 DISJOINT_XOR a8r8g8b8 ==
The DISJOINT_XOR operator applied to an a4r4g4b4 source pixel of
0xd0c0 and a destination pixel of 0x5300ea00 results in the exact
value:
fa = (1 - da) / sa = (1 - 0x53 / 255.0) / (0xd / 15.0) = 0.7782
fb = (1 - sa) / da = (1 - 0xd / 15.0) / (0x53 / 255.0) = 0.4096
r = fa * (0xc / 15.0) + fb * (0xea / 255.0) = 0.99853
But when computing in 8 bits, we get:
fa8 = ((255 - 0x53) * 255 + 0xdd / 2) / 0xdd = 0xc6
fb8 = ((255 - 0xdd) * 255 + 0x53 / 3) / 0x53 = 0x68
r8 = (fa8 * 0xcc + 127) / 255 + (fb8 * 0xea + 127) / 255 = 0xfd
and
0xfd / 255.0 = 0.9921568627450981
for a deviation of 0.00637118610187, which we then have to consider
acceptable given the current implementation.
By switching to computing the result with
r = (fa * s + fb * d + 127) / 255
rather than
r = (fa * s + 127) / 255 + (fb * d + 127) / 255
the deviation would be only 0.00244961747442, so at some point it may
be worth doing either this, or switching to floating point for
operators that involve divisions.
Note that the conversion from 4 bits to 8 bits does not cause any
error in this case because both rounding and bit replication produces
an exact result when the number of from-bits divide the number of
to-bits.
== a8r8g8b8 OVER r5g6b5 ==
When OVER compositing the a8r8g8b8 pixel 0x0f00c300 with the x14r6g6b6
pixel 0x03c0, the true floating point value of the resulting green
channel is:
0xc3 / 255.0 + (1.0 - 0x0f / 255.0) * (0x0f / 63.0) = 0.9887955
but when compositing 8 bit values, where the 6-bit green channel is
converted to 8 bit through bit replication, the 8-bit result is:
0xc3 + ((255 - 0x0f) * 0x3c + 127) / 255 = 251
which corresponds to a real value of 0.984314. The difference from the
true value is 0.004482 which is bigger than the acceptable deviation
of 0.004. So, if we were to compute all the CONJOINT/DISJOINT
operators in floating point, or otherwise make them more accurate, the
acceptable deviation could be set at 0.0045.
If we were doing the 6-bit conversion with rounding:
(x / 63.0 * 255.0 + 0.5)
instead of bit replication, the deviation in this particular case
would be only 0.0005, so we may want to consider this at some
point.
This test program contains a table of individual operator/pixel
combinations. For each pixel combination, images of various sizes are
filled with the pixels and then composited. The result is then
verified against the output of do_composite(). If the result doesn't
match, detailed error information is printed.
The initial 14 pixel combinations currently all fail.
The check-formats.c test depends on the exact format of the strings
returned from these functions, so add a test here.
a1-trap-test isn't the ideal place, but it seems like overkill to add
a new test just for these trivial checks.
Given an operator and two formats, this program will composite and
check all pixels where the red and blue channels are 0. That is, if
the two formats are a8r8g8b8 and a4r4g4b4, all source pixels matching
the mask
0xff00ff00
are composited with the given operator against all destination pixels
matching the mask
0xf0f0
and the result is then verified against the do_composite() function
that was moved to utils.c earlier.
This program reveals that a number of operators and format
combinations are not computed to within the precision currently
accepted by pixel_checker_t. For example:
check-formats over a8r8g8b8 r5g6b5 | grep failed | wc -l
30
reveals that there are 30 pixel combinations where OVER produces
insufficiently precise results for the a8r8g8b8 and r5g6b5 formats.
In c2cb303d33, return_if_fail()s were added to
prevent the trapezoid rasterizers from being called with non-alpha
formats. However, stress-test actually does call the rasterizers with
non-alpha formats, but because _pixman_log_error() is disabled in
versions with an odd minor number, the errors never materialized.
Fix this by changing the argument to random format to an enum of three
values DONT_CARE, PREFER_ALPHA, or REQUIRE_ALPHA, and then in the
switch that calls the trapezoid rasterizers, pass the appropriate
value for the function in question.
In particular this affects single-core ARMs (e.g. ARM11, Cortex-A8), which
are usually configured this way. For other CPUs, this should only add a
constant time, which will be cancelled out by the EXCLUDE_OVERHEAD runs.
The problems were caused by cachelines becoming permanently evicted from
the cache, because the code that was intended to pull them back in again on
each iteration assumed too long a cache line (for the L1 test) or failed to
read memory beyond the first pixel row (for the L2 test). Also, the reloading
of the source buffer was unnecessary.
These issues were identified by Siarhei in this post:
http://lists.freedesktop.org/archives/pixman/2013-January/002543.html
Old functions pixman_transform_point() and pixman_transform_point_3d()
now become just wrappers for pixman_transform_point_31_16() and
pixman_transform_point_31_16_3d(). Eventually their uses should be
completely eliminated in the pixman code and replaced with their
extended range counterparts. This is needed in order to be able
to correctly handle any matrices and parameters that may come
to pixman from the code responsible for XRender implementation.
This test uses __float128 data type when it is available
for implementing a "perfect" reference implementation. The
output from from pixman_transform_point_31_16() and
pixman_transform_point_31_16_affine() is compared with the
reference implementation to make sure that the rounding
errors may only show up in a single least significant bit.
The platforms and compilers, which do not support __float128
data type, can rely on crc32 checksum for the pseudorandom
transform results.
This adds two extra tests, src_n_8 and src_8_8, which I have been
using to benchmark my ARMv6 changes.
I'd also like to propose that it requires an exact test name as the
executable's argument, as achieved by this strstr to strcmp change.
Without this, it is impossible to only benchmark (for example)
add_8_8, add_n_8 or src_n_8, due to those also being substrings of
many other test names.
This function returns the name of the given format code, which is
useful for printing out debug information. The function is written as
a switch without a default value so that the compiler will warn if new
formats are added in the future. The fake formats used in the fast
path tables are also recognized.
The function is used in alpha_map.c, where it replaces an existing
format_name() function, and in blitters-test.c, affine-test.c, and
scaling-test.c.
This function returns the name of the given operator, which is useful
for printing out debug information. The function is done as a switch
without a default value so that the compiler will warn if new
operators are added in the future.
The function is used in affine-test.c, scaling-test.c, and
blitters-test.c.
The entry points add_trapezoids(), rasterize_trapezoid() and
composite_trapezoid() are exercised with random trapezoids.
This uncovers crashes with stress-test seeds 0x17ee and 0x313c.
