Details:
- Removed four trailing spaces after "BLIS" that occurs in most files'
commented-out license headers.
- Added UT copyright lines to some files. (These files previously had
only AMD copyright lines but were contributed to by both UT and AMD.)
- In some files' copyright lines, expanded 'The University of Texas' to
'The University of Texas at Austin'.
- Fixed various typos/misspellings in some license headers.
Details:
- Added lines associated with the testsuite's new threading option to
input.general.fast. This change was intended for the previous commit
(10d0735).
Details:
- Replaced critical sections that were conditional upon multithreading
being enabled (via pthreads or OpenMP) with unconditional use of
pthreads mutexes. (Why pthreads? Because BLIS already requires it
for its initialization mechanism: pthread_once().) This was done in
bli_error.c, bli_gks.c, bli_l3_ind.c. Also, replaced usage of BLIS's
mtx_t object and bli_mutex_*() API with pthread mutexes in
bli_thread.c. The previous status quo could result in a race condition
if the application called BLIS from more than one thread. The new
pthread-based code should be completely agnostic to the application's
threading configuration. Thanks to AMD for bringing to our attention
the need for a thread-safety review.
- Added an option to the testsuite to simulate application-level
multithreading. Specifically, each thread maintains a counter that is
incremented after each experiment. The thread only executes the
experiment if: counter % n_threads == thread_id. In other words, the
threads simply take turns executing each problem experiment. Also,
POSIX guarantees that fprintf() will not intermingle output, so
output was switched to fprintf() instead of libblis_test_fprintf().
- Changed membrk_t objects to use pthread_mutex_t intead of mtx_t and
replaced use of bli_mutex_init()/_finalize() in bli_membrk.c with
wrappers to pthread_mutex_init()/_destroy().
- Changed the implementation of bli_l3_ind_oper_enable_only() to fix
a race condition; specifically, two threads calling the function with
the same parameters could lead to a non-deterministic outcome.
- Added #include <pthread.h> to bli_cpuid.c and moved the same in
bli_arch.c.
- Added 'const' to declaration of OPT_MARKER in bli_getopt.c.
- Added #include <pthread.h> to bli_system.h.
- Added add-copyright.py script to automate adding new copyright lines
to (and updating existing lines of) source files.
Details:
- Fixed stale filepaths to check-blastest.sh and check-blistest.sh in
travis/do_testsuite.sh and travis/do_sde.sh.
- Create a symbolic link to the 'config' directory so that the top-level
Makefile can find the configs' make_defs.mk files during out-of-tree
builds.
- Added additional case handling to out-of-tree scenario to handle
situations where files 'Makefile', 'common.mk', or 'config' exist but
are not symbolic links. In such cases, configure warns the user and
exits.
- Homogenized various error messages throughout configure.
- Belated thanks to Victor Eijkhout for requesting the feature added
in 0f491e9 whereby lesser Makefiles can compile and link against
an existing installation of BLIS.
Details:
- Updated the build system so that "lesser" Makefiles, such as those in
belonging to example code or the testsuite, may be run even if the
directory is orphaned from the original build tree. This allows a
user to configure, compile, and install BLIS, delete the build tree
(that is, the source distribution, or the build directory for out-
of-tree builds) and then compile example or testsuite code and link
against the installed copy of BLIS (provided the example or testsuite
directory was preserved or obtained from another source). The only
requirement is that make be invoked while setting the
BLIS_INSTALL_PATH variable to the same installation prefix used when
BLIS was configured. The easiest syntax is:
make BLIS_INSTALL_PATH=/install/prefix
though it's also permissible to set BLIS_INSTALL_PATH as an
environment variable prior to running 'make'.
- Updated all lesser Makefiles to implement the new aforementioned build
behavior.
- Relocated check-blastest.sh and check-blistest.sh from build to
blastest and testsuite, respectively, so that if those directories are
copied elsewhere the user can still run 'make check' locally.
- Updated docs/Testsuite.md with language that mentions this new option
of building/linking against an installed copy of BLIS.
Details:
- Changed configure so that the absence of any C++ compiler from the
pre-defined search list does not result in an exit. Instead, in this
situation, the found_cxx variable is assigned 'c++notfound' and the
error message is changed to remind the user that C++ will not be
available in the sandbox. Thanks to Devangi Parikh for reporting this
issue.
- Also tweaked the message when a C++ compiler *is* found to remind any
would-be confused user that BLIS will only use C++ if it is needed by
code in the sandbox.
Details:
- Fixed a bug in the way that the variadic bli_cntx_set_l3_nat_ukrs()
function was defined. This function is meant to take a microkernel id,
microkernel datatype, microkernel address, and microkernel preference
as arguments, and is typically called within the bli_cntx_init_*()
function defined within a sub-configuration for initializing an
appropriate context. The problem is with the final argument: the
microkernel preference. These preferences are actually boolean values,
0 or 1 (encoded as FALSE or TRUE). Since the variadic function does
not give the compiler any type information for any variadic arguments,
they are "promoted" in the course of internal (macroized) processing
according to default argument promotion rules. Thus, integer literals
such as 0 and 1 become int and floating-point literals (such as 0.0 or
1.0) become double. Previous to this commit, we indicated to va_arg()
that the ukernel preference was a 'bool_t', which is a typedef of
int64_t on 64-bit systems. On systems where int is defined as 64 bits,
no problems manifest since int is the same size as the type we passed
in to va_arg(), but on systems where int is 32 bits, the ukernel
preference could be misinterpreted as a garbage value. (This was
observed on a modern armv8 system.) The fix was to interpret the
bool_t value as int and then immediately typecast it to and store it
as a bool_t. Special thanks to Devangi Parikh for helping track down
this issue, including deciphering the use of va_arg() and its
byzantine treatment of types.
- Added explicit typecasts for all invocations of va_arg() in
bli_cntx.c.
Details:
- Fixed a memory leak in the global kernel structure that resulted in 56
bytes per configured architecture (of which only 18 are presently
supported by BLIS). The leak would only manifest if BLIS was
initialized and then finalized before the application terminated.
Thanks to Devangi Parikh for helping track down this leak.
Details:
- Previously, bli_finalize_once()--which, like bli_init_once(), was
implemented in terms of pthread_once()--was using the same
pthread_once_t control object being used by bli_init(), thus
guaranteeing that it would never be called as long as BLIS had already
been initialized. This could manifest as a rather large memory leak to
any application that attempted to finalize BLIS midway through its
execution (since BLIS reserves several megabytes of storage for
packing buffers per thread used). The fix entailed giving each
function its own pthread_once_t object. Thanks to Devangi Parikh for
helping track down this very quiet bug.
Details:
- Changed the cleanmk target to delete makefile fragments from their new
home in obj/$(CONFIG_NAME). The old definition worked only because of
a typo (REFERKN_PATH instead of REFKERN_PATH), and only in the
non-verbose (V != 1) case.
Details:
- Disable sandbox-related obj directory creation, directory mirroring,
and makefile fragment generation when a sandbox is not enabled.
- Prevent various duplicate actions by configure (such as those
mentioned above for sandboxes above).
Details:
- The docs/ConfigurationHowTo.md document was written with examples that
did not yet contain the skx sub-configuration, but the previous commit
included bli_arch.c code copied and pasted from a recent commit that
does support skx. To keep things consistent, I've removed skx from the
recently-added ConfigurationHowTo.md code snippet.
Details:
- Added missing language directing the reader to modify the config_name
string array in bli_arch.c when adding a new sub-configuration. Thanks
to Devangi Parikh for reporting this missing section.
Details:
- Fixed some stale code that was preventing the -p option to configure
from working as expected (though the --prefix option was unaffected).
This bug was was most likely introduced in 7e5648c (May 7 2018).
Thanks to Dave Love for reporting this issue.
Details:
- Redefined the 'test' make target in the top-level Makefile so that the
final result ("everything passed" or at "least one failure") is echoed
to stdout. Note that 'check' is unchanged, and thus is now effectively
a fast version of 'test'.
- Updated docs/BuildSystem.md to reflect the above change.
Details:
- Fixed a linker error that occurred when attempting to compile and link
the testsuite and/or BLAS test drivers after having configured BLIS to
only generate a shared library (no static library). The chosen
solution involved
(1) adding the local library path, $(BASE_LIB_PATH), to the search
paths for the shared library via the link option
-Wl,-rpath,$(BASE_LIB_PATH).
(2) adding a local symlink to $(BASE_LIB_PATH) that uses the .so major
version number so that ld would find the shared library at
execution time.
Thanks to Sajid Ali for reporting this issue, to Devin Matthews for
pointing out the need for the -rpath option, and to Devangi Parikh for
helping Sajid isolate the problem.
- Added #include <ctype.h> to bli_system.h to avoid a compiler warning
resulting from using toupper() from bli_string.c without a prototype.
Thanks again to Sajid Ali, whose build log revealed this compiler
warning.
- Added '*.so.*' to .gitignore.
- CREDITS file update.
Details:
- Removed a stray/accidental redefinition of axpyv and scal2v function
types in frame/1d/bli_l1d_ft.h (probably a copy/paste leftover during
development).
Details:
- Updated older _ft kernel type suffixes used within penryn level-1v
and -1f kernels to use the newer _ker_ft suffix that was introduced
in 0175483. (Thank you Travis CI.)
Details:
- Previously, most object API functions (_oapi.c) used a function
chooser macro that would expand out to an if-elseif-elseif-else
conditional that used a num_t datatype to call the appropriate
type-specific API (_tapi.c). This always felt a little hackish, and
would get in the way somewhat of addig support for new num_t datatypes
in the future. So, I've replaced that functionality with code that
queries a function pointer that is then typecast appropriately. This
model of function calling was already pervasive for kernels queried
from the cntx_t structure. It was also already in use in various other
functions, such as macrokernels, and this commit simply extends that
pattern.
- The above change required many new files, mostly header files, that
define the function types (mostly _ft.h) for the queriable functions
as well as some source files to define the function pointer arrays and
their corresponding query functions (_fpa.c). Various other function
types, mostly for kernel function types, were renamed to reduce the
potential for confusion with the function types for expert and basic
(non-expert) typed API functions.
- Removed definitions for all of the "bli_call_ft_*()" function chooser
macros from bli_misc_macro_defs.h.
Details:
- Removed the dtime (delta time, or wallclock time) column from the
matlab output of all test drivers in test, test/3m4m, test/studies.
This value was rarely (if ever) really needed and usually only served
to take up screen space.
- Updated format specifier in test/studies/skx to use %7.2f instead of
%6.3f.
- For the test drivers in 'test' directory, added an initial line of
output that sets last entry of matlab matrix to zero in order to
induce a pre-allocation of the entire array of performance results.
Details:
- Changed the format specifier for the gflops column in the testsuite
output from %7.3f to %7.2f. This was done mainly to keep the output
aligned properly when the expected perfomance exceeded 1000 gflops.
Also, two decimal places still conveys plenty of precision for all
practical applications, including just eyeballing performance deltas
between two executions (let alone two implementations).
- Changed the format specifier for gflops in the test/3m4m drivers
from %6.3f to %7.2f (for the same reasons listed above).
Details:
- Fixed bug in static function bli_cntx_set_[packm/unpackm]_ker_dt(), which
were incorrectly calling bli_cntx_get_[packm/unpackm]_ker_dt to get the
corresponding func_t.
Details:
- Added links, and sandbox language to README.md.
- Adjusted some comments in high-level level-3 object functions to make
clear what bli_thread_init_rntm() does.
