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 explicit typecasting to various functions (mostly static
functions), primarily those in bli_param_macro_defs.h,
bli_obj_macro_defs.h, bli_cntx.h, bli_cntl.h, and a few other header
files.
- This change was prompted by feedback from Jacob Gorm Hansen, who
reported that #including "blis.h" from his application caused a
gcc to output error messages (relating to types being returned
mismatching the declared return types) when used via the C++ compiler
front-end. This is the first pass of fixes, and we may need to
iterate with additional follow-up commits (#233).
Details:
- Fixed an unused variable warning in frame/base/bli_rntm.c when
multithreading is disabled.
- Fixed a missing variable declaration in bli_thread_init_rntm_from_env()
when multithreading is disabled.
Details:
- Defined a new struct datatype, rntm_t (runtime), to house the thrloop
field of the cntx_t (context). The thrloop array holds the number of
ways of parallelism (thread "splits") to extract per level-3
algorithmic loop until those values can be used to create a
corresponding node in the thread control tree (thrinfo_t structure),
which (for any given level-3 invocation) usually happens by the time
the macrokernel is called for the first time.
- Relocating the thrloop from the cntx_t remedies a thread-safety issue
when invoking level-3 operations from two or more application threads.
The race condition existed because the cntx_t, a pointer to which is
usually queried from the global kernel structure (gks), is supposed to
be a read-only. However, the previous code would write to the cntx_t's
thrloop field *after* it had been queried, thus violating its read-only
status. In practice, this would not cause a problem when a sequential
application made a multithreaded call to BLIS, nor when two or more
application threads used the same parallelization scheme when calling
BLIS, because in either case all application theads would be using
the same ways of parallelism for each loop. The true effects of the
race condition were limited to situations where two or more application
theads used *different* parallelization schemes for any given level-3
call.
- In remedying the above race condition, the application or calling
library can now specify the parallelization scheme on a per-call basis.
All that is required is that the thread encode its request for
parallelism into the rntm_t struct prior to passing the address of the
rntm_t to one of the expert interfaces of either the typed or object
APIs. This allows, for example, one application thread to extract 4-way
parallelism from a call to gemm while another application thread
requests 2-way parallelism. Or, two threads could each request 4-way
parallelism, but from different loops.
- A rntm_t* parameter has been added to the function signatures of most
of the level-3 implementation stack (with the most notable exception
being packm) as well as all level-1v, -1d, -1f, -1m, and -2 expert
APIs. (A few internal functions gained the rntm_t* parameter even
though they currently have no use for it, such as bli_l3_packm().)
This required some internal calls to some of those functions to
be updated since BLIS was already using those operations internally
via the expert interfaces. For situations where a rntm_t object is
not available, such as within packm/unpackm implementations, NULL is
passed in to the relevant expert interfaces. This is acceptable for
now since parallelism is not obtained for non-level-3 operations.
- Revamped how global parallelism is encoded. First, the conventional
environment variables such as BLIS_NUM_THREADS and BLIS_*_NT are only
read once, at library initialization. (Thanks to Nathaniel Smith for
suggesting this to avoid repeated calls getenv(), which can be slow.)
Those values are recorded to a global rntm_t object. Public APIs, in
bli_thread.c, are still available to get/set these values from the
global rntm_t, though now the "set" functions have additional logic
to ensure that the values are set in a synchronous manner via a mutex.
If/when NULL is passed into an expert API (meaning the user opted to
not provide a custom rntm_t), the values from the global rntm_t are
copied to a local rntm_t, which is then passed down the function stack.
Calling a basic API is equivalent to calling the expert APIs with NULL
for the cntx and rntm parameters, which means the semantic behavior of
these basic APIs (vis-a-vis multithreading) is unchanged from before.
- Renamed bli_cntx_set_thrloop_from_env() to bli_rntm_set_ways_for_op()
and reimplemented, with the function now being able to treat the
incoming rntm_t in a manner agnostic to its origin--whether it came
from the application or is an internal copy of the global rntm_t.
- Removed various global runtime APIs for setting the number of ways of
parallelism for individual loops (e.g. bli_thread_set_*_nt()) as well
as the corresponding "get" functions. The new model simplifies these
interfaces so that one must either set the total number of threads, OR
set all of the ways of parallelism for each loop simultaneously (in a
single function call).
- Updated sandbox/ref99 according to above changes.
- Rewrote/augmented docs/Multithreading.md to document the three methods
(and two specific ways within each method) of requesting parallelism
in BLIS.
- Removed old, disabled code from bli_l3_thrinfo.c.
- Whitespace changes to code (e.g. bli_obj.c) and docs/BuildSystem.md.
* Add appveyor file
* Build script
* Remove fPIC for now
* copy as
* set CC and CXX
* Change the order of immintrin.h
* Fix testsuite header
* Move testsuite defs to .c
* Fix appveyor file
* Remove fPIC again and fix strerror_r missing bug
* Remove appveyor script
* cd to blis directory
* Fix sleep implementation
* Add f2c_types_win.h
* Fix f2c compilation
* Remove rdp and rename appveyor.yml
* Remove setenv declaration in test header
* set CPICFLAGS to empty
* Fix another immintrin.h issue
* Escape CFLAGS and LDFLAGS
* Fix more ?mmintrin.h issues
* Build x86_64 in appveyor
* override LIBM LIBPTHREAD AR AS
* override pthreads in configure
* Move windows definitions to bli_winsys.h
* Fix LIBPTHREAD default value
* Build intel64 in appveyor for now
Details:
- Implemented bli_obj_scalar_cast_to(), which will typecast the value in
the internal scalar of an obj_t to a specified datatype.
- Changed bli_obj_scalar_attach() so that the scalar value being attached
is first typecast to the storage datatype of the destination object
rather than the target datatype.
- Reformatted function type signatures in bli_obj_scalar.c as well as
prototypes in its corresponding header file.
Details:
- Added a new field to the auxinfo_t struct that can be used, in theory,
to request type conversion before the microkernel stores/accumulates
its microtile back to memory.
- Added the appropriate get/set static functions to bli_type_defs.h.
Details:
- Implemented castm and castv operations, which behave like copym and
copyv except where the obj_t operands can be of different datatypes.
These new operations, however, unlike copym/copyv, do not build upon
existing level-1v kernels.
- Reorganized projm, projv into a 'proj' subdirectory of frame/base (to
match the newly added frame/base/cast directory).
- Added new macros to bli_gentfunc_macro_defs.h, _gentprot_macro_defs.h
that insert GENTFUNC2/GENTPROT2 macros for all non-homogeneous datatype
combinations. Previously, one had to invoke two additional macros--one
which mixed domains only and another that included all remaining
cases--in order to get full type combination coverage.
- Defined a new static function, bli_set_dims_incs_2m(), to aid in the
setting of various variables in the implementations of bli_??castm().
This static function joins others like it in bli_param_macro_defs.h.
- Comment update to bli_copysc.h.
Details:
- Added a new static function to bli_blksz.h that scales both the default
(regular) blocksize as well as the maximum blocksize in the blksz_t
object. Reminder: maximum blocksizes have different meanings in
different contexts. For register blocksizes, they refer to the packing
register blocksizes (PACKMR or PACKNR) while for cache blocksizes, they
refer to the maximum blocksize to use during the final iteration of a
loop.
Details:
- Changed the way virtual microkernels are handled in the context.
Previously, there were query routines such as bli_cntx_get_l3_ukr_dt()
which returned the native ukernel for a datatype if the method was
equal to BLIS_NAT, or the virtual ukernel for that datatype if the
method was some other value. Going forward, the context native and
virtual ukernel slots will both be initialized to native ukernel
function pointers for native execution, and for non-native execution
the virtual ukernel pointer will be something else. This allows us
to always query the virtual ukernel slot (from within, say, the
macrokernel) without needing any logic in the query routine to decide
which function pointer (native or virtual) to return. (Essentially,
the logic has been shifted to init-time instead of compute-time.)
This scheme will also allow generalized virtual ukernels as a way
to insert extra logic in between the macrokernel and the native
microkernel.
- Initialize native contexts (in bli_cntx_ref.c) with native ukernel
function addresses stored to the virtual ukernel slots pursuant to
the above policy change.
- Renamed all static functions that were native/virtual-ambiguous, such
as bli_cntx_get_l3_ukr_dt() or bli_cntx_l3_ukr_prefers_cols_dt()
pursuant to the above polilcy change. Those routines now use the
substring "get_l3_vir_ukr" in their name instead of "get_l3_ukr". All
of these functions were static functions defined in bli_cntx.h, and
most uses were in level-3 front-ends and macrokernels.
- Deprecated anti_pref bool_t in context, along with related functions
such as bli_cntx_l3_ukr_eff_dislikes_storage_of(), now that 1m's
panel-block execution is disabled.
Details:
- Implemented bli_acquire_mpart(), a general-purpose submatrix view
function that will alias an obj_t to be a submatrix "view" of an
existing obj_t.
- Renumbered examples in examples/oapi and inserted a new example file,
03obj_view.c, which shows how to use bli_acquire_mpart() to obtain
submatrix views of existing objects, which can then be used to
indirectly modify the parent object.
Details:
- Defined new wrappers to setm/setv operations in frame/base/bli_setri.c
that will target only the real or only the imaginary parts of a
matrix/vector object.
- Updated bli_obj_real_part() so that the complex-specific portions of
the function are not executed if the object is real.
- Defined bli_obj_imag_part().
- Caveat: If bli_obj_imag_part() is called on a real object, it does
nothing, leaving the destination object untouched. The caller must
take care to only call the function on complex objects.
- Reordered some of the static functions in bli_obj_macro_defs.h related
to aliasing.
Details:
- Added an implementation for bli_projv() to go along with the
implementation of bli_projm() added in 0a4a27e. The only difference
between the two is that bli_projv() may only be used on vectors,
whereas bli_projm() is general-purpose.
- Added a _check() function corresponding to bli_projv().
Details:
- Defined additional functions in bli_param_map.c:
bli_param_map_char_to_blis_dt()
bli_param_map_blis_to_char_dt()
which will map a char to its corresponding num_t, or vice versa.
Details:
- Defined a new operation in frame/base/bli_proj.c, bli_projm(), which
behaves like bli_copym(), except that operands a and b are allowed to
contain data of differing domains (e.g. a is real while b is complex,
or vice versa). The file is named bli_proj.c, rather than bli_projm.c,
with the intention that a 'v' vector version of the function may be
added to the same file (at some point in the future).
- Added supporting bli_check_*() functions in bli_check.c to confirm
consistent precisions between to datatypes/objects, as well as the
appropriate error message in bli_error.c and a new error code in
bli_type_defs.h.
- Wrote a bli_projm_check() function to go along with bli_projm().
- Defined static function bli_obj_real_part() in bli_obj_macro_defs.h,
which will initialize an obj_t alias to the real part of the source
object.
- Fixed a bug in the static function bli_dt_proj_to_complex(), found
in bli_param_macro_defs.h. Thankfully, there were no calls to the
function to produce buggy behavior.
- Query pack schemas in level-3 bli_*_front() functions and store those
values in the schema bitfields of the correponding obj_t's when the
cntx's method is not BLIS_NAT. (When method is BLIS_NAT, the default
native schemas are stored to the obj_t's.)
- In bli_l3_cntl_create_if(), query the schemas stored to the obj_t's in
bli_*_front(), clear the schema bitfields, and pass the queried values
into bli_gemm_cntl_create() and bli_trsm_cntl_create().
- Updated APIs for bli_gemm_cntl_create() and bli_trsm_cntl_create() to
take schemas for A and B, and use these values to initialize the
appropriate control tree nodes. (Also cpp-disabled the panel-block cntl
tree creation variant, bli_gemmpb_cntl_create(), as it has not been
employed by BLIS in quite some time.)
- Simplified querying of schema in bli_packm_init() thanks to above
changes.
- Updated openmp and pthreads definitions of bli_l3_thread_decorator()
so that thread-local aliases of matrix operands are guaranteed, even
if aliasing is disabled within the internal back-end functions (e.g.
bli_gemm_int.c). Also added a comment to bli_thrcomm_single.c
explaining why the extra aliasing is not needed there.
- Change bli_gemm() and level-3 friends so that the operation's ind()
function is called only if all matrix operands have the same datatype,
and only if that datatype is complex. The former condition is needed
in preparation for work related to mixed domain operands, while the
latter helps with readability, especially for those who don't want to
venture into frame/ind.
- Reshuffled arguments in bli_cntx_set_thrloop_from_env() to be
consistent with BLIS calling conventions (modified argument(s) are
last), and updated all invocations in the level-3 _front() functions.
- Comment updates to bli_cntx_set_thrloop_from_env().
Details:
- Changed the void* arguments of the following static functions:
bli_is_aligned_to()
bli_is_unaligned_to()
bli_offset_past_alignment()
to siz_t, and the return type of bli_offset_past_alignment() from
guint_t to siz_t. This allows for more versatile usage of these
functions (e.g. when aligning both pointers and leading dimension).
- Updated all invocations of these functions, mostly in kernels/penryn
but also in kernels/bgq, to include explicit typecasts to siz_t when
pointer arguments are passed in.
- Thanks to Devin Matthews for pointing out this potential bug (via issue
#211).
- Deleted a few trailing spaces in various penryn kernels.
- Removed duplicate instances of the words "derived" and "THEORY" from
various kernel license headers, likely from a malformed recursive sed
performed long ago.
Details:
- Added HP Enterprise to the LICENSE file. Previously, only the source
files touched by HPE contained the corresponding copyright notices.
(This oversight was unintentional.)
- Updated file-level copyright notices to include a comma, to match
the formatting used for UT and AMD copyrights.
Details:
- Removed critical sections protecting the initialization/finalization of
bli_memsys.c. These synchronization mechanisms are no longer needed now
that BLIS initializes all APIs via pthread_once().
Details:
- Added logic to bli_arch.c that will call what was previously the body
of bli_arch_query_id() only once and then cache the value in a static
variable local to the file. (Previously, the arch_t associated with
the hardware/configuration was queried every time bli_arch_query_id()
was called, which was at least once per level-3 function call. Thanks
to Devin Matthews for suggesting this feature via issue #175.
- Added -lpthread to the compile/link command line of the compiler
invocation that compiles build/detect/config/config_detect.c, which
prints the string identifying the detected configuration, since it
is now needed due to new pthread_once() logic in bli_arch.c.
- Implementation note: I chose to implement this arch_t caching feature
via pthread_once(), using a separate pthread_once_t variable local to
the file, rather than calling bli_init_once(). The reason is that I
did not want to require bli_init() as a prerequisite to this function.
bli_init() already calls several sub-components, some of which make use
of bli_arch_query_id(), and therefore it would be easy to fall into a
circular self-init situation (which usually causes pthreads to hang
indefinitely).
Details:
- Renamed the following variables in config.mk (via build/config.mk.in):
BLIS_ENABLE_VERBOSE_MAKE_OUTPUT -> ENABLE_VERBOSE
BLIS_ENABLE_STATIC_BUILD -> MK_ENABLE_STATIC
BLIS_ENABLE_SHARED_BUILD -> MK_ENABLE_SHARED
BLIS_ENABLE_BLAS2BLIS -> MK_ENABLE_BLAS
BLIS_ENABLE_CBLAS -> MK_ENABLE_CBLAS
BLIS_ENABLE_MEMKIND -> MK_ENABLE_MEMKIND
and also renamed all uses of these variables in makefiles and makefile
fragments. Notice that we use the "MK_" prefix so that those variables
can be easily differentiated (such as via grep) from their "BLIS_" C
preprocessor macro counterparts.
- Other whitespace changes to build/config.mk.in.
- Renamed the following C preprocessor macros in bli_config.h (via
build/bli_config.h.in):
BLIS_ENABLE_BLAS2BLIS -> BLIS_ENABLE_BLAS
BLIS_DISABLE_BLAS2BLIS -> BLIS_DISABLE_BLAS
BLIS_BLAS2BLIS_INT_TYPE_SIZE -> BLIS_BLAS_INT_TYPE_SIZE
and also renamed all relevant uses of these macros in BLIS source
files.
- Renamed "blas2blis" variable occurrences in configure to "blas", as
was done in build/config.mk.in and build/bli_config.h.in.
- Renamed the following functions in frame/base/bli_info.c:
bli_info_get_enable_blas2blis() -> bli_info_get_enable_blas()
bli_info_get_blas2blis_int_type_size()
-> bli_info_get_blas_int_type_size()
- Remove bli_config.h during 'make cleanh' target of top-level Makefile.
Details:
- Converted most C preprocessor macros in bli_param_macro_defs.h and
bli_obj_macro_defs.h to static functions.
- Reshuffled some functions/macros to bli_misc_macro_defs.h and also
between bli_param_macro_defs.h and bli_obj_macro_defs.h.
- Changed obj_t-initializing macros in bli_type_defs.h to static
functions.
- Removed some old references to BLIS_TWO and BLIS_MINUS_TWO from
bli_constants.h.
- Whitespace changes in select files (four spaces to single tab).
Details:
- Added bli_setgetijm.c, which defines bli_setijm(), bli_getijm(), and
related functions that can be used to read and write individual
elements of an obj_t.
- Defined a new function, bli_obj_create_conf_to(), in bli_obj.c that will
create a new object with dimensions conformal to an existing object.
Transposition and conjugation states on the existing object are ignored,
as are structure and uplo fields.
- Defined a new function, bli_datatype_string(), in bli_obj.c that returns
a char* to a string representation of the name of each num_t datatype.
For example, BLIS_DOUBLE is "double" and BLIS_DCOMPLEX is "dcomplex".
BLIS_INT is included (as "int"), but BLIS_CONSTANT is not, and thus is
not a valid input argument to bli_datatype_string().
- Added calls to bli_init_once() to various functions in bli_obj.c, the
most important of which was bli_obj_create_without_buffer().
- Removed unintended/extra newline from the end of printv output.
- Whitespace changes to
- frame/base/bli_machval.c
- frame/base/bli_machval.h
- frame/0/copysc/bli_copysc.c
- Trivial changes to README.md and common.mk.
Details:
- Defined a new function, bli_string_mkupper(), that calls toupper() on
every non-NULL character in a string.
- Call bli_string_mkupper() prior to calling xerbla_() in the level-2/-3
BLAS _check() macros. This prevents the BLAS testsuite from complaining
that the operation name (e.g. "dgemm") does not match the expected
value (e.g. "DGEMM"). Thanks to Dave Love for reporting this issue.
Details:
- Updated/clarified the ARM preprocessor macro branch of bli_cpuid.c.
Going forward, cortexa57 (64-bit), cortexa15, and cortexa9 (32-bit)
sub-configurations are supported. However, the functions that detect
features specific to a15 and a9 are identical, and since a15 is tested
first, it will always be chosen for arm32 hardware (even if both
sub-configurations were enabled at configure-time and the library is
linked and run on an a9). Thus, more work needs to be done to
distinguish these two.
- Added cpp guard around x86_64 portions of bli_cpuid.c. Now, either
the x86_64 or ARM code will be compiled (or neither, if neither
environment is detected).
- In bli_arch_query_id(), call bli_cpuid_query_id() when the
BLIS_FAMILY_ARM64 or BLIS_FAMILY_ARM32 macros are defined.
- Added arm64 and arm32 configuration families to config_registry.
- Added a note to the arch_t typedef enum in bli_type_defs.h reminding
the developer to update the string array in bli_arch.c whenever new
enum values are added or existing values are reordered.
Details:
- Changed the mc blocksize for double real execution in the knl sub-
configuration from 160 to 148. The old value was not a multiple of
mr (which is 24), and thus the safeguards in bli_gks_register_cntx()
were tripping. Thanks for Dave Love for reporting this issue.
- Switch knl sub-configuration to use default blocksizes for datatypes
not supported by native kernels.
- Fixed typos in bli_error.c that prevented certain error strings
(which report maximum cache blocksizes not being multiples of their
corresponding register blocksize) from properly initializing.
Details:
- Merged contributions made by AMD via 'amd' branch (see summary below).
Special thanks to AMD for their contributions to-date, especially with
regard to intrinsic- and assembly-based kernels.
- Added column storage output cases to microkernels in
bli_gemm_zen_asm_d6x8.c and bli_gemmtrsm_l_zen_asm_d6x8.c. Even with
the extra cost of transposing the microtile in registers, this is
much faster than using the general storage case when the underlying
matrix is column-stored.
- Added s and d assembly-based zen gemmtrsm_u microkernel (including
column storage optimization mentioned above).
- Updated zen sub-configuration to reflect presence of new native
kernels.
- Temporarily reverted zen sub-configuration's level-3 cache blocksizes
to smaller haswell values.
- Temporarily disabled small matrix handling for zen configuration
family in config/zen/bli_family_zen.h.
- Updated zen CFLAGS according to changes in 1e4365b.
- Updated haswell microkernels such that:
- only one vzeroupper instruction is called prior to returning
- movapd/movupd are used in leiu of movaps/movups for double-real
microkernels. (Note that single-real microkernels still use
movaps/movups.)
- Added kernel prototypes to kernels/zen/bli_kernels_zen.h, which is
now included via frame/include/bli_arch_config.h.
- Minor updates to bli_amaxv_ref.c (and to inlined "test" implementation
in testsuite/src/test_amaxv.c).
- Added early return for alpha == 0 in bli_dotxv_ref.c.
- Integrated changes from f07b176, including a fix for undefined
behavior when executing the 1m method under certain conditions.
- Updated config_registry; no longer need haswell kernels for zen
sub-configuration.
- Tweaked marginal and pass thresholds for dotxf.
- Reformatted level-1v, -1f, and -3 amd kernels and inserted additional
comments.
- Updated LICENSE file to explicitly mention that parts are copyright
UT-Austin and AMD.
- Added AMD copyright to header templates in build/templates.
Summary of previous changes from 'amd' branch.
- Added s and d assembly-based zen gemm microkernels (d6x8 and d8x6) and
s and d assembly-based zen gemmtrsm_l microkernels (d6x8).
- Added s and d intrinsics-based zen kernels for amaxv, axpyv, dotv, dotxv,
and scalv, with extra-unrolling variants for axpyv and scalv.
- Added a small matrix handler to bli_gemm_front(), with the handler
implemented in kernels/zen/3/bli_gemm_small_matrix.c.
- Added additional logic to sumsqv that first attempts to compute the
sum of the squares via dotv(). If there is a floating-point exception
(FE_OVERFLOW), then the previous (numerically conservative) code is
used; otherwise, the result of dotv() is square-rooted and stored as
the result. This new implementation is only enabled when FE_OVERFLOW
is #defined. If the macro is not #defined, then the previous
implementation is used.
- Added axpyv and dotv standalone test drivers to test directory.
- Added zen support to old cpuid_x86.c driver in build/auto-detect/old.
- Added thread-local and __attribute__-related macros to bli_macro_defs.h.
Details:
- Added "-std=c99" to compiler arguments when building auto-detection
driver in configure script.
- Added #include <stdint.h> to all three source files needed by auto-
detection program.
Details:
- Reimplemented the hardware detection functionality invoked when running
"./configure auto". Previously, a standalone script in build/auto-detect
that used CPUID was used. However, the script attempted to enumerate all
models for each microarchitecture supported. The new approach recycles
the same code used for runtime hardware detection introduced in 2c51356.
This has two immediate benefits. First, it reduces and consolidates the
code required to detect microarchitectures via the CPUID instruction.
Second, it provides an indirect way of testing at configure-time the
code that is used to detect hardware at runtime. This code is (a) only
activated when targeting a configuration family (such as intel64 or
amd64) at configure-time and (b) somewhat difficult to test in
practice, since it relies on having access to older microarchitectures.
- The above change required placing conditional cpp macro blocks in
bli_arch.c and bli_cpuid.c which either #include "blis.h" or #include
a bare-bones set of headers that does not rely on the presence of a
bli_config.h header. This is needed because bli_config.h has not been
created yet when configure-time auto-detection takes places.
- Defined a new function in bli_arch.c, bli_arch_string(), which takes
an arch_t id and returns a pointer to a string that contains the
lowercase name of the corresponding microarchitecture. This function
is used by the auto-detection script to printf() the name of the
sub-configuration corresponding to the detected hardware.
Details:
- Added a new configure option, --[en|dis]able-packbuf-pools, which will
enable or disable the use of internal memory pools for managing buffers
used for packing. When disabled, the function specified by the cpp
macro BLIS_MALLOC_POOL is called whenever a packing buffer is needed
(and BLIS_FREE_POOL is called when the buffer is ready to be released,
usually at the end of a loop). When enabled, which was the status quo
prior to this commit, a memory pool data structure is created and
managed to provide threads with packing buffers. The memory pool
minimizes calls to bli_malloc_pool() (i.e., the wrapper that calls
BLIS_MALLOC_POOL), but does so through a somewhat more complex
mechanism that may incur additional overhead in some (but not all)
situations. The new option defaults to --enable-packbuf-pools.
- Removed the reinitialization of the memory pools from the level-3
front-ends and replaced it with automatic reinitialization within the
pool API's implementation. This required an extra argument to
bli_pool_checkout_block() in the form of a requested size, but hides
the complexity entirely from BLIS. And since bli_pool_checkout_block()
is only ever called within a critical section, this change fixes a
potential race condition in which threads using contexts with different
cache blocksizes--most likely a heterogeneous environment--can check
out pool blocks that are too small for the submatrices it wishes to
pack. Thanks to Nisanth Padinharepatt for reporting this potential
issue.
- Removed several functions in light of the relocation of pool reinit,
including bli_membrk_reinit_pools(), bli_memsys_reinit(),
bli_pool_reinit_if(), and bli_check_requested_block_size_for_pool().
- Updated the testsuite to print whether the memory pools are enabled or
disabled.
Details:
- Fixed a race condition in self-initialization whereby the bli_is_init
static variable could be erroneously read as TRUE by thread 1 while
thread 0 is still executing bli_init_apis(), thus allowing thread 1 to
use the library before it is actually ready. Thanks to to Minh Quan Ho
and Devin Matthews for pointing out this issue.
- Part of the solution to the aforementioned race condition was involved
replacing the runtime initialization of the global scalar constants
(e.g., BLIS_ONE, BLIS_ZERO, etc.) in bli_const.c with a static
initialization of those same constants. This eliminates the need for
bli_const_init() altogether. (The static initialization is made concise
via preprocess macros.)
- Defined bli_gks_query_cntx_noinit(), which behaves just like
bli_gks_query_cntx(), except that it does not call bli_init_once(). This
function is called in lieu of bli_gks_query_cntx() in bli_ind_init() and
bli_memsys_init() so as to not result in any recursion into
bli_init_once().
- Removed BLIS_ONE_HALF, BLIS_MINUS_ONE_HALF global scalar constants.
They have no use in BLIS or its test products, and we have little reason
to believe they are used by others.
- Removed testsuite/out file, which was accidentally committed as part
of 70640a3.
Details:
- Defined two new functions in bli_init.c: bli_init_once() and
bli_finalize_once(). Each is implemented with pthread_once(), which
guarantees that, among the threads that pass in the same pthread_once_t
data structure, exactly one thread will execute a user-defined function.
(Thus, there is now a runtime dependency against libpthread even when
multithreading is not enabled at configure-time.)
- Added calls to bli_init_once() to top-level user APIs for all
computational operations as well as many other functions in BLIS to
all but guarantee that BLIS will self-initialize through the normal
use of its functions.
- Rewrote and simplified bli_init() and bli_finalize() and related
functions.
- Added -lpthread to LDFLAGS in common.mk.
- Modified the bli_init_auto()/_finalize_auto() functions used by the
BLAS compatibility layer to take and return no arguments. (The
previous API that tracked whether BLIS was initialized, and then
only finalized if it was initialized in the same function, was too
cute by half and borderline useless because by default BLIS stays
initialized when auto-initialized via the compatibility layer.)
- Removed static variables that track initialization of the sub-APIs in
bli_const.c, bli_error.c, bli_init.c, bli_memsys.c, bli_thread, and
bli_ind.c. We don't need to track initialization at the sub-API level,
especially now that BLIS can self-initialize.
- Added a critical section around the changing of the error checking
level in bli_error.c.
- Deprecated bli_ind_oper_has_avail() as well as all functions
bli_<opname>_ind_get_avail(), where <opname> is a level-3 operation
name. These functions had no use cases within BLIS and likely none
outside of BLIS.
- Commented out calls to bli_init() and bli_finalize() in testsuite's
main() function, and likewise for standalone test drivers in 'test'
directory, so that self-initialization is exercised by default.
Details:
- In bli_cpuid.c, fixed an off-by-one indexing statement in vpu_count()
whereby a string-terminating NULL character, '\0', is written beyond
the bounds of the model_num string.
- Minor whitespace and formatting edits to bli_cpuid.c.
Details:
- Fixed implicit typecasting of conj_t to trans_t in bli_[un]packm_cxk.c.
- Properly typecast integer arguments to match format specifier in various
calls to printf() in bli_l3_thrinfo.c, bli_cntx.c, bli_pool.c, and
bli_util_oapi.c.
- Fixed "unsigned less-than-comparison with zero" checks in bli_check.c,
bli_cntx.h.
- Fixed mis-typed enums in bli_cntx.c (e.g., l1mkr_t that should have been
l1fkr_t or l1vkr_t).
- Fixed instances of opid_t value BLIS_GEMM that should have been l3ukr_t
value BLIS_GEMM_UKR in bli_cntx_ref.c.
- NOTE: These issues were identified via compiler warnings when building
BLIS with clang on a rather old installation of OS X:
$ clang --version
Apple LLVM version 5.0 (clang-500.2.79) (based on LLVM 3.3svn)
Target: x86_64-apple-darwin15.2.0
Thread model: posix
BLIS provides APIs to initialize and finalize its global context.
One application thread can finalize BLIS, while other threads
in the application are stil using BLIS.
This issue can be solved by removing bli_finalize() from API.
One way to do this is by getting bli_finalize() to execute by default
after application exits from main().
GCC supports this behaviour with the help of __attribute__((destructor))
added to the function that need to be executed after main exits.
Similarly bli_init() can be made to run before application enters main()
so that application need not call it.
Change-Id: I7ce6cfa28b384e92c0bdf772f3baea373fd9feac
Details:
- Fixed a bug in gemmtrsm test module that was due to improper partitioning
into a k x k triangular matrix for the purposes of obtaining an mr x k
micropanel of A with which to test.
- Fixed a bug in gemm and gemmtrsm test modules that would only manifest for
very large k (depending on the product of mr x kc on that architecture).
The bug arose from the fact that the test module was triggering the
allocation of blocks from the internal memory pools, which are limited in
size. This allocation imposes an implicit assumption that the micro-
panel being tested with will fit inside, and this assumption is violated
for large values of k. Arbitrarily large k may now be tested for both
operation tests.
- Added OpenMP/pthread critical sections around the setting or getting of
statuses from the induced method operation lookup table in bli_l3_ind.c.
- Added the 'static' keyword to all pthread_mutex_t global variables in BLIS.
- Thanks to Nisanth Padinharepatt of AMD for reporting the first and third
issues.
