Details:
- Applied the following C preprocessor macro renames
BLIS_DEFAULT_MR_THREAD_MAX -> BLIS_THREAD_MAX_IR
BLIS_DEFAULT_NR_THREAD_MAX -> BLIS_THREAD_MAX_JR
BLIS_DEFAULT_M_THREAD_RATIO -> BLIS_THREAD_RATIO_M
BLIS_DEFAULT_N_THREAD_RATIO -> BLIS_THREAD_RATIO_N
in src/test_libblis.c. This is apparently the result of a failure by
git to properly merge the 'master' and 'amd' branches in the previous
commit. (The 'master' branch contained a commit, 53a9ab1, in which
these same cpp macros were renamed throughout the source distribution.
Details:
- Updated testsuite to output various parameters related to parallelism
in BLIS. These parameters include:
- threading status: disabled, openmp, or pthreads;
- thread partitioning for jr/ir loops: slab or rr (round-robin);
- ways of parallelism from environment variables, and also actual
values used by gemm, herk, trmm_l, trmm_r, trsm_l, and trsm_r for
square problems (assuming all dimensions are set to 1000);
- automatic thread factorization parameters.
- Also output the status of two relatively new configure-time options:
libmemkind and the sandbox.
Details:
- Rewrote bli_winsys.c to define bli_setenv() and bli_sleep()
unconditionally, but differently for Windows and non-Windows, but
then disabled the definition of bli_setenv() entirely since BLIS
no longer needs to set environment variables. Updated bli_winsys.h
accordingly, and call bli_sleep() from within testsuite instead of
sleep() directly.
- Use
#if !defined(_POSIX_BARRIERS) || (_POSIX_BARRIERS != 200809L)
instead of
#if !defined(_POSIX_BARRIERS) || (_POSIX_BARRIERS < 0)
when guarding against local definition of pthread barrier in
testsuite. (The description for unistd.h implies that _POSIX_BARRIERS
should always be set to 200809L when barriers are supported, though I
won't be surprised if we encounter a case in the future where it is
set to something else such as 1 while still supported.)
- Removed old _VERS_CONF_INST definitions and installation rules in
top-level Makefile. These are no longer needed because we no longer
output libraries with the version and configuration name as
substrings.
- Comment/whitespace updates in Makefile, config.mk.in, common.mk,
configure, bli_extern_defs.h, and test_libblis.h.
- Added mention of 1m to README.md and other trivial tweaks.
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:
- 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:
- 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:
- 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:
- 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:
- Removed the line in each operation entry in input.operations titled
"test sequential front-end" and the corresponding support for the lines
in the testsuite input parsing code. This line was included in the some
of the earliest versions of the testsuite, back when I intended to
eventually have separate multithreaded APIs. Specifically, I envisioned
that multithreaded and sequential testing could be enabled or disabled
on an operation level. However, BLIS evolved in a different direction
and still does not have multithreaded-specific APIs (even if it will
eventually someday). But even if it did have such APIs, I doubt I would
allow the user to enable/disable them on an operation level. Thus, this
was a zombie future parameter that was never used and never made sense
to begin with. The one instance of the front_seq variable, used in the
various libblis_test_<operation>() functions to guard the call to the
operation test driver, that remains was commented out instead of
deleted so that someday it could be easily changed via sed, if desired.
- Various minor cleanups to the testsuite code, including consolidating
use of DISABLE and DISABLE_ALL and reexpressing certain conditional
expressions in the libblis_test_<operation>() functions in terms of
boolean functions.
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:
- Mistakenly was calling bli_cpuid_query_id() instead of
bli_arch_query_id() in the recent addition to the testsuite output
that prints the active sub-configuration. The former function is
only used for multi-architecture builds, whereas the latter is the
more general option that also works for single configuration
(including 'configure auto') builds.
Details:
- Added a line to the testsuite output that prints the name of the
current/active sub-configuration. This is useful when linking the
testsuite against multi-configuration builds because it confirms
the sub-configuration that is actually being employed at runtime.
Thanks to Devin Matthews for suggesting this feature.
Details:
- Updated the testsuite driver so that setting one or more individual
operation test switches to "2" in input.operations will enable ONLY
those operations and disable all others, regardless of the values of
the section overrides and other operation switches. This makes it
every easy to quickly test only one or two operations, and equally
easy to revert back to the previous combination of operation tests.
- Added more comments to input.operations describing the use of
individual "enable only" overrides.
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 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:
- 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:
- 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.
Details:
- Removed the family field inside the cntx_t struct and re-added it to the
cntl_t struct. Updated all accessor functions/macros accordingly, as well
as all consumers and intermediaries of the family parameter (such as
bli_l3_thread_decorator(), bli_l3_direct(), and bli_l3_prune_*()). This
change was motivated by the desire to keep the context limited, as much
as possible, to information about the computing environment. (The family
field, by contrast, is a descriptor about the operation being executed.)
- Added additional functions to bli_blksz_*() API.
- Added additional functions to bli_cntx_*() API.
- Minor updates to bli_func.c, bli_mbool.c.
- Removed 'obj' from bli_blksz_*() API names.
- Removed 'obj' from bli_cntx_*() API names.
- Removed 'obj' from bli_cntl_*(), bli_*_cntl_*() API names. Renamed routines
that operate only on a single struct to contain the "_node" suffix to
differentiate with those routines that operate on the entire tree.
- Added enums for packm and unpackm kernels to bli_type_defs.h.
- Removed BLIS_1F and BLIS_VF from bszid_t definition in bli_type_defs.h.
They weren't being used and probably never will be.
Details:
- Implemented the 1m method for inducing complex domain matrix
multiplication. 1m support has been added to all level-3 operations,
including trsm, and is now the default induced method when native
complex domain gemm microkernels are omitted from the configuration.
- Updated _cntx_init() operations to take a datatype parameter. This was
needed for the corresponding function for 1m (because 1m requires us
to choose between column-oriented or row-oriented execution, which
requires us to query the context for the storage preference of the
gemm microkernel, which requires knowing the datatype) but I decided
that it made sense for consistency to add the parameter to all other
cntx initialization functions as well, even though those functions
don't use the parameter.
- Updated bli_cntx_set_blkszs() and bli_gks_cntx_set_blkszs() to take
a second scalar for each blocksize entry. The semantic meaning of the
two scalars now is that the first will scale the default blocksize
while the second will scale the maximum blocksize. This allows scaling
the two independently, and was needed to support 1m, which requires
scaling for a register blocksize but not the register storage
blocksize (ie: "packdim") analogue.
- Deprecated bli_blksz_reduce_dt_to() and defined two new functions,
bli_blksz_reduce_def_to() and bli_blksz_reduce_max_to(), for reducing
default and maximum blocksizes to some desired blocksize multiple.
These functions are needed in the updated definitions of
bli_cntx_set_blkszs() and bli_gks_cntx_set_blkszs().
- Added support for the 1e and 1r packing schemas to packm, including
1e/1r packing kernels.
- Added a minor optimization to bli_gemm_ker_var2() that allows, under
certain circumstances (specifically, real domain beta and row- or
column-stored matrix C), the real domain macrokernel and microkernel
to be called directly, rather than using the virtual microkernel
via the complex domain macrokernel, which carries a slight additional
amount of overhead.
- Added 1m support to the testsuite.
- Added 1m support to Makefile and runme.sh in test/3m4m. Also simplified
some code in test_gemm.c driver.
Details:
- Changed the interface of bli_getopt() to take a new argument, a getopt_t
struct, that stores the values of optarg, optind, opterr, and optopt,
and updated the implementation accordingly. (Previously, these
variables were assumed to be global.)
- Added a function for initializing a getopt_t struct.
- Changed test_libblis.c--currently the only consumer of bli_getopt()--to
utilize the new getopt_t state object.
Details:
- Reworked the build system around a configuration registry file, named
config_registry', that identifies valid configuration targets, their
constituent sub-configurations, and the kernel sets that are needed by
those sub-configurations. The build system now facilitates the building
of a single library that can contains kernels and cache/register
blocksizes for multiple configurations (microarchitectures). Reference
kernels are also built on a per-configuration basis.
- Updated the Makefile to use new variables set by configure via the
config.mk.in template, such as CONFIG_LIST, KERNEL_LIST, and KCONFIG_MAP,
in determining which sub-configurations (CONFIG_LIST) and kernel sets
(KERNEL_LIST) are included in the library, and which make_defs.mk files'
CFLAGS (KCONFIG_MAP) are used when compiling kernels.
- Reorganized 'kernels' directory into a "flat" structure. Renamed kernel
functions into a standard format that includes the kernel set name
(e.g. 'haswell'). Created a "bli_kernels_<kernelset>.h" file in each
kernels sub-directory. These files exist to provide prototypes for the
kernels present in those directories.
- Reorganized reference kernels into a top-level 'ref_kernels' directory.
This directory includes a new source file, bli_cntx_ref.c (compiled on
a per-configuration basis), that defines the code needed to initialize
a reference context and a context for induced methods for the
microarchitecture in question.
- Rewrote make_defs.mk files in each configuration so that the compiler
variables (e.g. CFLAGS) are "stored" (renamed) on a per-configuration
basis.
- Modified bli_config.h.in template so that bli_config.h is generated with
#defines for the config (family) name, the sub-configurations that are
associated with the family, and the kernel sets needed by those
sub-configurations.
- Deprecated all kernel-related information in bli_kernel.h and transferred
what remains to new header files named "bli_arch_<configname>.h", which
are conditionally #included from a new header bli_arch.h. These files
are still needed to set library-wide parameters such as custom
malloc()/free() functions or SIMD alignment values.
- Added bli_cntx_init_<configname>.c files to each configuration directory.
The files contain a function, named the same as the file, that initializes
a "native" context for a particular configuration (microarchitecture). The
idea is that optimized kernels, if available, will be initialized into
these contexts. Other fields will retain pointers to reference functions,
which will be compiled on a per-configuration basis. These bli_cntx_init_*()
functions will be called during the initialization of the global kernel
structure. They are thought of as initializing for "native" execution, but
they also form the basis for contexts that use induced methods. These
functions are prototyped, along with their _ref() and _ind() brethren, by
prototype-generating macros in bli_arch.h.
- Added a new typedef enum in bli_type_defs.h to define an arch_t, which
identifies the various sub-configurations.
- Redesigned the global kernel structure (gks) around a 2D array of cntx_t
structures (pointers to cntx_t, actually). The first dimension is indexed
over arch_t and the inner dimension is the ind_t (induced method) for
each microarchitecture. When a microarchitecture (configuration) is
"registered" at init-time, the inner array for that configuration in the
2D array is initialized (and allocated, if it hasn't been already). The
cntx_t slot for BLIS_NAT is initialized immediately and those for other
induced method types are initialized and cached on-demand, as needed. At
cntx_t registration, we also store function pointers to cntx_init functions
that will initialize (a) "reference" contexts and (b) contexts for use with
induced methods. We don't cache the full contexts for reference contexts
since they are rarely needed. The functions that initialize these two kinds
of contexts are generated automatically for each targeted sub-configuration
from cpp-templatized code at compile-time. Induced method contexts that
need "stage" adjustments can still obtain them via functions in
bli_cntx_ind_stage.c.
- Added new functions and functionality to bli_cntx.c, such as for setting
the level-1f, level-1v, and packm kernels, and for converting a native
context into one for executing an induced method.
- Moved the checking of register/cache blocksize consistency from being cpp
macros in bli_kernel_macro_defs.h to being runtime checks defined in
bli_check.c and called from bli_gks_register_cntx() at the time that the
global kernel structure's internal context is initialized for a given
microarchitecture/configuration.
- Deprecated all of the old per-operation bli_*_cntx.c files and removed
the previous operation-level cntx_t_init()/_finalize() invocations.
Instead, we now query the gks for a suitable context, usually via
bli_gks_query_cntx().
- Deprecated support for the 3m2 and 3m3 induced methods. (They required
hackery that I was no longer willing to support.)
- Consolidated the 1e and 1r packm kernels for any given register blocksize
into a single kernel that will branch on the schema and support packing
to both formats.
- Added the cntx_t* argument to all packm kernel signatures.
- Deprecated the local function pointer array in all bli_packm_cxk*.c files
and instead obtain the packm kernel from the cntx_t.
- Added bli_calloc_intl(), which serves as the calloc-equivalent to to
bli_malloc_intl(). Useful when we wish to allocate and initialize to
zero/NULL.
- Converted existing cpp macro functions defined in bli_blksz.h, bli_func.h,
bli_cntx.h into static functions.
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.
Details:
- Removed the family field inside the cntx_t struct and re-added it to the
cntl_t struct. Updated all accessor functions/macros accordingly, as well
as all consumers and intermediaries of the family parameter (such as
bli_l3_thread_decorator(), bli_l3_direct(), and bli_l3_prune_*()). This
change was motivated by the desire to keep the context limited, as much
as possible, to information about the computing environment. (The family
field, by contrast, is a descriptor about the operation being executed.)
- Added additional functions to bli_blksz_*() API.
- Added additional functions to bli_cntx_*() API.
- Minor updates to bli_func.c, bli_mbool.c.
- Removed 'obj' from bli_blksz_*() API names.
- Removed 'obj' from bli_cntx_*() API names.
- Removed 'obj' from bli_cntl_*(), bli_*_cntl_*() API names. Renamed routines
that operate only on a single struct to contain the "_node" suffix to
differentiate with those routines that operate on the entire tree.
- Added enums for packm and unpackm kernels to bli_type_defs.h.
- Removed BLIS_1F and BLIS_VF from bszid_t definition in bli_type_defs.h.
They weren't being used and probably never will be.
Details:
- Implemented the 1m method for inducing complex domain matrix
multiplication. 1m support has been added to all level-3 operations,
including trsm, and is now the default induced method when native
complex domain gemm microkernels are omitted from the configuration.
- Updated _cntx_init() operations to take a datatype parameter. This was
needed for the corresponding function for 1m (because 1m requires us
to choose between column-oriented or row-oriented execution, which
requires us to query the context for the storage preference of the
gemm microkernel, which requires knowing the datatype) but I decided
that it made sense for consistency to add the parameter to all other
cntx initialization functions as well, even though those functions
don't use the parameter.
- Updated bli_cntx_set_blkszs() and bli_gks_cntx_set_blkszs() to take
a second scalar for each blocksize entry. The semantic meaning of the
two scalars now is that the first will scale the default blocksize
while the second will scale the maximum blocksize. This allows scaling
the two independently, and was needed to support 1m, which requires
scaling for a register blocksize but not the register storage
blocksize (ie: "packdim") analogue.
- Deprecated bli_blksz_reduce_dt_to() and defined two new functions,
bli_blksz_reduce_def_to() and bli_blksz_reduce_max_to(), for reducing
default and maximum blocksizes to some desired blocksize multiple.
These functions are needed in the updated definitions of
bli_cntx_set_blkszs() and bli_gks_cntx_set_blkszs().
- Added support for the 1e and 1r packing schemas to packm, including
1e/1r packing kernels.
- Added a minor optimization to bli_gemm_ker_var2() that allows, under
certain circumstances (specifically, real domain beta and row- or
column-stored matrix C), the real domain macrokernel and microkernel
to be called directly, rather than using the virtual microkernel
via the complex domain macrokernel, which carries a slight additional
amount of overhead.
- Added 1m support to the testsuite.
- Added 1m support to Makefile and runme.sh in test/3m4m. Also simplified
some code in test_gemm.c driver.
Details:
- Moved amaxv from being a utility operation to being a level-1v operation.
This includes the establishment of a new amaxv kernel to live beside all
of the other level-1v kernels.
- Added two new functions to bli_part.c:
bli_acquire_mij()
bli_acquire_vi()
The first acquires a scalar object for the (i,j) element of a matrix,
and the second acquires a scalar object for the ith element of a vector.
- Added integer support to bli_getsc level-0 operation. This involved
adding integer support to the bli_*gets level-0 scalar macros.
- Added a new test module to test amaxv as a level-1v operation. The test
module works by comparing the value identified by bli_amaxv() to the
the value found from a reference-like code local to the test module
source file. In other words, it (intentionally) does not guarantee the
same index is found; only the same value. This allows for different
implementations in the case where a vector contains two or more elements
containing exactly the same floating point value (or values, in the case
of the complex domain).
- Removed the directory frame/include/old/.
Details:
- Altered control tree node struct definitions so that all nodes have the
same struct definition, whose primary fields consist of a blocksize id,
a variant function pointer, a pointer to an optional parameter struct,
and a pointer to a (single) sub-node. This unified control tree type is
now named cntl_t.
- Changed the way control tree nodes are connected, and what computation
they represent, such that, for example, packing operations are now
associated with nodes that are "inline" in the tree, rather than off-
shoot braches. The original tree for the classic Goto gemm algorithm was
expressed (roughly) as:
blk_var2 -> blk_var3 -> blk_var1 -> ker_var2
| |
-> packb -> packa
and now, the same tree would look like:
blk_var2 -> blk_var3 -> packb -> blk_var1 -> packa -> ker_var2
Specifically, the packb and packa nodes perform their respective packing
operations and then recurse (without any loop) to a subproblem. This means
there are now two kinds of level-3 control tree nodes: partitioning and
non-partitioning. The blocked variants are members of the former, because
they iteratively partition off submatrices and perform suboperations on
those partitions, while the packing variants belong to the latter group.
(This change has the effect of allowing greatly simplified initialization
of the nodes, which previously involved setting many unused node fields to
NULL.)
- Changed the way thrinfo_t tree nodes are arranged to mirror the new
connective structure of control trees. That is, packm nodes are no longer
off-shoot branches of the main algorithmic nodes, but rather connected
"inline".
- Simplified control tree creation functions. Partitioning nodes are created
concisely with just a few fields needing initialization. By contrast, the
packing nodes require additional parameters, which are stored in a
packm-specific struct that is tracked via the optional parameters pointer
within the control tree struct. (This parameter struct must always begin
with a uint64_t that contains the byte size of the struct. This allows
us to use a generic function to recursively copy control trees.) gemm,
herk, and trmm control tree creation continues to be consolidated into
a single function, with the operation family being used to select
among the parameter-agnostic macro-kernel wrappers. A single routine,
bli_cntl_free(), is provided to free control trees recursively, whereby
the chief thread within a groups release the blocks associated with
mem_t entries back to the memory broker from which they were acquired.
- Updated internal back-ends, e.g. bli_gemm_int(), to query and call the
function pointer stored in the current control tree node (rather than
index into a local function pointer array). Before being invoked, these
function pointers are first cast to a gemm_voft (for gemm, herk, or trmm
families) or trsm_voft (for trsm family) type, which is defined in
frame/3/bli_l3_var_oft.h.
- Retired herk and trmm internal back-ends, since all execution now flows
through gemm or trsm blocked variants.
- Merged forwards- and backwards-moving variants by querying the direction
from routines as a function of the variant's matrix operands. gemm and
herk always move forward, while trmm and trsm move in a direction that
is dependent on which operand (a or b) is triangular.
- Added functions bli_thread_get_range_mdim(), bli_thread_get_range_ndim(),
each of which takes additional arguments and hides complexity in managing
the difference between the way ranges are computed for the four families
of operations.
- Simplified level-3 blocked variants according to the above changes, so that
the only steps taken are:
1. Query partitioning direction (forwards or backwards).
2. Prune unreferenced regions, if they exist.
3. Determine the thread partitioning sub-ranges.
<begin loop>
4. Determine the partitioning blocksize (passing in the partitioning
direction)
5. Acquire the curren iteration's partitions for the matrices affected
by the current variants's partitioning dimension (m, k, n).
6. Call the subproblem.
<end loop>
- Instantiate control trees once per thread, per operation invocation.
(This is a change from the previous regime in which control trees were
treated as stateless objects, initialized with the library, and shared
as read-only objects between threads.) This once-per-thread allocation
is done primarily to allow threads to use the control tree as as place
to cache certain data for use in subsequent loop iterations. Presently,
the only application of this caching is a mem_t entry for the packing
blocks checked out from the memory broker (allocator). If a non-NULL
control tree is passed in by the (expert) user, then the tree is copied
by each thread. This is done in bli_l3_thread_decorator(), in
bli_thrcomm_*.c.
- Added a new field to the context, and opid_t which tracks the "family"
of the operation being executed. For example, gemm, hemm, and symm are
all part of the gemm family, while herk, syrk, her2k, and syr2k are
all part of the herk family. Knowing the operation's family is necessary
when conditionally executing the internal (beta) scalar reset on on
C in blocked variant 3, which is needed for gemm and herk families,
but must not be performed for the trmm family (because beta has only
been applied to the current row-panel of C after the first rank-kc
iteration).
- Reexpressed 3m3 induced method blocked variant in frame/3/gemm/ind
to comform with the new control tree design, and renamed the macro-
kernel codes corresponding to 3m2 and 4m1b.
- Renamed bli_mem.c (and its APIs) to bli_memsys.c, and renamed/relocated
bli_mem_macro_defs.h from frame/include to frame/base/bli_mem.h.
- Renamed/relocated bli_auxinfo_macro_defs.h from frame/include to
frame/base/bli_auxinfo.h.
- Fixed a minor bug whereby the storage-to-ukr-preference matching
optimization in the various level-3 front-ends was not being applied
properly when the context indicated that execution would be via an
induced method. (Before, we always checked the native micro-kernel
corresponding to the datatype being executed, whereas now we check
the native micro-kernel corresponding to the datatype's real projection,
since that is the micro-kernel that is actually used by induced methods.
- Added an option to the testsuite to skip the testing of native level-3
complex implementations. Previously, it was always tested, provided that
the c/z datatypes were enabled. However, some configurations use
reference micro-kernels for complex datatypes, and testing these
implementations can slow down the testsuite considerably.
Details:
- Relaxed the base pointer and leading dimension alignment restrictions
in the sandybridge gemm microkernels, allowing the use of vmovups/vmovupd
instead of vmovaps/vmovapd. These change mimic those made to the haswell
microkernels in e0d2fa0 and ee2c139.
- Updated testsuite modules as well as standalone test drivers in 'test'
directory to use DBL_MAX as the initial time candidate. Thanks to Devin
Matthews for suggesting this change.
- Inserted #include "float.h" into bli_system.h (to gain access to DBL_MAX).
- Minor update (vis-a-vis contexts) to driver code in test/3m4m.
Details:
- Defined a new randomization operation, randn, on vectors and matrices.
The randnv and randnm operations randomize each element of the target
object with values from a narrow range of values. Presently, those
values are all integer powers of two, but they do not need to be powers
of two in order to achieve the primary goal, which is to initialize
objects that can be operated on with plenty of precision "slack"
available to allow computations that avoid roundoff. Using this method
of randomization makes it much more likely that testsuite residuals of
properly-functioning operations are close to zero, if not exactly zero.
- Updated existing randomization operations randv and randm to skip
special diagonal handling and normalization for matrices with structure.
This is now handled by the testsuite modules by explicitly calling a
testsuite function that loads the diagonal (and scales off-diagonal
elements).
- Added support for randnv and randnm in the testsuite with a new switch
in input.general that universally toggles between use of the classic
randv/randm, which use real values on the interval [-1,1], and
randnv/randnm, which use only values from a narrow range. Currently,
the narrow range is: +/-{2^0, 2^-1, 2^-2, 2^-3, 2^-4, 2^-5, 2^-6}, as
well as 0.0.
- Updated testsuite modules so that a testsutie wrapper function is called
instead of directly calling the randomization operations (such as
bli_randv() and bli_randm()). This wrapper also takes a bool_t that
indicates whether the object's elements should be normalized. (NOTE: As
alluded to above, in the test modules of triangular solve operations such
as trsv and trsm, we perform the extra step of loading the diagonal.)
- Defined a new level-0 operation, invertsc, which inverts a scalar.
- Updated the abval2ris and sqrt2ris level-0 macros to avoid an unlikely
but possible divide-by-zero.
- Updated function signature and prototype formatting in testsuite.
Details:
- Added a new input parameter to input.general that globally toggles
whether testsuite tests are performed on objects whose buffers and
leading dimensions have been aligned, and changed the implementation
of libblis_test_mobj_create() to employ alignment (or not) regardless
of whether row, column, or general storage is being tested.
- Updated configure script's "--help" text to indicate default behavior
for internal integer type size and BLAS/CBLAS integer type size
options.
Details:
- Updated level-1v, level-1f kernel function types (bli_l1?_ft.h) and
generic kernel prototypes (bli_l1?_ker.h) to use 'restrict' for all
numerical operand pointers (ie: all pointers except the cntx_t).
- Updated level-1f reference kernel definitions to use 'restrict' for
all numerical operand pointers. (Level-1v reference kernel definitions
were already updated in bdbda6e.)
- Rewrote the level-1v and level-1f reference kernel prototypes in
bli_l1v_ref.h and bli_l1f_ref.h, respectively, to simply #include
bli_l1v_ker.h and bli_l1f_ker.h with redefined function base names
(as was already being done for the level-3 micro-kernel prototypes
in bli_l3_ref.h), rather than duplicate the signatures from the
_ker.h files.
- Added definitions to frame/include/bli_kernel_prototypes.h for axpbyv
and xpbyv, which were probably meant for inclusion in bdbda6e.
- Converted a number of instances of four spaces, as introduced in
bdbda6e, to tabs.
- Add missing axpby and xpby operations (plus test cases).
- Add special case for scal2v with alpha=1.
- Add restrict qualifiers.
- Add special-case algorithms for incx=incy=1.
Details:
- Retrofitted a new data structure, known as a context, into virtually
all internal APIs for computational operations in BLIS. The structure
is now present within the type-aware APIs, as well as many supporting
utility functions that require information stored in the context. User-
level object APIs were unaffected and continue to be "context-free,"
however, these APIs were duplicated/mirrored so that "context-aware"
APIs now also exist, differentiated with an "_ex" suffix (for "expert").
These new context-aware object APIs (along with the lower-level, type-
aware, BLAS-like APIs) contain the the address of a context as a last
parameter, after all other operands. Contexts, or specifically, cntx_t
object pointers, are passed all the way down the function stack into
the kernels and allow the code at any level to query information about
the runtime, such as kernel addresses and blocksizes, in a thread-
friendly manner--that is, one that allows thread-safety, even if the
original source of the information stored in the context changes at
run-time; see next bullet for more on this "original source" of info).
(Special thanks go to Lee Killough for suggesting the use of this kind
of data structure in discussions that transpired during the early
planning stages of BLIS, and also for suggesting such a perfectly
appropriate name.)
- Added a new API, in frame/base/bli_gks.c, to define a "global kernel
structure" (gks). This data structure and API will allow the caller to
initialize a context with the kernel addresses, blocksizes, and other
information associated with the currently active kernel configuration.
The currently active kernel configuration within the gks cannot be
changed (for now), and is initialized with the traditional cpp macros
that define kernel function names, blocksizes, and the like. However,
in the future, the gks API will be expanded to allow runtime management
of kernels and runtime parameters. The most obvious application of this
new infrastructure is the runtime detection of hardware (and the
implied selection of appropriate kernels). With contexts in place,
kernels may even be "hot swapped" at runtime within the gks. Once
execution enters a level-3 _front() function, the memory allocator will
be reinitialized on-the-fly, if necessary, to accommodate the new
kernels' blocksizes. If another application thread is executing with
another (previously loaded) kernel, it will finish in a deterministic
fashion because its kernel information was loaded into its context
before computation began, and also because the blocks it checked out
from the internal memory pools will be unaffected by the newer threads'
reinitialization of the allocator.
- Reorganized and streamlined the 'ind' directory, which contains much of
the code enabling use of induced methods for complex domain matrix
multiplication; deprecated bli_bsv_query.c and bli_ukr_query.c, as
those APIs' functionality is now mostly subsumed within the global
kernel structure.
- Updated bli_pool.c to define a new function, bli_pool_reinit_if(),
that will reinitialize a memory pool if the necessary pool block size
has increased.
- Updated bli_mem.c to use bli_pool_reinit_if() instead of
bli_pool_reinit() in the definition of bli_mem_pool_init(), and placed
usage of contexts where appropriate to communicate cache and register
blocksizes to bli_mem_compute_pool_block_sizes().
- Simplified control trees now that much of the information resides in
the context and/or the global kernel structure:
- Removed blocksize object pointers (blksz_t*) fields from all control
tree node definitions and replaced them with blocksize id (bszid_t)
values instead, which may be passed into a context query routine in
order to extract the corresponding blocksize from the given context.
- Removed micro-kernel function pointers (func_t*) fields from all
control tree node definitions. Now, any code that needs these function
pointers can query them from the local context, as identified by a
level-3 micro-kernel id (l3ukr_t), level-1f kernel id, (l1fkr_t), or
level-1v kernel id (l1vkr_t).
- Removed blksz_t object creation and initialization, as well as kernel
function object creation and initialization, from all operation-
specific control tree initialization files (bli_*_cntl.c), since this
information will now live in the gks and, secondarily, in the context.
- Removed blocksize multiples from blksz_t objects. Now, we track
blocksize multiples for each blocksize id (bszid_t) in the context
object.
- Removed the bool_t's that were required when a func_t was initialized.
These bools are meant to allow one to track the micro-kernel's storage
preferences (by rows or columns). This preference is now tracked
separately within the gks and contexts.
- Merged and reorganized many separate-but-related functions into single
files. This reorganization affects frame/0, 1, 1d, 1m, 1f, 2, 3, and
util directories, but has the most obvious effect of allowing BLIS
to compile noticeably faster.
- Reorganized execution paths for level-1v, -1d, -1m, and -2 operations
in an attempt to reduce overhead for memory-bound operations. This
includes removal of default use of object-based variants for level-2
operations. Now, by default, level-2 operations will directly call a
low-level (non-object based) loop over a level-1v or -1f kernel.
- Converted many common query functions in blk_blksz.c (renamed from
bli_blocksize.c) and bli_func.c into cpp macros, now defined in their
respective header files.
- Defined bli_mbool.c API to create and query "multi-bools", or
heterogeneous bool_t's (one for each floating-point datatype), in the
same spirit as blksz_t and func_t.
- Introduced two key parameters of the hardware: BLIS_SIMD_NUM_REGISTERS
and BLIS_SIMD_SIZE. These values are needed in order to compute a third
new parameter, which may be set indirectly via the aforementioned
macros or directly: BLIS_STACK_BUF_MAX_SIZE. This value is used to
statically allocate memory in macro-kernels and the induced methods'
virtual kernels to be used as temporary space to hold a single
micro-tile. These values are now output by the testsuite. The default
value of BLIS_STACK_BUF_MAX_SIZE is computed as
"2 * BLIS_SIMD_NUM_REGISTERS * BLIS_SIMD_SIZE".
- Cleaned up top-level 'kernels' directory (for example, renaming the
embarrassingly misleading "avx" and "avx2" directories to "sandybridge"
and "haswell," respectively, and gave more consistent and meaningful
names to many kernel files (as well as updating their interfaces to
conform to the new context-aware kernel APIs).
- Updated the testsuite to query blocksizes from a locally-initialized
context for test modules that need those values: axpyf, dotxf,
dotxaxpyf, gemm_ukr, gemmtrsm_ukr, and trsm_ukr.
- Reformatted many function signatures into a standard format that will
more easily facilitate future API-wide changes.
- Updated many "mxn" level-0 macros (ie: those used to inline double loops
for level-1m-like operations on small matrices) in frame/include/level0
to use more obscure local variable names in an effort to avoid variable
shaddowing. (Thanks to Devin Matthews for pointing these gcc warnings,
which are only output using -Wshadow.)
- Added a conj argument to setm, so that its interface now mirrors that
of scalm. The semantic meaning of the conj argument is to optionally
allow implicit conjugation of the scalar prior to being populated into
the object.
- Deprecated all type-aware mixed domain and mixed precision APIs. Note
that this does not preclude supporting mixed types via the object APIs,
where it produces absolutely zero API code bloat.
Details:
- Fixed typos in README.md.
- Fixed column heading alignment for testsuite when matlab output is
enabled.
- Minor updates to test/3m4m/runme.sh and test/3m4m/Makefile.
Details:
- Added sgemm and dgemm micro-kernels, which employ 256-bit AVX vectors
and FMA instructions. (Complex support is currently provided by default
induced method, 4m1a.)
- Added a 'haswell' configuration, which uses the aforementioned kernels.
- Inserted auto-detection support for haswell configuration in
build/auto-detect/cpuid_x86.c.
- Modified configure script to explicitly echo when automatic or manual
configuration is in progress.
- Changed beta scalar in test_gemm.c module of test suite to -1.0 to 0.9.
Details:
- Replaced the old memory allocator, which was based on statically-
allocated arrays, with one based on a new internal pool_t type, which,
combined with a new bli_pool_*() API, provides a new abstract data
type that implements the same memory pool functionality but with blocks
from the heap (ie: malloc() or equivalent). Hiding the details of the
pool in a separate API also allows for a much simpler bli_mem.c family
of functions.
- Added a new internal header, bli_config_macro_defs.h, which enables
sane defaults for the values previously found in bli_config. Those
values can be overridden by #defining them in bli_config.h the same
way kernel defaults can be overridden in bli_kernel.h. This file most
resembles what was previously a typical configuration's bli_config.h.
- Added a new configuration macro, BLIS_POOL_ADDR_ALIGN_SIZE, which
defaults to BLIS_PAGE_SIZE, to specify the alignment of individual
blocks in the memory pool. Also added a corresponding query routine to
the bli_info API.
- Deprecated (once again) the micro-panel alignment feature. Upon further
reflection, it seems that the goal of more predictable L1 cache
replacement behavior is outweighed by the harm caused by non-contiguous
micro-panels when k % kc != 0. I honestly don't think anyone will even
miss this feature.
- Changed bli_ukr_get_funcs() and bli_ukr_get_ref_funcs() to call
bli_cntl_init() instead of bli_init().
- Removed query functions from bli_info.c that are no longer applicable
given the dynamic memory allocator.
- Removed unnecessary definitions from configurations' bli_config.h files,
which are now pleasantly sparse.
- Fixed incorrect flop counts in addv, subv, scal2v, scal2m testsuite
modules. Thanks to Devangi Parikh for pointing out these
miscalculations.
- Comment, whitespace changes.
Details:
- Defined a new "3ms" (separated 3m) pack schema and added appropriate
support in packm_init(), packm_blk_var2().
- Generalized packm_struc_cxk_3mi to take the imaginary stride (is_p)
as an argument instead of computing it locally. Exception: for trmm,
is_p must be computed locally, since it changes for triangular
packed matrices. Also exposed is_p in interface to dt-specific
packm_blk_var2 (and _var1, even though it does not use imaginary
stride).
- Renamed many functions/variables from _3mi to _3mis to indicate that
they work for either interleaved or separated 3m pack schemas.
- Generalized gemm and herk macro-kernels to pass in imaginary stride
rather than compute them locally.
- Added support for 3m2 and 3m3 algorithms to frame/ind, including 3m2-
and 3m3-specific virtual micro-kernels.
- Added special gemm macro-kernels to support 3m2 and 3m3.
- Added support for 3m2 and 3m3 to testsuite.
- Corrected the type of the panel dimension (pd_) in various macro-
kernels from inc_t to dim_t.
- Renamed many functions defined in bli_blocksize.c.
- Moved most induced-related macro defs from frame/include to
frame/ind/include.
- Updated the _ukernel.c files so that the micro-kernel function pointers
are obtained from the func_t objects rather than the cpp macros that
define the function names.
- Updated test/3m4m driver, Makefile, and run script.
Details:
- Consolidated most of the code relating to induced complex methods
(e.g. 4mh, 4m1, 3mh, 3m1, etc.) into frame/ind. Induced methods
are now enabled on a per-operation basis. The current "available"
(enabled and implemented) implementation can then be queried on
an operation basis. Micro-kernel func_t objects as well as blksz_t
objects can also be queried in a similar maner.
- Redefined several micro-kernel and operation-related functions in
bli_info_*() API, in accordance with above changes.
- Added mr and nr fields to blksz_t object, which point to the mr
and nr blksz_t objects for each cache blocksize (and are NULL for
register blocksizes). Renamed the sub-blocksize field "sub" to
"mult" since it is really expressing a blocksize multiple.
- Updated bli_*_determine_kc_[fb]() for gemm/hemm/symm, trmm, and
trsm to correctly query mr and nr (for purposes of nudging kc).
- Introduced an enumerated opid_t in bli_type_defs.h that uniquely
identifies an operation. For now, only level-3 id values are defined,
along with a generic, catch-all BLIS_NOID value.
- Reworked testsuite so that all induced methods that are enabled
are tested (one at a time) rather than only testing the first
available method.
- Reformated summary at the beginning of testsuite output so that
blocksize and micro-kernel info is shown for each induced method
that was requested (as well as native execution).
- Reduced the number of columns needed to display non-matlab
testsuite output (from approx. 90 to 80).
Details:
- Renamed all remaining 3m/4m packing files and symbols to 3mi/4mi
('i' for "interleaved"). Similar changes to 3M/4M macros.
- Renamed all 3m/4m files and functions to 3m1/4m1.
- Whitespace changes.
Details:
- Changed the recently-added micro-panel alignment macros so that we now
have two sets--one for micro-panels of matrix A and one for micro-
panels of matrix B: BLIS_UPANEL_[AB]_ALIGN_SIZE_?.
- Store each set of alignment values into a separate blksz_t object in
bli_gemm_cntl_init().
- Adjusted packm_init() to use the separate alignment values.
- Added query routines for the new alignment values to bli_info.c.
- Modified test suite output accordingly.
Details:
- This commit re-implements a feature that was removed in commit
c2b2ab62. It was removed because, at the time, I wasn't sure how the
micro-panel alignment feature would interact with the 4m method (when
applied at the micro-kernrel level), and so it seemed safer to disable
the feature entirely rather than allow possible breakage. This commit
revisits the issue and safely re-implements the feature in a way that
is compatible with 4m, 3m, 4mh, and 3mh (and native execution).
- Modified the static memory pool to account for micro-panel alignment
space.
- Modified packm_init and blocked variants to align whole micro-panels
by a datatype-specific alignment value that may be set by the
configuration. (If it is not set by the configuration, it will default
to BLIS_SIZEOF_?.)
- Modified macro-kernels so that:
- storage stride is handled properly given the new micro-panel
alignment behavior;
- indexing through 3m/4m/rih-type sub-panels, as is done by trmm and
trsm, is more robust (e.g. will work if the applicable packing
register blocksize is odd);
- imaginary strides are computed and stored within auxinfo_t structs,
which allows the virtual micro-kernels to more easily determine how
to index into the micro-panel operands.
- Modified virtual 3m and 4m micro-kernels to use the imaginary strides
within the auxinfo_t structs instead of panel strides.
- Deprecated the panel stride fields from the auxinfo_t structs.
- Updated test suite to print out the micro-panel alignment values.
