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.
Details:
- Redefined bli_is_last_iter() to take thread_id and num_thread
arguments, which allows the macro to correctly compute whether a
given iteration is the last that the thread will compute in that
particular loop. The new definition, however, remains disabled
(commented out) until someone can look at this more closely, as
the new definition seems to actually hurt performance slightly.
- Whitespace and related updates to level-3 macro-kernels.
- Updated test suite so that performance results in the hundreds of
gigaflops does not disrupt the column alignment of the output.
Details:
- Fixed a bug in the test suite for the trsm_ukr and gemmtrsm_ukr test
modules whereby the uplo bits of some packed matrix objects were not
being set properly, resulting in false FAILURE results for those
tests. Thanks to Tyler Smith for bringing this issue to my attention.
- Fixed a bug in bli_obj_alloc_buffer() that caused an unnecessary
"not yet implemented" abort() when creating a 1x1 object with non-unit
strides.
Details:
- Added _string() suffix to bli_info_get_*_ukr_type() function names.
This makes them consistent with the bli_info_get_*_impl_string()
functions.
Details:
- Added "4mh" and "3mh" APIs, which implement the 4m and 3m methods at
high levels, respectively. APIs for trmm and trsm were NOT added due
to the fact that these approaches are inherently incompatible with
implementing 4m or 3m at high levels (because the input right-hand
side matrix is overwritten).
- Added 4mh, 3mh virtual micro-kernels, and updated the existing 4m and
3m so that all are stylistically consistent.
- Added new "rih" packing kernels (both low-level and structure-aware)
to support both 4mh and 3mh.
- Defined new pack_t schemas to support real-only, imaginary-only, and
real+imaginary packing formats.
- Added various level0 scalar macros to support the rih packm kernels.
- Minor tweaks to trmm macro-kernels to facilitate 4mh and 3mh.
- Added the ability to enable/disable 4mh, 3m, and 3mh, and adjusted
level-3 front-ends to check enabledness of 3mh, 3m, 4mh, and 4m (in
that order) and execute the first one that is enabled, or the native
implementation if none are enabled.
- Added implementation query functions for each level-3 operation so
that the user can query a string that describes the implementation
that is currently enabled.
- Updated test suite to output implementation types for reach level-3
operation, as well as micro-kernel types for each of the five micro-
kernels.
- Renamed BLIS_ENABLE_?COMPLEX_VIA_4M macros to _ENABLE_VIRTUAL_?COMPLEX.
- Fixed an obscure bug when packing Hermitian matrices (regular packing
type) whereby the diagonal elements of the packed micro-panels could
get tainted if the source matrix's imaginary diagonal part contained
garbage.
Details:
- Modified macro-kernels to pass the pack_t schema values for matrices
A and B into the datatype-specific functions, where they are now
inserted into a newly-expanded auxinfo_t struct. This gives gives the
micro-kernels access to the pack_t schema values embedded in the
control trees, which determine the precise format into which the
matrix elements are packed.
- Updated a call to bli_packm_init_pack() in src/test_libblis.c to
remove densify argument. Meant to include this in commit c472993b.
Details:
- Changed semantics of cache and register blocksize extensions so that
the extended values are tracked, rather than just the marginal
extensions.
- BLIS_EXTEND_[MKN]C_? has been renamed BLIS_MAXIMUM_[MKN]C_?.
- BLIS_EXTEND_[MKN]R_? has been renamed BLIS_PACKDIM_[MKN]R_?.
- bli_blksz_ext_*() APIs have been renamed to bli_blksz_max_*(). Note
that these "max" query routines grab the maximum value for cache
blocksizes and the packdim value for register blocksizes.
- bli_info_*() API has been updated accordingly.
- All configurations have been updated accordingly.
Details:
- Reverted some changes that were unintentionally included in the
previous commit (9526ce98). Thanks to Tony Kelman for pointing
this out. (Note: a few select changes were not reverted.)
Details:
- Updated copyright headers to include "at Austin" in the name of the
University of Texas.
- Updated the copyright years of a few headers to 2014 (from 2011 and
2012).
Details:
- Added a new API family, bli_info_*(), which can be used to query
information about how BLIS was configured. Most of these values are
returned as gint_t, with the exception of the version string which
is char*.
- Changed how the testsuite driver queries information about how BLIS
was configured (from using macro constants directly to using the
new bli_info API).
- Removed bli_version.c and its header file.
- Added STRINGIFY_INT() macro to bli_macro_defs.h
- Renamed info_t type in bli_type_defs.h to objbits_t (not because of
an actual naming conflict, but because the name 'info_t' would now be
somewhat misleading in the presence of the new bli_info API, as the
two are unrelated).
Details:
- Added wrappers for micro-kernels so that users may invoke the
micro-kernels without knowing what the function names actually are.
This is useful when an application wishes to call the micro-kernel
from a shared library instance of BLIS, where the application may not
necessarily have the luxury of grabbing the micro-kernel name(s) from
C preprocessor macros at compile-time. Also, since the wrappers use
void* pointers, one's environment does not need to be aware of some
BLIS types such as scomplex and dcomplex. These wrappers now join the
level-1 and level-1f kernel wrappers, which pre-dated this commit.
- Removed the wrapper definitions and prototypes from the micro-kernel
test suite modules, and replaced calls to them with calls to the new
wrappers mentioned above.
Details:
- Defined new INSERT_GENTFUNC macros so that the macro always takes
exactly the number of arguments needed for the particular operation or
variant being defined. Many operations were using INSERT_GENTFUNC
macros that expected one auxiliary argument even though none were
needed. Those instances have now been updated. Most of these instances
were in the level-0 and -1v operations, as well as some operations
defined in frame/util.
Details:
- Completely reoganized norm operations:
- Renames:
- fnormsc, fnormv, fnormm -> normfsc, normfv, normfm (2-norm)
- absumv -> norm1v (vector 1-norm)
- New operations:
- norm1m (matrix 1-norm)
- normiv, normim (infinity-norm)
- amaxv (BLAS-like absolute maximum value index)
- asumv (BLAS-like absolute sum)
- Deprecated absumm, as it did not correspond to any actual norm.
(However, an inlined version now exists in the testsuite module for
randm.)
Added a multithreading infrastructure that should be independent of multithreading implementation in the future.
Currently, gemm blocked variants 1f and 2f, and packm variant blocked variant 1 is parallelized.
Details:
- Removed BLIS_CONTIG_STRIDE_ALIGN_SIZE from bli_config.h of all
configurations. It was already going unused in packm_init() since the
recent 4m/3m commit. This setting was rarely, if ever, useful, and its
existence only posed a potential risk for 4m/3m-based implementations.
- Removed BLIS_CONTIG_STRIDE_ALIGN_SIZE usage from mem_pool_macro_defs.h.
- Updated comments regarding CONTIG_STRIDE_ALIGN_SIZE in template
micro-kernels.
Details:
- Standard names for reference kernels (levels-1v, -1f and 3) are now
macro constants. Examples:
BLIS_SAXPYV_KERNEL_REF
BLIS_DDOTXF_KERNEL_REF
BLIS_ZGEMM_UKERNEL_REF
- Developers no longer have to name all datatype instances of a kernel
with a common base name; [sdcz] datatype flavors of each kernel or
micro-kernel (level-1v, -1f, or 3) may now be named independently.
This means you can now, if you wish, encode the datatype-specific
register blocksizes in the name of the micro-kernel functions.
- Any datatype instances of any kernel (1v, 1f, or 3) that is left
undefined in bli_kernel.h will default to the corresponding reference
implementation. For example, if BLIS_DGEMM_UKERNEL is left undefined,
it will be defined to be BLIS_DGEMM_UKERNEL_REF.
- Developers no longer need to name level-1v/-1f kernels with multiple
datatype chars to match the number of types the kernel WOULD take in
a mixed type environment, as in bli_dddaxpyv_opt(). Now, one char is
sufficient, as in bli_daxpyv_opt().
- There is no longer a need to define an obj_t wrapper to go along with
your level-1v/-1f kernels. The framework now prvides a _kernel()
function which serves as the obj_t wrapper for whatever kernels are
specified (or defaulted to) via bli_kernel.h
- Developers no longer need to prototype their kernels, and thus no
longer need to include any prototyping headers from within
bli_kernel.h. The framework now generates kernel prototypes, with the
proper type signature, based on the kernel names defined (or defaulted
to) via bli_kernel.h.
- If the complex datatype x (of [cz]) implementation of the gemm micro-
kernel is left undefined by bli_kernel.h, but its same-precision real
domain equivalent IS defined, BLIS will use a 4m-based implementation
for the datatype x implementations of all level-3 operations, using
only the real gemm micro-kernel.
Details:
- Added the ability to induce complex domain level-3 operations via new
virtual complex micro-kernels which are implemented via only real
domain micro-kernels. Two new implementations are provided: 4m and 3m.
4m implements complex matrix multiplication in terms of four real
matrix multiplications, where as 3m uses only three and thus is
capable of even higher (than peak) performance. However, the 3m method
has somewhat weaker numerical properties, making it less desirable
in general.
- Further refined packing routines, which were recently revamped, and
added packing functionality for 4m and 3m.
- Some modifications to trmm and trsm macro-kernels to facilitate indexing
into micro-panels which were packed for 4m/3m virtual kernels.
- Added 4m and 3m interfaces for each level-3 operation.
- Various other minor changes to facilitate 4m/3m methods.
Details:
- Consolidated the functionality previously supported by packm_blk_var2()
and packm_blk_var3() into a new variant, packm_blk_var1().
- Updates to packm_gen_cxk(), packm_herm_cxk.c(), and packm_tri_cxk()
to accommodate above changes.
- Removed packm_blk_var3() and retired packm_blk_var2() to
frame/1m/packm/old.
- Updated all level-3 _cntl_init() functions so that the new, more
versatile packm_blk_var1 is used for all level-3 matrix packing.
Details:
- In the test suite driver, inserted an explicit typecast of the return
value of bli_getopt() prior parsing. The lack of typecast caused a
problem on at least one system whereby a return value of -1 was
interpreted as garbage character. Thanks to Francisco Igual for finding
and submitting this fix.
Details:
- Added bli_getopt.c and .h files to frame/base. These files implement
a custom version of getopt(), which may be used to parse command line
options passed into a program via argc/argv. I am implementing this
function myself, as opposed to using the version available via unistd.h,
for portability reasons, as the only requirements are string.h (which
is available via the standard C library).
- Modified test suite to allow the user to specify the file name (and/or
path) to the parameters and operations input files: -g may be used to
specify the general input file and -o to specify the operations input
file). If -g or -o or both are not given, default filenames are assumed
(as well as their existence in the current directory).
Details:
- Replaced conditional expressions in macro-kernels related to computing
the addresses a2 and b2 (a_next and b_next) with a preprocessor macro
invocation, bli_is_last_iter(), that tests the same condition.
- Updated gemm_ukr module to use auxinfo_t argument.
- Whitespace changes in test suite ukr modules.
Details:
- Removed a_next and b_next arguments to micro-kernels and replaced them
with a pointer to a new datatype, auxinfo_t, which is simply a struct
that holds a_next and b_next. The struct may hold other auxiliary
information that may be useful to a micro-kernel, such as micro-panel
stride. Micro-kernels may access struct fields via accessor macros
defined in bli_auxinfo_macro_defs.h.
- Updated all instances of micro-kernel definitions, micro-kernel calls,
as well as macro-kernels (for declaring and initializing the structs)
according to above change.
Details:
- Fixed copy-and-paste bug whereby [scz]gemmtrsm_u_opt_d4x4 kernels
for x86_64/core2 were calling the wrong reference code (l instead
of u).
- Fixed some unused variables in x86_64/core2 dotaxpyv and dotxaxpyf
kernels.
- Minor typecasting fix in testsuite/src/test_libblis.c.
- Makefile updates.
Details:
- Added infrastructure to support a new scalar representation, whereby
every object contains an internal scalar that defaults to 1.0. This
facilitates passing scalars around without having to house them in
separate objects. These "attached" scalars are stored in the internal
atom_t field of the obj_t struct, and are always stored to be the same
datatype as the object to which they are attached. Level-3 variants no
longer take scalar arguments, however, level-3 internal back-ends stll
do; this is so that the calling function can perform subproblems such
as C := C - alpha * A * B on-the-fly without needing to change either
of the scalars attached to A or B.
- Removed scalar argument from packm_int().
- Observe and apply attached scalars in scalm_int(), and removed scalar
from interface of scalm_unb_var1().
- Renamed the following functions (and corresponding invocations):
bli_obj_init_scalar_copy_of()
-> bli_obj_scalar_init_detached_copy_of()
bli_obj_init_scalar() -> bli_obj_scalar_init_detached()
bli_obj_create_scalar_with_attached_buffer()
-> bli_obj_create_1x1_with_attached_buffer()
bli_obj_scalar_equals() -> bli_obj_equals()
- Defined new functions:
bli_obj_scalar_detach()
bli_obj_scalar_attach()
bli_obj_scalar_apply_scalar()
bli_obj_scalar_reset()
bli_obj_scalar_has_nonzero_imag()
bli_obj_scalar_equals()
- Placed all bli_obj_scalar_* functions in a new file, bli_obj_scalar.c.
- Renamed the following macros:
bli_obj_scalar_buffer() -> bli_obj_buffer_for_1x1()
bli_obj_is_scalar() -> bli_obj_is_1x1()
- Defined new macros to set and copy internal scalars between objects:
bli_obj_set_internal_scalar()
bli_obj_copy_internal_scalar()
- In level-3 internal back-ends, added conditional blocks where alpha and
beta are checked for non-unit-ness. Those values for alpha and beta are
applied to the scalars attached to aliases of A/B/C, as appropriate,
before being passed into the variant specified by the control tree.
- In level-3 blocked variants, pass BLIS_ONE into subproblems instead of
alpha and/or beta.
- In level-3 macro-kernels, changed how scalars are obtained. Now, scalars
attached to A and B are multiplied together to obtain alpha, while beta
is obtained directly from C.
- In level-3 front-ends, removed old function calls meant to provide
future support for mixed domain/precision. These can be added back later
once that functionality is given proper treatment. Also, removed the
creating of copy-casts of alpha and beta since typecasting of scalars
is now implicitly handled in the internal back-ends when alpha and
beta are applied to the attached scalars.
Details:
- Added missing object wrappers to level-1f test suite modules. This was
only apparent if you were configuring with something other than the
reference configuration.
- Commented out object-wrappers in level-1f front-ends. These were not
working as intended the reference configuration was selected, because
most kernel sets, such as those in the template set, do not have object
wrappers.
- Whitespace changes to template micro-kernels.
- Comment changes to template level-1f kernel headers.
Details:
- Removed support for duplication from the gemmtrsm/trsm micro-kernels
and all framework code.
- Updated test suite modules according to above changes.
