Details:
- Textually replaced nearly all non-comment instances of bool_t with the
C99 bool type. A few remaining instances, such as those in the files
bli_herk_x_ker_var2.c, bli_trmm_xx_ker_var2.c, and
bli_trsm_xx_ker_var2.c, were promoted to dim_t since they were being
used not for boolean purposes but to index into an array.
- This commit constitutes the third phase of a transition toward using
C99's bool instead of bool_t, which was raised in issue #420. The first
phase, which cleaned up various typecasts in preparation for using
bool as the basis for bool_t (instead of gint_t), was implemented by
commit a69a4d7. The second phase, which redefined the bool_t typedef
in terms of bool (from gint_t), was implemented by commit 2c554c2.
Details:
- The 'ref99' sandbox was broken by multiple refactorings and internal
API changes over the last two years. Rather than try to fix it, I've
replaced it with a much simpler version based on var2 of gemmsup.
Why not fix the previous implementation? It occurred to me that the
old implementation was trying to be a lightly simplified duplication
of what exists in the framework. Duplication aside, this sandbox
would have worked fine if it had been completely independent of the
framework code. The problem was that it was only partially
independent, with many function calls calling a function in BLIS
rather than a duplicated/simplified version within the sandbox. (And
the reason I didn't make it fully independent to begin with was that
it seemed unnecessarily duplicative at the time.) Maintaining two
versions of the same implementation is problematic for obvious
reasons, especially when it wasn't even done properly to begin with.
This explains the reimplementation in this commit. The only catch is
that the newer implementation is single-threaded only and does not
perform any packing on either input matrix (A or B). Basically, it's
only meant to be a simple placeholder that shows how you could plug
in your own implementation. Thanks to Francisco Igual for reporting
this brokenness.
- Updated the three reference gemmsup kernels (defined in
ref_kernels/3/bli_gemmsup_ref.c) so that they properly handle
conjugation of conja and/or conjb. The general storage kernel, which
is currently identical to the column-storage kernel, is used in the
new ref99 sandbox to provide basic support for all datatypes
(including scomplex and dcomplex).
- Minor updates to docs/Sandboxes.md, including adding the threading
and packing limitations to the Caveats section.
- Fixed a comment typo in bli_l3_sup_var1n2m.c (upon which the new
sandbox implementation is based).
Details:
- Updated all static function definitions to use the cpp macro
BLIS_INLINE instead of the static keyword. This allows blis.h to
use a different keyword (inline) to define these functions when
compiling with C++, which might otherwise trigger "defined but
not used" warning messages. Thanks to Giorgos Margaritis for
reporting this issue and Devin Matthews for suggesting the fix.
- Updated the following files, which are used by configure's
hardware auto-detection facility, to unconditionally #define
BLIS_INLINE to the static keyword (since we know BLIS will be
compiled with C, not C++):
build/detect/config/config_detect.c
frame/base/bli_arch.c
frame/base/bli_cpuid.c
- CREDITS file update.
Details:
- Fixed an inadvertently disabled edge case optimization in the two
gemmsup variants in bli_l3_sup_var1n2m.c. Background: These edge case
optimizations allow the last millikernel operation in the jr loop to
be executed with inflated an register blocksize if it is the last
(or only) iteration. For example, if mr=6 and nr=8 and the gemmsup
problem is m=8, n=100, k=100. (In this case, the panel-block variant
(var1n) is executed, which places the jr loop in the m dimension.)
In principle, this problem could be executed as two millikernels: one
with dimensions 6x100x100, and one as 2x100x100. However, with the
support for inflated blocksizes in the kernel, the entire 8x100x100
problem can be passed to the millikernel function, which will then
execute it more favorably as two 4x100x100 millikernel sub-calls.
Now, this optimization is disabled under certain circumstances, such
as when multithreading. Previously, the is_mt predicate was being set
incorrectly such that it was non-zero even when running
single-threaded.
- Upon fixing the is_mt issue above, another bit of code needed to be
moved so that the result of the optimization could have an impact on
the assignment of loop bounds ranges to threads.
Details:
- Renamed instances of bli_thread_obarrier() and bli_thread_obroadcast()
that were made in the supmt-specific code commited to the 'amd'
branch, which has now been merged with 'master'. Prior to the merge,
'master' received commit c01d249, which applied these renamings to
the existing, non-sup codebase.
Details:
- Renamed two bli_thread_*() APIs:
bli_thread_obarrier() -> bli_thread_barrier()
bli_thread_obroadcast() -> bli_thread_broadcast()
The 'o' was a leftover from when thrcomm_t objects tracked both
"inner" and "outer" communicators. They have long since been
simplified to only support the latter, and thus the 'o' is
superfluous.
Details:
- Added multithreading support to the sup framework (via either OpenMP
or pthreads). Both variants 1n and 2m now have the appropriate
threading infrastructure, including data partitioning logic, to
parallelize computation. This support handles all four combinations
of packing on matrices A and B (neither, A only, B only, or both).
This implementation tries to be a little smarter when automatic
threading is requested (e.g. via BLIS_NUM_THREADS) in that it will
recalculate the factorization in units of micropanels (rather than
using the raw dimensions) in bli_l3_sup_int.c, when the final
problem shape is known and after threads have already been spawned.
- Implemented bli_?packm_sup_var2(), which packs to conventional row-
or column-stored matrices. (This is used for the rrc and crc storage
cases.) Previously, copym was used, but that would no longer suffice
because it could not be parallelized.
- Minor reorganization of packing-related sup functions. Specifically,
bli_packm_sup_init_mem_[ab]() are called from within packm_sup_[ab]()
instead of from the variant functions. This has the effect of making
the variant functions more readable.
- Added additional bli_thrinfo_set_*() static functions to bli_thrinfo.h
and inserted usage of these functions within bli_thrinfo_init(), which
previously was accessing thrinfo_t fields via the -> operator.
- Renamed bli_partition_2x2() to bli_thread_partition_2x2().
- Added an auto_factor field to the rntm_t struct in order to track
whether automatic thread factorization was originally requested.
- Added new test drivers in test/supmt that perform multithreaded sup
tests, as well as appropriate octave/matlab scripts to plot the
resulting output files.
- Added additional language to docs/Multithreading.md to make it clear
that specifying any BLIS_*_NT variable, even if it is set to 1, will
be considered manual specification for the purposes of determining
whether to auto-factorize via BLIS_NUM_THREADS.
- Minor comment updates.
Details:
- Implemented optional packing for A or B (or both) within the sup
framework (which currently only supports gemm). The request for
packing either matrix A or matrix B can be made via setting
environment variables BLIS_PACK_A or BLIS_PACK_B (to any
non-zero value; if set, zero means "disable packing"). It can also
be made globally at runtime via bli_pack_set_pack_a() and
bli_pack_set_pack_b() or with individual rntm_t objects via
bli_rntm_set_pack_a() and bli_rntm_set_pack_b() if using the expert
interface of either the BLIS typed or object APIs. (If using the
BLAS API, environment variables are the only way to communicate the
packing request.)
- One caveat (for now) with the current implementation of selective
packing is that any blocksize extension registered in the _cntx_init
function (such as is currently used by haswell and zen subconfigs)
will be ignored if the affected matrix is packed. The reason is
simply that I didn't get around to implementing the necessary logic
to pack a larger edge-case micropanel, though this is entirely
possible and should be done in the future.
- Spun off the variant-choosing portion of bli_gemmsup_ref() into
bli_gemmsup_int(), in bli_l3_sup_int.c.
- Added new files, bli_l3_sup_packm_a.c, bli_l3_sup_packm_b.c, along
with corresponding headers, in which higher-level packm-related
functions are defined for use within the sup framework. The actual
packm variant code resides in bli_l3_sup_packm_var.c.
- Pass the following new parameters into var1n and var2m: packa, packb
bool_t's, pointer to a rntm_t, pointer to a cntl_t (which is for now
always NULL), and pointer to a thrinfo_t* (which for nowis the address
of the global single-threaded packm thread control node).
- Added panel strides ps_a and ps_b to the auxinfo_t structure so that
the millikernel can query the panel stride of the packed matrix and
step through it accordingly. If the matrix isn't packed, the panel
stride of interest for the given millikernel will be set to the
appropriate value so that the mkernel may step through the unpacked
matrix as it normally would.
- Modified the rv_6x8m and rv_6x8n millikernels to read the appropriate
panel strides (ps_a and ps_b, respectively) instead of computing them
on the fly.
- Spun off the environment variable getting and setting functions into
a new file, bli_env.c (with a corresponding prototype header). These
functions are now used by the threading infrastructure (e.g.
BLIS_NUM_THREADS, BLIS_JC_NT, etc.) as well as the selective packing
infrastructure (e.g. BLIS_PACK_A, BLIS_PACK_B).
- Added a static initializer for mem_t objects, BLIS_MEM_INITIALIZER.
- Added a static initializer for pblk_t objects, BLIS_PBLK_INITIALIZER,
for use within the definition of BLIS_MEM_INITIALIZER.
- Moved the global_rntm object to bli_rntm.c and extern it where needed.
This means that the function bli_thread_init_rntm() was renamed to
bli_rntm_init_from_global() and relocated accordingly.
- Added a new bli_pack.c function, which serves as the home for
functions that manage the pack_a and pack_b fields of the global
rntm_t, including from environment variables, just as we have
functions to manage the threading fields of the global rntm_t in
bli_thread.c.
- Reorganized naming for files in frame/thread, which mostly involved
spinning off the bli_l3_thread_decorator() functions into their own
files. This change makes more sense when considering the further
addition of bli_l3_sup_thread_decorator() functions (for now limited
only to the single-threaded form found in the _single.c file).
- Explicitly initialize the reference sup handlers in both
bli_cntx_init_haswell.c and bli_cntx_init_zen.c so that it's more
obvious how to customize to a different handler, if desired.
- Removed various snippets of disabled code.
- Various comment updates.
Details:
- Fixed a subtle and complicated bug that only manifested via the BLAS
test drivers in the generic subconfiguration, and possibly any other
subconfiguration that did not register complex-domain gemm ukernels,
or registered ONLY real-domain ukernels as row-preferential. This is
a long story, but it boils down to an exception to the "transpose the
operation to bring storage of C into agreement with ukernel pref"
optimization in bli_hemm_front.c and bli_symm_front.c sabotaging the
proper functioning of the 1m method, but only when the imaginary
component of beta is zero. See the comments in issue #342 for more
details. Thanks to Dave Love for identifying the commit in which this
bug was introduced, and other feedback related to this bug.
Details:
- Added cpp macros to trmm and trmm3 front-ends to optionally force
those operations to be cast so the structured matrix is on the left.
symm and hemm already had such macros, but these too were renamed so
that the macros were individual to the operation. We now have four
such macros:
#define BLIS_DISABLE_HEMM_RIGHT
#define BLIS_DISABLE_SYMM_RIGHT
#define BLIS_DISABLE_TRMM_RIGHT
#define BLIS_DISABLE_TRMM3_RIGHT
Also, updated the comments in the symm and hemm front-ends related to
the first two macro guards, and added corresponding comments to the
trmm and trmm3 front-ends for the latter two guards. (They all
functionally do the same thing, just for their specific operations.)
Thanks to Jeff Hammond for reporting the bugs that led me to this
change (via #359).
- Updated config/old/haswellbb subconfiguration (used to debug issues
related to duplicating B during packing) to register: a packing
kernel for single-precision real; gemmbb ukernels for s, c, and z;
trsmbb ukernels for s, c, and z; gemmtrsmbb virtual ukrnels for s, c
and z; and to use non-default cache and register blocksizes for s, c,
and z datatypes. Also declared prototypes for all of the gemmbb,
trsmbb, and gemmtrsmbb ukernel functions within the
bli_cntx_init_haswellbb() function. This should, once applied to the
power9 configuration, fix the remaining issues in #359.
- Defined bli_spackm_6xk_bb4_ref(), which packs single reals with a
duplication factor of 4. This function is defined in the same file as
bli_dpackm_6xk_bb2_ref() (bli_packm_cxk_bb_ref.c).
Details:
- Added missing license header to bli_pwr9_asm_macros_12x6.h.
- Reverted temporary changes to various files in 'test' and 'testsuite'
directories.
- Moved testsuite/jobscripts into testsuite/old.
- Minor whitespace/comment changes across various files.
Implemented and registered power9 dgemm ukernel.
Details:
- Implemented 12x6 dgemm microkernel for power9. This microkernel
assumes that elements of B have been duplicated/broadcast during the
packing step. The microkernel uses a column orientation for its
microtile vector registers and thus implements column storage and
general stride IO cases. (A row storage IO case via in-register
transposition may be added at a future date.) It should be noted that
we recommend using this microkernel with gcc and *not* xlc, as issues
with the latter cropped up during development, including but not
limited to slightly incompatible vector register mnemonics in the GNU
extended inline assembly clobber list.
Details:
- In bli_syrk_front(), moved the conditional call to bli_syrk_check()
(if error checking is enabled) and the conditional scaling of C by
beta (if alpha is zero) so that they occur after, instead of before,
the call to bli_syrk_small(). This sequencing now matches that of
bli_gemm_small() in bli_gemm_front() and bli_trsm_small() in
bli_trsm_front().
Details:
- NOTE: This is a merge commit of 'master' of git://github.com/amd/blis
into 'amd-master' of flame/blis.
- Fixed a bug in the downstream value of BLIS_NUM_ARCHS, which was
inadvertantly not incremented when the Zen2 subconfiguration was
added.
- In bli_gemm_front(), added a missing conditional constraint around the
call to bli_gemm_small() that ensures that the computation precision
of C matches the storage precision of C.
- In bli_syrk_front(), reorganized and relocated the notrans/trans logic
that existed around the call to bli_syrk_small() into bli_syrk_small()
to minimize the calling code footprint and also to bring that code
into stylistic harmony with similar code in bli_gemm_front() and
bli_trsm_front(). Also, replaced direct accessing of obj_t fields with
proper accessor static functions (e.g. 'a->dim[0]' becomes
'bli_obj_length( a )').
- Added #ifdef BLIS_ENABLE_SMALL_MATRIX guard around prototypes for
bli_gemm_small(), bli_syrk_small(), and bli_trsm_small(). This is
strictly speaking unnecessary, but it serves as a useful visual cue to
those who may be reading the files.
- Removed cpp macro-protected small matrix debugging code from
bli_trsm_front.c.
- Added a GCC_OT_9_1_0 variable to build/config.mk.in to facilitate gcc
version check for availability of -march=znver2, and added appropriate
support to configure script.
- Cleanups to compiler flags common to recent AMD microarchitectures in
config/zen/amd_config.mk, including: removal of -march=znver1 et al.
from CKVECFLAGS (since the -march flag is added within make_defs.mk);
setting CRVECFLAGS similarly to CKVECFLAGS.
- Cleanups to config/zen/bli_cntx_init_zen.c.
- Cleanups, added comments to config/zen/make_defs.mk.
- Cleanups to config/zen2/make_defs.mk, including making use of newly-
added GCC_OT_9_1_0 and existing GCC_OT_6_1_0 to choose the correct
set of compiler flags based on the version of gcc being used.
- Reverted downstream changes to test/test_gemm.c.
- Various whitespace/comment changes.
Details:
- Added support for being able to duplicate (broadcast) elements in
memory when packing matrix B (ie: the left-hand operand) in level-3
operations. This turns out advantageous for some architectures that
can afford the cost of the extra bandwidth and somehow benefit from
the pre-broadcast elements (and thus being able to avoid using
broadcast-style load instructions on micro-rows of B in the gemm
microkernel).
- Support optionally disabling right-side hemm and symm. If this occurs,
hemm_r is implemented in terms of hemm_l (and symm_r in terms of
symm_l). This is needed when broadcasting during packing because the
alternative--supporting the broadcast of B while also allowing matrix
B to be Hermitian/symmetric--would be an absolute mess.
- Support alignment factors for packed blocks of A, B, and C separately
(as well as for general-purpose buffers). In addition, we support
byte offsets from those alignment values (which is different from
aligning by align+offset bytes to begin with). The default alignment
values are BLIS_PAGE_SIZE in all four cases, with the offset values
defaulting to zero.
- Pass pack_t schema into bli_?packm_cxk() so that it can be then passed
into the packm kernel, where it will be needed by packm kernels that
perform broadcasts of B, since the idea is that we *only* want to
broadcast when packing micropanels of B and not A.
- Added definition for variadic bli_cntx_set_l3_vir_ukrs(), which can be
used to set custom virtual level-3 microkernels in the cntx_t, which
would typically be done in the bli_cntx_init_*() function defined in
the subconfiguration of interest.
- Added a "broadcast B" kernel function for use with NP/NR = 12/6,
defined in in ref_kernels/1m/bli_packm_cxk_bb_ref.c.
- Added a gemm, gemmtrsm, and trsm "broadcast B" reference kernels
defined in ref_kernels/3/bb. (These kernels have been tested with
double real with NP/NR = 12/6.)
- Added #ifndef ... #endif guards around several macro constants defined
in frame/include/bli_kernel_macro_defs.h.
- Defined a few "broadcast B" static functions in
frame/include/level0/bb for use by "broadcast B"-style packm reference
kernels. For now, only the real domain kernels are tested and fully
defined.
- Output the alignment and offset values for packed blocks of A and B
in the testsuite's "BLIS configuration info" section.
- Comment updates to various files.
- Bumped so_version to 3.0.0.
Details:
- Fixed a bug in bli_l3_thrinfo_print_gemm_paths() and
bli_l3_thrinfo_print_trsm_paths(), defined in bli_l3_thrinfo.c,
whereby subnodes of the thrinfo_t tree are "dereferenced" near the
beginning of the functions, which may lead to segfaults in certain
situations where the thread tree was not fully formed because the
matrix problem was too small for the level of parallelism specified.
(That is, too small because some problems were assigned no work due
to the smallest units in the m and n dimensions being defined by the
register blocksizes mr and nr.) The fix requires several nested levels
of if statements, and this is one of those few instances where use of
goto statements results in (mostly) prettier code, especially in the
case of _gemm_paths(). And while it wasn't necessary, I ported this
goto usage to the loop body that prints the thrinfo_t work_id and
comm_id values for each thread. Thanks to Nicholai Tukanov for helping
to find this bug.
Details:
- Fixed an obscure but in the bli_dgemmsup_rv_haswell_asm_5x8n() kernel
that only affected the beta == 0, column-storage output case. Thanks
to the BLAS test drivers for catching this bug.
- Previously, bli_gemmsup_ref_var1n() and _var2m() were returning if
k = 0, when the correct action would be to scale by beta (and then
return). Thanks to the BLAS test drivers to catching this bug.
- Changed the sup threshold behavior such that the sup implementation
only kicks in if a matrix dimension is strictly less than (rather than
less than or equal to) the threshold in question.
- Initialize all thresholds to zero (instead of 10) by default in
ref_kernels/bli_cntx_ref.c. This, combined with the above change to
threshold testing means that calls to BLIS or BLAS with one or more
matrix dimensions of zero will no longer trigger the sup
implementation.
- Added disabled debugging output to frame/3/bli_l3_sup.c (for future
use, perhaps).
Details:
- Removed already limited use of the BLIS_ENABLE_SUP_MR_EXT and
BLIS_ENABLE_SUP_NR_EXT macros in bli_gemmsup_ref_var1n() and
bli_gemmsup_ref_var2m(). Their purpose was merely to avoid a long
conditional that would determine whether to allow the last iteration
to be merged with the second-to-last iteration. Functionally, the
macros were not needed, and they ended up causing problems when
building configuration families such as intel64 and x86_64.
Details:
- Fixed an incorrectly-named macro guard that is intended to allow
disabling of the sup framework via the configure option
--disable-sup-handling. In this case, the preprocessor macro,
BLIS_DISABLE_SUP_HANDLING, was still named by its name from an older
uncommitted version of the code (BLIS_DISABLE_SM_HANDLING).
Details:
- Implemented a new sub-framework within BLIS to support the management
of code and kernels that specifically target matrix problems for which
at least one dimension is deemed to be small, which can result in long
and skinny matrix operands that are ill-suited for the conventional
level-3 implementations in BLIS. The new framework tackles the problem
in two ways. First the stripped-down algorithmic loops forgo the
packing that is famously performed in the classic code path. That is,
the computation is performed by a new family of kernels tailored
specifically for operating on the source matrices as-is (unpacked).
Second, these new kernels will typically (and in the case of haswell
and zen, do in fact) include separate assembly sub-kernels for
handling of edge cases, which helps smooth performance when performing
problems whose m and n dimension are not naturally multiples of the
register blocksizes. In a reference to the sub-framework's purpose of
supporting skinny/unpacked level-3 operations, the "sup" operation
suffix (e.g. gemmsup) is typically used to denote a separate namespace
for related code and kernels. NOTE: Since the sup framework does not
perform any packing, it targets row- and column-stored matrices A, B,
and C. For now, if any matrix has non-unit strides in both dimensions,
the problem is computed by the conventional implementation.
- Implemented the default sup handler as a front-end to two variants.
bli_gemmsup_ref_var2() provides a block-panel variant (in which the
2nd loop around the microkernel iterates over n and the 1st loop
iterates over m), while bli_gemmsup_ref_var1() provides a panel-block
variant (2nd loop over m and 1st loop over n). However, these variants
are not used by default and provided for reference only. Instead, the
default sup handler calls _var2m() and _var1n(), which are similar
to _var2() and _var1(), respectively, except that they defer to the
sup kernel itself to iterate over the m and n dimension, respectively.
In other words, these variants rely not on microkernels, but on
so-called "millikernels" that iterate along m and k, or n and k.
The benefit of using millikernels is a reduction of function call
and related (local integer typecast) overhead as well as the ability
for the kernel to know which micropanel (A or B) will change during
the next iteration of the 1st loop, which allows it to focus its
prefetching on that micropanel. (In _var2m()'s millikernel, the upanel
of A changes while the same upanel of B is reused. In _var1n()'s, the
upanel of B changes while the upanel of A is reused.)
- Added a new configure option, --[en|dis]able-sup-handling, which is
enabled by default. However, the default thresholds at which the
default sup handler is activated are set to zero for each of the m, n,
and k dimensions, which effectively disables the implementation. (The
default sup handler only accepts the problem if at least one dimension
is smaller than or equal to its corresponding threshold. If all
dimensions are larger than their thresholds, the problem is rejected
by the sup front-end and control is passed back to the conventional
implementation, which proceeds normally.)
- Added support to the cntx_t structure to track new fields related to
the sup framework, most notably:
- sup thresholds: the thresholds at which the sup handler is called.
- sup handlers: the address of the function to call to implement
the level-3 skinny/unpacked matrix implementation.
- sup blocksizes: the register and cache blocksizes used by the sup
implementation (which may be the same or different from those used
by the conventional packm-based approach).
- sup kernels: the kernels that the handler will use in implementing
the sup functionality.
- sup kernel prefs: the IO preference of the sup kernels, which may
differ from the preferences of the conventional gemm microkernels'
IO preferences.
- Added a bool_t to the rntm_t structure that indicates whether sup
handling should be enabled/disabled. This allows per-call control
of whether the sup implementation is used, which is useful for test
drivers that wish to switch between the conventional and sup codes
without having to link to different copies of BLIS. The corresponding
accessor functions for this new bool_t are defined in bli_rntm.h.
- Implemented several row-preferential gemmsup kernels in a new
directory, kernels/haswell/3/sup. These kernels include two general
implementation types--'rd' and 'rv'--for the 6x8 base shape, with
two specialized millikernels that embed the 1st loop within the kernel
itself.
- Added ref_kernels/3/bli_gemmsup_ref.c, which provides reference
gemmsup microkernels. NOTE: These microkernels, unlike the current
crop of conventional (pack-based) microkernels, do not use constant
loop bounds. Additionally, their inner loop iterates over the k
dimension.
- Defined new typedef enums:
- stor3_t: captures the effective storage combination of the level-3
problem. Valid values are BLIS_RRR, BLIS_RRC, BLIS_RCR, etc. A
special value of BLIS_XXX is used to denote an arbitrary combination
which, in practice, means that at least one of the operands is
stored according to general stride.
- threshid_t: captures each of the three dimension thresholds.
- Changed bli_adjust_strides() in bli_obj.c so that bli_obj_create()
can be passed "-1, -1" as a lazy request for row storage. (Note that
"0, 0" is still accepted as a lazy request for column storage.)
- Added support for various instructions to bli_x86_asm_macros.h,
including imul, vhaddps/pd, and other instructions related to integer
vectors.
- Disabled the older small matrix handling code inserted by AMD in
bli_gemm_front.c, since the sup framework introduced in this commit
is intended to provide a more generalized solution.
- Added test/sup directory, which contains standalone performance test
drivers, a Makefile, a runme.sh script, and an 'octave' directory
containing scripts compatible with GNU Octave. (They also may work
with matlab, but if not, they are probably close to working.)
- Reinterpret the storage combination string (sc_str) in the various
level-3 testsuite modules (e.g. src/test_gemm.c) so that the order
of each matrix storage char is "cab" rather than "abc".
- Comment updates in level-3 BLAS API wrappers in frame/compat.
Change void*-typed function pointers to void_fp.
- Updated all instances of void* variables that store function pointers
to variables of a new type, void_fp. Originally, I wanted to define
the type of void_fp as "void (*void_fp)( void )"--that is, a pointer
to a function with no return value and no arguments. However, once
I did this, I realized that gcc complains with incompatible pointer
type (-Wincompatible-pointer-types) warnings every time any such a
pointer is being assigned to its final, type-accurate function
pointer type. That is, gcc will silently typecast a void* to
another defined function pointer type (e.g. dscalv_ker_ft) during
an assignment from the former to the latter, but the same statement
will trigger a warning when typecasting from a void_fp type. I suspect
an explicit typecast is needed in order to avoid the warning, which
I'm not willing to insert at this time.
- Added a typedef to bli_type_defs.h defining void_fp as void*, along
with a commented-out version of the aborted definition described
above. (Note that POSIX requires that void* and function pointers
be interchangeable; it is the C standard that does not provide this
guarantee.)
- Comment updates to various _oapi.c files.
Details:
- After merging PR #303, at Isuru's request, I removed the use of
BLIS_EXPORT_BLIS from all function prototypes *except* those that we
potentially wish to be exported in shared/dynamic libraries. In other
words, I removed the use of BLIS_EXPORT_BLIS from all prototypes of
functions that can be considered private or for internal use only.
This is likely the last big modification along the path towards
implementing the functionality spelled out in issue #248. Thanks
again to Isuru Fernando for his initial efforts of sprinkling the
export macros throughout BLIS, which made removing them where
necessary relatively painless. Also, I'd like to thank Tony Kelman,
Nathaniel Smith, Ian Henriksen, Marat Dukhan, and Matthew Brett for
participating in the initial discussion in issue #37 that was later
summarized and restated in issue #248.
- CREDITS file update.
* Revert "restore bli_extern_defs exporting for now"
This reverts commit 09fb07c350b2acee17645e8e9e1b8d829c73dca8.
* Remove symbols not intended to be public
* No need of def file anymore
* Fix whitespace
* No need of configure option
* Remove export macro from definitions
* Remove blas export macro from definitions
Details:
- Updated the BLAS compatibility layer for level-3 operations so that
the corresponding BLIS object API is called directly rather than first
calling the typed BLIS API. The previous code based on the typed BLIS
API calls is still available in a deactivated cpp macro branch, which
may be re-activated by #defining BLIS_BLAS3_CALLS_TAPI. (This does not
yet correspond to a configure option. If it seems like people might
want to toggle this behavior more regularly, a configure option can be
added in the future.)
- Updated the BLIS typed API to statically "pre-initialize" objects via
new initializor macros. Initialization is then finished via calls to
static functions bli_obj_init_finish_1x1() and bli_obj_init_finish(),
which are similar to the previously-called functions,
bli_obj_create_1x1_with_attached_buffer() and
bli_obj_create_with_attached_buffer(), respectively. (The BLAS
compatibility layer updates mentioned above employ this new technique
as well.)
- Transformed certain routines in bli_param_map.c--specifically, the
ones that convert netlib-style parameters to BLIS equivalents--into
static functions, now in bli_param_map.h. (The remaining three classes
of conversation routines were left unchanged.)
- Added the aforementioned pre-initializor macros to bli_type_defs.h.
- Relocated bli_obj_init_const() and bli_obj_init_constdata() from
bli_obj_macro_defs.h to bli_type_defs.h.
- Added a few macros to bli_param_macro_defs.h for testing domains for
real/complexness and precisions for single/double-ness.
Details:
- Parallelism within the IC loop (3rd loop around the microkernel) is
now supported within the trsm operation. This is done via a new branch
on each of the control and thread trees, which guide execution of a
new trsm-only subproblem from within bli_trsm_blk_var1(). This trsm
subproblem corresponds to the macrokernel computation on only the
block of A that contains the diagonal (labeled as A11 in algorithms
with FLAME-like partitioning), and the corresponding row panel of C.
During the trsm subproblem, all threads within the JC communicator
participate and parallelize along the JR loop, including any
parallelism that was specified for the IC loop. (IR loop parallelism
is not supported for trsm due to inter-iteration dependencies.) After
this trsm subproblem is complete, a barrier synchronizes all
participating threads and then they proceed to apply the prescribed
BLIS_IC_NT (or equivalent) ways of parallelism (and any BLIS_JR_NT
parallelism specified within) to the remaining gemm subproblem (the
rank-k update that is performed using the newly updated row-panel of
B). Thus, trsm now supports JC, IC, and JR loop parallelism.
- Modified bli_trsm_l_cntl_create() to create the new "prenode" branch
of the trsm_l cntl_t tree. The trsm_r tree was left unchanged, for
now, since it is not currently used. (All trsm problems are cast in
terms of left-side trsm.)
- Updated bli_cntl_free_w_thrinfo() to be able to free the newly shaped
trsm cntl_t trees. Fixed a potentially latent bug whereby a cntl_t
subnode is only recursed upon if there existed a corresponding
thrinfo_t node, which may not always exist (for problems too small
to employ full parallelization due to the minimum granularity imposed
by micropanels).
- Updated other functions in frame/base/bli_cntl.c, such as
bli_cntl_copy() and bli_cntl_mark_family(), to recurse on sub-prenodes
if they exist.
- Updated bli_thrinfo_free() to recurse into sub-nodes and prenodes
when they exist, and added support for growing a prenode branch to
bli_thrinfo_grow() via a corresponding set of help functions named
with the _prenode() suffix.
- Added a bszid_t field thrinfo_t nodes. This field comes in handy when
debugging the allocation/release of thrinfo_t nodes, as it helps trace
the "identity" of each nodes as it is created/destroyed.
- Renamed
bli_l3_thrinfo_print_paths() -> bli_l3_thrinfo_print_gemm_paths()
and created a separate bli_l3_thrinfo_print_trsm_paths() function to
print out the newly reconfigured thrinfo_t trees for the trsm
operation.
- Trival changes to bli_gemm_blk_var?.c and bli_trsm_blk_var?.c
regarding variable declarations.
- Removed subpart_t enum values BLIS_SUBPART1T, BLIS_SUBPART1B,
BLIS_SUBPART1L, BLIS_SUBPART1R. Then added support for two new labels
(semantically speaking): BLIS_SUBPART1A and BLIS_SUBPART1B, which
represent the subpartition ahead of and behind, respectively,
BLIS_SUBPART1. Updated check functions in bli_check.c accordingly.
- Shuffled layering/APIs for bli_acquire_mpart_[mn]dim() and
bli_acquire_mpart_t2b/b2t(), _l2r/r2l().
- Deprecated old functions in frame/3/bli_l3_thrinfo.c.
Details:
- Implemented a sophisticated data structure and set of APIs that track
the small blocks of memory (around 80-100 bytes each) used when
creating nodes for control and thread trees (cntl_t and thrinfo_t) as
well as thread communicators (thrcomm_t). The purpose of the small
block allocator, or sba, is to allow the library to transition into a
runtime state in which it does not perform any calls to malloc() or
free() during normal execution of level-3 operations, regardless of
the threading environment (potentially multiple application threads
as well as multiple BLIS threads). The functionality relies on a new
data structure, apool_t, which is (roughly speaking) a pool of
arrays, where each array element is a pool of small blocks. The outer
pool, which is protected by a mutex, provides separate arrays for each
application thread while the arrays each handle multiple BLIS threads
for any given application thread. The design minimizes the potential
for lock contention, as only concurrent application threads would
need to fight for the apool_t lock, and only if they happen to begin
their level-3 operations at precisely the same time. Thanks to Kiran
Varaganti and AMD for requesting this feature.
- Added a configure option to disable the sba pools, which are enabled
by default; renamed the --[dis|en]able-packbuf-pools option to
--[dis|en]able-pba-pools; and rewrote the --help text associated with
this new option and consolidated it with the --help text for the
option associated with the sba (--[dis|en]able-sba-pools).
- Moved the membrk field from the cntx_t to the rntm_t. We now pass in
a rntm_t* to the bli_membrk_acquire() and _release() APIs, just as we
do for bli_sba_acquire() and _release().
- Replaced all calls to bli_malloc_intl() and bli_free_intl() that are
used for small blocks with calls to bli_sba_acquire(), which takes a
rntm (in addition to the bytes requested), and bli_sba_release().
These latter two functions reduce to the former two when the sba pools
are disabled at configure-time.
- Added rntm_t* arguments to various cntl_t and thrinfo_t functions, as
required by the new usage of bli_sba_acquire() and _release().
- Moved the freeing of "old" blocks (those allocated prior to a change
in the block_size) from bli_membrk_acquire_m() to the implementation
of the pool_t checkout function.
- Miscellaneous improvements to the pool_t API.
- Added a block_size field to the pblk_t.
- Harmonized the way that the trsm_ukr testsuite module performs packing
relative to that of gemmtrsm_ukr, in part to avoid the need to create
a packm control tree node, which now requires a rntm_t that has been
initialized with an sba and membrk.
- Re-enable explicit call bli_finalize() in testsuite so that users who
run the testsuite with memory tracing enabled can check for memory
leaks.
- Manually imported the compact/minor changes from 61441b24 that cause
the rntm to be copied locally when it is passed in via one of the
expert APIs.
- Reordered parameters to various bli_thrcomm_*() functions so that the
thrcomm_t* to the comm being modified is last, not first.
- Added more descriptive tracing for allocating/freeing small blocks and
formalized via a new configure option: --[dis|en]able-mem-tracing.
- Moved some unused scalm code and headers into frame/1m/other.
- Whitespace changes to bli_pthread.c.
- Regenerated build/libblis-symbols.def.
Details:
- SYRK for small matrix was implemented by reusing small GEMM routine. This was
resulting in output written to the full C matrix, and C being symmetric the
lower and upper triangles of C matrix contained same results. BLAS SYRK API
spec demands either lower or upper triangle of C matrix to be written with
results. So, this was resulting in BLAS test failures, even though testsuite
of BLIS was passing small SYRK operation.
- To fix BLAS test failures of small matrix SYRK, separate kernel routines are
implemented for small SYRK for both single and double precision. The newly
added small SYRK routines are in file kernels/zen/3/bli_syrk_small.c.
Now the intermediate results of matrix C are written to a scratch buffer.
Final results are written from scratch buffer to matrix C using SIMD
copy to either lower or upper traingle part of matrix C.
- Source and header files frame/3/syrk/bli_syrk_front.c and
frame/3/syrk/bli_syrk_front.h are changed to invoke new small SYRK routines.
Change-Id: I9cfb1116c93d150aefac673fca033952ecac97cb
Details:
- Added malloc_ft and free_ft fields to pool_t, which are provided when
the pool is initialized, to allow bli_pool_alloc_block() and
bli_pool_free_block() to call bli_fmalloc_align()/bli_ffree_align()
with arbitrary align_size values (according to how the pool_t was
initialized).
- Added a block_ptrs_len argument to bli_pool_init(), which allows the
caller to specify an initial length for the block_ptrs array, which
previously suffered the cost of being reallocated, copied, and freed
each time a new block was added to the pool.
- Consolidated the "buf_sys" and "buf_align" pointer fields in pblk_t
into a single "buf" field. Consolidated the bli_pblk API accordingly
and also updated the bli_mem API implementation. This was done
because I'd previously already implemented opaque alignment via
bli_malloc_align(), which allocates extra space and stores the
original pointer returned by malloc() one element before the element
whose address is aligned.
- Tweaked bli_membrk_acquire_m() and bli_membrk_release() to call
bli_fmalloc_align() and bli_ffree_align(), which required adding an
align_size field to the membrk_t struct.
- Pass the pack schemas directly into bli_l3_cntl_create_if() rather
than transmit them via objects for A and B.
- Simplified bli_l3_cntl_free_if() and renamed to bli_l3_cntl_free().
The function had not been conditionally freeing control trees for
quite some time. Also, removed obj_t* parameters since they aren't
needed anymore (or never were).
- Spun-off OpenMP nesting code in bli_l3_thread_decorator() to a
separate function, bli_l3_thread_decorator_thread_check().
- Renamed:
bli_malloc_align() -> bli_fmalloc_align()
bli_free_align() -> bli_ffree_align()
bli_malloc_noalign() -> bli_fmalloc_noalign()
bli_free_noalign() -> bli_ffree_noalign()
The 'f' is for "function" since they each take a malloc_ft or free_ft
function pointer argument.
- Inserted various printf() calls for the purposes of tracing memory
allocation and freeing, guarded by cpp macro ENABLE_MEM_DEBUG, which,
for now, is intended to be a "hidden" feature rather than one hooked
up to a configure-time option.
- Defined bli_rntm_equals(), which compares two rntm_t for equality.
(There are no use cases for this function yet, but there may be soon.)
- Whitespace changes to function parameter lists in bli_pool.c, .h.
Details:
- Removed explicit reference to The University of Texas at Austin in the
third clause of the license comment blocks of all relevant files and
replaced it with a more all-encompassing "copyright holder(s)".
- Removed duplicate words ("derived") from a few kernels' license
comment blocks.
- Homogenized license comment block in kernels/zen/3/bli_gemm_small.c
with format of all other comment blocks.
Details:
- Lifted the constraint that 1m only be used when all operands' storage
datatypes (along with the computation datatype) are equal. Now, 1m may
be used as long as all operands are stored in the complex domain. This
change largely consisted of adding the ability to pack to 1e and 1r
formats from one precision to another. It also required adding logic
for handling complex values of alpha to bli_packm_blk_var1_md()
(similar to the logic in bli_packm_blk_var1()).
- Fixed a bug in several virtual microkernels (bli_gemm_md_c2r_ref.c,
bli_gemm1m_ref.c, and bli_gemmtrsm1m_ref.c) that resulted in the wrong
ukernel output preference field being read. Previously, the preference
for the native complex ukernel was being read instead of the pref for
the native real domain ukernel. This bug would not manifest if the
preference for the native complex ukernel happened to be equal to that
of the native real ukernel.
- Added support for testing mixed-precision 1m execution via the gemm
module of the testsuite.
- Tweaked/simplified bli_gemm_front() and bli_gemm_md.c so that pack
schemas are always read from the context, rather than trying to
sometimes embed them directly to the A and B objects. (They are still
embedded, but now uniformly only after reading the schemas from the
context.)
- Redefined cpp macro bli_l3_ind_recast_1m_params() as a static function
and renamed to bli_gemm_ind_recast_1m_params() (since gemm is the only
consumer).
- Added 1m optimization logic (via bli_gemm_ind_recast_1m_params()) to
bli_gemm_ker_var2_md().
- Added explicit handling for beta == 1 and beta == 0 in the reference
gemm1m virtual microkernel in ref_kernels/ind/bli_gemm1m_ref.c.
- Rewrote various level-0 macro defs, including axpyris, axpbyris,
scal2ris, and xpbyris (and their conjugating counterparts) to
explicitly support three operand types and updated invocations to
xpbyris in bli_gemmtrsm1m_ref.c.
- Query and use the storage datatype of the packed object instead of the
storage datatype of the source object in bli_packm_blk_var1().
- Relocated and renamed frame/ind/misc/bli_l3_ind_opt.h to
frame/3/gemm/ind/bli_gemm_ind_opt.h.
- Various whitespace/comment updates.
Details:
- Added a num_t datatype bitfield to the obj_t in the form of a new
info2 field in the obj_t. This change was made primarily so that in
the case of mixed-datatype gemm, the alpha scalar would not need to
be cast to the storage datatype of B (or A) before then being cast to
the computation datatype just before the macrokernel is called. This
double-casting regime could result in loss of precision if the storage
datatype of B (or A) is less than the computation precision. In
practice, it was likely not going to be a big deal since most usage of
alpha is for -1.0, 0.0, and 1.0 (or integer multiples thereof), which
can all be represented exactly in single or double precision.
- The type of objbits_t was changed to uint32_t, so the new format
potentially takes up the same space as the previous obj_t definition,
assuming no padding inserted by the compiler. Shrinking info to 32
bits and spilling over into a second field was chosen over using the
high 32 bits of a single 64-bit objbits_t info field because many of
the bitwise operations are performed with enums such as num_t, dom_t,
and prec_t, which may take on the type of 32-bit ints. It's easier to
just keep all of those bitwise operations in 32 bits than perform a
million typecasts throughout bli_type_defs.h and bli_obj_macro_defs.h
to ensure that the integers are treated as 64-bit for the purposes of
the ANDs, ORs, and bitshifts.
- Many comment updates.
- Thanks to Devin Matthews and Devangi Parikh for their feedback and
involvement during this commit cycle.
Details:
- Fixed a bug in frame/3/bli_l3_oapi.c in the conditional that divides
use of induced method (1m) execution from native execution. The former
was intended to only be used in cases where all storage datatypes are
complex and the datatype of C is equal to the computation datatype.
(If mixed datatypes are detected, native execution would be used.)
However, the code in bli_gemm() was erroneously checking the execution
datatype instead of the computation datatype, which at that point is
guaranteed to be equal to the storage datatype even if the computation
datatype contains a different value. Thanks to Devangi Parikh for
helping in isolating this bug.
Details:
- Fixed a bug in the code that prints out the communicator and work ids
from the various threads' thrinfo_t nodes. This bug manifested when
the dimension being parallelized was not large enough such that every
thread was assigned actual work (since the minimum amount of work is
determined by the register blocksize in the dimension being
parallelized). In those cases, the threads that receive no work in
that dimension do not finish building their thrinfo_t tree, leaving
lower-level nodes non-existent. (The bug itself was usally observed as
a segfault when the printing code attempted to dereference all the way
down the thrinfo_t tree.) The solution involves explicitly checking
each node as it is dereferenced, and if at any time NULL is found, all
subsequent communicator and work ids are set to -1.
