Issue: For the default values of mc, kc and nc with multi instance mode the performance across the cores dip drastically.
Fix: After experimentation found different set of values (mc, kc and nc) which fits in the cache size, and performance across the remains same across all the cores.
Change-Id: I98265e3b7e61cd7602a0cc5596240e86c08c03fe
Details:
- Updated the BLASFEO performance graphs shown in PerformanceSmall.md
using a new commit of BLASFEO (2c9f312); updated PerformanceSmall.md
accordingly.
- Updated test/sup/octave/plot_l3sup_perf.m so that the .m files
containing the mpnpkp results do not need to be preprocessed in order
to plot half the problem size range (ie: up to 400 instead of the
800 range of the other shape cases).
- Trivial updates to runme.m.
Details:
- Updated the graphs linked in PerformanceSmall.md with BLASFEO results,
and added documenting language accordingly.
- Updated scripts in test/sup/octave to plot BLASFEO data.
- Minor tweak to language re: how OpenBLAS was configured for
docs/Performance.md.
Details:
- Added a new markdown document, docs/PerformanceSmall.md, which
publishes new performance graphs for Kaby Lake and Epyc showcasing
the new BLIS sup (small/skinny/unpacked) framework logic and kernels.
For now, only single-threaded dgemm performance is shown.
- Reorganized graphs in docs/graphs into docs/graphs/large, with new
graphs being placed in docs/graphs/sup.
- Updates to scripts in test/sup/octave, mostly to allow decent output
in both GNU octave and Matlab.
- Updated README.md to mention and refer to the new PerformanceSmall.md
document.
Details:
- Commented out redundant setting of LIBBLIS_LINK within all driver-
level Makefiles. This variable is already set within common.mk, and
so the only time it should be overridden is if the user wants to link
to a different copy of libblis.
- Very minor changes to build/gen-make-frags/gen-make-frag.sh.
- Whitespace and inconsequential quoting change to configure.
- Moved top-level 'windows' directory into a new 'attic' directory.
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.
Details:
- Updated the level-3 performance graphs in docs/graphs with new Eigen
results, this time using a development version cloned from their git
mirror on March 27, 2019 (version 3.3.90). Performance is improved
over 3.3.7, though still noticeably short of BLIS/MKL in most cases.
- Very minor updates to docs/Performance.md and matlab scripts in
test/3/matlab.
Details:
- Updated the Haswell, SkylakeX, and Epyc performance graphs in
docs/graphs to report on Eigen implementations, where applicable.
Specifically, Eigen implements all level-3 operations sequentially,
however, of those operations it only provides multithreaded gemm.
Thus, mt results for symm/hemm, syrk/herk, trmm, and trsm are
omitted. Thanks to Sameer Agarwal for his help configuring and
using Eigen.
- Updated docs/Performance.md to note the new implementation tested.
- CREDITS file update.
Details:
- Adjusted test/3/Makefile so that the test drivers are linked against
Eigen's BLAS library for hemm, herk, trmm, and trsm. We have to do
this since Eigen's headers don't define implementations to the
standard BLAS APIs.
- Simplified #included headers in hemm, herk, trmm, and trsm source
driver files, since nothing specific to Eigen is needed at
compile-time for those operations.
Details:
- Use compile-time implementations of Eigen in test_gemm.c via new
EIGEN cpp macro, defined on command line. (Linking to Eigen's BLAS
library is not necessary.) However, as of Eigen 3.3.7, Eigen only
parallelizes the gemm operation and not hemm, herk, trmm, trsm, or
any other level-3 operation.
- Fixed a bug in trmm and trsm drivers whereby the wrong function
(bli_does_trans()) was being called to determine whether the object
for matrix A should be created for a left- or right-side case. This
was corrected by changing the function to bli_is_left(), as is done
in the hemm driver.
- Added support for running Eigen test drivers from runme.sh.
Details:
- Added a new markdown document, docs/Performance.md, which reports
performance of a representative set of level-3 operations across a
variety of hardware architectures, comparing BLIS to OpenBLAS and a
vendor library (MKL on Intel/AMD, ARMPL on ARM). Performance graphs,
in pdf and png formats, reside in docs/graphs.
- Updated README.md to link to new Performance.md document.
- Minor updates to CREDITS, docs/Multithreading.md.
- Minor updates to matlab scripts in test/3/matlab.
Details:
- Made extra explicit the fact that: (a) multithreading in BLIS is
disabled by default; and (b) even with multithreading enabled, the
user must specify multithreading at runtime in order to observe
parallelism. Thanks to M. Zhou for suggesting these clarifications
in #292.
- Also made explicit that only the environment variable and global
runtime API methods are available when using the BLAS API. If the
user wishes to use the local runtime API (specify multithreading on
a per-call basis), one of the native BLIS APIs must be used.
Details:
- Added export annotations to additional function prototypes in order to
accommodate the testsuite.
- Disabled calling bli_amaxv_check() from within the testsuite's
test_amaxv.c.
Details:
- Introduced a new configure option, --enable-export-all, which will
cause all shared library symbols to be exported by default, or,
alternatively, --disable-export-all, which will cause all symbols to
be hidden by default, with only those symbols that are annotated for
visibility, via BLIS_EXPORT_BLIS (and BLIS_EXPORT_BLAS for BLAS
symbols), to be exported. The default for this configure option is
--disable-export-all. Thanks to Isuru Fernando for consulting on
this commit.
- Removed BLIS_EXPORT_BLIS annotations from frame/1m/bli_l1m_unb_var1.h,
which was intended for 5a5f494.
- Relocated BLIS_EXPORT-related cpp logic from bli_config.h.in to
frame/include/bli_config_macro_defs.h.
- Provided appropriate logic within common.mk to implement variable
symbol visibility for gcc, clang, and icc (to the extend that each of
these compilers allow).
- Relocated --help text associated with debug option (-d) to configure
slightly further down in the list.
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:
- Minor updates to matlab graph-generating scripts.
- Added a plot_all.m script that is more of a scratchpad for copying and
pasting function invocations into matlab to generate plots that are
presently of interest to us.
Details:
- Added language to remind the reader to disable sup if the intended
behavior is for the sandbox implementation to handle all problem
sizes, even the smaller ones that would normally be handled by the
sup code path.
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:
- Changed the typedef that defines bool_t from:
typedef gint_t bool_t;
where gint_t is a signed integer that forms the basis of most other
integers in BLIS, to:
typedef bool bool_t;
- Changed BLIS's TRUE and FALSE macro definitions from being in terms of
integer literals:
#define TRUE 1
#define FALSE 0
to being in terms of C99 boolean constants:
#define TRUE true
#define FALSE false
which are provided by stdbool.h.
- This commit constitutes the second phase of a transition toward using
C99's bool instead of bool_t, which will address 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.
Details:
- Updated Makefiles in test, test/3, and test/sup so that running any of
the usual targets without having first built BLIS results in a helpful
error message. For example, if BLIS is not yet configured, make will
output:
Makefile:327: *** Cannot proceed: config.mk not detected! Run
configure first. Stop.
Similarly, if BLIS is configured but not yet built, make will output:
Makefile:340: *** Cannot proceed: BLIS library not yet built! Run
make first. Stop.
In previous commits, these actions would result in a rather cryptic
make error such as:
make: *** No rule to make target 'test_sgemm_2400_asm_blis_st.x',
needed by 'blis-nat-st'. Stop.
Details:
- Fixed various typecasts in
frame/base/bli_cntx.h
frame/base/bli_mbool.h
frame/base/bli_rntm.h
frame/include/bli_misc_macro_defs.h
frame/include/bli_obj_macro_defs.h
frame/include/bli_param_macro_defs.h
that were missing or being done improperly/incompletely. For example,
many return values were being typecast as
(bool_t)x && y
rather than
(bool_t)(x && y)
Thankfully, none of these deficiencies had manifested as actual bugs
at the time of this commit.
- Changed the return type of bli_env_get_var() from dim_t to gint_t.
This reflects the fact that bli_env_get_var() needs to be able to
return a signed integer, and even though dim_t is currently defined
as a signed integer, it does not intuitively appear to necessarily be
signed by inspection (i.e., an integer named "dim_t" for matrix
"dimension"). Also, updated use of bli_env_get_var() within
bli_pack.c to reflect the changed return type.
- Redefined type of thrcomm_t.barrier_sense field from bool_t to gint_t
and added comments to the bli_thrcomm_*.h files that will explain a
planned replacement of bool_t with C99's bool type.
- Note: These changes are being made to facilitate the substitution of
'bool' for 'bool_t', which will eliminate the namespace conflict with
arm_sve.h as reported in issue #420. This commit implements the first
phase of that transition. Thanks to RuQing Xu for reporting this
issue.
- CREDITS file update.
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:
- Added support to bli_gemmsup_rv_haswell_asm_d6x8n.c for handling
various n = 6 edge cases with a single sup kernel call. Previously,
only n = {4,2,1} were handled explicitly as single kernel calls;
that is, cases where n = 6 were previously being executed via two
kernel calls (n = 4 and n = 2).
- Added commented debug line to testsuite's test_libblis.c.
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:
- Added the -fomit-frame-pointer compiler option to the CKOPTFLAGS
variable in the following make_defs.mk files:
config/haswell/make_defs.mk
config/skx/make_defs.mk
as well as comments that mention why the compiler option is needed.
This option is needed to prevent the compiler from using the rbp
frame register (in the very early portion of kernel code, typically
where k_iter and k_left are defined and computed), which, as of
1c719c9, is used explicitly by the gemmsup millikernels. Thanks to
Devin Matthews for identifying this missing option and to Jeff
Diamond for reporting the original bug in #417.
- The file
config/zen/amd_config.mk
which feeds into the make_defs.mk for both zen and zen2 subconfigs,
was also touched, but only to add a commented-out compiler option
(and the aforementioned explanatory comment) since that file already
uses -fomit-frame-pointer in COPTFLAGS, which forms the basis of
CKOPTFLAGS.
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:
- Updated the test/sup source file (test_gemm.c) and Makefile to support
building matrices with small or large leading dimensions, and updated
runme.sh to support executing both kinds of test drivers.
- Updated runme.sh to allow for executing sup drivers with unpacked (the
default) or packed matrices (via setting BLIS_PACK_A, BLIS_PACK_B
environment variables), and for capturing output to files that encode
both the leading dimension (small or large) and packing status into
the filenames.
- Consolidated octave scripts in test/sup/octave_st, test/sup/octave_mt
into test/sup/octave and updated the octave code in that consolidated
directory to read the new output filename format (encoding ldim and
packing). Also added comments and streamlined code, particularly in
plot_panel_trxsh.m. Tested the octave scripts with octave 5.2.0.
- Moved old octave_st, octave_mt directories to test/sup/old.
Details:
- Previously, the entry for shiftd in the Operation index section of
BLISTypedAPI.md was incorrectly linking to the shiftd operation entry
in BLISObjectAPI.md. This has been fixed. Thanks to Jeff Diamond for
helping find this incorrect link.
Details:
- Fixed a few not-really-bugs:
- Previously, the d6x8m kernels were still prefetching the next upanel
of A using MR*rs_a instead of ps_a (same for prefetching of next
upanel of B in d6x8n kernels using NR*cs_b instead of ps_b). Given
that the upanels might be packed, using ps_a or ps_b is the correct
way to compute the prefetch address.
- Fixed an obscure bug in the rd_d6x8m kernel that, by dumb luck,
executed as intended even though it was based on a faulty pointer
management. Basically, in the rd_d6x8m kernel, the pointer for B
(stored in rdx) was loaded only once, outside of the jj loop, and in
the second iteration its new position was calculated by incrementing
rdx by the *absolute* offset (four columns), which happened to be the
same as the relative offset (also four columns) that was needed. It
worked only because that loop only executed twice. A similar issue
was fixed in the rd_d6x8n kernels.
- Various cleanups and additions, including:
- Factored out the loading of rs_c into rdi in rd_d6x8[mn] kernels so
that it is loaded only once outside of the loops rather than
multiple times inside the loops.
- Changed outer loop in rd kernels so that the jump/comparison and
loop bounds more closely mimic what you'd see in higher-level source
code. That is, something like:
for( i = 0; i < 6; i+=3 )
rather than something like:
for( i = 0; i <= 3; i+=3 )
- Switched row-based IO to use byte offsets instead of byte column
strides (e.g. via rsi register), which were known to be 8 anyway
since otherwise that conditional branch wouldn't have executed.
- Cleaned up and homogenized prefetching a bit.
- Updated the comments that show the before and after of the
in-register transpositions.
- Added comments to column-based IO cases to indicate which columns
are being accessed/updated.
- Added rbp register to clobber lists.
- Removed some dead (commented out) code.
- Fixed some copy-paste typos in comments in the rv_6x8n kernels.
- Cleaned up whitespace (including leading ws -> tabs).
- Moved edge case (non-milli) kernels to their own directory, d6x8,
and split them into separate files based on the "NR" value of the
kernels (Mx8, Mx4, Mx2, etc.).
- Moved config-specific reference Mx1 kernels into their own file
(e.g. bli_gemmsup_r_haswell_ref_dMx1.c) inside the d6x8 directory.
- Added rd_dMx1 assembly kernels, which seems marginally faster than
the corresponding reference kernels.
- Updated comments in ref_kernels/bli_cntx_ref.c and changed to using
the row-oriented reference kernels for all storage combos.
Details:
- Reran all existing single-threaded performance experiments comparing
BLIS sup to other implementations (including the conventional code
path within BLIS), using the latest versions (where appropriate).
- Added multithreaded results for the three existing hardware types
showcased in docs/PerformanceSmall.md: Kaby Lake, Haswell, and Epyc
(Zen1).
- Various minor updates to the text in docs/PerformanceSmall.md.
- Updates to the octave scripts in test/sup/octave, test/supmt/octave.
Details:
- Updated the Makefile, test_gemm.c, and runme.sh in test/sup to be able
to compile and run both single-threaded and multithreaded experiments.
This should help with maintenance going forward.
- Created a test/sup/octave_st directory of scripts (based on the
previous test/sup/octave scripts) as well as a test/sup/octave_mt
directory (based on the previous test/supmt/octave scripts). The
octave scripts are slightly different and not easily mergeable, and
thus for now I'll maintain them separately.
- Preserved the previous test/sup directory as test/sup/old/supst and
the previous test/supmt directory as test/sup/old/supmt.
Details:
- Return early from bli_thrinfo_sup_grow() if the thrinfo_t object
address is equal to either &BLIS_GEMM_SINGLE_THREADED or
&BLIS_PACKM_SINGLE_THREADED.
- Added preprocessor logic to bli_l3_sup_thread_decorator() in
bli_l3_sup_decor_single.c that (by default) disables code that
creates and frees the thrinfo_t tree and instead passes
&BLIS_GEMM_SINGLE_THREADED as the thrinfo_t pointer into the
sup implementation.
- The net effect of the above changes is that a small amount of
thrinfo_t overhead is avoided when running small/skinny dgemm
problems when BLIS is compiled with multithreading disabled.
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:
- Fixed an error that manifests only when using C++ (specifically,
modern versions of g++) to compile drivers in 'test' (and likely most
other application code that #includes blis.h. Thanks to Ajay Panyala
for reporting this issue (#374).
