- Currently TRSM reference kernels are derived from GEMM blocksizes and GEMM_UKR.
- This does not allow the flexibility to use different GEMM_UKR for GEMM and TRSM if optimized TRSM_UKR are not available.
- Made changes so that ref TRSM kernels are derived from TRSM blocksizes.
- Changed ZEN4 and ZEN5 cntx to use AVX2 kernels for CTRSM.
AMD-Internal: [SWLCSG-3702]
- The existing row-preferred reference kernels for GEMM SUP path were
not taking into consideration the packing state of matrices A or B.
Thus, whenever either or both A and B matrices were packed the
kernel was unable to iterate appropriately through the matrices
thereby calculating incorrect values resulting in failures.
- Though, for generic configuration, the SUP path is disabled by default
the set of Pack and Compute Extension APIs use these kernels thus,
this issue resulted in their failures as well.
- With this patch, the loops being used in these kernels have been fixed
to iterate over steps of MR and NR while also accounting for the
fringe cases. Within the updated loops, temporary pointers used to
point to the correct block/panel of the matrices are incremented with
panel strides of respective matrices.
AMD-Internal: [CPUPL-5674]
Change-Id: Ic3939877c79ebb9ccf9e53b1d1672cea4b8c5959
SCALV is used directly by BLAS, CBLAS and BLIS scal{v} APIs but
also within many other APIs to handle special cases. In general
it is preferred to use SETV when alpha=0, but BLAS and CBLAS
continue to multiple all vector element by alpha. This has
different behaviour for propagating NaNs or Infs.
Changes in this commit:
- Standardize early returns from SCALV reference and optimized
kernels.
- User supplied N<0 is handled at the top level API layer. Use
negative values of N in kernel calls to signify that SETV
should _not_ be used when alpha=0. This should only be
required in SCALV.
- Include serial threshold in zdscal (as in dscal) to reduce
overhead for small problem sizes.
- Code tidying to make different variants more consistent.
- More standardization of tests in SCALV gtestsuite programs.
- Remove scalv_extreme_cases.cpp as it is now redundant.
AMD-Internal: [CPUPL-4415]
Change-Id: I42e98875ceaea224cc98d0cdfe0133c9abc3edae
* commit 'cfa3db3f':
Fixed bug in mixed-dt gemm introduced in e9da642.
Removed support for 3m, 4m induced methods.
Updated do_sde.sh to get SDE from GitHub.
Disable SDE testing of old AMD microarchitectures.
Fixed substitution bug in configure.
Allow use of 1m with mixing of row/col-pref ukrs.
AMD-Internal: [CPUPL-2698]
Change-Id: I961f0066243cf26aeb2e174e388b470133cc4a5f
Details:
- pack and compute extension APIs derive blocksizes(MR, NR...) from
SUP cntx.
- SUP blocksizes are not set for generic/skx configs. As a result pack
and compute APIs cause floating point exceptions.
- To fix these issues, we have enabled non-zero SUP blocksizes for
generic config and zen4 SUP blocksizes for skx config.
- However, these changes will not enable SUP path for skx/generic config
as thresholds are set to zero.
- To enable SUP path for skx config, more work is needed like non-zero
thresholds and modifications to build system.
Change-Id: I54483ab0c196845ca175b8cb8deeb9e9ac2a42b9
* commit 'b683d01b':
Use extra #undef when including ba/ex API headers.
Minor preprocessor/header cleanup.
Fixed typo in cpp guard in bli_util_ft.h.
Defined eqsc, eqv, eqm to test object equality.
Defined setijv, getijv to set/get vector elements.
Minor API breakage in bli_pack API.
Add err_t* "return" parameter to malloc functions.
Always stay initialized after BLAS compat calls.
Renamed membrk files/vars/functions to pba.
Switch allocator mutexes to static initialization.
AMD-Internal: [CPUPL-2698]
Change-Id: Ied2ca8619f144d4b8a7123ac45a1be0dda3875df
Details:
- Eliminated the need for override function in SUP for GEMMT/SYRK.
- New set of block sizes, kernels and kernel preferences
are added to cntx data structure for level-3 triangular routines.
- Added supporting functions to set and get the above parameters from cntx.
- Modified GEMMT/SYRK SUP code to use these new block sizes/kernels.
In case they are not set, use the default block sizes/kernels of
Level-3 SUP.
AMD-Internal: [CPUPL-3649]
Change-Id: Iee11bd4c4f1d8fbbb749c296258d1b8121c009a0
- When alpha is equal 1 in scal2v the computation can be reduced to
copyv. The condition check in else if condition has to be a check
for alpha equal to one and not zero.
- BLIS_NO_CONJ has been passed while invoking copy. In case of single
and double complex, the appropriate conjx needs to be passed with
copyv so that the vector can be conjugated before copying to the
destination.
AMD-Internal: [CPUPL-2985]
Change-Id: Ieb1ad111dff68098a08d870da7215bbd4ff5c9d0
Details:
- Now AOCL BLIS uses AX512 - 32x6 DGEMM kernel for native code path.
Thanks to Moore, Branden <Branden.Moore@amd.com> for suggesting and
implementing these optimizations.
- In the initial version of 32x6 DGEMM kernel, to broadcast elements of B packed
we perform load into xmm (2 elements), broadcast into zmm from xmmm and then to get the
next element, we do vpermilpd(xmm). This logic is replaced with direct broadcast from
memory, since the elements of Bpack are stored contiguously, the first broadcast fetches
the cacheline and then subsequent broadcasts happen faster. We use two registers for broadcast
and interleave broadcast operation with FMAs to hide any memory latencies.
- Native dTRSM uses 16x14 dgemm - therefore we need to override the default blkszs (MR,NR,..)
when executing trsm. we call bli_zen4_override_trsm_blkszs(cntx_local) on a local cntx_t object
for double data-type as well in the function bli_trsm_front(), bli_trsm_xx_ker_var2, xx = {ll,lu,rl,ru}.
Renamed "BLIS_GEMM_AVX2_UKR" to "BLIS_GEMM_FOR_TRSM_UKR" and in the bli_cntx_init_zen4() we replaced
dgemm kernel for TRSM with 16x14 dgemm kernel.
- New packm kernels - 16xk, 24xk and 32xk are added.
- New 32xk packm reference kernel is added in bli_packm_cxk_ref.c and it is
enabled for zen4 config (bli_dpackm_32xk_zen4_ref() )
- Copyright year updated for modified files.
- cleaned up code for "zen" config - removed unused packm kernels declaration in kernels/zen/bli_kernels.h
- [SWLCSG-1374], [CPUPL-2918]
Change-Id: I576282382504b72072a6db068eabd164c8943627
- Added configuration option for zen4 architecture
- Added auto-detection of zen4 architecture
- Added zen4 configuration for all checks related
to AMD specific optimizations
AMD-Internal: [CPUPL-1937]
Change-Id: I1a1a45de04653f725aa53c30dffb6c0f7cc6e39a
Details:
- Removed support for all induced methods except for 1m. This included
removing code related to 3mh, 3m1, 4mh, 4m1a, and 4m1b as well as any
code that existed only to support those implementations. These
implementations were rarely used and posed code maintenance challenges
for BLIS's maintainers going forward.
- Removed reference kernels for packm that pack 3m and 4m micropanels,
and removed 3m/4m-related code from bli_cntx_ref.c.
- Removed support for 3m/4m from the code in frame/ind, then reorganized
and streamlined the remaining code in that directory. The *ind(),
*nat(), and *1m() APIs were all removed. (These additional API layers
no longer made as much sense with only one induced method (1m) being
supported.) The bli_ind.c file (and header) were moved to frame/base
and bli_l3_ind.c (and header) and bli_l3_ind_tapi.h were moved to
frame/3.
- Removed 3m/4m support from the code in frame/1m/packm.
- Removed 3m/4m support from trmm/trsm macrokernels and simplified some
pointer arithmetic that was previously expressed in terms of the
bli_ptr_inc_by_frac() static inline function (whose definition was
also removed).
- Removed the following subdirectories of level-0 macro headers from
frame/include/level0: ri3, rih, ri, ro, rpi. The level-0 scalar macros
defined in these directories were used exclusively for 3m and 4m
method codes.
- Simplified bli_cntx_set_blkszs() and bli_cntx_set_ind_blkszs() in
light of 1m being the only induced method left within BLIS.
- Removed dt_on_output field within auxinfo_t and its associated
accessor functions.
- Re-indexed the 1e/1r pack schemas after removing those associated with
variants of the 3m and 4m methods. This leaves two bits unused within
the pack format portion of the schema bitfield. (See bli_type_defs.h
for more info.)
- Spun off the basic and expert interfaces to the object and typed APIs
into separate files: bli_l3_oapi.c and bli_l3_oapi_ex.c; bli_l3_tapi.c
and bli_l3_tapi_ex.c.
- Moved the level-3 operation-specific _check function calls from the
operations' _front() functions to the corresponding _ex() function of
the object API. (This change roughly maintains where the _check()
functions are called in the call stack but lays the groundwork for
future changes that may come to the level-3 object APIs.) Minor
modifications to bli_l3_check.c to allow the check() functions to be
called from the expert interface APIs.
- Removed support within the testsuite for testing the aforementioned
induced methods, and updated the standalone test drivers in the 'test'
directory so reflect the retirement of those induced methods.
- Modified the sandbox contract so that the user is obliged to define
bli_gemm_ex() instead of bli_gemmnat(). (This change was made in light
of the *nat() functions no longer existing.) Also updated the existing
'power10' and 'gemmlike' sandboxes to come into compliance with the
new sandbox rules.
- Updated BLISObjectAPI.md, BLISTypedAPI.md, Testsuite.md documentation
to reflect the retirement of 3m/4m, and also modified Sandboxes.md to
bring the document into alignment with new conventions.
- Updated various comments; removed segments of commented-out code.
Details:
- Fixed a bug that broke the use of 1m for dcomplex when the single-
precision real and double-precision real ukernels had opposing I/O
preferences (row-preferential sgemm ukernel + column-preferential
dgemm ukernel, or vice versa). The fix involved adjusting the API
to bli_cntx_set_ind_blkszs() so that the induced method context init
function (e.g., bli_cntx_init_<subconfig>_ind()) could call that
function for only one datatype at a time. This allowed the blocksize
scaling (which varies depending on whether we're doing 1m_r or 1m_c)
to happen on a per-datatype basis. This fixes issue #557. Thanks to
Devin Matthews and RuQing Xu for helping discover and report this bug.
- The aforementioned 1m fix required moving the 1m_r/1m_c logic from
bli_cntx_ref.c into a new function, bli_l3_set_schemas(), which is
called from each level-3 _front() function. The pack_t schemas in the
cntx_t were also removed entirely, along with the associated accessor
functions. This in turn required updating the trsm1m-related virtual
ukernels to read the pack schema for B from the auxinfo_t struct
rather than the context. This also required slight tweaks to
bli_gemm_md.c.
- Repositioned the logic for transposing the operation to accommodate
the microkernel IO preference. This mostly only affects gemm. Thanks
to Devin Matthews for his help with this.
- Updated dpackm pack ukernels in the 'armsve' kernel set to avoid
querying pack_t schemas from the context.
- Removed the num_t dt argument from the ind_cntx_init_ft type defined
in bli_gks.c. The context initialization functions for induced methods
were previously passed a dt argument, but I can no longer figure out
*why* they were passed this value. To reduce confusion, I've removed
the dt argument (including also from the function defintion +
prototype).
- Commented out setting of cntx_t schemas in bli_cntx_ind_stage.c. This
breaks high-leve implementations of 3m and 4m, but this is okay since
those implementations will be removed very soon.
- Removed some older blocks of preprocessor-disabled code.
- Comment update to test_libblis.c.
Details:
- Adding threshold function pointers to cntx gives flexibility to choose
different threshold functions for different configurations.
- In case of fat binary where configuration is decided at run-time,
adding threshold functions under a macro enables these functions for
all the configs under a family. This can be avoided by adding function
pointers to cntx which can be queried from cntx during run-time
based on the config chosen.
Change-Id: Iaf7e69e45ae5bb60e4d0f75c7542a91e1609773f
Merge conflicts araised has been fixed while downstreaming BLIS code from master to milan-3.1 branch
Implemented an automatic reduction in the number of threads when the user requests parallelism via a single number (ie: the automatic way) and (a) that number of threads is prime, and (b) that number exceeds a minimum threshold defined by the macro BLIS_NT_MAX_PRIME, which defaults to 11. If prime numbers are really desired, this feature may be suppressed by defining the macro BLIS_ENABLE_AUTO_PRIME_NUM_THREADS in the appropriate configuration family's bli_family_*.h. (Jeff Diamond)
Changed default value of BLIS_THREAD_RATIO_M from 2 to 1, which leads to slightly different automatic thread factorizations.
Enable the 1m method only if the real domain microkernel is not a reference kernel. BLIS now forgoes use of 1m if both the real and complex domain kernels are reference implementations.
Relocated the general stride handling for gemmsup. This fixed an issue whereby gemm would fail to trigger to conventional code path for cases that use general stride even after gemmsup rejected the problem. (RuQing Xu)
Fixed an incorrect function signature (and prototype) of bli_?gemmt(). (RuQing Xu)
Redefined BLIS_NUM_ARCHS to be part of the arch_t enum, which means it will be updated automatically when defining future subconfigs.
Minor code consolidation in all level-3 _front() functions.
Reorganized Windows cpp branch of bli_pthreads.c.
Implemented bli_pthread_self() and _equals(), but left them commented out (via cpp guards) due to issues with getting the Windows versions working. Thankfully, these functions aren't yet needed by BLIS.
Allow disabling of trsm diagonal pre-inversion at compile time via --disable-trsm-preinversion.
Fixed obscure testsuite bug for the gemmt test module that relates to its dependency on gemv.
AMD-internal-[CPUPL-1523]
Change-Id: I0d1df018e2df96a23dc4383d01d98b324d5ac5cd
Details:
- Renamed the files, variables, and functions relating to the packing
block allocator from its legacy name (membrk) to its current name
(pba). This more clearly contrasts the packing block allocator with
the small block allocator (sba).
- Fixed a typo in bli_pack_set_pack_b(), defined in bli_pack.c, that
caused the function to erroneously change the value of the pack_a
field of the global rntm_t instead of the pack_b field. (Apparently
nobody has used this API yet.)
- Comment updates.
1. CMake script changes for build with Clang compiler.
2. CMake script changes for build test and testsuite based on the lib type ST/MT
3. CMake script changes for testcpp and blastest
4. Added python scripts to support library build and testsuite build.
AMD Internal : [CPUPL-1422]
Change-Id: Ie34c3e60e9f8fbf7ea69b47fd1b50ee90099c898
Details:
- Expanded support for disabling trsm diagonal pre-inversion to other
microkernel types, including the reference microkernel as well as the
kernel implementations for 1m and the pre-broadcast B (bb) format used
by the power9 subconfig. This builds on the 'haswell' and 'penryn'
kernel support added in 7038bba. Thanks to Bhaskar Nallani for
reminding me, in #461 (post-closure), that 1m support was missing from
that commit.
- Removed cpp branch of ref_kernels/3/bli_trsm_ref.c that contained the
omp simd implementation after making a stripped-down copy in 'old'.
This code has been disabled for some time and it seemed better suited
to rot away out of sight rather than clutter up a file that is already
cluttered by the presence of lower and upper versions.
- Minor comment update to bli_ind_init().
Merged contributions from AMD's AOCL BLIS (#448).
Details:
- Added support for level-3 operation gemmt, which performs a gemm on
only the lower or upper triangle of a square matrix C. For now, only
the conventional/large code path will be supported (in vanilla BLIS).
This was accomplished by leveraging the existing variant logic for
herk. However, some of the infrastructure to support a gemmtsup is
included in this commit, including
- A bli_gemmtsup() front-end, similar to bli_gemmsup().
- A bli_gemmtsup_ref() reference handler function.
- A bli_gemmtsup_int() variant chooser function (with variant calls
commented out).
- Added support for inducing complex domain gemmt via the 1m method.
- Added gemmt APIs to the BLAS and CBLAS compatiblity layers.
- Added gemmt test module to testsuite.
- Added standalone gemmt test driver to 'test' directory.
- Documented gemmt APIs in BLISObjectAPI.md and BLISTypedAPI.md.
- Added a C++ template header (blis.hh) containing a BLAS-inspired
wrapper to a set of polymorphic CBLAS-like function wrappers defined
in another header (cblas.hh). These two headers are installed if
running the 'install' target with INSTALL_HH is set to 'yes'. (Also
added a set of unit tests that exercise blis.hh, although they are
disabled for now because they aren't compatible with out-of-tree
builds.) These files now live in the 'vendor' top-level directory.
- Various updates to 'zen' and 'zen2' subconfigurations, particularly
within the context initialization functions.
- Added s and d copyv, setv, and swapv kernels to kernels/zen/1, and
various minor updates to dotv and scalv kernels. Also added various
sup kernels contributed by AMD to kernels/zen/3. However, these
kernels are (for now) not yet used, in part because they caused
AppVeyor clang failures, and also because I have not found time to
review and vet them.
- Output the python found during configure into the definition of PYTHON
in build/config.mk (via build/config.mk.in).
- Added early-return checks (A, B, or C with zero dimension; alpha = 0)
to bli_gemm_front.c.
- Implemented explicit beta = 0 handling in for the sgemm ukernel in
bli_gemm_armv7a_int_d4x4.c, which was previously missing. This latent
bug surfaced because the gemmt module verifies its computation using
gemm with its beta parameter set to zero, which, on a cortexa15 system
caused the gemm kernel code to unconditionally multiply the
uninitialized C data by beta. The C matrix likely contained
non-numeric values such as NaN, which then would have resulted in a
false failure.
- Fixed a bug whereby the implementation for bli_herk_determine_kc(),
in bli_l3_blocksize.c, was inadvertantly being defined in terms of
helper functions meant for trmm. This bug was probably harmless since
the trmm code should have also done the right thing for herk.
- Used cpp macros to neutralize the various AOCL_DTL_TRACE_ macros in
kernels/zen/3/bli_gemm_small.c since those macros are not used in
vanilla BLIS.
- Added cpp guard to definition of bli_mem_clear() in bli_mem.h to
accommodate C++'s stricter type checking.
- Added cpp guard to test/*.c drivers that facilitate compilation on
Windows systems.
- Various whitespace changes.
Details:
- Amin api returns index of minimum absolute value in a vector.
- Added amin reference blis kernel.
- Added blas and cblas interface for amin.
AMD-Internal: [CPUPL-1155]
Change-Id: I89c1e37e86950a4582bba70a5d8fc70ac915bd3c
Details:
- In trying to clean up kappa_cast variables in the reference packm
kernels, which I initally believed to be redundant given the other
void* -> ctype* changes in 645d771, I accidentally ended up violating
restrict semantics for 1e/1r packing and possibly other packm kernels.
(Normally, my pre-commit testsuite run would have caught this, but I
was unknowingly using an edited input.operations file in which I'd
disabled most tests as part of unrelated work.) This commit reverts
the kappa_cast changes in 645d771.
Details:
- Changed all void* function arguments in reference packm kernels to
those of the native type (ctype*). These pointers no longer need to
be void* and are better represented by their native types anyway.
(See below for details.) Updated knl packm kernels accordingly.
- In the definition of the PACKM_KER_PROT prototype macro template in
frame/1m/bli_l1m_ker_prot.h, changed the pointer types for kappa, a,
and p from void* to ctype*. They were originally void* because these
function signatures had to share the same type so they could all be
stored in a single array of that shared type, from which they were
queried and called by packm_cxk(). This is no longer how the function
pointers are stored, and so it no longer makes sense to force the
caller of packm kernels to use void*, only so that the implementor
of the packm kernels can typecast back to the native datatype within
the kernel definition. This change has no effect internally within
BLIS because currently all packm kernels are called after querying
the function addresses from the context and then typecasting to the
appropriate function pointer type, which is based upon type-specific
function pointers like float* and double*.
- Removed a comment in frame/1m/bli_l1m_ft_ker.h that was outdated and
misleading due to changes to the handling of packm kernels since
moving them into the context.
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:
- 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:
- 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).
This library ported on Windows 10 using CMake scripts and Visual Studio 2019 with clang compiler
AMD internal:[CPUPL-657]
Change-Id: Ie701f52ebc0e0585201ba703b6284ac94fc0feb9
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:
- 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.
Change-Id: If9ec9a2383dfb02e1cfc74918f87a1fabddbd55b
* Fix vectorized version of bli_amaxv
To match Netlib, i?amax should return:
- the lowest index among equal values
- the first NaN if one is encountered
* Fix typos.
* And another one...
* Update ref. amaxv kernel too.
* Re-enabled optimized amaxv kernels.
Details:
- Re-enabled the optimized, intrinsics-based amaxv kernels in the 'zen'
kernel set for use in haswell, zen, zen2, knl, and skx subconfigs.
These two kernels (for s and d datatypes) were temporarily disabled in
e186d71 as part of issue #380. However, the key missing semantic
properties that prompted the disabling of these kernels--returning the
index of the *first* rather than of the last element with largest
absolute value, and returning the index of the first NaN if one is
encountered--were added as part of #382 thanks to Devin Matthews.
Thus, now that the kernels are working as expected once more, this
commit causes these kernels to once again be registered for the
affected subconfigs, which effectively reverts all code changes
included in e186d71.
- Whitespace/formatting updates to new macros in bli_amaxv_zen_int.c.
Co-authored-by: Field G. Van Zee <field@cs.utexas.edu>
Details:
- Fixed a copy-paste bug in the new bli_spackm_6xk_bb4_ref() that
manifested as failures in single-precision real level-3 operations.
Also replaced the duplication factor constants with a const-qualifed
varialbe, dfac, so that this won't happen again.
- Changed NC for single-precision real from 4080 to 8160 so that the
packed matrix B will have the same byte footprint in both single
and double real.
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:
- 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:
- Previously, some versions of gcc would complain that the same
pointer, one_r, is being passed in for both alpha and beta in the
fourth call to the real gemm ukernel in bli_gemmtrsm4m1_ref.c. This
is understandable since the compiler knows that the real gemm ukernel
qualifies all of its floating-point arguments (including alpha and
beta) with restrict. A small hack has been inserted into the file
that defines a new variable to store the value 1.0, which is now used
in lieu of one_r for beta in the fourth call to the real gemm ukernel,
which should pacify the compiler now. Thanks to Dave Love for
reporting this issue (#328) and for Devin Matthews for offering his
'restrict' expertise.
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:
- 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:
- Replaced direct usage of _Pragma( "omp simd" ) in reference kernels
with PRAGMA_SIMD, which is defined as a function of the compiler being
used in a new bli_pragma_macro_defs.h file. That definition is cleared
when BLIS detects that the -fopenmp-simd command line option is
unsupported. Thanks to Devin Matthews and Jeff Hammond for suggestions
that guided this commit.
- Updated configure and bli_config.h.in so that the appropriate anchor
is substituted in (when the corresponding pragma omp simd support is
present).
Details:
- Fixed a bug that mainfested anytime a configuration was used in which
optimized microkernels were registered and the trsm operation (or
kernel) was invoked. The bug resulted from the optimized microkernels'
register blocksizes conflicting with the hard-coded values--expressed
in the form of constant loop bounds--used in the new reference trsm
ukernels that were introduced in bdd46f9. The fix was easy: reverting
back to the implementation that uses variable-bound loops, which
amounted to changing an #if 0 to #if 1 (since I preserved the older
implementation in the file alongside the new code based on constant-
bound loops). It should be noted that this fix must be permanent,
since the trsm kernel code with constant-bound loops can never work
with gemm ukernels that use different register blocksizes.
Details:
- Rewrote level-1v, -1f, and -3 reference kernels in terms of simplified
indexing annotated by the #pragma omp simd directive, which a compiler
can use to vectorize certain constant-bounded loops. (The new kernels
actually use _Pragma("omp simd") since the kernels are defined via
templatizing macros.) Modest speedup was observed in most cases using
gcc 5.4.0, which may improve with newer versions. Thanks to Devin
Matthews for suggesting this via issue #286 and #259.
- Updated default blocksizes defined in ref_kernels/bli_cntx_ref.c to
be 4x16, 4x8, 4x8, and 4x4 for single, double, scomplex and dcomplex,
respectively, with a default row preference for the gemm ukernel. Also
updated axpyf, dotxf, and dotxaxpyf fusing factors to 8, 6, and 4,
respectively, for all datatypes.
- Modified configure to verify that -fopenmp-simd is a valid compiler
option (via a new detect/omp_simd/omp_simd_detect.c file).
- Added a new header in which prefetch macros are defined according to
which compiler is detected (via macros such as __GNUC__). These
prefetch macros are not yet employed anywhere, though.
- Updated the year in copyrights of template license headers in
build/templates and removed AMD as a default copyright holder.
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.
