the comment contains an incorrect link, which is trivially fixed here.
@fgvanzee I hope you don't mind that I committed directly to master but this cannot break anything.
Details:
- Fixed a bug in sdsdot_sub() that redundantly added the "alpha" scalar,
named 'sb'. This value was already being added by the underlying
sdsdot_() function. Thus, we no longer add 'sb' within sdsdot_sub().
Thanks to Simon Lukas Märtens for reporting this bug via #367.
- Fixed a second bug in order of typecasting intermediate products in
sdsdot_(). Previously, the "alpha" scalar was being added after the
"outer" typecast to float. However, the operation is supposed to first
add the dot product to the (promoted) scalar and THEN downcast the sum
to float. Thanks to Devin Matthews for catching this bug.
Details:
- Added BLIS_EXPORT_BLIS annotation to function prototypes for
bli_thrcomm_bcast()
bli_thrcomm_barrier()
bli_thread_range_sub()
so that these functions are exported to shared libraries by default.
This (hopefully) fixes issue #366. Thanks to Kyungmin Lee for
reporting this bug.
- CREDITS file update.
Updates and fixes to power9 subconfig.
Details:
- Register s,c,z reference gemm and trsm ukernels that assume elements
of B have been broadcast.
- Added prototypes for level-3 ukernels that assume elements of B have
been broadcast. Also added prototype for an spackm function that
employs a duplication/broadcast factor of 4.
- Register virtual gemmtrsm ukernels that work with broadcasting of B.
- Disable right-side hemm, symm, trmm, and trmm3 in bli_family_power9.h.
- Thanks to Nicholai Tukanov for providing these updates.
Details:
- Optimized daxpyf kernel with fuse_factor=5 and iter_unroll=2.
- Modified framework files of dgemv to remove dependency on cntx variable.
- Updated cntx_init file of zen2 to choose optimized kernels.
- Modified BLAS interface call for DGEMV to reduce framework overhread.
- Currently these changes are applicable for zen2 configuration.
They will be enabled for zen family processors in future.
- Changed naming convention for new BLAS macros to indicate their use.
- Added new optimized kernel for axpyf under zen2 folder.
- Implemented basic GEMV kernel without using axpyv or axpyf.
This kernel is chosen for small sizes.
Change-Id: I4278d37e494854879c71499b8b9da8c5dbe3bf5b
Signed-off-by: Meghana Vankadari <Meghana.Vankadari@amd.com>
AMD-Internal: [CPUPL-885]
Details
Added SUP support for cgemm in M direction
SUP kernels are 3x8m, 3x4m, 3x2m is implemeted
Sub kernels are implemented to support various dimenions
SUP CGEMM supports matrix C & A row/col major and Matrix B is row major matrix
Change-Id: Ia6854b929d3b5741a4900422d05df1257f5d014d
Description:
Pannel strides are updated using variables rather than constant values to
support selecive packing in sgemm sup kernels
Change-Id: Ic098eb70592d12d7d2174a1166aebf3bc749140c
Details:
-Kernel is called directly from API call to avoid framework
overhead in case of single and double precisions.
-Currently these changes are applicable only for zen2 configuration.
They will be enabled for zen family processors in future.
-These changes improve performance of BLAS and CBLAS interfaces of API.
They do not affect BLIS-specific APIs.
-setv simd kernel is added for single and double precision elements
Change-Id: I1b343aa232f2571717c2b01ada5914f869883e1a
Signed-off-by: Kiran ND <Kiran.Devrajegowda@amd.com>
AMD-Internal: [CPUPL-817]
Details:
Support for inputs with general strides is not yet implemented in sup. This check will redirect to default path.
Change-Id: I594672e56ffb60c8d89a634e27f30f2ac2a7e38f
Details:
-Kernel is called directly from API call to avoid framework
overhead in case of single and double precisions.
-Currently these changes are applicable only for zen2 configuration.
They will be enabled for zen family processors in future.
-These changes improve performance of BLAS and CBLAS interfaces of API.
They do not affect BLIS-specific APIs.
Change-Id: I1eb7ca470ced82c3cfa8b22f2b53000d42fef96c
Signed-off-by: Meghana Vankadari <Meghana.Vankadari@amd.com>
AMD-Internal: [CPUPL-847,CPUPL-816]
Details:
- Separate kernel for copyv function added to improve performance.
- Modified cntx_init file in zen and zen2 configuration
- Added test_copyv.c in test folder
- Modified test/Makefile to include test_copyv.c
Change-Id: I297f539f2ddd2d71997b127a71a460991cd07b41
Signed-off-by: Kiran N D <kiran.Devrajegowda@amd.com>
AMD-Internal: [CPUPL-818]
Details:
-Kernel is called directly from API call to avoid framework
overhead in case of single and double precisions.
-Currently these changes are applicable only for zen2 configuration.
They will be enabled for zen family processors in future.
-These changes improve performance of BLAS and CBLAS interfaces of API.
They do not affect BLIS-specific APIs.
Change-Id: Ib12f5a4f66a3227681fb3028207a08cb69cc2406
Signed-off-by: Meghana Vankadari <Meghana.Vankadari@amd.com>
AMD-Internal: [CPUPL-855]
Details:
-Kernel is called directly from API call to avoid framework
overhead in case of single and double precisions.
-Currently these changes are applicable only for zen2 configuration.
They will be enabled for zen family processors in future.
Change-Id: Ifa17dc28d3b38e1e16b28bb785d9fdf4a223d909
Signed-off-by: Meghana Vankadari <Meghana.Vankadari@amd.com>
AMD-Internal: [CPUPL-805]
Details:
- Tuned block sizes to get better performance for sgemm default path.
Change-Id: I892e8642fa2d03a07a6d53537131536e6b1b091e
Signed-off-by: Kiran N D <kiran.Devrajegowda@amd.com>
AMD-Internal: [CPUPL-832]
Details:
-Added SIMD kernels for SWAPV for both single and double precisions.
-Modified cntx_init file for zen and zen2 configurations to choose opt kernels for
SWAPV.
-Added test_swapv.c in test folder.
-Modified test/Makefile to include test_swapv.c
Change-Id: Ida786eec722e634aee0dacdd51c327823c80f01a
Signed-off-by: Meghana Vankadari <Meghana.Vankadari@amd.com>
AMD-Internal: [CPUPL-847]
Details:
-Calling the kernel directly from API call to avoid framework
overhead.
-Currently these changes are only applicable for zen2 configuration.
They will be enabled for zen family processors in future.
Change-Id: I0139e185178f726f5cd8cba0ff6a441a00d67868
Signed-off-by: Meghana Vankadari <Meghana.Vankadari@amd.com>
AMD-Internal: [CPUPL-805]
Details:
-A Macro 'FILE_IN_OUT' is defined to read matrix dimensions and strides from a csv file.
Format for input file if 'FILE_IN_OUT' is defined:
Each line defines a TRSM problem with the following parameters: m n cs_a cs_b
The operation implemented by default is AX=B where A is lower-triangular and matrices are in column-major order.
When macro is disabled, it reverts back to original implementation.
Usage: ./test_trsm_<mkl/blis/openblas>.x input.csv output.csv
-A macro 'READ_ALL_PARAMS_FROM_FILE' is defined to read all the parameters for TRSM from a csv file.
This macro can be defined only when 'FILE_IN_OUT' is already defined.
Format for the input file if 'READ_ALL_PARAMS_FROM_FILE' is defined:
Each line defines a TRSM problem with the following paramenters: sideA uploA transA diagA m n cs_a cs_b
By default, column-major order is chosen as storage scheme for matrices.
Usage: ./test_trsm_<mkl/blis/openblas>.x input.csv output.csv
Change-Id: I349bc69ca968911c16e04d1ce70974d01e65a2fb
Signed-off-by: Meghana Vankadari <Meghana.Vankadari@amd.com>
Details:
- In case of GEMM, whenever beta is zero, we need to perform C = alpha
*(A * B) instead of C = beta * C + alpha * (A * B)
Added conditions to check the value of beta at different levels inside
small_gemm kernels and decide whether to perform scaling C with beta or
not.
-Modified small_gemm kernels to use BLIS specific functions to retrieve
different fields of objects.
-Calling bli_gemm_check before entering bli_gemm_small to facilitate
early return in case of invalid inputs.
-For corner cases inside small_gemm kernels, a buffer called f_temp
is used to load and store data to and from registers.
populating the buffer with zeroes before use.
-In bli_gemm_front, datatypes of status and return value from
bli_gemm_small are not matching.
Corrected the datatype of the variable 'status' inside bli_gemm_front
to err_t.
Change-Id: I8b52ad55008f028d6c8b7e0d20f746a869d9daea
Signed-off-by: Meghana Vankadari <Meghana.Vankadari@amd.com>
AMD-Internal: [CPUPL-689,SWLCSG-104]
Details:
- Added a missing return statement to the body of an early case handling
branch in bli_thread_partition_2x2(). This bug only affected cases
where n_threads < 4, and even then, the code meant to handle cases
where n_threads >= 4 executes and does the right thing, albeit using
more CPU cycles than needed. Nonetheless, thanks to Kiran Varaganti
for reporting this bug via issue #377.
- Whitespace changes to bli_thread.c (spaces -> tabs).
Change-Id: I2182be0911f76861dd14bec9b6bacb6c20c2725d
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.
Change-Id: Ia1066752849f1dfc0cd98f8ac0302e2f7b0f8bf0
Details:
- Fixed a syntax bug in bli_l3_sup_decor_single.c as a result of
changing function interface for the thread entry point function
(of type l3supint_t).
- Unfortunately, fixing the interface was not enough, as it caused
a memory leak in the sba at bli_finalize() time. It turns out that,
due to the new multithreading-capable variant code useing thrinfo_t
objects--specifically, their calling of bli_thrinfo_grow()--we
have to pass in a real thrinfo_t object rather than the global
objects &BLIS_PACKM_SINGLE_THREADED or &BLIS_GEMM_SINGLE_THREADED.
Thus, I inserted the appropriate logic from the OpenMP and pthreads
versions so that single-threaded execution would work as intended
with the newly upgraded variants.
Change-Id: I2bfff849abf3fa30c73e0c5876128400854bbcb5
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.
AMD-Internal: [CPUPL-713]
Change-Id: I9536648e7befac4d2dc17805e44ef34470961662
Details:
-This commit addresses the performance optimization(single-thread and
multi-thread) for DTRSM on zen2.
-This new optimization employs different MC, KC & NC values for TRSM than
what is being used in other Level-3 routines like DGEMM.
-Changed TRSM framework code to choose these blocksizes for TRSM
on zen family configurations.
-Added a new field called "trsm_blkszs" to cntx structure in order to
store TRSM specific block sizes.
-Implemented routines to initialize, set and query the TRSM-specific
block sizes.
-Defined a new macro "AOCL_BLIS_ZEN" in configure script.
This macro is automatically defined for zen family architectures.
It enables us to choose different cache block sizes for TRSM instead of common level-3 block sizes.
Change-Id: Id8557b1c962a316b1edecca9cd582675eaf35fe6
Signed-off-by: Meghana Vankadari <meghana.vankadari@amd.com>
AMD-Internal: [CPUPL-656]
For the kernel of size 4x8, cs_b is used instead of cs_a to calculate address of diagonal elements of matrix A.
Correcting the mistake.
Change-Id: Ie74e0f6a397fcd32fefb5804cd00f1e90bfe5523
