* Fix heap corruption in mixed-domain/precision GEMM
- In the BLIS_DISABLE_SYSTEM single-threaded stub, bli_pthread_once()
ignored the once-control state and unconditionally called init() on
every invocation. bli_init_once() (invoked at the top of essentially
every public BLIS API entry via bli_rntm_init_from_global() etc.)
therefore re-ran bli_init_apis() -> bli_pba_init() -> bli_pool_init()
on every call, reallocating each pool's block_ptrs[] array and
orphaning any pblk_t already checked out.
* Update bli_pthread.c
* Potential fix for pull request finding
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
* reset gks_once_init in bli_gks_finalize and run init before marking once-control done
---------
Co-authored-by: harsdave <harsdave@amd.com>
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
Co-authored-by: KR, Chandrashekara <Chandrashekara.KR@amd.com>
- bli_nthreads_optimum's per-shape AOCL_DYNAMIC heuristic
picks substantially different thread counts across consecutive calls
(e.g. 16 for small fringe shapes, 96 for medium shapes), forcing the
underlying OpenMP team to repeatedly park and wake the same idle
threads.
- Bypass the heuristic when either operand is conjugated for the
dcomplex GEMM dispatch path (Zen6 / Zen5 / Zen4 and the pre-Zen4
fallback) so n_threads_ideal stays at the application-requested
value, which lets the OpenMP team be reused as-is across calls.
Non-conjugate ZGEMM continues to go through the existing AOCL_DYNAMIC
cascade unchanged.
Co-authored-by: harsdave <harsdave@amd.com>
Commit 8310b2d5d3 added new functions and global variables in
blis.h intended only for internal use. These were causing
missing symbol problems when blis.h is included in C
applications as they are not exported from the shared library.
Use BLIS_IS_BUILDING_LIBRARY and BLIS_CONFIGURETIME_CPUID
preprocessor definitions to only expose these when compiling BLIS
and not when using it.
AMD-Internal: [CPUPL-8091]
Implement zen6 cpuid and arch changes, and add zen6 as a
separate BLIS sub-configuration and code path within amdzen
configuration family. Currently all optimization choices are
copies of zen5 sub-configuration.
AMD-Internal: [CPUPL-7162]
Changes to simplify AMD CPUID functionality:
- Variable "features" is limited in size as each bit represents a
specific hardware function. Move detection of FP datapath
width to a separate variable. Also mask the FP datapath bits
explicitly for a more reliable test.
- Add detection of facility to downgrade FP512 datapath to FP256.
- bli_cpuid_is_avx512_fallback function does not exist, so remove header
definition.
AMD-Internal: [CPUPL-7303]
bli_arch_query_id() is used to select kernels in optimized BLAS APIs. Previous
implementation incurred the overhead of multiple function calls. This has
been reduced by:
- Changing the function to be defined in a header file so it can be inlined.
- Avoiding call to bli_arch_check_id_once that was a wrapper for a call to
bli_pthread_once. Instead bli_pthread_once is called directly.
- For builds with a single BLIS sub-configuration, correct arch_id is taken
directly from a header file in the corresponding config subdirectory,
avoiding the bli_pthread_once call and making the value explicit at
compile time, which may enable additional optimizations.
To enable these changes, the variables arch_id and model_id defined in
frame/base/bli_arch.c are no longer static, as they must be accessed in multiple
files (i.e. they are now global variables). Rename to g_arch_id and g_model_id
to distinguish from any locally defined arch_id or model_id variables.
- Added `#pragma omp barrier` just before threads start releasing their threadinfo / global
communicator.
- This ensures all threads reach this sync point, preventing interleaved cleanup.
Co-authored-by: harsdave <harsdave@amd.com>
* DTL Log update
Updates logs with nt and AOCL Dynamic selected nt for axpy, scal and dgemv
Modified bench_gemv.c to able to process modified dtl logs.
* Updated DTL log for copy routine with actual nt and dynamic nt
* Refactor OpenMP pragmas and clean up code
Removed unnecessary nested OpenMP pragma and cleaned up function end comment.
* Fixed DTL log for sequential build
* Added thread logging in bla_gemv_check for invalid inputs
---------
Co-authored-by: Smyth, Edward <Edward.Smyth@amd.com>
- AMD specific BLAS1 and BLAS2 franework: changes to make variants
more consistent with each other
- Initialize kernel pointers to NULL where not immediately set
- Fix code indentation and other other whitespace changes in DTL
code and addon/aocl_gemm/frame/s8s8s32/lpgemm_s8s8s32_sym_quant.c
- Fix typos in DTL comments
- Add missing newline at end of test/CMakeLists.txt
- Standardize on using arch_id variable name
AMD-Internal: [CPUPL-6579]
- Change begin_asm and end_asm comments and unused code in files
kernels/haswell/3/sup/s6x16/bli_gemmsup_rv_haswell_asm_sMx6.c
kernels/zen4/3/sup/bli_gemmsup_cd_zen4_asm_z12x4m.c
to avoid problems in clobber checking script.
- Add missing clobbers in files
kernels/zen4/1m/bli_packm_zen4_asm_d24xk.c
kernels/zen4/1m/bli_packm_zen4_asm_z12xk.c
kernels/zen4/3/sup/bli_gemmsup_cv_zen4_asm_z12x4m.c
- Add missing newline at end of files.
- Update some copyright years for recent changes.
- Standardize license text formatting.
AMD-Internal: [CPUPL-6579]
Change handling of AOCL_VERBOSE environment variable and DTL APIs
AOCL_DTL_Enable_Logs() and AOCL_DTL_Disable_Logs() to better handle
threading within the calling application or library. Previously
this was a global setting, which was not thread-safe if these APIs
were called by different application threads. Recent changes made
them thread-safe but resulted in initialization issues.
Details of changes in this commit:
- Move DTL initialization and finalization out of bli_init_apis()
and handle pthread_once protection separately within DTL code.
- Check AOCL_VERBOSE environment variable and update global ICV
gbIsLoggingEnabled. Each application thread then initializes
from this to a thread local variable tlIsLoggingEnabled.
- tlIsLoggingEnabled is then used by AOCL_DTL_Enable_Logs() and
AOCL_DTL_Disable_Logs() to enable each application thread to
control logging separately.
- DTL_Initialize() no longer required the desired tracing level
(AOCL_DTL_TRACE_LEVEL) to be passed as an argument, as this
is available from the blis.h header file.
AMD-Internal: [CPUPL-7010]
- Adjust the DCOPY aocl_dynamic threshold on Zen4 for optimal
fast-path selection.
- Extending the Zen5 dynamic-scheduling logic beyond the previous
8-thread limit.
- Update corresponding fast_path_thresh values in the frame such
that it matches the new dynamic logic.
- For Conjugate inputs, ZTRSM small code path is less accurate than native codepath.
- Redirected the conjugate inputs to native code path on ZEN4 if TRSM preinversion is disabled.
- Tuned AOCL_DYNAMIC to handle the new inputs redirected to ZTRSM native.
* Added DGEMV no transpose multithreaded Implementations
- Added new avx512 M and N kernels for DGEMV.
- Added multiple MT implementations for same kernels.
- Added AOCL_dynamic logic for L2 apis.
- Tuned AOCL_dynamic and code path selection for DGEMV on ZEN5.
- Added same kernels for SGEMV, but these kernels are not enabled yet.
- Added SGEMV reference kernel.
AMD-Internal: [SWLCSG-3408]
Co-authored-by: Varaganti, Kiran <Kiran.Varaganti@amd.com>
amdzen and x86_64 configuration family: On Intel processors supporting
AVX-512, the zen4 sub-configuration was dispatched by default, as even
though it is not optimized specifically for Intel processors, it includes
a range of additional optimizations than are present in the the older skx
sub-configuration. However, the zen4 data path is 256 bit, thus this
sub-configuration uses a mixture of AVX2 and AVX-512 kernels. Now that
zen5 sub-configuration is available, with more extensive use of AVX-512
kernels, switch to use this by default on relevant Intel processors.
intel64 configuration family: On AMD processors supporting AVX-512 or
AVX2, the generic sub-configuation was dispatched by default. Change to
dispatch skx or haswell sub-configuation, based on the available ISA
support.
AMD-Internal: [CPUPL-6743]
- Updated the thresholds to enter the AVX512 SUP codepath in
ZGEMM(on ZEN5). This caters to inputs that scale well with
multithreaded-execution(in the SUP path).
- Also updated the thresholds to decide ideal threads, based on
'm', 'n' and 'k' values. The thread-setting logic involves
determining the number of tiles for computation, and using them
to further tune for the optimal number of threads.
- This logic builds over the assumption that the current thread
factorization logic is optimal. Thus, an additional data analysis
was performed(on the existing ZEN4 and the new ZEN5 thresholds),
to also cover the corner cases, where this assumption doesn't hold
true.
- As part of the future work, we could reimplement the thread
factorization for GEMM, which would additionally require a new
set of threshold tuning for every datatype.
AMD-Internal: [CPUPL-7028]
Co-authored-by: Vignesh Balasubramanian <vignbala@amd.com>
Code cleanup: Removing some redundant if-else code in the CGEMM
aocl-dynamic logic. This should ensure that multiple branching is
avoided, while preserving existing heuristics.
AMD Internal: [CPUPL - 6579]
Co-authored-by: Rayan <rohrayan@amd.com>
- Updated the thresholds to enter the AVX512 Tiny and SUP codepaths
for ZGEMM(on ZEN4). This caters to inputs that perform well on
a single-threaded execution(in the Tiny-path), and inputs that
scale well with multithreaded-execution(in the SUP path).
- Also updated the thresholds to decide ideal threads, based on
'm', 'n' and 'k' values. The thread-setting logic involves
determining the number of tiles for computation, and using them
to further tune for the optimal number of threads.
AMD-Internal: [CPUPL-6378][CPUPL-6661]
Co-authored-by: Vignesh Balasubramanian <vignbala@amd.com>
- Added a set of thresholds(based on input dimensions) that
determine and set the ideal number of threads to be used
for CGEMM (on ZEN4 and ZEN5 architectures).
- The thread-setting logic is as follows :
- The underlying kernels(single-threaded) work on blocks
of MRxk of A, kxNR of B and MRxNR of C. Thus, it is
initially assumed that the optimal number of threads is
ceil(m/MR)*ceil(n/NR). This is the upper bound on the
actual number of threads that is ideal.
- The actual ideal thread count could be lesser than the
upper bound, based on the work that every thread receives.
This is mainly determined by the value of 'k'.
- If 'k' is small, the arithmetic intensity(AI) is low and
memory bandwidth becomes the limiting factor, thus favoring
smaller thread counts. In contrast, if 'k' is high, the AI
is high and the workload scales well with higher thread counts.
- So, we limit the number of threads when 'k' is small to avoid
bandwidth contention. Using fewer threads ensures each thread
gets more bandwidth, improving efficiency. In contrast, we allow
more threads when 'k' is large, as the computation becomes more
compute-bound and less limited by memory bandwidth, thereby benefitting
with a higher-thread count.
- The new logic will now set the upper bound for the optimal number of threads
(based on the number of tiles), and then further reduce it based on the values
of 'm', 'n' and 'k'. This comes under the 'AOCL_DYNAMIC' feature for CGEMM,
specifically for ZEN4 and ZEN5 architectures.
AMD-Internal: [CPUPL-6498]
Co-authored-by: Vignesh Balasubramanian <vignbala@amd.com>
Co-authored-by: Varaganti, Kiran <Kiran.Varaganti@amd.com>
- Implemented multithreading framework for the DGEMV API on Zen architectures. Architecture specific AOCL-dynamic logic determines the optimal number of threads for improved performance.
- The condition check for the value of beta is optimized by utilizing masked operations. The mask value is set based on value of beta, and the masked operations are applied when the vector y is loaded or scaled with beta.
AMD-Internal: [CPUPL-6746]
- Introducted new assembly kernel that copies data from source
to destination from the front and back of the vector at the
same time. This kernel provides better performance for larger
input sizes.
- Added a wrapper function responsible for selecting the kernel
used by DCOPYV API to handle the given input for zen5
architecture.
- Updated AOCL-dynamic threshold for DCOPYV API in zen4 and
zen5 architectures.
- New unit-tests were included in the grestsuite for the new
kernel.
AMD-Internal: [CPUPL-6650]
Change-Id: Ie2af88b8e97196b6aa02c089e59247742002f568
This reverts commit a028108cbb.
Reason for revert: With libgomp, scalability issues were observed with a
higher number of threads, leading to the use of fewer
threads. However, with different OpenMP libraries
like libomp, this scalability issue was not observed,
and using fewer threads resulted in performance loss.
The AOCL dynamic logic has been updated to select a
higher number of threads, considering the iomp OpenMP
library.
Change-Id: I2432b715eff01fc99b2c0f8b60bdecfaf5a6568f
- Added AOCL_DYNAMIC thresholds for DSCALV for Zen4 and Zen5
architectures, since earlier they were using the Zen thresholds.
- Also updated ST_THRESH for Zen4 and Zen5 to avoid the OpenMP overheads
incurred when the single-threaded path is optimally performant.
AMD-Internal: [CPUPL-5934]
Change-Id: I2d89cf5392516206fab83b672498fb8d98a5b033
Change usage of global_rntm and tl_rntm to elimate need
for mutex operations when accessing global_rntm. Usage of
these data structures is now as follows:
* global_rntm is set once during bli_init_apis and includes
all getenv calls to check BLIS threading and error printing
environment variables. global_rntm is then read-only.
* tl_rntm is intialized once from global_rntm on each
application thread. Any calls to BLIS set threading/ways
APIs will update tl_rntm for that application thread only
(Previously they updated global_rntm for all application threads).
* Re-initialize info_value in tl_rntm in every call to bli_init APIs.
* In bli_rntm_init_from_global() we initialize the local (per API
call) rntm as a copy of tl_rntm and then update threading values
in bli_thread_update_rntm_from_env() to reflect the current status
of OpenMP runtime ICVs.
AMD-Internal: [CPUPL-6168][SWLCSG-3143]
Change-Id: Ib9387ee2b51f507ed08cc38267057109acea14a6
bli_nthreads_optimum is exported and called directly by AOCL libFLAME,
however it was only defined if building a multithreaded BLIS library
with AOCL_DYNAMIC enabled. Change to always define this function. If
BLIS is serial or if AOCL_DYNAMIC is disabled, this function returns
without modifying the supplied rntm.
Change-Id: Ie65690e9e6ec2a8ea77b3778f96676a68e6260be
- Reverted the change done for tuning ddotv API. When number of threads
is mentioned using BLIS_IC_NT or BLIS_JC_NT, ... number of threads
are not calculated and as a result number of threads value is -1.
OpenMP threads are launched with -1 value. This results in crash.
This bug is fixed by correctly calculating number of threads.
AMD-Internal: [SWLCSG-3028][CPUPL-5689]
Change-Id: Ib9284dca02bdb115752926109beb28dc342e300a
Different Zen processors may have a 512-bit, 256-bit or 128-bit
FP/SIMD execution datapath width (FP512, FP256, FP128). Zen5 allows
a selection of FP512 or FP256 width in BIOS settings. Add cpuid
code to detect the width and store an indication of it in the
global variable bli_fp_datapath. This should be accessed internally
via the function bli_cpuid_query_fp_datapath(). This functionality
is currently only enabled on x86_64 platforms and only currently
reports a value for AMD CPUs.
Also add Zen3 as a fallback path for any unknown AMD processors if
AVX512 is not supported or has been disabled.
AMD-Internal: [CPUPL-4415]
Change-Id: Idf3fb5a697b43bc035ce110e86f60706dcc67f2a
- Delete unused cmake files.
- Add guards around call to bli_cpuid_is_avx2fma3_supported
in frame/3/bli_l3_sup.c, currently assumes that non-x86
platforms will not use bli_gemmtsup.
- Correct variable in frame/base/bli_arch.c on non-x86
builds.
- Add guards around omp pragma to avoid possible gcc
compiler warning in kernels/zen/2/bli_gemv_zen_int_4.c.
- Add missing registers in clobber list in
kernels/zen4/1/bli_dotv_zen_int_avx512.c.
- Add gtestsuite ERS_IIT tests for TRMV, copied from TRSV.
- Correct calls to cblas_{c,z}swap in gtestsuite.
- Correct test name in ddotxf gtestsuite program.
AMD-Internal: [CPUPL-4415]
Change-Id: I69ad56390017676cc609b4d3aba3244a2df6a6b5
- Standardize formatting (spacing etc).
- Add full copyright to cmake files (excluding .json)
- Correct copyright and disclaimer text for frame and
zen, skx and a couple of other kernels to cover all
contributors, as is commonly used in other files.
- Fixed some typos and missing lines in copyright
statements.
AMD-Internal: [CPUPL-4415]
Change-Id: Ib248bb6033c4d0b408773cf0e2a2cda6c2a74371
- Create seperate AOCL Dynamic values for
multithreading dcopy API for zen1, zen2 and zen3
AMD-Internal: [CPUPL-5238]
Change-Id: I42f56393716edeeace8bfe71d7adab0ba7325b47
- Removed some of the unrolling factors that affected the
performance of AVX2 DAXPYV kernel. In addition to improving
the current performance on sizes compatible to single-threaded
runs, this will now perform better for tiny sizes as well
since the overhead to reach the computation is less.
- Updated the vector partitioning logic, by using
bli_thread_range_sub( ... ), which ensures that there is no
false sharing among multiple threads.
- Updated the AOCL-DYNAMIC logic for the API, to include thresholds
or zen4 and zen5 micro-architectures.
AMD-Internal: [CPUPL-5514]
Change-Id: Iee9edddac685334213cd6694421ab3df3547e930
- Replaced "vmovupd" with "vmovups" for "bli_scopyv_zen4_asm_avx512"
kernel.
- Optimization of loop unrolling for "bli_dcopyv_zen4_asm_avx512"
and "bli_scopyv_zen4_asm_avx512" kernels.
- Replaced existing load balancing algorithm for dcopy API with
"bli_thread_range_sub" algorithm.
- Included AOCL-dynamic values for optimial number of threads
for zen5 architecture.
AMD-Internal: [CPUPL-5238]
Change-Id: Ic82bdfad9478c8f75dc5a3dcfed0df85fbcae957
- Replaced 'bli_zaxpyv_zen_int5' kernel with optimised
'bli_zaxpyv_zen_int_avx512' kernel for zen4 and
zen5 config.
- Implemented multithreading support and AOCL-dynamic
for ZAXPY API.
- Utilized 'bli_thread_range_sub' function to achieve
better work distribution and avoid false sharing.
AMD-Internal: [CPUPL-5250]
Change-Id: I46ad8f01f9d639e0baa78f4475d6e86458d8069b
* 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
* commit '81e10346':
Alloc at least 1 elem in pool_t block_ptrs. (#560)
Fix insufficient pool-growing logic in bli_pool.c. (#559)
Arm SVE C/ZGEMM Fix FMOV 0 Mistake
SH Kernel Unused Eigher
Arm SVE C/ZGEMM Support *beta==0
Arm SVE Config armsve Use ZGEMM/CGEMM
Arm SVE: Update Perf. Graph
Arm SVE CGEMM 2Vx10 Unindex Process Alpha=1.0
Arm SVE ZGEMM 2Vx10 Unindex Process Alpha=1.0
A64FX Config Use ZGEMM/CGEMM
Arm SVE Typo Fix ZGEMM/CGEMM C Prefetch Reg
Arm SVE Add SGEMM 2Vx10 Unindexed
Arm SVE ZGEMM Support Gather Load / Scatt. St.
Arm SVE Add ZGEMM 2Vx10 Unindexed
Arm SVE Add ZGEMM 2Vx7 Unindexed
Arm SVE Add ZGEMM 2Vx8 Unindexed
Update Travis CI badge
Armv8 Trash New Bulk Kernels
Enable testing 1m in `make check`.
Config ArmSVE Unregister 12xk. Move 12xk to Old
Revert __has_include(). Distinguish w/ BLIS_FAMILY_**
Register firestorm into arm64 Metaconfig
Armv8 DGEMMSUP Fix Edge 6x4 Switch Case Typo
Armv8 DGEMMSUP Fix 8x4m Store Inst. Typo
Add test for Apple M1 (firestorm)
Firestorm CPUID Dispatcher
Armv8 GEMMSUP Edge Cases Require Signed Ints
Make error checking level a thread-local variable.
Fix data race in testsuite.
Update .appveyor.yml
Firestorm Block Size Fixes
Armv8 Handle *beta == 0 for GEMMSUP ??r Case.
Move unused ARM SVE kernels to "old" directory.
Add an option to control whether or not to use @rpath.
Fix $ORIGIN usage on linux.
Arm micro-architecture dispatch (#344)
Use @path-based install name on MacOS and use relocatable RPATH entries for testsuite inaries.
Armv8 Handle *beta == 0 for GEMMSUP ?rc Case.
Armv8 Fix 6x8 Row-Maj Ukr
Apply patch from @xrq-phys.
Add explicit handling for beta == 0 in armsve sd and armv7a d gemm ukrs.
bli_error: more cleanup on the error strings array
Arm SVE Exclude SVE-Intrinsic Kernels for GCC 8-9
Arm SVE: Correct PACKM Ker Name: Intrinsic Kers
Fix config_name in bli_arch.c
Arm Whole GEMMSUP Call Route is Asm/Int Optimized
Arm: DGEMMSUP `Macro' Edge Cases Stop Calling Ref
Header Typo
Arm: DGEMMSUP ??r(rv) Invoke Edge Size
Arm: DGEMMSUP ?rc(rd) Invoke Edge Size
Arm: Implement GEMMSUP Fallback Method
Arm64 Fix: Support Alpha/Beta in GEMMSUP Intrin
Added Apple Firestorm (A14/M1) Subconfig
Arm64 8x4 Kernel Use Less Regs
Armv8-A Supplimentary GEMMSUP Sizes for RD
Armv8-A Fix GEMMSUP-RD Kernels on GNU Asm
Armv8-A Adjust Types for PACKM Kernels
Armv8-A GEMMSUP-RD 6x8m
Armv8-A GEMMSUP-RD 6x8n
Armv8-A s/d Packing Kernels Fix Typo
Armv8-A Introduced s/d Packing Kernels
Armv8-A DGEMMSUP 6x8m Kernel
Armv8-A DGEMMSUP Adjustments
Armv8-A Add More DGEMMSUP
Armv8-A Add GEMMSUP 4x8n Kernel
Armv8-A Add Part of GEMMSUP 8x4m Kernel
Armv8A DGEMM 4x4 Kernel WIP. Slow
Armv8-A Add 8x4 Kernel WIP
AMD-Internal: [CPUPL-2698]
Change-Id: I194ff69356740bb36ca189fd1bf9fef02eec3803
- Implemented bli_dnorm2fv_unb_var1_avx512( ... ) AVX512
computational kernel for DNRM2 API.
- Updated the header to include this kernel signature, as well
as the framework layer to use this function in case of ZEN4
and ZEN5 configurations.
- Updated the tipping points for ideal thread setting in DNRM2
for ZEN5 micro-architecture. These thresholds are specific
to the library's linkage to LLVM's OpenMP or GNU's OpenMp.
- Further abstracted the AOCL-DYNAMIC logic to separate functions
for ?NRM2 APIs that currently support it(namely, DNRM2 and ZNRM2).
- Further updated the ?NRM2 framework to accommodate the necessary
changes to invoke the newer AOCL-DYNAMIC functions and the AVX512
kernel, when needed.
- Added micro-kernel and memory tests for this kernel in GTestsuite,
to validate accuracy and out-of-bounds read and write.
AMD-Internal: [CPUPL-5265]
Change-Id: I4fc0d0f1e6906bf27d46562ca387c338cc4d2049
- Modifying threading framework for L1 APIs to update only number of threads from runtime env and avoid overhead of reading other ICVs.
- Removing bli_arch_set_id_once() from bli_arch_set_id_once() flow as bli_arch_check_id_once() calls it.
AMD-Internal: [CPUPL-4877]
Change-Id: I87b346825a96d74e746a41530b6d22ae162f19ba
Changes to how AOCL_ENABLE_INSTRUCTIONS handles requests
for different ISAs (i.e. BLIS sub-configurations):
- Add missing SSE and AVX options. These will all chose the
generic option in amdzen builds.
- For unsupported ISAs (e.g. AVX512 on Milan), select the
hardware's default sub-configuration instead of trying
to step down through alternative choices.
- For invalid options, or options not implemented in the BLIS
build (e.g. skx in amdzen build), select the hardware's
default sub-configuration instead of aborting.
Currently BLIS_ARCH_TYPE behaviour is not affected by these
changes.
AMD-Internal: [CPUPL-5078]
Change-Id: Idbd00d2806b1679889a9249878c51981c8d23b3f
- Updated nt_ideal to 12 for n_elem <= 2500000 and nt_ideal to 16 for
n_elem <= 4000000
AMD-Internal: [CPUPL-4408]
Change-Id: I97c143ab0d9b97e797358af93181c71d948757cc
- Fixed bug in DAXPYF MT kernel when incx != inca.
- Added AOCL Dynamic function for 1f kernels.
- Moved all DOTXF and AXPYF kernels into one file.
AMD-Internal: [CPUPL-4880]
Change-Id: I7d9f44625bc42fad4a9e5b218ecc382efdf22cbe
AOCL libFLAME optimizations directly call some internal
BLIS symbols. Export them to enable this to work with
the BLIS shared library.
AMD-Internal: [CPUPL-5044]
Change-Id: Icb62dcb51e12d72dde8434593ab17de3c227c93d
- Added AVX512 kernel for ZDOTV.
- Multithreaded both ZDOTC and ZDOTU with AOCL_DYNAMIC support.
AMD-Internal: [CPUPL-5011]
Change-Id: I56df9c07ab3b8df06267a99835b088dcada81bd8
Existing Design:
- GEMM AVX2 kernel performs computation and updates temporary C buffer
- Portion of temporary C buffer is copied to output C buffer
based on UPLO parameter
- For diagonal blocks, using GEMM kernels is not efficient
New Design: Implemented in current patch when UPLO='L'
- GEMMT kernel used for computation, temporary buffer is not required.
- Only required elements are computed using mask load store for all
fringe cases
- Exception: AVX2 code path is used when storage format is RRC, CRR, CRC
- AOCL-Dynamic is added based on dimension
- Check for AVX platform is added in SUP interface, It returns to
native implementation if hardware doesnot support AVX platform
- SUP ref_var2m is expanded for dcomplex datatype to avoid condition
check which exists for double datatype
AMD_Internal: [CPUPL-5006]
Change-Id: I3e21404b732b8f2df9cbdba394303752fdf36286
- Kernel dimensions are 4x4.
- Two kernels are implemented, Right Upper and
Right lower.
- In case of Left variants of TRSM, transpose is
induced so that Right variant kernels can be used.
- No packing is performed in these kernels.
- Changes are made in the threshold to pick ZTRSM small
code path.
- BLIS_INLINE is removed from signature of
"TRSMSMALL_KER_PROT".
- These kernels do not support "ENABLE_TRSM_PREINVERSION".
- Newly added kernels do not support conjugate
transpose.
- Added multithreading to ZTRSM small code path.
AMD-Internal: [CPUPL-4324]
Change-Id: I683b1d5239593e54f433e7f27497d72dfbd9141c
- Added DAXPYF and DDOTXF AVX512 kernels.
- Fuse factor for ddotxf kernel is 8.
- 2 DAXPYF kernels are added, with fuse
factor 8 and 32.
- Multithreading is also added to the DAXPYf
kernel with fuse factor 32.
- These kernels are internally used by TRSM.
- Added changes in TRSV to call these kernels
in ZEN4
AMD-Internal: [CPUPL-4880]
Change-Id: I12850de974b437bbca07677b68bc3d6a35858770
- Implemented AVX512 kernels for scopyv_, dcopyv_ and zcopyv_
using respective AVX512 intrinsics including masked
load and store operations.
- Implemented AVX512 kernels for scopy_, dcopy_ and
zcopy_ using assembly language to prevent loss of
performance during the translation of intrinsics.
- Updated the dcopy_blis_impl( ... ) and
zcopy_blis_impl( ... ) function to support
multithreaded calls to the respective computational
kernels, if and when the OpenMP support is enabled.
- Implemented OpenMP parallelization for dcopyv_ and
zcopyv_ APIs, while scopyv_ and ccopyv_ only support
single thread.
AMD-Internal: [CPUPL-4854]
Change-Id: I5fbd0bcca4e59001fbe2b1168b624d0c33242b3e
