- Implemented bli_zgemm_4x4_avx2_k1_nn( ... ) kernel to replace
bli_zgemm_4x6_avx2_k1_nn( ... ) kernel in the BLAS layer of
ZGEMM. The kernel is built for handling the GEMM computation
with inputs having k = 1, and the transpose values for A and
B as N.
- The kernel dimension has been changed from 4x6 to 4x4,
due to the following reasons :
- The 1xNR block of B in the n-loop can be reused over multiple
MRx1 blocks of A in the m-loop during computation. Similar
analogy exists for the fringe cases.
- Every 1xNR block of B was scaled with alpha and stored in
registers before traversing in the m-dimension. Similar change
was done for fringe cases in n-dimension.
- These registers should not be modified during compute, hence
the kernel dimension was changed from 4x6 to 4x4.
- The check for early exit(with regards to BLAS mandate) has been
removed, since it is already present in the BLAS layer.
- The check for parallel ZGEMM has been moved post the redirection to
this kernel, since the kernel is single-threaded.
- The bli_kernels_zen.h file was updated with the new kernel signature.
AMD-Internal: [CPUPL-3622]
Change-Id: Iaf03b00d5075dd74cc412290d77a401986ba0bea
- Added AVX512-based kernel for ZDSCAL. This will be dispatched from
the BLAS layer for machines that have AVX512 flags.
- In AVX2 kernel for ZDSCALV, vectorized fringe compute using SSE
instructions.
- Removed the negative incx handling checks from the blis_impli layer
of ZDSCAL as BLAS expects early return for incx <= 0.
AMD-Internal: [CPUPL-3648]
Change-Id: I820808e3158036502b78b703f5f7faa799e5f7d9
- ZSCALV kernel now uses fmaddsub intrinsics instead of mul
followed by addsub instrinsics.
- Removed the negative incx handling checks from the BLAS impli
layer as BLAS expects early return for incx <= 0.
- Moved all exceptions in the kernel to the BLAS impli layer.
AMD-Internal: [SWLCSG-2224]
Change-Id: I03b968d21ca5128cb78ddcef5acfd5e579b22674
- Existing logic is not picking the ideal number
of threads for some problem sizes.
- Problem size and their corresponding ideal number
of threads are retuned for daxpy in aocl dynamic.
AMD-Internal: [CPUPL-3484]
Change-Id: Ice874ceef0a1815383f74f1a4b9677677b276af7
- Number of threads and gflops are added
in the DTL logs for GEMMT, TRSM and NRM2
AMD-Internal: [CPUPL-2144]
Change-Id: If68887a5150bd0feda351180f379996497a1e678
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 n = 1 and A matrix is transposed ZGEMV row major variant is
invoked.
- When m = 1 and B matrix is not transposed ZGEMV row major variant
is invoked.
- This redirection happens before parallel ZGEMM check. This is done to
avoid the unneccesary condition check. Any parallelization check is
expected to happen in the invoked ZGEMV interface.
AMD-Internal: [CPUPL-2773]
Change-Id: I6b7b31db712edc682c089475d12e98730a960138
Remove unnecessary ifdef BLIS_ENABLE_CBLAS statement from cblas.h
and cblas_f77.h. These were erroneously added when fixing the
--disable-blas functionality but are not needed in the CBLAS
headers, as these files will not be generated when BLAS or CBLAS
is disabled.
This is a fix to commit 5bd2a777ba
AMD-Internal: [CPUPL-3541]
Change-Id: If38bd795d31098a7023d575672b0a913338c0d2d
Prevented calling avx2 based bli_zgemm_ref_k1_nn code on
non-supported systems.
Changed the name of the function bli_zgemm_ref_k1_nn to bli_zgemm_4x6_avx2_k1_nn().
Changed the name of the function bli_dgemm_ref_k1_nn to bli_dgemm_8x6_avx2_k1_nn().
Thanks to Kiran Varaganti <Kiran.Varaganti@amd.com>
for identifying and helping to fix the issue.
AMD-Internal: [CPUPL-3352]
Change-Id: I02530ab197ed84c96cbad4f7dd56eedca0109c35
- Missing break statement will result in unexpected control flow.
This function will not launch the threads for the API in question
according to the AOCL dynamic logic without the break statement.
AMD-Internal: [CPUPL-3436]
Change-Id: Ic47d773169c09e84086a27b50cd59dba33529698
- In the bli_x86_asm_macros.h file, the set of vinsertf?x? and
vextractf?x? instructions are facing macro expansion errors due to
ambiguous macro redirection. The lower-case macro definitions of
these instructions are not properly redirected to their corresponding
upper-case macro definitions.
- This error occurs due to ambiguity in the upper-case macro name.
At the place of lower-case macro definition, the redirection is to
macros of the form VINSERTF?x? and VEXTRACTF?x?, while at the place
of upper-case macro definition, they are of the form VINSERTF?X? and
VEXTRACTF?X?. This causes a mismatch of the upper-case macro due to
different case sensitive 'x' being used.
- This patch corrects this issue, by changing the lower-case 'x' to
upper-case, among the upper case macros at the place of redirection.
This provides uniformity and facilitates the expected macro-expansion.
AMD-Internal: [CPUPL-3276]
Change-Id: Id1f45f8e4bb083cd4b87632b713ff6baba616ff2
- When the number of threads launched is not equal to the
number of threads requested the garbage value in the created
buffer will not be overwritten by valid values.
- To handle the above scenario, the created temporary buffer is
initialized with zeroes.
AMD-Internal: [CPUPL-3268]
Change-Id: I439a1da18eb1b380491fea14f42b0ede05ccf5a9
- Partial completion of compute was happening since BLIS was unable
to launch the required number of threads. This was because rntm
was returning a thread count greater than the maximum number of
threads that can be launched in the subsequent parallel region.
- Added 'omp_get_num_threads' inside the parallel regions to get the
actual number of threads spawned. The work distribution happens
based on the actual number of threads launched in that region.
AMD-Internal: [CPUPL-3268]
Change-Id: I086ad4b9b644f966b7bab439e43222396f0c2bf0
Some text files were missing a newline at the end of the file.
One has been added.
Also correct file format of windows/tests/inputs.yaml, which
was missed in commit 0f0277e104
AMD-Internal: [CPUPL-2870]
Change-Id: Icb83a4a27033dc0ff325cb84a1cf399e953ec549
- Added Smart Threading logic for AVX-512 based SGEMM SUP.
- Calculating ic and jc for optimal work distribution to the allocated
threads based on logic similar to Zen3.
- Zen4 Architecture specific Native-to-SUP check has been added to
redirect few Native inputs to the SUP path based on the fact that in a
multi-threaded environment some Native cases perfom better as SUP.
- For the same, the SUP thresholds, namely, BLIS_MT and BLIS_NT have
been increased from 512 and 200 to 682 and 512, respectively.
- Further optimizations to the work distribution logic will be added
subsequently.
AMD-Internal: [CPUPL-3248]
Change-Id: Ibccbbefef251010ec94bd37ffc86c35b7866a5ca
Details:
- Added Doxyfile, a configuration file in docs directory for generating Doxygen document from source files.
- Currently only CBLAS interface of (Batched gemm and gemmt)extension APIs are included.
- Support for BLAS interface is yet to be added.
- To generate Doxygen based document for extension API, use given command.
$ doxygen docs/Doxyfile
AMD-Internal: [CPUPL-3188]
Change-Id: I76e70b08f0114a528e86514bcb01d666acc591e8
Incorporate a means of detecting submodels of a microarchitecture,
so that different optimizations e.g. block sizes or kernel choices
can be used. The details are as follows:
- Different models are currently only enabled for zen3 and zen4
architectures (for server parts).
- There is a single enumeration (model_t) for all models for all
architectures, but function bli_check_valid_model_id() should
check the provided model_id against the suitable range within
the enumeration for the provided arch_id.
- To enable the model_id to be used within the cntx setup functions,
checking of a user specified value of BLIS_ARCH_TYPE against
the enabled configurations is delayed to a separate function,
bli_arch_check_id().
- Default selection based on hardware can be overridden using the
BLIS_MODEL_TYPE environment variable. Valid values are:
Genoa, Bergamo, Genoa-X, Milan, Milan-X
Values are case-insensitive and -X can also be specified as _X or X
- Specifying an incorrect value for BLIS_MODEL_TYPE is not an error,
but will result in the default option for that architecture being
selected. This is different to specifying an incorrect value of
BLIS_ARCH_TYPE, which is an error.
- The environment variable BLIS_MODEL_TYPE can be renamed using
the --rename-blis-model-type argument to configure (or cmake
equivalent), in a similar way to renaming BLIS_ARCH_TYPE with
--rename-blis-arch-type.
- Configure option --disable-blis-arch-type will disable both
BLIS_ARCH_TYPE and BLIS_MODEL_TYPE environment variables.
- Added code in bli_cpuid.c to detect L1, L2 and L3 cache sizes,
currently only for AMD cpus. Functions are provided to query
these from other parts of the code, namely:
uint32_t bli_cpuid_query_{l1d,l1i,l2,l3}_cache_size()
AMD-Internal: [CPUPL-3033]
Change-Id: I37a3741abfd59a95e0e905d926c6ede9a0143702
Details:
- Overriding of blocksizes with avx-2 specific ones(6x8) is done
for gemmt/syrk because near-to-square shaped kernel performs
better than skewed/rectangular shaped kernel.
- Overriding is done for S,D and Z datatypes.
AMD-Internal: [CPUPL-3060]
Change-Id: I304ff4264ff735b7c31f7b803b046e1c49c9ad53
Thanks to Moore, Branden <Branden.Moore@amd.com> for identifying the
race condition and suggesting the changes to fix the same
Existing Design:
- AOCL progress callback pointer is a global pointer which is shared
across all threads
Existing Design challenges:
- The callback function cannot safely disable the progress mechanism,
as another thread may have already checked to see if the function
pointer is set, and then re-reads the pointer upon invocation of
the callback. If one thread sets the callback to NULL in this time,
then the resulting thread will attempt to call the null pointer as a
function pointer, leading to a segfault.
New Design :
- Each thread maintains a local copy of progress pointer
AMD-Internal: [SWLCSG-1971]
Change-Id: I282989805a4a2a8a759a7373b645f3569bf42ed4
Corrections for spelling and other mistakes in code comments
and doc files.
AMD-Internal: [CPUPL-2870]
Change-Id: Ifbb5df7df2d6312fe73e06ee6d41c00b16c593ce
Correct argument alpha in call to ZDSCAL kernel function in serial
code path. This resolves numerous instances of incorrect results
in ACML LAPACK test programs when BLIS_ARCH_TYPE=generic.
AMD-Internal: [CPUPL-3227]
Change-Id: Ibf5ee79392e80c2d93a0d336a7b0e2568e149f94
- In level-1 kernels, with multi-threading enabled, only the partial
job was getting executed.
- The bug was in bli_thread_vector_partition and occurred only
when minimum work for a thread >= 1 i.e., when the number of threads
launched is less than number of elements and the number of elements
is not a multiple of the number of threads launched.
AMD-Internal: [CPUPL-3231]
Change-Id: Ie20abb93468282cd6ac2372267714fb80c26d7cc
- Added AVX512 function's to the BLAS layer of daxpy, dscal and
ddot.
- Added BLAS exceptions for incx <= 0 to DSCALV
- Added BLIS_KERNELS_ZEN4 macro check to guard AVX512 kernels
as they will not be available in other contexts.
AMD-Internal: [CPUPL-2766][CPUPL-2765][CPUPL-2793][CPUPL-2800]
Change-Id: I68860c2ff6b65624907cc1b590173f0e909bd271
- In gemmt and normf, #ifdef BLIS_KERNELS_* is added
to make sure only compiled kernels are used.
- In bal_copy and bla_swap, missing '\' is added.
AMD-Internal: [CPUPL-2870]
Change-Id: I83452dff761f60db6957f557321ce210ab72c037
Details:
- Added a new function for choosing between SUP and
native implementation for a given size.
- This function pointer is stored in cntx for zen4 config.
- Divided total combinations of sizes into 3 categories:
- one dimension is small
- Two dimensions are small
- All dimensions are small
- Added different threshold conditions for each of the
categories.
AMD-Internal: [CPUPL-2755]
Change-Id: Iae4bf96bb7c9bf9f68fd909fb757d7fe13bc6caf
- Set the variables to zero to avoid the compiler warning
(-Wmaybe-uninitialized) in bli_dgemm_ref_k1.c,
bli_gemm_small.c, bli_trsm_small.c, bli_zgemm_ref_k1.c and
bli_trsm_small_AVX512.c
- Changed the datatype from dim_t to siz_t for i,k,j
in bli_hemv_unf_var1_amd.c and bli_hemv_unf_var3_amd.c to
avoid the compiler warning (-Waggressive-loop-optimizations)
AMD-Internal: [CPUPL-2870]
Change-Id: Ib2bc050fa47cb8a280d719283ab4539c70e19d03
Threading related changes
--------------------------
- Created function bli_nthreads_l1 that dispatches the AOCL dynamic
logic for a L1 function based on the kernel ID and input datatypes.
- bli_nthreads_l1 gets the number of threads to be launched from the
rntm variable.
- Added aocl_'ker?'_dynamic function for DAXPYV, DSCALV, ZDSCALV and
DDOTV. This function contains the AOCL dynamic logic for the
respective kernels.
- Added handling for cases when number of elements (n) is less than
number of threads spawned (nt) in AOCL dynamic.
- Added function bli_thread_vector_partition that calculates the
amount of work the calling thread is supposed to perform on a
vector.
Interface changes
-----------------
- In BLIS impli layer of DSCALV, ZDSCALV and AXPYV, added logic to pick
kernel based on architecture ID and removed AVX2 flag check.
- Modified function signature of ZDSCALV. Alpha is passed as dcomplex
and only the real part of the alpha passed is used inside the kernel.
The change was done to facilitate kernel dispatch based on arch ID.
- Added n <= 0, BLAS exception in BLAS layer of DAXPYV and DDOTV.
Without this multithreaded code might crash because of minimum work
calculation.
Misc
-----
- Removed unused variables from ZSCAL2V and AXPYV kernels.
AMD-Internal: [CPUPL-3095]
Change-Id: I4fc7ef53d21f2d86846e86d88ed853deb8fe59e9
- Added AVX512 based double and float AXPYV which will be used in
Zen4 context.
- Added n <= 0 check and alpha == 0 check to the BLAS layer of
SAXPY.
- Modified BLAS framework of float AXPYV to remove flag check and
pick kernels based on architecture ID.
- AVX512 kernel is disabled for other Zen configurations using
BLIS_KERNELS_ZEN4 macro.
AMD-Internal: [CPUPL-2793]
Change-Id: Ie6a0976c2cfcf81ae5125f5f9aad14477d4ebbd1
- Following sequence is followed for getting number of threads
for given input.
- Divides total range of input into 3 category(m < n, m > n, m = n)
- For each range it is further divided into 4 sub category.(K <= 32,
K <= 64, K <=128, K > 128)
- As per the input range, number of threads is being decided.
AMD-Internal: [CPUPL-2966]
Change-Id: I0b04e9de1615e87acb189b228544afac74664f02
- 8x8 kernels are used for DTRSM SMALL
- Matrix A(a10) is packed for GEMM operations.
- Packed martix A will be re-used in all the col-block
along N-dimension.
- Diagonal elements of A matrix are packed(a11) for
TRSM operations.
- Implemented fringe cases with below block sizes
8x8, 8x4, 8x3, 8x2, 8x1
4x8, 4x4, 4x3, 4x2, 4x1
3x8, 3x4, 3x3, 3x2, 3x1
2x8, 2x4, 2x3, 2x2, 2x1
1x8, 1x4, 1x3, 1x2, 1x1
AMD-Internal: [CPUPL-2745]
Change-Id: I5bb57501f6d3783eb654e375d63901467dd14734
- Added AVX512 based double and float DOTV which will be used in
Zen4 context.
- Added n <= 0 check to the BLAS layer of SDOTV.
- Modified BLAS framework of float DOTV to remove flag check and
pick kernels based on architecture ID.
- AVX512 kernel is disabled for other Zen configurations using
BLIS_KERNELS_ZEN4 macro.
AMD-Internal: [CPUPL-2800]
Change-Id: I550fbcbb17d6d887b9ecbea23237dc806b208702
- Added AVX512 based double and float SCALV which will be used in
Zen4 context.
- Added incx <= 0 check and alpha == 1 check to the BLAS layer of
SSCAL.
- Modified BLAS framework of float SCAL to remove flag check and
pick kernels based on architecture ID.
- AVX512 kernel is disabled for other Zen configurations using
BLIS_KERNELS_ZEN4 macro.
AMD-Internal: [CPUPL-2766],[CPUPL-2765]
Change-Id: I4cdd93c9adbfbf8f7632730b8606ddcf70edd1dc
- Reverted the SUP blocksizes and kernels to use AVX2 SUP kernels for
SGEMM. This can be updated once GEMMT specific optimization are added
for AVX-512.
- Updated 'bli_zen4_override_gemm_blkszs()' in zen4 context to override
blocksize and kernels for SGEMM SUP to enable AVX-512 kernels for
SGEMM operation.
AMD-Internal: [CPUPL-3060]
Change-Id: Ic9b3037363b6e5b59e5035c81651c97ce95d6d9a
Where a processor has not been targeted for optimization, the slow
generic code path may be selected by default. Another code path
could perform much better, even if not specifically optimized for
this processor.
Changes to enable this:
- Always call bli_cpuid_query_id() to get actual hardware info, even
if the user is overriding the choice at build time or by setting
BLIS_ARCH_TYPE.
- Use bli_cpuid_query_id() to gather availability of AVX2 and AVX512
instructions.
- Include AVX-512 fallback test to select zen4 code path on future
AMD processors (that don't yet have a specific codepath).
- Also use AVX-512 and AVX2 tests on Intel processors to select
zen4 or zen3 code paths over the generic code path. If both zen
and skx/haswell code paths are enabled, the zen code path will be
given preference as zen paths have additional optimizations that
should, in general, benefit Intel processors too.
AMD-Internal: [CPUPL-3031]
Change-Id: Ib7d0ebdb02fec872f9443a1d20070026f2020516
Modify code to correct some warning messages from GCC 12.2 or
AOCC 4.0:
- Increase size of nbuf in blastest/f2c/endfile.c
- Remove unused variables in kernels/zen/1/bli_scal2v_zen_int.c
and kernels/zen/1/bli_axpyv_zen_int10.c
- Remove extraneous parentheses in frame/compat/bla_trsm_amd.c
and kernels/zen4/3/bli_zgemm_zen4_asm_12x4.c
- Add __attribute__ ((unused)) to several variables in
frame/1m/packm/bli_packm_struc_cxk.c and
frame/1m/packm/bli_packm_struc_cxk_md.c
AMD-Internal: [CPUPL-2870]
Change-Id: I595e46f0a3d737beb393c3ab531717565220b10d
- Implemented 12x4m column preferential SUP kernels(main and fringe
cases). The main kernel dimension is 12x4, and the associated fringe
kernel dimensions are : 12x3m, 12x2m, 12x1m
8x4, 8x3, 8x2, 8x1
4x4, 4x3, 4x2, 4x1
2x4, 2x3, 2x2, 2x1.
- Included in-register transposition support for C, thus extending
the storage scheme supports to CCC, CCR, RCC and RCR inside the
milli-kernel.
- Integrated conditional packing of A onto the SUP front end for
dcomplex datatype. This redirects RRC and CRC storage schemes
onto the preceding set of SUP kernels through storage scheme
transformation(RCC and CCC respectively).
- Updated the zen4 context file with the new set of SUP kernels, to
get enabled appropriately. Furthermore, the context file was updated
with the AVX-2 dotxv signatures for dcomplex datatype. This redirects
the fringe cases of type 1x? to the pre-existing AVX-2 GEMV routines.
- Added C prefetching onto L2-cache, and an unroll factor of 4 for the
k loop in all the kernels.
- Work in progress to include conjugate support and input spectrum
extension for the AVX-512 SUP kernels. The current thresholds in zen4
context is the same as that of the zen3 thresholds for ZGEMM SUP.
AMD-Internal: [CPUPL-3122]
Change-Id: If40bc4409c6eb188765329508cf1f24c0eb12d1e
Fixes for a couple of issues:
- Modify alpha argument in kernel call in zscal_blis_impl to
avoid compiler warning message about discarding 'const'
qualifier from pointer target type.
- When BLIS_ARCH_TYPE=generic, call to bli_cntx_get_l1v_ker_dt
in ref_kernels/1/bli_scalv_ref.c for ZSCAL was causing a
segmentation fault. This was because the cntx was NULL on
entry to this function. Correct by getting zscal_blis_impl
to pass the cntx it has initialized for non-Zen codepaths.
This changes has been copied to idamax_blis_impl for
consistency.
AMD-Internal: [CPUPL-2773]
Change-Id: Ib02e4c1a2a7bf30c208732241d4959f7a2696179
- Fixed segmentation fault that was seen on non zen and non avx2
machines.
- cntx object was not passed to the invoked kernel causing a seg
fault.
AMD-Internal: [CPUPL-3167]
Change-Id: I2640d3f905e78398935cf6ed667b04a6418baa5d
BLAS1 and BLAS2 routines may not immediately call bli_init_auto, as
the full cntx and other global data structures may not be required
for all code paths. This may cause a problem if the user sets
BLIS_ARCH_TYPE, as it needs to check the requested value against the
available options configured in cntx. Solution: add a separate
pthread_once call to run bli_gks_init().
AMD-Internal: [CPUPL-3031]
Change-Id: Icd73a8dd161b34b23cc336623d675248f28ed23f
Improvements to BLIS cpuid functionality:
- Tidy names of avx support test functions, especially rename
bli_cpuid_is_avx_supported() to bli_cpuid_is_avx2fma3_supported()
to more accurately describe what it tests.
- Fix bug in frame/base/bli_check.c related to changes in commit
6861fcae91
AMD-Internal: [CPUPL-3031]
Change-Id: Iacd8fb0ffbd45288e536fc6314660709055ea2d5
Details:
- Added checks in top-level BLAS layer for alpha = zero. Scale C with
beta or set C with 0 appropriately if true and return. This ensures
that input matrices are not referenced, and thus that any Inf or NaN
values in them are not propagated to output matrix.
- Scalm internally handles the case where both alpha and beta are zero
by calling setm to populate the output matrix with zeroes.
AMD-Internal: [CPUPL-3134]
Change-Id: I14f14419049e7fcc55bf7fd30ddbd3d5a12c4427
- Added in-register transpose support for c matrix to
support row stored C matrix for dgemm sup.
- Support is added for all edge case kernels.
- FMA are made independent of each other, for faster
computation while storing data back to C matrix.
AMD-Internal: [CPUPL-2966]
Change-Id: I1d13af99a17ee66adbf5f537a4664ade489a7cad
- Main kernel is of size 24x8 and the associated fringe kernels
added are
- 24x7m, 24x6m, 24x5m, 24x4m, 24x3m, 24x2m, 24x1m
- 24x8, 24x7, 24x6, 24x5, 24x4, 24x3, 24x2, 24x1
- 16x8, 16x7, 16x6, 16x5, 16x4, 16x3, 16x2, 16x1
- 8x8, 8x7, 8x6, 8x5, 8x4, 8x3, 8x2, 8x1
- For fringe kernels, 24x? kernel handles 16 < m_remainder < 24
16x? kernel handles 8 < m_remainder <= 16
8x? kernel handles 0 < m_remainder <= 8
- Added a function 'bli_zen4_override_gemm_blkszs' to override
blocksizes and kernels to be used for SUP for supported storage
schemes.
- Updated the zen4 config to enable these kernels in zen4 path.
- Thresholds are yet to be derived.
- Updated CMakeLists.txt with DGEMM SUP kernels for windows build.
Kernel-specific details:
- K-loop is unrolled by 8 times to facilitate prefetch of B.
- For every load of one column of A, the corresponding column in
next panel of A is prefetched with T1 hint.
- One column of C is prefetched with T0 hint per iteration of LOOP2.
- TAIL_NITER is derived to be 3.
- For every unroll of k-loop, one row of B is prefetched with T0 hint.
- C-prefetching for row-storage is yet to be added.
- B-prefetching for col-storage is yet to be added.
- Support for C transpose is yet to added.
AMD-Internal: [CPUPL-2755], [CPUPL-2409]
Change-Id: Ie240c893469032dc2271cbfe00cceccfe6c4ea48
Added a check in scalm framework for alpha=0.
Set the output matrix to zero when alpha=0.
This ensures that any Inf or NaN values in the matrix are not
propagated to the output matrix.
AMD-Internal: [CPUPL-3053]
Change-Id: I62b9b5405be220eb4df97aadda14701abcccb475
Details:
- To be BLAS compliant, if increment is zero then iterate through the first element n times.
- For n<=0, the correct result (0) is returned so we remove this extra check. This is checked on BLIS-typed interface level.
AMD-Internal: [SWLCSG-1900]
Change-Id: I098bb9560a790050018bc8d8c63b06bfbcc1aebd
- Enabled DTRSM small mt for sizes where performance is better
than small or native.
- Threshold Tuning for small path is updated.
- Function signature for bli_trsm_small_mt has been made similar
to bli_trsm_small so that one function pointer can be used for
all functions.
- Early return condition in DTRSM small for sizes > 1000 has been
removed so that the sizes for which small path to take can be
decided on bla layer instead of inside kernel.
AMD-Internal: [CPUPL-2735]
Change-Id: Ieea31343dc660517acc18c92713381a8b84d3a2f
Add test in top-level GEMM BLAS layer for alpha = zero. Scale C
appropriately if true and return. This ensures that A and B are not
referenced, and thus that any Inf or NaN values in A or B are not
propagated to C. This was tested in some lower level code paths,
but not consistently.
Solution throughout GEMM codebase assumes scalm handles scale value
(beta from GEMM) equal to 0 without propagating inf/NaNs in C matrix.
Also call AOCL_DTL exits and bli_finalize_auto() in a more consistent
way.
AMD-Internal: [CPUPL-3053]
Change-Id: I4009f311951eb1ce9416cf846e9fa93b7c9219cc
- Moved *_blis_impl function declaration outside the BLIS_ENABLE_BLAS
guard.
- Changed Makefile to continue to compile bla_ files to get
*_blis_impl interfaces.
- Modify CBLAS headers, bli_macro_defs.h and bli_util_api_wrap.{c,h}
to add BLIS_ENABLE_CBLAS guards.
- Comment out BLIS_ENABLE_BLAS guards in various headers and utility
functions.
- Define BLIS Fortran-style functions lsame_blis_impl and
xerbla_blis_impl. New macros PASTE_LSAME and PASTE_XERBLA are
used in bla_*_check headers and some other places to select
whether to call lsame and xerbla, or the _blis_impl versions.
- Defined various other missing _blis_impl functions.
- In bli_util_api_wrap.c, only define any functions if
BLIS_ENABLE_BLAS is defined, and only define the subroutine
versions of functions like dot, nrm2, etc if BLIS_ENABLE_CBLAS
is defined.
- BLAS layer is needed if CBLAS layer is enabled. Changed header
files build/bli_config.h.in and bli_blas.h, and configure
program to help ensure consistency in generated blis.h header
and configure output.
Undefining BLIS_ENABLE_BLAS_DEFS appears to be broken in UTA BLIS
too, thus BLIS_ENABLE_BLAS_DEFS is currently permanently defined.
AMD-Internal: [CPUPL-3015]
Change-Id: I7c0fe07db85781db46f2c690e174451860b37635
