No longer requires OpenMP to compile
Define the following in bli_config.h in order to enable multithreading:
BLIS_ENABLE_MULTITHREADING
BLIS_ENABLE_OPENMP
Also fixes a bug with bli_get_range_weighted
Details:
- Relaxed the constraint in bli_obj_attach_buffer_check(), which required
the buffer address being attached to be non-NULL. This is acceptable
because the user was already able to create and use objects with NULL
buffers (via bli_obj_create_without_buffer(), which initializes the
buffer to NULL).
- Inserted calls to newly defined function, bli_check_object_buffer(),
into nearly all operations' _check() or _int_check() functions. This
allows BLIS to abort peacefully if a computational routine is called
with an object containing a NULL buffer. By contrast, under such
conditions, BLAS would typically fail with a segmentation fault.
- Within operation front-ends, moved the calls to _check()/_int_check()
so that zero dimensions are checked first (and if found, execution
returns with trivial or no computation). This resolves issue #7. Thanks
to Jack Poulson for reporting this bug.
Details:
- Added a new field to blksz_t objects that allows one to attach a
sub-object. Doing this allows us to associate a register blocksize with
any given cache blocksize. That way, the register blocksize can be
queried wherever the cache blocksize would normally be accessible
(e.g. a blocked algorithm).
- Modified bli_gemm_cntl.c (and 4m/3m variants) so that the register
blocksizes are attached to the cache blocksizes after they are created.
Details:
- Changed level-2 _cntl.c files so that the blocksizes for gemv are
imported and used, rather than blocksizes being declared locally.
- Whitespace changes to gemv_cntl.c and gemm_cntl.c files (as well as
4m/3m variants).
- Removed test/old/test_blis2.c.
Removed barrier after unpackm in all level3 blocked variants
Now there is an implicit barrier inside unpackm that only occurs if C is packed (which is usually not the case)
Moved the enabling of the tree barriers into bli_config.h
Fed the default MR and NR for double precision into bli_get_range instead of the number 8
Fixed up some stuff in the thread info free functions
Disabled threading for TRSM so that it actually works when threading environment variables are set
Details:
- Added initialization statements to various macros used in level 1m and
1m-like operations. I wasn't able to reproduce the reported behavior,
so hopefully this takes care of it. Thanks to Jeff Hammond for the
report.
This also fixed a bug where barriers in the blocked variants were inserted after the inner packing routines,
but not the outer packing routines.
This allowed, for instance, the block of B to not be finished being packed before computation to occur.
Also enabled weighted partitioning for herk, trmm
Fixed bug where multiple threads would try to modify the same state in the internal level 3 functions
Correctly computed a_next and b_next for gemm, herk macrokernels
a_next and b_next point to the current micropanels in trmm
Details:
- Defined new INSERT_GENTFUNC macros so that the macro always takes
exactly the number of arguments needed for the particular operation or
variant being defined. Many operations were using INSERT_GENTFUNC
macros that expected one auxiliary argument even though none were
needed. Those instances have now been updated. Most of these instances
were in the level-0 and -1v operations, as well as some operations
defined in frame/util.
Details:
- Simplified some code that would have allowed the diagonal of a trmm
or trsm triangular matrix to intersect the short end of a micro-panel.
This is disallowed via higher-level constraints on cache blocksizes, so
this code was never needed and only served to obfuscate.
- Updated some comments in trmm, trsm macro-kernels.
Details:
- Completely reoganized norm operations:
- Renames:
- fnormsc, fnormv, fnormm -> normfsc, normfv, normfm (2-norm)
- absumv -> norm1v (vector 1-norm)
- New operations:
- norm1m (matrix 1-norm)
- normiv, normim (infinity-norm)
- amaxv (BLAS-like absolute maximum value index)
- asumv (BLAS-like absolute sum)
- Deprecated absumm, as it did not correspond to any actual norm.
(However, an inlined version now exists in the testsuite module for
randm.)
The environment variables all follow the format BLIS_X_NT,
where X is the index of the loop as described in our paper
Anatomy of High Performance Many-Threaded Matrix Multiplication.
These indices are IR, JR, IC, KC, and JC.
Also enabled parallelism for hemm and symm, but these are currently untested.
This change makes each operation have its own thread info type,
allowing more fine control of threading in operations that have different types of suboperations
Details:
- Minor update to bli_sumsqv_unb_var1() to bring it up-to-date with
LAPACK 3.5.0's zlassq.f, which, starting with 3.4.2, returns NaN when
the vector (or matrix) contains a NaN.
- Minor change to bli_abmaxv_unb_var1() to more closely mimic the
behavior of netlib BLAS's izamax(). There, a "less than or equal to"
operator is used in the search instead of "less than", which would
change the element index returned if there were multiple maximum values.
- Added macro function definitions for bli_isinf() and bli_isnan(), which
are currently implemented in terms of isinf() and isnan() from math.h.
Details:
- Fixed various bugs in packm_*_cxk(), the 4m/3m micro-kernels, and
elsewhere in the framework that were not yet set up to work properly
when BLIS_ENABLE_C99_COMPLEX is defined in bli_config.h
- Extensive changes to f2c-derived files in frame/compat/f2c to allow
C99 complex storage. Most of these changes center around accessing
real and imaginary components via bli_?real()/bli_?imag() accessor
macros, and setting of values via bli_?sets() assignment macros.
(Thanks to Vladimir Sukarev for pointing out that _ENABLE_C99_COMPLEX
was broken.)
In packm variant 1, the variable p_begin was incremented each iteration, causing a dependency.
This dependeny was removed, allowing each iteration to be executed in parallel.
Somewhere in bli_threading.c, I was allocating an array of pointers instead of an array of structs.
