Disallow 64b BLAS integers + 32b BLIS integers.

Details:
- Print an error message from configure if the user attempts to
  explicitly configure BLIS for simultaneous use of 64-bit integers in
  the BLAS API with 32-bit integers in the BLIS API.
- Added cpp macro conditional to bli_type_defs.h to mandate that BLIS
  integers be 64 bits if the BLAS integers are 64 bits. This and the
  above item take care of issue #274. Thanks to Devin Matthews and
  Jeff Hammond for suggesting these safeguards.
- Slight reorganization and relabeling (for clarity) of BLAS/CBLAS
  sections and BLIS integer size line of the testsuite configuration
  output.
- Very minor edits to docs/MixedDatatypes.md.
This commit is contained in:
Field G. Van Zee
2018-10-26 17:07:15 -05:00
parent e90e7f309b
commit f19c33af4c
4 changed files with 33 additions and 18 deletions

View File

@@ -13,7 +13,7 @@
This document serves as a guide to users interested in taking advantage of
BLIS's support for performing the `gemm` operation on operands of differing
types.
datatypes (domain and/or precision).
## Categories of mixed datatypes
@@ -182,10 +182,9 @@ distribution.
## Known issues
While BLIS implements 128 mixed-datatype combinations of `gemm`, there may be
odd behavior in the current implementation that does not conform to the reader's
expectations. Below is a list of issues that BLIS developers are aware of in
the context of mixed-datatype `gemm`. If any of these issues poses a problem for
There may be odd behavior in the current implementation of mixed-datatype `gemm`
that does not conform to the reader's expectations. Below is a list of issues
that BLIS developers are aware of. If any of these issues poses a problem for
your application, please contact us by
[opening an issue](https://github.com/flame/blis/issues).