Eleni Vlachopoulou 863b73dfaf Adding AVX2 support for DZNRM2 ...

- For the cases where AVX2 is available, an optimized function is called,
based on Blue's algorithm. The fallback method based on sumsqv is used
otherwise.

- Scaling is used to avoid overflow and underflow.

- Works correctly for negative increments.

- Cleaned up some white space in the AVX2 implementation for DNRM2.

AMD-Internal: [CPUPL-2551]
Change-Id: I0875234ea735540307168fe7efc3f10fe6c40ffc

2022-09-30 07:51:04 -04:00

..

0

AOCL Windows: 3.1 BLIS changes

2021-03-08 19:04:17 +05:30

1

AOCL Windows: 3.1 BLIS changes

2021-03-08 19:04:17 +05:30

1d

AOCL Windows: 3.1 BLIS changes

2021-03-08 19:04:17 +05:30

1f

AOCL Windows: 3.1 BLIS changes

2021-03-08 19:04:17 +05:30

1m

Added functionality support for dzgemm

2022-05-17 18:01:55 +05:30

2

Code cleanup and warnings fixes

2022-08-29 08:22:30 -04:00

3

Fixed ASAN reported issues in bli_l3_packm.c

2022-09-23 16:41:00 +05:30

base

Update zen4 test in bli_cpuid.c

2022-09-01 05:12:24 -04:00

compat

Parallelized DDOT using OpenMP.

2022-09-30 07:36:17 -04:00

include

Vectorized and parallelized zdscal routine

2022-09-30 06:11:07 -04:00

ind

3m1 turning OFF

2021-05-26 10:06:54 +05:30

thread

Runtime Thread Control Feature Update

2022-08-19 05:43:01 -04:00

util

Adding AVX2 support for DZNRM2

2022-09-30 07:51:04 -04:00

CMakeLists.txt

AOCL Windows: 3.1 BLIS changes

2021-03-08 19:04:17 +05:30