mirror of
https://github.com/amd/blis.git
synced 2026-05-11 17:50:00 +00:00
Optimized AXPBYV Kernel using AVX2 Intrinsics
Details: - Intrinsic implementation of axpbyv for AVX2 - Bench written for axpbyv - Added definitions in zen contexts AMD-Internal: [CPUPL-1963] Change-Id: I9bc21a6170f5c944eb6e9e9f0e994b9992f8b539
This commit is contained in:
committed by
Dipal M Zambare
parent
d687bd36ea
commit
86690f9fd3
@@ -57,6 +57,16 @@ AXPBYV_KER_PROT( dcomplex, z, axpbyv_zen_int )
|
||||
AXPBYV_KER_PROT( float, s, axpbyv_zen_int10 )
|
||||
AXPBYV_KER_PROT( double, d, axpbyv_zen_int10 )
|
||||
|
||||
// axpbyv (intrinsics)
|
||||
AXPBYV_KER_PROT( float, s, axpbyv_zen_int )
|
||||
AXPBYV_KER_PROT( double, d, axpbyv_zen_int )
|
||||
AXPBYV_KER_PROT( scomplex, c, axpbyv_zen_int )
|
||||
AXPBYV_KER_PROT( dcomplex, z, axpbyv_zen_int )
|
||||
|
||||
// axpbyv (intrinsics, unrolled x10)
|
||||
AXPBYV_KER_PROT( float, s, axpbyv_zen_int10 )
|
||||
AXPBYV_KER_PROT( double, d, axpbyv_zen_int10 )
|
||||
|
||||
// axpyv (intrinsics)
|
||||
AXPYV_KER_PROT( float, s, axpyv_zen_int )
|
||||
AXPYV_KER_PROT( double, d, axpyv_zen_int )
|
||||
|
||||
Reference in New Issue
Block a user