[CPU][s390x] Optimize inference perf and add oneDNN INT8 GEMM for s390x (#50219)
Signed-off-by: Rehan Khan <Rehan.Khan7@ibm.com> Co-authored-by: Li, Jiang <jiang1.li@intel.com>
This commit is contained in:
co-authored by
Li, Jiang <jiang1.li@intel.com>
parent
482cfc20f0
commit
88bc8fb56f
@@ -183,4 +183,15 @@
|
||||
|
||||
#endif // __powerpc__
|
||||
|
||||
// IBM Z (s390x) VXE
|
||||
#ifdef __s390x__
|
||||
// FP32Vec16::exp() in cpu_types_vxe.hpp delegates to FP32Vec8::exp(), which
|
||||
// implements a vectorised 5-term minimax polynomial using VXE intrinsics.
|
||||
#define DEFINE_FAST_EXP \
|
||||
auto fast_exp = [&](const vec_op::FP32Vec16& vec) \
|
||||
__attribute__((always_inline)) { return vec.exp(); }; \
|
||||
auto fast_exp_f16 = fast_exp;
|
||||
|
||||
#endif // __s390x__
|
||||
|
||||
#endif
|
||||
|
||||
Reference in New Issue
Block a user