x64: matmul: Weight decompression fix group blocking

build: bumped version to v3.9.2

build: bumped version to v3.9.1

doc: oneDNN v3.9 release notes

Co-authored-by: Romain Biessy <romain.biessy@codeplay.com>
Co-authored-by: Vadim Pirogov <vadim.o.pirogov@intel.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: YixinBao <yixin.bao@intel.com>
Co-authored-by: Primak, Tatyana <tatyana.primak@intel.com>
Co-authored-by: Chereshnev, Eugene <eugene.chereshnev@intel.com>
Co-authored-by: Lv, Tao A <tao.a.lv@intel.com>
Co-authored-by: Dmitry Zarukin <dmitry.zarukin@intel.com>

benchdnn: graph: setting_handler: check function return status

gpu: intel: ocl: rnn: fix LSTM regressions

build: bumped version to v3.8.1

meta: updated citation file

build: bumped version to v3.7.3

cpu: x64: conv: disable zp with large zp buffer on AMX