Optimize `merge` algorithm for data sizes equal or greater then 4M items with SLM cache usage #11006

Job	Run time
codespell	16s
CPU,bknd=dpcpp,cmplr=icpx,ubuntu-latest,std=с++17,cfg=release	12m 5s
FPGA_EMU,bknd=dpcpp,cmplr=icpx,ubuntu-latest,std=с++17,cfg=release	12m 58s
HOST,bknd=tbb,cmplr=icpx,ubuntu-latest,std=с++17,cfg=release	11m 43s
HOST,bknd=omp,cmplr=icpx,ubuntu-latest,std=с++17,cfg=release	9m 45s
clang-format	10s
HOST,bknd=omp,cmplr=g++,ubuntu-latest,std=с++17,cfg=release	5m 57s
documentation	21s
HOST,bknd=tbb,cmplr=g++,ubuntu-latest,std=с++17,cfg=release	8m 59s
HOST,bknd=omp,cmplr=clang++,macos-latest,std=c++17,cfg=release	5m 39s
HOST,bknd=tbb,cmplr=g++,ubuntu-latest,std=с++17,cfg=release	8m 42s
HOST,bknd=tbb,cmplr=icx-cl,windows-latest,std=c++17,cfg=release	17m 46s
HOST,bknd=tbb,cmplr=clang++,ubuntu-latest,std=с++17,cfg=release	11m 8s
HOST,bknd=tbb,cmplr=cl,windows-latest,std=c++17,cfg=release	15m 33s
HOST,bknd=omp,cmplr=clang++,ubuntu-latest,std=с++17,cfg=release	8m 22s
CPU,bknd=dpcpp,cmplr=icx,windows-latest,std=c++17,cfg=release	12m 8s
HOST,bknd=tbb,cmplr=clang++,ubuntu-latest,std=с++17,cfg=release	11m 1s
HOST,bknd=tbb,cmplr=icpx,ubuntu-latest,std=с++17,cfg=release	11m 51s
HOST,bknd=serial,cmplr=g++,ubuntu-latest,std=с++17,cfg=release	4m 58s
CPU,bknd=dpcpp,cmplr=icpx,ubuntu-latest,std=с++20,cfg=release	10m 54s
HOST,bknd=tbb,cmplr=icpx,ubuntu-latest,std=с++20,cfg=release	11m 13s
HOST,bknd=omp,cmplr=icpx,ubuntu-latest,std=с++20,cfg=release	10m 58s
	3h 22m 27s

Provide feedback