Implement alternative `-O0` workaround for reduce-then-scan with compiler optimization detection #708

Job	Run time
clang-format	19s
HOST,bknd=omp,cmplr=clang++,macos-latest,std=c++17,cfg=release	5m 38s
HOST,bknd=tbb,cmplr=icx-cl,windows-latest,std=c++17,cfg=release	19m 4s
CPU,bknd=dpcpp,cmplr=icpx,ubuntu-latest,std=с++17,cfg=release	15m 27s
HOST,bknd=tbb,cmplr=cl,windows-latest,std=c++17,cfg=release	16m 57s
FPGA_EMU,bknd=dpcpp,cmplr=icpx,ubuntu-latest,std=с++17,cfg=release	24m 16s
CPU,bknd=dpcpp,cmplr=icx,windows-latest,std=c++17,cfg=release	12m 13s
HOST,bknd=tbb,cmplr=icpx,ubuntu-latest,std=с++17,cfg=release	12m 19s
HOST,bknd=omp,cmplr=icpx,ubuntu-latest,std=с++17,cfg=release	10m 15s
HOST,bknd=omp,cmplr=g++,ubuntu-latest,std=с++17,cfg=release	6m 38s
HOST,bknd=tbb,cmplr=g++,ubuntu-latest,std=с++17,cfg=release	10m 9s
HOST,bknd=tbb,cmplr=g++,ubuntu-latest,std=с++17,cfg=release	9m 57s
HOST,bknd=tbb,cmplr=clang++,ubuntu-latest,std=с++17,cfg=release	11m 38s
HOST,bknd=omp,cmplr=clang++,ubuntu-latest,std=с++17,cfg=release	8m 33s
HOST,bknd=tbb,cmplr=clang++,ubuntu-latest,std=с++17,cfg=release	11m 23s
HOST,bknd=tbb,cmplr=icpx,ubuntu-latest,std=с++17,cfg=release	12m 20s
HOST,bknd=serial,cmplr=g++,ubuntu-latest,std=с++17,cfg=release	5m 20s
CPU,bknd=dpcpp,cmplr=icpx,ubuntu-latest,std=с++20,cfg=release	27m 19s
HOST,bknd=tbb,cmplr=icpx,ubuntu-latest,std=с++20,cfg=release	18m 2s
HOST,bknd=omp,cmplr=icpx,ubuntu-latest,std=с++20,cfg=release	19m 21s
	4h 17m 8s

Provide feedback