Some thing about Memory Benchmark
https://akkadia.org/drepper/cpumemory.pdf
benchmark: memmove vs memcpy
https://github.com/UK-MAC/WMTools/blob/master/tests/memtest.c
memcpy
https://stackoverflow.com/questions/2963898/faster-alternative-to-memcpy
something about optimize
https://www.embedded.com/optimizing-memcpy-improves-speed/
https://skywind3000.com/blog/archives/1587/
https://stackoverflow.com/questions/22793669/poor-memcpy-performance-on-linux
avx implements in folly
https://github.com/facebook/folly/blob/main/folly/memcpy.S
benchmark: sse vs std::memcpy
https://gist.github.com/stdpain/212709433e26d08598e0be8f15c6d678
benchmark report
https://squadrick.dev/journal/going-faster-than-memcpy.html
fetch page problem
https://stackoverflow.com/questions/47231791/hint-to-compiler-that-it-can-use-aligned-memcpy