Consider a 1-MByte cache with 4-word cachelines (a cacheline is also known as a cache block, each word is 4-Bytes). The address is 64-bits wide.

(c) What is the overhead and actual size of the direct-mapped cache? What is the overhead and actual size of the 4-way set-associative cache? Does the structure change the overhead in terms of number of memory bits? Consider 1-valid bit per-cacheline. (d) Write VHDL code 1-KByte cache (RAM)