I cannot find a to-the-point reference for my question. Am I correct in assuming that if you have an L1 and an L2 cache, typically the L2 cache linesize is larger?
For the following, let's assume a word size of 1 byte, an array 'a'of one byte words, an L2 cache with blocksize of 8 bytes, and an L1 cache of 4 bytes.
So, if you try to access an element a[2] in an array, given that both caches are cold, then a[0] - a[7] will be transferred to L2, and then a[0] - a[3] will be transferred to L1, and then a[2] can be sent to the register?