edited by
406 views
0 votes
0 votes

First level data cache: Direct mapping , writeThrough/write allocate , 8kb data and lines of 8 bytes, miss rate= 17%

First level instructions cache: Direct mapping,, 4kb data and lines of 8 bytes, miss rate= 2%

Second level unified cache:  2-way associative, write-back/write-allocate, 2 mb data and lines of 32 bytes, miss rate= 12%, 50% of the lines has true dirty bit

Hit time l1= 1c , Hit time l2= 10c, access time to main memory= 100 c for the first word of the bus width and then each word of the bus takes one cycle. There is a 128-bit wide bus between the second cache level and main memory and 64 bits wide between l1 and l2

Questions:

1) What percentage of data memory accesses cause one access to main memory?

2) How many bits are needed to index each of the caches?

3) In what case is memory access given slower? How many cycles does it demand?

4) Assuming that 30% are data memory accesses, what is the percentage of accesses to data memory and instructions of the total number of accesses?

5)What is the average memory access time?

Thanks !!

 

edited by

Please log in or register to answer this question.

Related questions

2 votes
2 votes
2 answers
2
Veerendra V asked Nov 6, 2016
1,611 views
What is virtual indexed cache? How is it different from physical indexed cache? What is virtually indexed physical tagged cache? If possible point me to proper resources....
0 votes
0 votes
1 answer
3
Mrityudoot asked Jun 5, 2023
670 views
In a 2 level hierarchy, the cache has an access time of 15 ns and the main memory has an access time of 110 ns, the hit rate of the cache is 90%. If the block size of the...
2 votes
2 votes
0 answers
4
h4kr asked Dec 27, 2022
544 views
In $T_{Read Avg}$, shouldn’t it be $T_{Read Avg}$ = (10*0.9) + 0.1*(10+100), because it must be checking the cache in case of cache miss too, right?