(b) Consider a system with multiple level memory as in Table Q520. Table Q52 (i) (ii) Component Cache Hit Rate Cache Hit Time Off Chip Cache Hit Rate Off Chip Cache Hit Time Main Memory Hit Rate Main Memory Hit Time Main Memory Miss Penalty Value 90% 5 ns 96% 10 ns 99.8% 60 ns 10 000 ns Calculate the Global Miss Rate for this system. Assume that the size of the Off Chip Cache is increased in a way that the Global Miss Rate is reduced up to 20%. Calculate the new value for Global Miss Rate and Global Hit Rate.

(b) Consider a system with multiple level memory as in Table Q520. Table Q52 (i) (ii) Component Cache Hit Rate Cache Hit Time Off Chip Cache Hit Rate Off Chip Cache Hit Time Main Memory Hit Rate Main Memory Hit Time Main Memory Miss Penalty Value 90% 5 ns 96% 10 ns 99.8% 60 ns 10 000 ns Calculate the Global Miss Rate for this system. Assume that the size of the Off Chip Cache is increased in a way that the Global Miss Rate is reduced up to 20%. Calculate the new value for Global Miss Rate and Global Hit Rate.

Database System Concepts

7th Edition

ISBN:9780078022159

Author:Abraham Silberschatz Professor, Henry F. Korth, S. Sudarshan

Publisher:Abraham Silberschatz Professor, Henry F. Korth, S. Sudarshan

Chapter1: Introduction

Section: Chapter Questions

Problem 1PE

See similar textbooks

Similar questions

Consider a system with 2 level cache. Access times of Level 1 cache, Level 2 cache and main memory are 1 ns, 10 ns, and 500 ns, respectively. The hit rates of Level 1 and Level 2 caches are 0.8 and 0.9, respectively. What is the average access time of the system ignoring the search time within the cache?
Consider a memory system with a cache access time of 100ns and a memory access timeof 1200ns. If the effective access time is 10% greater than the cache access time, what is thehit ratio H?
Suppose a 1 MiB L1 cache has an access time of 1 clock cycle, the 16 MiB L2 has an access time of 4 clock cycles, and the 8 GiB DRAM has an average access time of 40 clock cycles. 80% of memory reads are satisfied by the L1 cache. Only 10% have to go to main memory. (a) What is the AMAT following a miss on L1? (b) What is the AMAT for memory overall?
Consider a two-level memory system (i.e., cache and main memory). Assume the cache access time is 3 clock cycles, and the hit rate is 95%. What should be the main memory access time (penalty) to ensure the memory access efficiency stays at 0.90?
Suppose you have a processor with a base CPI 1.0, assuming all references hit in theprimary cache (L1), and a clock rate of 3 GHz. Assume that you have two caches (L1and L2). L2 cache access time is 10 ns and main memory access time is 200 ns,including all the miss handling. Suppose the miss rate per instruction at the L1 cache is10%, L2 cache is 5%.a) What is the effective CPI?b) What will be the effective CPI if we add a new cache (L3) that has 50 nsaccess time and reduce the miss rate to main memory to 1%?
For a RAM size of 512 KB and a 2-way set - associative cache size of 8 kB with cache block size of 8B Considering that the actual cache size will be greater than 8 KB because of the overhead including tag bits and valid bit , what will be ratio ( in percentage ) of the given cache size to the actual cache size . Hint : First , consider calculating the actual cache size including the overhead. show all the steps
Please explain the question below Objective: Show the influence of the cache size on the miss rate Development Configure a system with the following architectural characteristics: Processors in SMP = 1 Cache coherence protocol = MESI Scheme for bus arbitration = Random Word wide (bits) = 16 Words by block = 16 (block size = 32 bytes) Blocks in main memory = 8192 (main memory size = 256 KB) Mapping = Fully-Associative Replacement policy = LRU Configure the blocks in cache using the following configurations: 2(cache size = 0,03 KB), 4,8, 16, 32, 64, 128, 256, and 512 (cache size = 16 KB). For each of the configurations, obtain the miss rate using the trace files: Hydro, Naasa7, Cexp, Comp, and Wave. Are there conflict misses in these experiments? Why? In these cases, it may be observed that for great cache sizes, the miss rate is stabilized. Why? We can also see great differences in miss rate for a concrete increment of cache size. What do these great differences indicate?
In paging (given diagram), for CPU request there are two access time one for accessing page table and one for physical memory access. How should we minimize this access time? Redraw the figure. Formulate the formula for Effective Access Time. 3. Calculate the Effective Access Time (EAT) by assuming the Hit ratio (?) 85% and 95%. Cache Access Time (ε) is 20 microsecond and Memory Access Time (Τ) is 100 microsecond
You are asked to perform capacity planning for a two-level memory system. The first level, M1 is a cache with three capacity choices of 64Kbytes, 128Kbytes, and 256Kbytes. The second level, M2, is a main memory with a 4Mbyte capacity. Let c1 and c2 be the costs per byte and t1 and t2 be the access times for M1 and M2, respectively. Assume c1 = 20 * c2 and t2 = 10 * t1. The cache hit ratios for the 3 capacities are assumed to be 0.7, 0.9 and 0.95, respectively. What is the average memory access time, AMAT, if t1 = 20ns in the three cache designs? (Note that t1 is the time from M1 to CPU and t2 is that from M2 to CPU. This means that t2 includes t1).
Assuming a computer memory system with following specifications: Address size = 32b Word size = 32b Block size = word size Cache size = 16KB a. Give the address format for Direct Mapping, 4-way Set Associative Mapping and Fully Associative Mapping. b. Analyse the size of Tag Versus Associativity. c. Total no. of comparators required for each mapping. d. Impact of multi word cache block on cache hit and miss ratio. e. Identify the optimal mapping function with respect to Tag size
Assuming a base CPI of 1.0 without any memory stalls, what is the total CPI for P1 with the addition of an L2 cache?
Compare and contrast cache and virtual memory and give an example scenario where each can be applied.