Suppose our cache memory has parameters b = 4, l = 8, a = 1 ns, and μ = 16 ns. Assume that when necessary we replace the block in cache that was least-recently used, and that we set naccess=256 in the program fragment above. Consider the following table of estimated times per access in nanoseconds and show how each entry is derived. m = 16 m = 32 m = 64 m=128 S 1 2 4 8 16 1.125 1.125 1.125 1.125 1.063 1.250 1.250 3.000 5.000 1.250 9.000 1.250 17.000 1.125 1.250 3.000 5.000 9.000 17.000 17.000

Suppose our cache memory has parameters b = 4, l = 8, a = 1 ns, and μ = 16 ns. Assume that when necessary we replace the block in cache that was least-recently used, and that we set naccess=256 in the program fragment above. Consider the following table of estimated times per access in nanoseconds and show how each entry is derived. m = 16 m = 32 m = 64 m=128 S 1 2 4 8 16 1.125 1.125 1.125 1.125 1.063 1.250 1.250 3.000 5.000 1.250 9.000 1.250 17.000 1.125 1.250 3.000 5.000 9.000 17.000 17.000

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

Now, we consider a 16-byte, four-way, fully-associative cache. Since the capacity of the cache is 16 bytes, the array "a" in our example (does/does not) fit inside the cache. We can deduce that the block size for this cache is ( ？ ) bytes per block. So the block index size b=2 bits. For a memory trace record such as: L 1fff000116,2 the 2-bit block offset is (0b01/0b10/0b11/0b00). The tag bits are all the rest of the bits not part of the block offset.
Consider a processor that uses a 48-bit virtual memory address. The main memory installed onthe system is 4GB. Page size is set to be 32KB. Determine the following:I. Address space of virtual memory and physical memory. II. Total Number of virtual pages and the total physical pagesIII. How many bits are necessary to store (i) Page Table entry and (ii) TLB entry, consideringthe TLB entry stores valid, reference and dirty bits.IV. What is the size of the page table? And how many pages of memory is needed to storethe entire Page table? What fraction of physical memory is needed to store the entirepage table?
A computer uses virtual memory, and a new solid-state drive (SSD) as space for paging. Refer to the last ppt file. In the case presented there, the hard disk drive (HDD) required 25 ms to read in a page, and a rate of 1 page fault per 1000 references introduced a 250 slowdown. If the SSD offers a time of only 80 µs, what is the slowdown in performance caused by 1 pf per 1000 references (you are not concerned with dirty vs. clean pages). What is the maximum rate of page faults you can accept if you want no more than a 5% slowdown in execution using virtual memory? Know your metric prefixes and symbols for time: s for seconds, ms for milliseconds, µs for microseconds, ns for nanoseconds.
A common unit of measure for failure rates of electronic components is the Failure unIT (FIT), expressed as a rate of failures per billion device hours. Another well known but less used measure is mean time between failures (MTBF), which is the av- erage time of operation of a particular component until it fails. Consider a 1 MB memory of a 16-bit microprocessor with 256K X 1 L `AMs. Calculate its MTBF as- suming 2000 FITS for each DRAM.
The overhead required to read an entry in a page table (including the time to access TIB) is 60 nanoseconds. To reduce this overhead, the computer has a TIB that can hold 16 entries and be accessed in 10 nanoseconds.a) Let B = TLB lookup time, T - memory cycle time, and p = hit ratio. Finda formula that expresses the effective access time.b) What hit ratio is needed to reduce the effective access time to 70 nanoseconds?
Consider a fully-associative cache of size 4. Each slot in the cache can have just one item (i.e. the line size is 1 item). The cache is empty to start with. The cache uses an LRU replacement policy: every slot has a counter; every time a slot is accessed, a global counter is incremented and the value is stored in the slot counter; the slot with the lowest counter value is chosen for replacement. Sequence Id 1 2 3 4 5 6 7 8 10 Address Ox0012 0x0014 Ox0016 Ox0018 0x0016 0x0012 0x0020 Ox0022 0x0014 Ox0012 Hit/Miss Accesses 1 to 10 are respectively: Select one: O a. Miss, Miss, Miss, Miss, Hit, Hit, Miss, Miss, Miss, Miss O b. Miss, Miss, Miss, Miss, Hit, Hit, Miss, Miss, Hit, Hit O. Miss, Miss, Miss, Miss, Hit, Hit, Miss, Miss, Hit, Miss O d. Miss, Miss, Miss, Miss, Hit, Miss, Miss, Miss, Miss, Hit O e. Miss, Miss, Miss, Miss, Hit, Hit, Miss, Miss, Miss, Hit
Assume a program has 20% store and load. When we run this program in a computer, we observe that L1 instruction cache has a hit rate of 98% and L1 data cache has a hit rate of 96%. The L2 cache has a hit rate of 80%. The access time of L1 cache is 2 cycle, and the access time of L2 cache is 40 cycles. If a miss occurs in L2, we have to go to main memory and the penalty is 100 cycles. Assume that the cache uses physical address.a) Without a TLB, what is the AMAT?b) Assume a TLB is built in the cache and its access time is ignored. If the TLB has a 99% hit rate, what is the new AMAT?c) If there is a 0.01% chance that a page fault happens, and the penalty to fetch a page from the disk is 106cycles, what is the new AMAT?
6. A cache has the following parameters: b, block size given in numbers of words; S, number of sets; N, number of ways;and A, number of 页2 address bits.A 16-word cache has the parameters given above. Consider the following repeating sequence of lw addresses (given in hexadecimal) and cache con.gurations: 74 A0 78 38C AC 84 88 8C 7C 34 38 13C 388 18C The cache capacity is still 16 words. Assuming least recently used (LRU) replacement for associative caches, determine the efective miss rate if the sequence is input to the following caches, ignoring startup effects (i.e., compulsory misses) (1) two-way set associative cache, b = 2 words (2) direct mapped cache, b= 4 words
A cache memory has a line size of eight 64-bit words and a capacity of 4K words. The main memory size that is cacheable is 1024 Mbits. Assuming 4-way set associative mapping and that the addressing is done at the byte level. What is the format of the main memory addresses (i.e s-d, d, and w)? For the hexadecimal main memory location 2BFACEDH, find the corresponding 4-way set-associative memory format
Given that a 4-way set associative cache memory has 64 KB data and each block contains 32 bytes. The main memory capacity is 4 GB. a. Find the number of bits for the main memory address. ANSWER: b. How many blocks are there in a set? ANSWER: c. How many sets the cache has? ANSWER: d. The main memory address format is => | Tag: bits | blocks sets bits | Set: e. Which set will be mapped by the main memory address 458195h. ANSWER: decimal) bits bits | Word: (in
Consider a memory of size 8KB (8192 bytes) that allows dynamic, variable sized partitioning among processes and uses a linked list to keep track of free spaces (hereafter referred to as the free list) in the memory at any given time. Assume that there are 6 processes and assume that their memory size requirements (in bytes) are as given below: Р1: 500, Р2: 600, Р3: 1300, Р4: 2000, Р5: 100, Р6: 200 Assume that the initial state of the free list is as shown below (BA is the base address and Sz is the size of each free space): ВА: 0; Sz: 1100 — ВА: 1200; Sz: 600 > BА: 2000; Sz: 1800> ВА: 6000%; Sz 400
Let's pretend for a moment that we have a byte-addressable computer with fully associative mapping, 16-bit main memory addresses, and 32 blocks of cache memory. The following holds true if each block is 16 bits in size:a) Determine how many bytes the offset field is.Measure the tag field's width and height in pixels (b).