Q4. CISC/RISC and Cache Memory (24pts)
Q4-1. Assume that UltraSpark-like processor has an L1 cache with the following specifications:
Instructions that are not found in the on-chip cache will cause the processor to stop all program execution and do a burst memory read access of one refill line from main memory to the cache.
For this memory design, burst accesses from main memory requires an address set-up time of 64 clock cycles, and then all subsequent burst fetches from main memory require 8 clock cycles per memory fetch.
Q4-1-i. Calculate 1 clock cycle, (i.e., the time length of 1 clock) (3pts)
|
Your answer: |
Q4-1-ii. How many memory fetches must be done upon a cache miss? (3pts)
|
Your answer: |
Q4-1-iii. Calculate CPU cycles required to read data from system memory upon a cache miss. (# clocks but not time) (3pts)
|
Your answer: |
Q4-1-iv. What is the effective instruction execution time for this UltraSpark-like processor? (3pts)
|
Your answer: |
Data bus size = 64 bit = 8 bytes
Block size = 64 bytes
Number of access needed to fetch 1 Block = 64/8 = 8
clock frequency = 200 MHz
(i)1 clock cycle = 1/(200 * 106) = 5 * 10-9 = 5 nanosecond
(ii)Number of memory fetches = 8
(iii)Total number of cycle needed = 64 + 8*8 = 128 cycles.
(iv) The effective instruction execution time
=> (0.9 * 1) + (0.1 * 128) = 13.7 cycles
=> 13.7 * 5 nanoseconds = 68.5 nanoseconds
Q4. CISC/RISC and Cache Memory (24pts) Q4-1. Assume that UltraSpark-like processor has an L1 cache with...
4B, 20%) compare performance of a Processor with cache vs. without cache. Assume an Ideal processor with 1 cycle memory access, CPI1 Assume main memory access time of 8 cycles Assume 40% instructions require memory data access Assume cache access time of I cycle Assume hit rate 0.90 for instructiens, 0.80 for data Assume miss penalty (time to read memory inte cache and from cache to Processor with cache processor) is 10 cycles >Compare execution times of 100-thousand instructions:
4B,...
2. Cache hierarchy You are building a computer system with in-order execution that runs at 1 GHz and has a CPI of 1, with no memory accesses. The memory system is a split L1 cache. Both the I-cache and the D-cache are direct mapped and hold 32 KB each, with a block size of 64 bytes. The memory system is split L1 cache. Both the I-cache and the D-cache are direct mapped and hold 32 KB each, with a block...
1. Cache memory (8pts) Consider adding cache to a processor-memory system design. The microprocessor without cache needs 12 clock cycles to read a 16-bit word from the memory. With cache, it takes only 4 clock cycles if the data happens to be in the cache and a total 20 clock cycles including the cache misses. a. What is the performance ratio of the cache system to the non-cache system given a hit rate of 80%? b. For what hit rate...
1. Cache memory (8pts) Consider adding cache to a processor-memory system desigrn. The microprocessor without cache needs 12 clock cycles to read a 16-bit word from the memory. With cache, it takes only 4 clock cycles if the data happens to be in the cache and a total 20 clock cycles including the cache misses a. What is the performance ratio of the cache system to the non-cache system given a hit rate of 80%? b. For what hit rate...
Assume the cache can hold 64 kB. Data are transferred between main memory and the cache in blocks of 4 bytes each. This means that the cache is organized as 16K=2^14 lines of 4 bytes each. The main memory consists of 16 MB, with each byte directly addressable by a 24-bit address (2^24 =16M). Thus, for mapping purposes, we can consider main memory to consist of 4M blocks of 4 bytes each. Please show illustrations too for all work. Part...
6. Memory Access Time [15 points] Consider a MIPS processor that includes a cache, a main memory, and a hard drive. Access times of cache memory, main memory, and hard drive are 5 ns, 200 ns, and 1000 ns, respectively. Assume that cache memory is divided into instruction cache and data cache. Assume that data cache has a 90% hit rate. Assume that main memory has a 98% hit rate and hard drive is perfect (it has a 100% hit...
Question 4 - [25 Points] Part (a) - Average Access Time (AMAT) The average memory access time for a microprocessor with One (1) level (L1) of cache is 2.4 clock cycles - If data is present and valid in the cache, it can be found in 1 clock cycle If data is not found in the cache, 80 clock cycles are needed to get it from off- chip memory Designers are trying to improve the average memory access time to...
Base machine has a 2.4GHz clock rate. There is L1 and L2 cache. L1 cache is 256K, direct mapped write through. 90% (read) hit rate without penalty, miss penalty is 4 cycles. (cost of reading L2) All writes take 1 cycle. L2 cache is 2MB, 4 way set associative write back. 95% hit rate, 60 cycle miss penalty (cost of reading memory). 30% of all instructions are reads, 10% writes. All instructions take 1 cycle - except reads which take...
Consider a memory hierarchy using one of the three organization for main memory shown in a figure below. Assume that the cache block size is 32 words, That the width of organization b is 4 words, and that the number of banks in organization c is 2. If the main memory latency for a new access is 10 cycles, sending address time is 1 cycle and the transfer time is 1 cycle, What are the miss penalties for each of...
Example 4.2 For all three cases, the example includes the following elements: The cache can hold 64 Kbytes. Data are transferred between main memory and the cache in blocks of 4 bytes each. This means that the cache is organized as 16K = 214 lines of 4 bytes each. The main memory consists of 16 Mbytes, with each byte directly addressable by a 24-bit address (24 = 16M). Thus, for mapping purposes, we can consider main memory to consist of...