Category: computer-sciences-systems-analysis-and-design

Order the answer to: The test-and-set spin lock is the simplest synchronization mechanism possible

computer-sciences-systems-analysis-and-design

Order the answer to: The test-and-set spin lock is the simplest synchronization mechanism possible

Posted By George smith

Question
Unlocking a spin lock simply requires a store of the value 0.
As discussed in Section 4.7, the more optimized test-and-test-and-set lock uses a load to check the lock, allowing it to spin with a shared variable in the cache.

Read More
Order the answer to: Assume the cache contents of Figure 4.37 and the timing

computer-sciences-systems-analysis-and-design

Order the answer to: Assume the cache contents of Figure 4.37 and the timing

Posted By George smith

Question
Assume the cache contents of Figure 4.37 and the timing of Implementation 1 in Figure 4.38. What are the total stall cycles for the following code sequences with both the base protocol and the new MESI protocol in Exercise 4.5? Assume state

Read More
Order the answer to: Some applications read a large data set first, then modify

computer-sciences-systems-analysis-and-design

Order the answer to: Some applications read a large data set first, then modify

Posted By George smith

Question
Some applications read a large data set first, then modify most or all of it. The base MSI coherence protocol will first fetch all of the cache blocks in the Shared state, and then be forced to perform an invalidate operation to

Read More
Order the answer to: For the following code sequences and the timing parameters for

computer-sciences-systems-analysis-and-design

Order the answer to: For the following code sequences and the timing parameters for

Posted By George smith

Question
For the following code sequences and the timing parameters for the two implementations in Figure 4.38, compute the total stall cycles for the base MSI protocol and the optimized MOSI protocol in Exercise 4.3. Assume state transitions that do not require bus

Read More
Order the answer to: Many snooping coherence protocols have additional states, state transitions, or

computer-sciences-systems-analysis-and-design

Order the answer to: Many snooping coherence protocols have additional states, state transitions, or

Posted By George smith

Question
Many snooping coherence protocols have additional states, state transitions, or bus transactions to reduce the overhead of maintaining cache coherency. In Implementation 1 of Exercise 4.2, misses are incurring fewer stall cycles when they are supplied by cache than when they are

Read More
Order the answer to: Some directory protocols add an Owned (O) state to the

computer-sciences-systems-analysis-and-design

Order the answer to: Some directory protocols add an Owned (O) state to the

Posted By George smith

Question
Some directory protocols add an Owned (O) state to the protocol, similar to the optimization discussed for snooping protocols. The Owned state behaves like the Shared state, in that nodes may only read Owned blocks. But it behaves like the Modified state,

Read More
Order the answer to: In the case of a cache miss, both the switched

computer-sciences-systems-analysis-and-design

Order the answer to: In the case of a cache miss, both the switched

Posted By George smith

Question
In the case of a cache miss, both the switched snooping protocol described earlier and the directory protocol in this case study perform the read or write operation as soon as possible. In particular, they do the operation as part of the

Read More
Order the answer to: For the multiprocessor illustrated in Figure 4.42 implementing the protocol

computer-sciences-systems-analysis-and-design

Order the answer to: For the multiprocessor illustrated in Figure 4.42 implementing the protocol

Posted By George smith

Question
Figure 4.45 Directory coherence latencies
For the sequences of operations below, the cache contents of Figure 4.42, and the directory protocol above, what is the latency observed by each processor node?
a. P0: read 100
b. P0: read 128
Read More

Order the answer to: Consider the advanced directory protocol described above and the cache

computer-sciences-systems-analysis-and-design

Order the answer to: Consider the advanced directory protocol described above and the cache

Posted By George smith

Question
Consider the advanced directory protocol described above and the cache contents from Figure 4.20. What are the sequence of transient states that the affected cache blocks move through in each of the following cases?
a. P0: read 100
b. P0:

Read More
Order the answer to: The performance of a snooping cache-coherent multiprocessor depends on many

computer-sciences-systems-analysis-and-design

Order the answer to: The performance of a snooping cache-coherent multiprocessor depends on many

Posted By George smith

Question
Figure 4.38 Snooping coherence latencies.

Subject
computer-sciences-systems-analysis-and-design

Read More