Lecture-Cap8-Part23-Cache Coherence Protocol

Invalidate this block as there was an attempt to write a shared block

Place cache block on bus, write back the cache block, and abort memory access.

The need for broadcasting messages, which can negatively impact the benefits of DSM memory organization.

<p>Which caches have copies of the block, whether it is dirty, and the block status (shared, uncached, modified)</p> Signup and view all the answers

<p>It eliminates the need for broadcasting messages.</p> Signup and view all the answers

<p>Along with the memory, as shown in Fig. 8.5.</p> Signup and view all the answers

<p>The written value is returned.</p> Signup and view all the answers

<p>Writes to the same location are seen in the same order by all processors.</p> Signup and view all the answers

<p>To keep track of the status of any sharing of a data block.</p> Signup and view all the answers

<p>Snooping tracks sharing status in every cache, while directory-based protocols track it in a central location.</p> Signup and view all the answers

<p>To ensure that processors see the same order of writes to the same location.</p> Signup and view all the answers

<p>It is more scalable and efficient for large-scale systems.</p> Signup and view all the answers

<p>The state changes from invalid to shared.</p> Signup and view all the answers

<p>A CPU write hits the shared block.</p> Signup and view all the answers

<p>To place an invalidate on the bus.</p> Signup and view all the answers

<p>It is not scalable.</p> Signup and view all the answers

<p>A regular miss is placed on the bus.</p> Signup and view all the answers

<p>They illustrate the same finite-state machine from the CPU and bus perspectives.</p> Signup and view all the answers

<p>They track caches that share the memory addresses of the memory portion in the node.</p> Signup and view all the answers

<p>The directory-based protocol is based on message passing between nodes, whereas snooping-based coherence protocols are based on snooping on the bus.</p> Signup and view all the answers

<p>In each core.</p> Signup and view all the answers

<p>Because each processor has its own independent memory and address space, and there is no other computer writing on its memory.</p> Signup and view all the answers

<p>It allows multiple threads to share the functional units of a single processor in an overlapping way.</p> Signup and view all the answers

<p>Multithreading is a form of explicit parallelism, whereas ILP is a form of implicit parallelism.</p> Signup and view all the answers

<p>Multithreading shares most of the processor core among a set of threads, and duplicates just private state, whereas multiprocessing has multiple independent threads operating at once and in parallel.</p> Signup and view all the answers

<p>SMT can execute multiple instructions from independent threads without noticing dependencies among them, due to register renaming and dynamic scheduling.</p> Signup and view all the answers

<p>To interleave the execution of instructions from multiple threads and skip stalled threads.</p> Signup and view all the answers

<p>They use simultaneous multithreading (SMT) to execute multiple instructions from independent threads concurrently.</p> Signup and view all the answers

<p>It only switches threads on costly stalls, such as L2 or L3 cache misses, which can lead to inefficient processor utilization.</p> Signup and view all the answers

<p>Multithreading can execute multiple threads concurrently, improving thread-level parallelism and overall processor utilization.</p> Signup and view all the answers