Consider the advantages and disadvantages of shared vs. private L2 caches for single-threaded, multi-threaded, and multiprogrammed workloads, and revisit if on-chip L3 caches are available.

If a microprocessor has a cycle time of 0.5 nanoseconds, what’s the processor clock rate? If the fetch cycle is 40% of the processor cycle time, what memory access speed is required to implement load operations with zero wait states and load operations with two wait states?

Processor R is a 64-bit RISC processor with a 2 GHz clock rate. The average instruction requires one cycle to complete, assuming zero wait state memory accesses. Processor C is a CISC processor with a 1.8 GHz clock rate. The average simple instruction requires one cycle to complete, assuming zero wait state memory accesses. The average complex instruction requires two cycles to complete, assuming zero wait state memory accesses. Processor R can’t directly implement the complex processing instructions of Processor C. Executing an equivalent set of simple instructions requires an average of three cycles to complete, assuming zero wait state memory accesses. Program S contains nothing but simple instructions. Program C executes 70% simple instructions and 30% complex instructions. Which processor will execute program S more quickly? Which processor will execute program C more quickly? At what percentage of complex instructions will the performance of the two processors be equal?

How does pipelining improve CPU efficiency? What’s the potential effect on pipelining’s efficiency when executing a conditional BRANCH instruction? What techniques can be used to make pipelining more efficient when executing conditional BRANCH instructions?