- A common approach used to qualify or evaluate the performance of a new system has been to place a portion of the expected target load on the system, or execute one or more micro-benchmarks and observe how the system performs or observe the amount of work the application does per some unit of time.
- However, to evaluate the performance of a SPARC T-series processor, it must be loaded with enough concurrent application threads to keep the large number of hardware threads busy.
- The workload needs to be large enough for the SPARC T-series to reap the benefit of switching to a different runnable thread on the next clock cycle when long latency event such as CPU cache misses occur.
It seems to me that the author tried to explain to us why SPARC T-series perform so bad, instead of telling us the right approach to test the system performance. He paid very little attention to other platforms or CPU architectures, but just tried to downplay the others. Maybe it is not true. But that is my feeling when I read this section.
No comments:
Post a Comment