計算機組織與結構›Ch6 記憶體(Memory)
第 43 題/共 83 題
◀ CC 43/83
43. Direct-Mapped Cache、CPI、Miss Rate
#CC-06-043易Direct-Mapped CacheCPIMiss Rate
題組題幹(本題:第29題,共 4 小題)點擊展開

You have designed a brand new CPU: NYCU (New Younker Compute Unit). We know:

real CPI=ideal CPI+data access prob∗avg stall cyclesreal\ CPI = ideal\ CPI + data\ access\ prob * avg\ stall\ cycles avg stall=miss rate∗miss penaltyavg\ stall = miss\ rate * miss\ penalty

Assume that NYCU can run at 2GHz and its lw/sw share 25% of total NN instructions. Let us ignore the instruction cache issue and ideal CPI is 1. The access time of main memory is 100 ns.

We build a direct-mapped L1 data cache to match the NYCU1 pipeline. Assume that the miss rate is 4% for each cache access. What is the real CPI of NYCU1?

📄 交大111
跳轉到第題
▤完整推導請見《WH 資工筆記 · 計算機組織與結構》Ch6 記憶體(Memory)
本章題號 · 41–60 / 83