問66
頻出度★★☆
PCのキャッシュメモリを説明したものはどれか。
平成22年度 春期 ITパスポート試験 問66
テクノロジ系コンピュータ構成要素 › メモリ
This question's explanation and your answers so far.
解説
問 66
- ア
正解 The correct answer is ア. Cache memory is a small but very fast memory placed between the CPU core (the processing unit) and the main memory. Compared with the operating speed of the CPU, reading from and writing to main memory is slow, so without any countermeasure the time the CPU spends waiting for main memory to respond is simply wasted. To avoid this, data and instructions that have already been used once, together with data that is likely to be used next, are copied into the cache memory; the next time the same data is needed, it is read from or written to the cache instead of going all the way to main memory. This reduces the number of accesses to main memory, shortens the effective memory access time, and raises processing performance. Choice ア, “Memory located between the CPU core and the main memory, used to read and write data at high speed”, correctly states both where it is placed (between the CPU and main memory) and what it is for (high-speed reading and writing), and this is exactly the definition of cache memory. In an actual PC, caches are also arranged in levels such as L1, L2 and L3; the closer a cache is to the CPU, the faster it is and the smaller its capacity.
Incorrectイ
Recording the same data in two places at the same time to improve reliability describes mirroring (RAID1 for storage devices, memory mirroring for main memory). By holding the same data twice, processing can continue with the other copy even if one side fails; this is a mechanism for improving reliability (availability). Its purpose is reliability rather than speed, and that is where it differs from cache memory. Cache memory is not an area for duplicating data.
Incorrectウ
A mechanism that lets even programs larger than the main memory capacity run describes virtual memory. The part that does not fit into main memory is saved out to auxiliary storage (a hard disk or an SSD) and read back into main memory when it becomes necessary (paging / swapping), which expands the apparent capacity of main memory. Its purpose is to expand capacity, not to absorb a difference in speed, and because slow auxiliary storage is used the speed actually drops. It is a technology that works in the opposite direction from cache memory.
Incorrectエ
Enabling simultaneous access by dividing the main memory into multiple blocks describes memory interleaving. Main memory itself is divided into several banks, and consecutive addresses are assigned to different banks so that they can be accessed in parallel, which raises the effective transfer speed of main memory; in other words, what is sped up lies inside main memory. That is a different mechanism from cache memory, which places a separate high-speed memory between the CPU and main memory.
ここがポイント
- Cache memory = a small, high-speed buffer memory placed between the CPU and main memory to bridge the gap between their operating speeds. It keeps frequently used data, reduces the number of accesses to main memory, and shortens the effective access time. Caches are arranged in levels such as L1, L2 and L3; the closer to the CPU, the faster and the smaller.
- Telling apart the confusing memory-related terms: cache memory (absorbs the difference in speed) / virtual memory (expands the apparent capacity of main memory) / memory interleaving (divides main memory into several banks for parallel access) / mirroring (improves reliability by writing the same data twice). Sorting them by whether the purpose is speed, capacity, or reliability keeps them straight.
用語