Virtual Memory and High Performance Architectures

Podcast

Play an AI-generated podcast conversation about this lesson

Questions and Answers

What is the first step in the virtual memory management process?

Search the cache

Search the page table

Search the virtual address in the TLB (correct)

Search the physical memory

What is the advantage of a larger page size?

It allows for larger caches, leading to fast cache hit times (correct)

It reduces the number of TLB entries

It increases the number of page table entries

It increases the number of page faults

What is the disadvantage of a larger page size?

It leads to internal fragmentation (correct)

It increases the number of page faults

It increases the number of page table entries

It reduces the number of TLB entries

What is the primary advantage of virtual caches?

They make the common case fast by using virtual addresses Signup and view all the answers

Why are virtual caches not more popular?

They can result in duplicate addresses and incorrect data Signup and view all the answers

What is the alternative approach to getting the best of both virtual and physical caches?

Using part of the page offset to index the cache Signup and view all the answers

What is the primary function of memory modules in RAM construction?

To facilitate the handling and exploit memory interleaving Signup and view all the answers

What is the advantage of using part of the page offset to index the cache?

It allows the cache read to begin immediately, and the tag comparison is still with physical addresses Signup and view all the answers

What happens when the row is not open in a DRAM?

Precharge is required, leading to longer access time Signup and view all the answers

What is the main difference between virtual memory and cache?

Replacement on cache misses is primarily controlled by hardware, while VM replacement is primarily controlled by the operating system Signup and view all the answers

What is the main difference between virtual and physical caches?

Virtual caches use virtual addresses, while physical caches use physical addresses Signup and view all the answers

What is the primary goal of virtual memory management?

To provide a balance between page size and memory usage Signup and view all the answers

What is the primary function of virtual memory?

To automatically manage the two levels of the memory hierarchy Signup and view all the answers

What is the term used to describe the mapping of virtual memory to physical memory?

Address translation Signup and view all the answers

What is the result of using a larger page size?

It reduces the size of the page table Signup and view all the answers

What is the size of the blocks used in segmentation in virtual memory?

Variable-size blocks ranging from 216 to 232 bytes Signup and view all the answers

What is the primary function of the operating system in virtual memory?

To decide what to replace in virtual memory Signup and view all the answers

What is the term used to describe the phenomenon when the processor produces virtual addresses that are translated into physical addresses?

Address translation Signup and view all the answers

What is the main difference between the memory hierarchy and the file system?

The memory hierarchy is used for main memory, while the file system is used for secondary storage Signup and view all the answers

What is the size of the page table in terms of the page size and PTE size?

PT size = Page Size × PTE size Signup and view all the answers

What is the term used to describe the process of relieving programmers from the overlays?

Virtual memory Signup and view all the answers

What is the purpose of the translation lookaside buffer (TLB)?

To reduce address translation time Signup and view all the answers

What is the basic OS guideline for page replacement?

To minimize page faults Signup and view all the answers

What is the approach used by the OS to replace the least recently used block?

Recording the reference bits and resetting them periodically Signup and view all the answers

What is the write strategy used in virtual memory management?

Write back with the dirty bit Signup and view all the answers

Where are page tables typically stored?

In the main memory Signup and view all the answers

What is the size of the inverted page table (IPT) considering a 512 MiB physical memory?

220 (1 MiB) Signup and view all the answers

What is the purpose of the hash function in the block identification scheme?

To allow the data structure to be the length of the number of physical pages Signup and view all the answers

Study Notes

Virtual Memory

Virtual Memory (VM) automatically manages two levels of the memory hierarchy represented by main memory and secondary storage.
Key points of VM include memory space sharing and protection, and memory relocation, which is the mapping of virtual memory to physical memory.

Virtual Memory Size

PT (Page Table) size = 2^32 / Page Size = 12 × 2^22 = 2^22 (4 MiB) for a page size of 4 KiB.
In an inverted page table scheme, IPT (Inverted Page Table) size = 2^29 / Page Size = 2^20 (1 MiB) for a page size of 4 KiB and 4 bytes per page table entry.

Translation Lookaside Buffer (TLB)

TLB is a cache dedicated to reducing address translation time.
Page tables are stored in main memory and can be large in size, so first, the virtual address is searched in the TLB; if it fails, it is searched in the page table.

Block Identification

An alternative to page table is to apply a hash function to the virtual address, allowing the data structure to be the length of the number of physical pages in main memory, which is smaller than the number of virtual pages.

Page Replacement

The basic OS guideline is to minimize page faults.
Almost all OS try to replace the least recently used (LRU) block.
The approach uses an "use bit" or "reference bit" which is set whenever the page is accessed, and in a given period, the OS resets the reference bits and records them to check which pages were accessed during that time.

Write Strategy

Simply, write back with the dirty bit.
Write through is too costly and not commonly used.

Page Size Selection

Points in favor of a larger page size:
- Size of the page table is inversely proportional to the page size, so memory can be saved by making pages bigger.
- Larger page size allows for larger caches, leading to fast cache hit times.
- Transferring larger pages to/from secondary storage is more efficient than transferring smaller pages.
- The number of TLB entries is restricted, so larger page size means more memory can be mapped efficiently, reducing the number of TLB misses.
Points in favor of a smaller page size:
- Conserving storage – less wasted storage when contiguous region of virtual memory is not equal in size to a multiple of the page size.
- Avoiding unused memory in a page, i.e., internal fragmentation.
- Process start-up time, many processes are small, so a large page size would make longer the time to invoke a process.

Virtual and Physical Caches

Virtual caches are not more popular because OS and user programs may use two different virtual addresses for the same physical address, resulting in duplicate addresses and duplicated information in the cache.
One alternative to get the best of both virtual and physical caches is to use part of the page offset to index the cache, and in parallel, the virtual part of the address is translated, and the tag match uses physical addresses.

RAM Construction Technology

Modules are used to facilitate handling and exploit memory interleaving, with memory modules having 4 to 16 memory chips and a 64-bit bus.
The part of the page offset that is identical in both virtual and physical addresses is used to index the cache.

Studying That Suits You

Use AI to generate personalized quizzes and flashcards to suit your learning preferences.

Description

Quiz on virtual memory, page size, and high performance architectures for ITA students in CSC-25 class.