Skip to content
DenseChip
Learn
PracticeCode labInterview

DenseChip

Navigate

Menu

LearnPracticeCode labInterview

Tools

All toolsSV editorCode repoResume
DenseChip

Practice, courses, and chip-design tools in one focused workspace.

LearnPracticeCode labInterviewToolsLearning paths

© 2026 DenseChip

AboutContactPrivacyTerms
Skip to lesson

Course contents

  • Architecture Metrics Reference
  • Workload Taxonomy for Architects
  • Architecture Glossary
  • Computer Architecture Cheatsheet
  • Pipeline Fundamentals14
  • Memory Hierarchy15
    • Caches
    • Memory Bandwidth and Latency
    • Virtual Memory and the TLB
      • Pages and Multi-Level Page Tables
      • TLB Reach and Miss Cost
      • Huge Pages
      • Translation and Cache Indexing
  • NoC and Interconnect Architecture6
  • Coherency and Memory Ordering9
  • Performance Analysis9
  • Accelerator Architectures6
  • SoC Architecture Tradeoffs9
  • Architecture Interview Prep14
Loading lesson

‹Memory Hierarchy
  1. Topics
  2. Computer Architecture
  3. Memory Hierarchy
  4. Virtual Memory and the TLB

Computer Architecture · All levels

Virtual Memory and the TLB

Virtual addresses, page tables, TLB reach, huge pages, and how translation meets caches.

  • 4topics
  • 4lessons

Every load and store uses a virtual address. A page table translates each page to physical memory, and a TLB caches recent translations.

Term

Meaning

Page

A fixed-size, aligned block of virtual address space, commonly 4 KiB.

VPN / PPN

Virtual and physical page numbers: the address with the page offset removed.

PTE

A page-table entry: the PPN plus present, permission, accessed and dirty bits.

Walk

The sequence of table reads that resolves one VPN on a TLB miss.

TLB reach

Entries times page size: the memory mapped without revisiting the table.

ASID

An address-space tag so entries from several processes share the TLB.

Translation path with TLB hit and miss.
A TLB hit translates in one step; a miss walks the page table first.

Lesson

What it covers

Pages and multi-level walks

Page format, four-level tables, and a worked address split.

TLB reach and miss cost

TLB organization, reach arithmetic, and average translation cost.

Huge pages

2 MiB and 1 GiB pages: shorter walks, larger reach, fragmentation cost.

Translation and cache indexing

VIPT caches and the size rule that keeps the index translation-free.

Check yourself A TLB miss still returns the right data, just slower. What does that say about what the TLB is?

It is a cache of translations, not the translation itself. The page table holds the mapping; the TLB only avoids re-walking it.

Interview

Carry one sentence per lesson: tables map VPN to PPN in levels, reach is entries times size, huge pages trade fragmentation for reach, and VIPT index bits must fit the page offset.

PreviousNext: Pages and Multi-Level Page Tables

Up next

Up nextPages and Multi-Level Page Tables

Sign in to save progress

Practice this lessonReport an error

See also

  • Caches
  • Memory Bandwidth and Latency