Material Insights · Understanding the Material World

Dynamic random-access memory

Each bit is a charge on a tiny capacitor, refreshed many times a second.

Computing and AI · Data storage · No. 283

  • Electronic age
  • Readiness 9 of 9
  • Component
Computing and AI · Technology

Your computer's main memory forgets everything within moments unless each bit is topped up several times a second.

Chart: Illustration: Dynamic random-access memory

Where it comes from

Chart: Map of where it comes from

After an IBM review in the autumn of 1966, Robert Dennard wondered whether a small capacitor could replace the magnetic ring of core memory. By 1967 he had reduced a memory cell to one transistor and one capacitor.

Three things to know
  1. A DRAM cell is just one transistor and one capacitor: a charged capacitor means 1 and an empty one means 0.
  2. Intel's 1103 of 1970 held 1024 bits at 1 cent per bit and quickly pushed magnetic core memory out of computers.
  3. Memory chips were the second-largest chip category in 2024, with sales of 165.1 billion US dollars, up 78.9%.
The journey
  1. 1 Silicon waferVery pure silicon, as for any chip
  2. 2 CellEach bit gets one MOS transistor and one tiny capacitor
  3. 3 ArrayBillions of cells are laid out in rows and columns
  4. 4 Chip and moduleChips are packaged and mounted on memory modules
  5. 5 UseThe computer reads, writes and refreshes the cells as it runs
Go deeper pick a tab to open it in full