Memory Bandwidth (GPU)

Search for glossary terms (regular expression allowed)
Begin with Contains Exact termSounds like

Glossaries

Term Definition
Memory Bandwidth (GPU)

Memory Bandwidth (GPU) -- Memory bandwidth is one of the most frequently showcased stats for any new GPU, often rating in hundreds of gigabytes per second of throughput potential. Memory Bandwidth is the theoretical maximum amount of data that the bus can handle at any given time, playing a determining role in how quickly a GPU can access and utilize its framebuffer. Memory bandwidth can be best explained by the formula used to calculate it:

Memory bus width / 8 * memory clock * 2 * 2

Breaking this formula down, here's what each component means:

The memory bus width is our Memory Interface, which is a given in specs listings. We're dividing by 8 to convert the bus width to bytes (for easier reading by humans). We then multiply by the memory clock (also a given -- use GPU-Z to see this), then multiply the product by 2 (for DDR) and then by 2 again (for GDDR5). This gives us our memory bandwidth rating.

See Also

 

Author: Steve Burke

We moderate comments on a ~24~48 hour cycle. There will be some delay after submitting a comment.

  VigLink badge