A Shortcut to Understanding Memory Timings

Do you have a question? Post it now! No Registration Necessary.  Now with pictures!

 A Shortcut to Understanding Memory Timings


By Loyd Case

If "DDR2-800 5-5-5-15" makes you glassy-eyed, then read on to learn
how to decipher it and why you should care. But first let's clarify
how memory works.

Memory accesses don't happen in a single step. Memory is laid out on a
chip in rows and columns, and it requires repeated pulses of
electricity, referred to as "strobing," to reach each location. When
memory is accessed, each strobing cycle takes a fixed amount of time,
as follows:

tCL    Column address strobe (CAS) latency; the number of clock cycles
required to access a specific column of data. (The initial t refers to
tRCD    Row address strobe (RAS)-to-CAS delay; the number of clock cycles
needed between a row address strobe and a column address strobe.
tRP    RAS precharge; the number of clock cycles needed to close one row
of memory and open another.
tRAS    The number of clock cycles needed to access a specific row of
data in RAM.

Now let's break down the DRAM label above. 800 is the effective clock
speed in megahertz. That's the actual clock speed times data per clock
cycle (200 MHz [for DDR2-800] X 4 [4 samples per clock cycle for
DDR2]). DDR2-800 has a maximum bandwidth of 6.4 GBps. "5-5-5-15"
refers to a tCL of 5, tRCD of 5, tRP of 5, and tRAS of 15.
Since latency is measured in clock cycles, the smaller the numbers,
the better. That means less time is required for memory accesses. The
time is measured in nanoseconds, with a typical system making millions
of memory accesses each second. Latency and memory speed trade off.
For example, the same DDR2-667 memory module can run at 333 MHz, with
latencies of 5-5-5-13, or at DDR2-533 speed at 266 MHz with latencies
of 4-4-4-11. Since higher clock frequencies represent smaller time
intervals, the total time is practically the same for both these

What you pay for with premium memory is the ability to run at high
clock speeds and lower latencies. If your apps are sensitive to memory
performance, premium memory can pay off in better performance. Games,
media transcoding, and 3D rendering are all sensitive to memory
latencies. Web browsing, office applications, and streaming media
typically are less sensitive.

Site Timeline