7
$\begingroup$
  • I have been reading this for quiet a long time that "RAM can be accessed hundreds of times faster than a hard drive".
  • But, no one has been able to explain it properly.
  • I searched on Internet and found that "Access time of RAM is faster because they have less addresses(~4GB RAM) than Hard Drive(~1TB), and therefore address-resolution is faster".

Please guide me on this topic.

$\endgroup$
7
  • 3
    $\begingroup$ The explanation is totally wrong. It's just a completely different type of hardware. $\endgroup$ Feb 1, 2017 at 12:52
  • $\begingroup$ This question is hardware-related, and so verged on off-topicality. $\endgroup$ Feb 1, 2017 at 12:53
  • 1
    $\begingroup$ A phone call to a friend is much faster than visiting them by car. Can you explain how? $\endgroup$
    – gnasher729
    Feb 1, 2017 at 20:13
  • $\begingroup$ How is this a computer science question? $\endgroup$
    – Raphael
    Feb 4, 2017 at 21:09
  • 1
    $\begingroup$ @Raphael - You yourself added the tag "computer-architecture", which suggests its a "computer science" question !! $\endgroup$ Feb 6, 2017 at 11:50

2 Answers 2

7
$\begingroup$

Wikipedia has great information on this topic, but as a brief, simplified explanation, know that it boils down mainly to the involvement of mechanical moving parts in a traditional Hard Disk Drive (HDD).

The size of the addressing space in itself doesn't affect the access times. Otherwise you could theoretically build a very small hard-disk drive with only 4GB and expect it to run just as fast as your RAM chip. In reality that is not possible.

Hard Disk Drives

All the data is read and written by the read and write heads, laying on the round disks that physically store all the data. Whenever data in a specific address is specified, the heads must move to the correct track (the time it takes is the Seek Time) and the disk must rotate until the requested sector is under the head (Rotational Latency). The time until both of these tasks are completed is the Access Time, and only then the data transfer can actually start.

Hard disk structure diagram A - Track ; C - (Track) Sector

RAM

In contrast, RAM cards have no such mechanical moving parts and therefore the time constraints are much lower. They are mainly there to allow proper synchronization of the electronic components that comprise the memory card and ensure that it works reliably.

SSD

You probably also heard of the term Solid State Drive (SSD). Seagate recently manufactured such a drive with 60TB capacity, and its access times are still much shorter than those of hard-disk drives. How? Like RAM chips, they have no moving parts.

$\endgroup$
4
  • $\begingroup$ I have one more doubt - "Hard Disks are farther from processor AND RAM is itself in the motherboard, i.e. they are nearer to processor". Can this also play some part in access time difference ?? $\endgroup$ Feb 2, 2017 at 10:34
  • 1
    $\begingroup$ Electricity flows at almost what we know as the speed of light in vacuum, so the physical distance of a few millimeters of cable more is extremely negligible. It is true that the RAM in standard PCs were historically closer to the CPU in terms of components in their paths (south-bridge/north-bridge, on-chip/PCH, etc...), but this cuts off a couple of nanoseconds at best, not a hundred-times-faster improvement. I also refer you again to the SSD vs. HDD comparison. This is where you see the major speed improvement. $\endgroup$
    – oranja
    Feb 2, 2017 at 11:24
  • $\begingroup$ If you want to learn how other factors (not mechanical moving parts) affect the performance characteristics, a good question would be about the difference in RAM vs. SDD performance, not HDD. $\endgroup$
    – oranja
    Feb 2, 2017 at 11:27
  • $\begingroup$ The following video supports this answer : youtube.com/watch?v=d0xn68w3KPE $\endgroup$ Feb 9, 2017 at 9:13
1
$\begingroup$

RAM is a matrix memory, which is made of capacitors. The matrix is an array of transverse lines (rows) and vertical lines (columns). A capacitor can't be charged if its row terminal isn't grounded and its column terminal doesn't have voltage, the voltage can just exist if it can flow from high voltage to ground. So an IC would scan the columns and rows to charge the capacitors, that process can be done very fast without any mechanical movement. In contrast, hard drives use motors to control the reader arm and rotate the disk, so can't be as fast as RAM.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge that you have read and understand our privacy policy and code of conduct.

Not the answer you're looking for? Browse other questions tagged or ask your own question.