Comment by jjoonathan | Hacker News Reader

Comment by jjoonathan | Hacker News Reader

Parent Full thread

So this might be a dumb question but it's been bothering me and you sound like you might know.

What's the big advantage of DRAM over SRAM? In school we learned that DRAM was cheaper -- but surely the difference between 1T1C and 6T isn't more than 6 and my intuition says C is big so it's probably 2 or 3 or something for a given process generation. The problem is that the latency of DRAM is absolutely dreadful. On one hand I see a staggering amount of engineering that goes into hiding DRAM latency, and on the other hand I see that DRAM has become so cheap that many systems are over-provisioned by a factor larger than its theoretical cost advantage purely by accident. The "obvious solution" would seem to be DIMMs of SRAM with (comparatively) wicked fast timings -- but this doesn't happen, despite the fact that the memory industry is extremely competitive and filled to the gills with smart people, so presumably there's another factor that stops "DIMMs of SRAM" from being viable. Do you happen to know what it is?

Density. Storing a bit in DRAM requires one capacitor, whose dielectric is simply the gate insulation layer on a transistor. Storing a bit in SRAM takes at least two complete transistors.

That's precisely the answer I didn't find convincing for the reasons I mentioned. If it were that simple, I strongly suspect we would have SRAM-DIMMs and DRAM-DIMMs duking it out in the marketplace in analogy to SSD vs HDD a decade ago.

> one capacitor, whose dielectric is simply the gate insulation

Every DRAM cell depiction I've seen in the last ~5 years has had a gigantic trench capacitor. Are those not in production?

Density isn't the only issue - power usage is also a contributing factor. Because SRAM uses more transistors per bit, leakage of the transistors in large arrays is a significant source of power draw. In DRAM leakage of the single transistor per cell can be compensated for by adjusting the refresh rate.

MRAM and other persistent memory technologies might be used someday, but there's a lot of R&D work to get them to the same level of price and performance as DRAM. It's sad that Intel gave up prematurely (imho) on Optane.

and it's not like SRAM isn't used in modern computers -- it's baked directly into the silicon of your CPU to serve as register banks and cache

Ah, that makes sense! It's too bad that CMOS becomes leaky at small sizes.

Yeah, too bad about Optane, but CXL gives me hope that the next decade will bring more action in this space.

Great question! I wasn't smart enough to ask it myself. Gonna learn something here I hope. ..

Reply on news.ycombinator.com