They will. DDR5 is more focused on increasing capacity and lowering voltage (ie: increased efficiency), with the drawback of slightly higher overall latency (despite running at higher MT/s). Primarily designed due to servers requiring more and more memory, and these are the end devices for DRAM that end up both consuming the most wattage and where the most revenue is made.
From a business standpoint, yeah, it makes sense that they'd focus the design to benefit that market the most.
From a consumer standpoint, yeah, it's dumb that we're going to lose a bit of latency, but at the end of the day this should mean DRAM is cheaper to produce for the same capacity (and DRAM pricing is the biggest problem on the market for consumers right now), and if latency's that big a deal to you, G.Skill/Crucial/Corsair/etc. will be providing memory kits that can overclock to higher MT/s and lower latencies than official JEDEC specs for DDR5.
CAS Latency goes up, sure, but when bundled with the frequency gain, the real world latency often stays around the same. We're still a long way out from the fine tuning that will be required when the IP actually goes into real world chips.
I'm aware, I was speaking of CAS Latency and other individual RAM subtimings, as you presumed correctly.
Total latency does stay roughly the same generation to generation as you've stated, although I expect this generation to dip just a bit in total latency, though, because I don't particularly see any kind of "Moore's law equivalence" (in regards to a presumed law that every generation of DRAM always increases MT/s, increases capacity, slows subtimings, but still maintains the same total latency) to hold up over time for memory.
I'd like to be wrong, but the thing is DDR4 was ~supposed~ to bring cost and capacity benefits over DDR3. That didn't pan out. At this point I don't think DRAM can achieve improving all three of the following: 1) capacity 2) cost 3) speed
DDR4 failed on cost over DDR3, and the speed stayed the same. We just got 1 improvement with capacity, kept the speed the same, and got worse cost. So I don't even think we'd be looking at a "pick 2 of 3" scenario for the above, but maybe just improve 1, keep the other constant, and the other gets worse. And my bet is on improving capacity, keeping the current (exorbitant) memory cost, and slightly worse speed.
That being said, these are obviously all my own speculation given trends I've personally noticed in the memory market over time. My speculation is just that-- speculation.
Possible, but they're currently under supervision/investigation of collusion. Also, current projected DRAM prices are expected to lower into Q4, although after that memory prices are expected to rise again.
"Keep in mind that the DRAM manufacturers have been engaging in price fixing with DDR4." That lawsuit is pretty flimsy, having read it in its entirety.
DRAM pricing is only a problem due to price fixing by the major manufacturers. We are just about due for another lawsuit.
Prices have double since 2016, not held stable, not slightly fluctuated. Doubled. There was not a magic cause for the price of the same thing you made two years ago being twice as expensive now. That's pure greed, and sadly with hyperscale companies consuming the lion's share of the product, they've been able to get away with it.
I dont know why everyone keeps raving on about latency for memory, with all the level2 and level3 caches on CPU's it's a like fraction of a nice market where memory latency makes a difference. It's been tested over and over .. why do people waste money on these DDR4->9999 MEGAHURTS, when they could get a faster cpu or gpu and actually increase framerate?
I agree. We had one fool that was posting in the comments about wanting extreme speed memory + overclocking it further... For database/software development workloads. And just did not understand that for these workloads memory latency isn't a real bottleneck, completely discounted going with an HEDT platform processor (even though you have more cache, cores, DRAM slots, and other professional features like ECC support, extended AVX instruction support, etc.) and wanted to stick with a 9900k + high capacity+speed RAM.
Kinda curious what the workload is where RAM latency is a major issue these days. I mean, it mostly affects things like multi-user databases where you have several calls to RAM at once. No games or desktop software is going to see any major performance gains on reduced latency. Typically the MHz increases more than the CAS, so you end up with (very slightly) lower latency, but massive increase in throughput. The main thing to keep in mind is that DDR5 is focused on the data center where latency is very important. If their massive data sets and thousands of users hitting their servers are not a latency issue, then I am sure that my desktop will be fine lol. More importantly, if latency was a major issue for these people where latency is a main concern, then it would be reflected in the new standards. Latency use to be a big concern back in the DDR and DDR2 days... DDR3 and beyond there are much bigger fish to fry.
Gaming benefits heavily from lower latency (as in real latency, not just lower timings), particularly with regards to worse case scenarios (min fps, 99th percentile fps metrics) if trying to drive higher fps (high refresh displays) in non GPU limited scenarios.
For consumers, latency (as well as power, bandwidth, and compactness) might be better addressed with HBM. I expect by 2021+ we'll be on HBM3 or HBM4 or something. You get better latency simply by virtue of shorter traces between memory cells and the CPU/caches - and also by more parallelism (when you have lots of concurrent requests from multiple cores/threads, this gets to be important.) Yes, you get lower maximum capacity with HBM than what's possible with DRAM, but for most consumer workloads that's not really a huge issue - particularly given the HBM capacity roadmaps. The only real issue is price - but on that account, DRAM hasn't been doing itself any favors, lately...
Except they didn't plan Raven Ridge very well, given the lack of LPDDR support which put them out of the race for the ever expanding 2-in-1 detachable tablet market (i.e. Surface Pro, Lenovo Miix, Envy X2, etc.).
Hopefully Picasso will support LPDDR4x or even LPDDR5. Fingers crossed.
We’ve updated our terms. By continuing to use the site and/or by logging into your account, you agree to the Site’s updated Terms of Use and Privacy Policy.
Facebook
Twitter
RSS
18 Comments
Back to Article
The Chill Blueberry - Wednesday, October 17, 2018 - link
Hoping the bandwidth improvements doesn't come with a big latency increase.JoeyJoJo123 - Wednesday, October 17, 2018 - link
They will. DDR5 is more focused on increasing capacity and lowering voltage (ie: increased efficiency), with the drawback of slightly higher overall latency (despite running at higher MT/s). Primarily designed due to servers requiring more and more memory, and these are the end devices for DRAM that end up both consuming the most wattage and where the most revenue is made.From a business standpoint, yeah, it makes sense that they'd focus the design to benefit that market the most.
From a consumer standpoint, yeah, it's dumb that we're going to lose a bit of latency, but at the end of the day this should mean DRAM is cheaper to produce for the same capacity (and DRAM pricing is the biggest problem on the market for consumers right now), and if latency's that big a deal to you, G.Skill/Crucial/Corsair/etc. will be providing memory kits that can overclock to higher MT/s and lower latencies than official JEDEC specs for DDR5.
Ian Cutress - Wednesday, October 17, 2018 - link
CAS Latency goes up, sure, but when bundled with the frequency gain, the real world latency often stays around the same. We're still a long way out from the fine tuning that will be required when the IP actually goes into real world chips.JoeyJoJo123 - Wednesday, October 17, 2018 - link
I'm aware, I was speaking of CAS Latency and other individual RAM subtimings, as you presumed correctly.Total latency does stay roughly the same generation to generation as you've stated, although I expect this generation to dip just a bit in total latency, though, because I don't particularly see any kind of "Moore's law equivalence" (in regards to a presumed law that every generation of DRAM always increases MT/s, increases capacity, slows subtimings, but still maintains the same total latency) to hold up over time for memory.
I'd like to be wrong, but the thing is DDR4 was ~supposed~ to bring cost and capacity benefits over DDR3. That didn't pan out. At this point I don't think DRAM can achieve improving all three of the following:
1) capacity
2) cost
3) speed
DDR4 failed on cost over DDR3, and the speed stayed the same. We just got 1 improvement with capacity, kept the speed the same, and got worse cost. So I don't even think we'd be looking at a "pick 2 of 3" scenario for the above, but maybe just improve 1, keep the other constant, and the other gets worse. And my bet is on improving capacity, keeping the current (exorbitant) memory cost, and slightly worse speed.
That being said, these are obviously all my own speculation given trends I've personally noticed in the memory market over time. My speculation is just that-- speculation.
Mr Perfect - Wednesday, October 17, 2018 - link
Keep in mind that the DRAM manufacturers have been engaging in price fixing with DDR4. https://www.theregister.co.uk/2018/04/30/dram_vend...DDR5 may suffer the same fate.
JoeyJoJo123 - Wednesday, October 17, 2018 - link
Possible, but they're currently under supervision/investigation of collusion. Also, current projected DRAM prices are expected to lower into Q4, although after that memory prices are expected to rise again.James5mith - Thursday, October 18, 2018 - link
Lower to what? 2016 era prices? I bought the same set of 32GB (2x16GB) DDR4-2666 SO-DIMMs three times (two NUCs and a laptop).2016 - $171 for the kit
2017 - $239 for the kit
2018 - $370 for the kit
Adramtech - Thursday, October 18, 2018 - link
"Keep in mind that the DRAM manufacturers have been engaging in price fixing with DDR4." That lawsuit is pretty flimsy, having read it in its entirety.James5mith - Thursday, October 18, 2018 - link
DRAM pricing is only a problem due to price fixing by the major manufacturers. We are just about due for another lawsuit.Prices have double since 2016, not held stable, not slightly fluctuated. Doubled. There was not a magic cause for the price of the same thing you made two years ago being twice as expensive now. That's pure greed, and sadly with hyperscale companies consuming the lion's share of the product, they've been able to get away with it.
brunis.dk - Wednesday, October 17, 2018 - link
I dont know why everyone keeps raving on about latency for memory, with all the level2 and level3 caches on CPU's it's a like fraction of a nice market where memory latency makes a difference. It's been tested over and over .. why do people waste money on these DDR4->9999 MEGAHURTS, when they could get a faster cpu or gpu and actually increase framerate?JoeyJoJo123 - Wednesday, October 17, 2018 - link
I agree. We had one fool that was posting in the comments about wanting extreme speed memory + overclocking it further... For database/software development workloads. And just did not understand that for these workloads memory latency isn't a real bottleneck, completely discounted going with an HEDT platform processor (even though you have more cache, cores, DRAM slots, and other professional features like ECC support, extended AVX instruction support, etc.) and wanted to stick with a 9900k + high capacity+speed RAM.Somethings~something~fool~and~money~departed~something...
No skin off my back. Marketing teams are obviously working their magic on the uninformed.
CaedenV - Wednesday, October 17, 2018 - link
Kinda curious what the workload is where RAM latency is a major issue these days. I mean, it mostly affects things like multi-user databases where you have several calls to RAM at once. No games or desktop software is going to see any major performance gains on reduced latency. Typically the MHz increases more than the CAS, so you end up with (very slightly) lower latency, but massive increase in throughput.The main thing to keep in mind is that DDR5 is focused on the data center where latency is very important. If their massive data sets and thousands of users hitting their servers are not a latency issue, then I am sure that my desktop will be fine lol. More importantly, if latency was a major issue for these people where latency is a main concern, then it would be reflected in the new standards.
Latency use to be a big concern back in the DDR and DDR2 days... DDR3 and beyond there are much bigger fish to fry.
limitedaccess - Wednesday, October 17, 2018 - link
Gaming benefits heavily from lower latency (as in real latency, not just lower timings), particularly with regards to worse case scenarios (min fps, 99th percentile fps metrics) if trying to drive higher fps (high refresh displays) in non GPU limited scenarios.boeush - Thursday, October 18, 2018 - link
For consumers, latency (as well as power, bandwidth, and compactness) might be better addressed with HBM. I expect by 2021+ we'll be on HBM3 or HBM4 or something. You get better latency simply by virtue of shorter traces between memory cells and the CPU/caches - and also by more parallelism (when you have lots of concurrent requests from multiple cores/threads, this gets to be important.) Yes, you get lower maximum capacity with HBM than what's possible with DRAM, but for most consumer workloads that's not really a huge issue - particularly given the HBM capacity roadmaps. The only real issue is price - but on that account, DRAM hasn't been doing itself any favors, lately...Valantar - Wednesday, October 17, 2018 - link
Looking forward to seeing what can be done for APUs with this. Seems like AMD planned (very!) well when they said AM4 would last until 2020.ToTTenTranz - Wednesday, October 17, 2018 - link
Except they didn't plan Raven Ridge very well, given the lack of LPDDR support which put them out of the race for the ever expanding 2-in-1 detachable tablet market (i.e. Surface Pro, Lenovo Miix, Envy X2, etc.).Hopefully Picasso will support LPDDR4x or even LPDDR5. Fingers crossed.
Amandtec - Wednesday, October 17, 2018 - link
2020 + 5nm chips + DDR4 + QLC flash = good time to buy an APU that doesn't suck.boozed - Thursday, October 18, 2018 - link
So those two photos of a red circuit board simply entitled "DDR5 board" but which carry no explanation or caption. What is it?