Fractal Design Pop Air RGB Black TG review
Palit GeForce GTX 1630 4GB Dual review
FSP Dagger Pro (850W PSU) review
Razer Leviathan V2 gaming soundbar review
Guru3D NVMe Thermal Test - the heatsink vs. performance
EnGenius ECW220S 2x2 Cloud Access Point review
Alphacool Eisbaer Aurora HPE 360 LCS cooler review
Noctua NH-D12L CPU Cooler Review
Silicon Power XPOWER XS70 1TB NVMe SSD Review
Hyte Y60 chassis review
Rumor: Samsung to release M.2 980 Pro SSD within two months
Samsung would be planning tor release its new M.2 PCI-E 4.0 based 980 Pro SSDs within the next two months, which, and would have higher speeds than the SSD present in the Playstation 5.
This new line of SSDs will be quite a notch faster compared to the current generation, as they are able to maintain sustained reads of up to 6500 MB/s, and writes of up to 5000 MB/s. For comparison, the Playstation 5 SSD has maximum unzipped information readings of 5500 MB/s, so this new Samsung model will outperform it by 1000 MB/s.
The new Samsung 980 Pro will be based on the Phison E16 controller and will use their own MLC Nand Flash memories, reaching these high speeds. Still, they will not be the fastest SSDs on the market: For example, ADATA is preparing SSDs with read speeds above 7000 MB/s, and there are several more companies working on similar products that will reach the limits of the PCI-E connection. 4.0 x4.
It will be interesting to see if developers start optimizing for NVME SSDs on PCs as they get faster and faster, but their difference in load times versus SATA SSDs is almost nil due to lack of I/O optimization. The new consoles, and especially the Xbox Series X that will use a system very similar to Windows 10, could help in this regard, although to know it we will have to wait a little longer until 100% designed games arrive with the new generation in mind.
The 6th generation V-NAND, the latest 3D NAND from Samsung, will be used for NAND flash memory. The number of stacked layers has increased to 128, and not only capacity and access speed but also power efficiency have been improved compared to the previous generation V-NAND.The table below compares speed and power consumption with the previous model 970 EVO Plus. When using the 980 PRO with PCIe 4.0, the power consumption is the highest, but the performance per power is the highest.
Also, when using the 980 PRO with PCIe 3.0, power consumption is greatly reduced and it operates with lower power consumption than the 970 EVO Plus, so it has an advantage in the PCIe 3.0 environment. Three models will be released, 250GB, 500GB and 1TB. The release is scheduled for the second quarter of this year
| 980 PRO 1TB PCIe 4.0 | 980 PRO 1TB PCIe 3.0 | 970 EVO Plus 1TB | ||||
|---|---|---|---|---|---|---|
| Read | Write | Read | Write | Read | Write | |
| Sequential access speed | 6,500MB/s | 5,000MB/s | 3,500MB/s | 3,300MB/s | 3,541MB/s | 3,018MB/s |
| power consumption | 7.11W | 6.44W | 4.03W | 4.02W | 4.94W | 4.98W |
| Rate of speed per power | 914 | 776 | 868 | 821 | 717 | 606 |
Samsung optimizes New QLED TVs for gaming with Adaptive Sync and HDMI 2.1 - 06/11/2020 09:06 AM
LG not too long ago announced improved support for gaming on their new tellys, so Samsung now also makes an effort. The 2019 and newer QLED TV sets are are optimised for "more immersive and re...
Samsung 870 QVO (SATA3) SSD tagged at 8TB Spotted on Amazon - 06/09/2020 05:57 PM
Wowzers, can you imagine 8TB storage on a SATA3 SSD, well we can and we'll also show you as this puppy popped up at Amazon, priced at 899 USD. ...
Samsung Starts fabbing New V-NAND Flash Facility - 06/01/2020 08:17 AM
Samsung announced plans to expand its NAND flash production capacity in Pyeongtaek, Korea, reinforcing the company's ability to meet demands from emerging technologies. Construction, which began this...
Samsung Globally Launches Odyssey G7 Curved Gaming Monitor - 06/01/2020 08:16 AM
Samsung announced the global launch of its groundbreaking Odyssey G7 gaming monitor. Unveiled at CES 2020 in Las Vegas, the Odyssey lineup reimagines the gaming experience by combining the deepest, mo...
Samsung releases Mobile Computing with Galaxy Book S (Lakefield SoC) - 05/29/2020 12:24 PM
Samsung announced the availability of Galaxy Book S with Intel Lakefield processor. To ensure consumers have access to a wide range of computing devices to best fit their lifestyle, Samsung introduce...
EspHack
Senior Member
Posts: 2731
Joined: 2010-01-03
Senior Member
Posts: 2731
Joined: 2010-01-03
#5799359 Posted on: 06/14/2020 04:37 AM
Besides that it is slower than GDDR6 memory and needs an additional step before hitting the GPU?
And then comes additional time used loading a game into memory every time, I didn't run over any "smart" caching solution that does a real difference so far, even with smaller games it really doesn't get there.
The PC and OS needs a proper controller with a co-processor for NVME and onboard GDDR6 besides OS support for it all to get these 3 seconds game loading times.
Shouldn't forget that the Xbox Series X also is blazing fast, so MS would be stupid if it is not in their interest to push the technology to the PC.
I'm quite sure that PC's will get there in time, question is more if they can do it via addon to existing hardware or if it needs a complete new motherboard.
DDR4 is orders of magnitude faster than any nv storage solution today, not even optane can get close to it, the GPU can tap into cpu ram and tends to do it fairly often on systems with less than 4gb vram, it has almost no impact on a 16x pcie3 bus, its not as direct as the ps5 solution but its not that bad and can be better in some ways
as for the fancy hardware accelerated compression/decompression chip; we master race have spare cores for that, thanks to AMD
and microsoft promised you can keep 5-6 games suspended with instant resume, if they can do that with a plebian nvme 3.0 and 16gb ram, we sure as hell can do the same/better, and that to me sounds a lot better than faster loading
Besides that it is slower than GDDR6 memory and needs an additional step before hitting the GPU?
And then comes additional time used loading a game into memory every time, I didn't run over any "smart" caching solution that does a real difference so far, even with smaller games it really doesn't get there.
The PC and OS needs a proper controller with a co-processor for NVME and onboard GDDR6 besides OS support for it all to get these 3 seconds game loading times.
Shouldn't forget that the Xbox Series X also is blazing fast, so MS would be stupid if it is not in their interest to push the technology to the PC.
I'm quite sure that PC's will get there in time, question is more if they can do it via addon to existing hardware or if it needs a complete new motherboard.
DDR4 is orders of magnitude faster than any nv storage solution today, not even optane can get close to it, the GPU can tap into cpu ram and tends to do it fairly often on systems with less than 4gb vram, it has almost no impact on a 16x pcie3 bus, its not as direct as the ps5 solution but its not that bad and can be better in some ways
as for the fancy hardware accelerated compression/decompression chip; we master race have spare cores for that, thanks to AMD
and microsoft promised you can keep 5-6 games suspended with instant resume, if they can do that with a plebian nvme 3.0 and 16gb ram, we sure as hell can do the same/better, and that to me sounds a lot better than faster loading
Fox2232
Senior Member
Posts: 11809
Joined: 2012-07-20
Senior Member
Posts: 11809
Joined: 2012-07-20
#5799461 Posted on: 06/14/2020 04:09 PM
Maybe I misunderstand you but game loading can not solved by game code optimization alone, check this from 8:11
These are old XBOX games coded for the current generation that uses a slow controller and HDD, the hardware and OS is what archives those loading speeds, not the game code.
You really misunderstand given situation.
One is saved memory footprint (switching between games) which is just dump and load at maximum speed storage can do. And other is actual loading of assets from drive which have certain type of compression and are stored on drive with certain bandwidth.
Maybe I misunderstand you but game loading can not solved by game code optimization alone, check this from 8:11
These are old XBOX games coded for the current generation that uses a slow controller and HDD, the hardware and OS is what archives those loading speeds, not the game code.
You really misunderstand given situation.
One is saved memory footprint (switching between games) which is just dump and load at maximum speed storage can do. And other is actual loading of assets from drive which have certain type of compression and are stored on drive with certain bandwidth.
wavetrex
Senior Member
Posts: 1465
Joined: 2008-07-16
Senior Member
Posts: 1465
Joined: 2008-07-16
#5799478 Posted on: 06/14/2020 06:32 PM
The question is... when are we going to see a Samsung 980 EVO with a price that is within normal people budget ?
Hopefully also doing 7000 MB/s in sequential transfer, even if slightly lower 4K performance than the Pro.
That would be an SSD which I could probably buy. The Pro, not so much, as I expect it to cost an arm and a leg and a few kidneys too.
The question is... when are we going to see a Samsung 980 EVO with a price that is within normal people budget ?
Hopefully also doing 7000 MB/s in sequential transfer, even if slightly lower 4K performance than the Pro.
That would be an SSD which I could probably buy. The Pro, not so much, as I expect it to cost an arm and a leg and a few kidneys too.
Click here to post a comment for this news story on the message forum.
Senior Member
Posts: 5409
Joined: 2007-05-05
3 seconds loading time not the question of NVMe being faster/slower on PC. It is question of compression used on data. In other words it is choice of game developer.
Often, developer makes choice that's most fitting old HDD. That's to get maximum compression ratio regardless of decompression cost on CPU as HDD reads usually 80~120MB/s.
But then this heavy compression hits CPU wall with SSD and it can't pull from HDD more than 200~250MB/s. Change compression and you suddenly can read 1000~1500MB/s from NVMe per CPU core (with one thread). Run it with SMT and get maybe to 2GB/s.
Is it an problem to sacrifice entire core when game is loading? (Thread that loads data from SSD with inefficient compression uses entire core anyway as it becomes limiting factor.) Or maybe two cores to get higher throughput? It depends if you really can(need) use all 8C/16T, your gaming PC has available, for rendering while game actually load data from storage. Answer to this is no. Games are at edge where 4C/8T is not OK (can't maximize fps under all usual gaming scenarios). Sometimes 6C/6T shows reduced performance too. But 6C/12T is OK.
And that summarizes current issue. Game engines often look backwards to support HDD. If they used tooling adequate for SSDs, then NVMe-s would already provide considerable boost too. If games were not dumb coded, but were bit more CPU aware, then many more workloads would have been spread across more cores.
Stupid java had parallelism built in for loops long time ago. Engine Developer should just ask simple question: "Is this CPU heavy loop self iterative or can it be parallelized?" And this applies to any processing.
Maybe I misunderstand you but game loading can not solved by game code optimization alone, check this from 8:11
These are old XBOX games coded for the current generation that uses a slow controller and HDD, the hardware and OS is what archives those loading speeds, not the game code.