Hitman III: PC graphics perf benchmark review
TeamGroup CX2 1TB SATA3 SSD review
EVGA GeForce RTX 3070 FTW3 Ultra review
Corsair 5000D PC Chassis Review
NZXT Kraken X63 RGB Review
ASUS Radeon RX 6900 XT STRIX OC LC Review
TerraMaster F5-221 NAS Review
MSI Radeon RX 6800 XT Gaming X TRIO Review
Sapphire Radeon RX 6800 NITRO+ review
Corsair HS70 Bluetooth Headset Review
Samsung starts GDDR6 production that offers bandwidth of 18Gbit/s
Samsung has started producing 10nm GDDR6 16 Gbit graphics card memory that can manage 18 Gbit/s per pin. The new solution performs at an 18-gigabits-per-second (Gbps) pin speed with data transfers of 72 gigabytes per second (GBps).
Samsung Electronics, the world leader in advanced memory technology, today announced that it has started mass production of the industry’s first 16-gigabit (Gb) Graphics Double Data Rate 6 (GDDR6) memory for use in advanced graphics processing for gaming devices and graphics cards as well as automotive, network and artificial intelligence systems.
“Beginning with this early production of the industry’s first 16Gb GDDR6, we will offer a comprehensive graphics DRAM line-up, with the highest performance and densities, in a very timely manner,” said Jinman Han, senior vice president, Memory Product Planning & Application Engineering at Samsung Electronics. “By introducing next-generation GDDR6 products, we will strengthen our presence in the gaming and graphics card markets and accommodate the growing need for advanced graphics memory in automotive and network systems.
Built on Samsung’s advanced 10-nanometer (nm) class* process technology, the new GDDR6 memory comes in a 16Gb density, which doubles that of the company’s 20-nanometer 8Gb GDDR5 memory. The new solution performs at an 18-gigabits-per-second (Gbps) pin speed with data transfers of 72 gigabytes per second (GBps), which represents a more than two-fold increase over 8Gb GDDR5 with its 8Gbps pin speed.
Using an innovative, low-power circuit design, the new GDDR6 operates at 1.35V to lower energy consumption approximately 35 percent over the widely used GDDR5 at 1.55V. The 10nm-class 16Gb GDDR6 also brings about a 30 percent manufacturing productivity gain compared to the 20nm 8Gb GDDR5.
Samsung’s immediate production of GDDR6 will play a critical role in early launches of next-generation graphics cards and systems. With all of its improvements in density, performance and energy efficiency, the 16Gb GDDR6 will be widely used in rapidly growing fields such as 8K Ultra HD video processing, virtual reality (VR), augmented reality (AR) and artificial intelligence.
With extensive graphics memory lineups including the new 18Gbps 16Gb GDDR6 and recently introduced 2.4Gbps 8GB HBM2, Samsung expects to dramatically accelerate growth of premium memory market over the next several years.
Samsung 860 Pro (4TB) Shows On Company Website - 01/17/2018 11:35 AM
It's likely a bit of a mistake, then again could be done to create a bit of a viral. But a new Samsung series 860 PRO SSD just turned up on the company website. The thing is, this is a 4TB model....
Samsung Starts Volume Production 2.4 Gbps 8GB HBM2 Stacks - 01/11/2018 08:48 AM
Samsung announced that it has started mass production of its 2nd-generation 8-gigabyte (GB) High Bandwidth Memory-2 (HBM2) with the fastest data transmission speed on the market today. ...
Samsung To Introduce Galaxy S9 end of February - 01/10/2018 03:48 PM
Samsung's new Galaxy S9 smartphone will be announced at the Mobile World Congress in Barcelona, which is at the end of February. A release date hasn't been mentioned, Samsung unveiled its predece...
Samsung Unveils The Wall, World’s First Modular MicroLED 146-inch TV - 01/08/2018 10:16 AM
Samsung Electronics today introduced “The Wall” – the world’s first consumer modular MicroLED 146-inch TV – at its annual First Look CES event. The mo...
Samsung Unveils First Thunderbolt 3 QLED Curved Monitor - 01/03/2018 08:35 AM
Samsung is to launch a new curved QLED monitor with Thunderbolt 3 connectivity, at the 2018 Consumer Electronics Show (CES) next week. The 34-inch CJ791 has been fitted with a single Thunderbolt 3 cab...
Ricepudding
Senior Member
Posts: 748
Joined: 2017-02-17
Senior Member
Posts: 748
Joined: 2017-02-17
#5511900 Posted on: 01/18/2018 10:49 AM
How does it compare to HBM2 ?
Could bring good news to the ridiculous prices we have today
Depends how the HBM2 layout is done, i think the Titan Xp and 1080ti had faster memory (GDDR5X) than say the Vega 56/64 since that was running dual HBM2 chips(seems to limit bandwidth if i remember correctly), but i think stuff like Titan V would run faster.
But honestly they both run pretty close to each other right now GDDR6 would most likely be faster in many consumer cases, though there is already talks of HBM3 whenever that is set to come out
How does it compare to HBM2 ?
Could bring good news to the ridiculous prices we have today
Depends how the HBM2 layout is done, i think the Titan Xp and 1080ti had faster memory (GDDR5X) than say the Vega 56/64 since that was running dual HBM2 chips(seems to limit bandwidth if i remember correctly), but i think stuff like Titan V would run faster.
But honestly they both run pretty close to each other right now GDDR6 would most likely be faster in many consumer cases, though there is already talks of HBM3 whenever that is set to come out
user1
Senior Member
Posts: 1630
Joined: 2016-01-29
Senior Member
Posts: 1630
Joined: 2016-01-29
#5511912 Posted on: 01/18/2018 11:22 AM
How does it compare to HBM2 ?
Could bring good news to the ridiculous prices we have today
if we do the basic calculation
rx 580 with 8gbps gddr5 memory we have
(2ghz real frequency) x(4 ,quad data rate) x (256bit bus) /8 = 256GB/s
for 18Gbps gddr6 on a 256bit bus
(4.5ghz real frequency)x(4 ,quad data rate)x(256bit bus) /8 = 576 GB/s
for 18Gbps gddr6 on a 384bit bus (like a titan Xp)
(4.5ghz)x(4)x(384)/8 = 864GB/s
for hbm 2 2.4gbps on 2 stacks (feasibly a vega 64 card could be equiped with this)
(1.2ghz real frequency)x ( 2 ,double data rate) x (2048 bit bus) /8 = 614GB/s
for hbm2 on 4 stacks (vega 20 machine learning gpu)
(1228.8gb/s)
so i'd say that the gddr6 has an advantage if its cheaper than hbm2 particularly in the consumer range of products, since its offers similar bandwidth and doesn't need an interposer.
however i will say once you go past a 384bit bus things get more expensive, and require alot more space than a similar hbm2 solution,
hbm is still superior interm of its charateristics (power consumption (pretty sure), space efficency, memory density ect) but its cost is the inhibiting factor
what i would expect to see from gddr6 is the return of 64 bit and 128bit bus gpus to mainstream, since the bandwidth provided will actually be enough to be useful, will either make cards cheaper , or more profitable .
How does it compare to HBM2 ?
Could bring good news to the ridiculous prices we have today
if we do the basic calculation
rx 580 with 8gbps gddr5 memory we have
(2ghz real frequency) x(4 ,quad data rate) x (256bit bus) /8 = 256GB/s
for 18Gbps gddr6 on a 256bit bus
(4.5ghz real frequency)x(4 ,quad data rate)x(256bit bus) /8 = 576 GB/s
for 18Gbps gddr6 on a 384bit bus (like a titan Xp)
(4.5ghz)x(4)x(384)/8 = 864GB/s
for hbm 2 2.4gbps on 2 stacks (feasibly a vega 64 card could be equiped with this)
(1.2ghz real frequency)x ( 2 ,double data rate) x (2048 bit bus) /8 = 614GB/s
for hbm2 on 4 stacks (vega 20 machine learning gpu)
(1228.8gb/s)
so i'd say that the gddr6 has an advantage if its cheaper than hbm2 particularly in the consumer range of products, since its offers similar bandwidth and doesn't need an interposer.
however i will say once you go past a 384bit bus things get more expensive, and require alot more space than a similar hbm2 solution,
hbm is still superior interm of its charateristics (power consumption (pretty sure), space efficency, memory density ect) but its cost is the inhibiting factor
what i would expect to see from gddr6 is the return of 64 bit and 128bit bus gpus to mainstream, since the bandwidth provided will actually be enough to be useful, will either make cards cheaper , or more profitable .
Silva
Senior Member
Posts: 1358
Joined: 2013-06-04
Senior Member
Posts: 1358
Joined: 2013-06-04
#5511984 Posted on: 01/18/2018 03:13 PM
With the mining craze we are seeing and knowing how corporations work, I'd say more profitable for sure!
What i would expect to see from gddr6 is the return of 64 bit and 128bit bus gpus to mainstream, since the bandwidth provided will actually be enough to be useful, will either make cards cheaper , or more profitable .
With the mining craze we are seeing and knowing how corporations work, I'd say more profitable for sure!
reix2x
Senior Member
Posts: 372
Joined: 2010-01-20
Senior Member
Posts: 372
Joined: 2010-01-20
#5512006 Posted on: 01/18/2018 04:13 PM
Come on friends, we have to see this situation from a mature point of view, gaming is an industry that have decades around, but just about 20 years or so it has been taken seriously, probably the same had happens to movie industry (a century ago). in my opinion the issue in here isn't the mining industry, the issue is that from 5 years ago we have learned how to do OTHER things with GPUs, we have optimized our ways to work with this kind of processors and now we need many of them, for AI and many types of computation, right now we are crying about hi prices of GPUs, but what probably will happens is a separation from the computing market (different price points for this kind of computing cards) and the gaming market, we have seen how some technologies has improved general computing instead of the FPS for your games (hbm or vega architecture maybe), we just have to understand that AMD and Nvidia doesn't have any responsibility with the "gaming" community but with GPU tech in general.
Come on friends, we have to see this situation from a mature point of view, gaming is an industry that have decades around, but just about 20 years or so it has been taken seriously, probably the same had happens to movie industry (a century ago). in my opinion the issue in here isn't the mining industry, the issue is that from 5 years ago we have learned how to do OTHER things with GPUs, we have optimized our ways to work with this kind of processors and now we need many of them, for AI and many types of computation, right now we are crying about hi prices of GPUs, but what probably will happens is a separation from the computing market (different price points for this kind of computing cards) and the gaming market, we have seen how some technologies has improved general computing instead of the FPS for your games (hbm or vega architecture maybe), we just have to understand that AMD and Nvidia doesn't have any responsibility with the "gaming" community but with GPU tech in general.
Click here to post a comment for this news story on the message forum.
Senior Member
Posts: 200
Joined: 2016-12-28
How does it compare to HBM2 ?
Could bring good news to the ridiculous prices we have today