Samsung Powers NVIDIA Quadro RTX Graphics Cards With 16Gb GDDR6 Memory – Up To 14 Gbps Speeds, 672 GB/s Bandwidth For Professional Cards
Samsung has just announced that the NVIDIA Quadro RTX professional graphics card series is powered by their latest GDDR6 memory solution. The NVIDIA Turing GPU based graphics cards were announced yesterday at SIGGRAPH and feature some of the most impressive GPU specs we've seen to date.
NVIDIA Features Samsung GDDR6 Memory on Their Professional Quadro RTX Graphics Cards With Turing GPU - 16Gb Memory Dies With Up To 14 Gbps Speeds, 672 GB/s Bandwidth
Samsung commenced their GDDR6 mass production back in Q1 2018 and we are looking at the first products featuring the new memory dies today. The GDDR6 memory solution from Samsung features a 16Gb die is aimed at professional Quadro RTX graphics cards which focus on 8K Ultra HD video processing, virtual reality (VR), augmented reality (AR) and artificial intelligence (AI).
According to Samsung, the GDDR6 memory solution effectively doubles the memory capacity over existing GDDR5 memory, offering much higher pin speeds and transfer speeds of up to 56 GB/s on a single die, a 75% increase over 8 Gb GDDR5 solutions with 8 Gbps speeds. At the same time, their new memory consumes 35% less power and since it is using a new low-power circuit design, these memory chips operate at just 1.35V.
“It’s a tremendous privilege to have been selected by NVIDIA to launch Samsung’s 16Gb GDDR6, and to have enjoyed the full confidence of their design team in making our key contribution to the NVIDIA Quadro RTX GPUs,” said Jim Elliott, Corporate Senior Vice President at Samsung Semiconductor.
“Our new Quadro RTX professional GPUs are the industry’s first to integrate Samsung’s high-speed GDDR6 memory technology,” said Bob Pette, Vice President, Professional Visualization, NVIDIA. “With up to 48GB capacity, our GPUs accommodate the largest models and scenes, and increase application performance, enabling professionals to design, develop and deliver much better results with faster turnaround.” via Samsung
The NVIDIA Quadro RTX graphics cards featuring Samsung's GDDR6 memory would be available in October 2018 with capacities of up to 48 GB VRAM, double that when using NVLINK for completely monstrous 96 GB VRAM buffer. NVIDIA’s upcoming GeForce products are going to feature support for GDDR6 memory allowing them to deliver faster speeds than conventional GDDR5 and GDDR5X solutions which have been around for some time.
The Samsung GDDR6 Memory Specifications Detailed
Coming to the specifications in-detail, the Samsung 16 Gb GDDR6 memory die will be built on the 10nm process node which Samsung is calling as the most advanced memory node to date. It will double the density of their GDDR5 solution which was composed of a 20nm 8 Gb die. According to Samsung, their solution will be operating at up to 18 Gbps against a previous standard speed of 16 Gbps and that is a big deal here. Each die will be able to deliver a data transfer rate of 72 Gbps and hold a capacity of 2 GB VRAM. The solution will be able to do all of this with 35% lower power input at just 1.35V compared to 1.55V.
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. via Samsung
This means that a solution based on a 384-bit interface and surrounded by 12 DRAM dies could feature up to 24 GB of VRAM while a 256-bit solution can house up to 16 GB of VRAM. That’s twice the VRAM capacity as current generation cards. While VRAM is one thing, the maximum bandwidth output on a 384-bit card can reach a blistering fast 864 GB/s while the 256-bit solution can reach a stunning 576 GB/s transfer rate.
We know from yesterday's announcement that NVIDIA is using 14 Gbps memory chips on their RTX Quadro parts. These give us speeds of 672 GB/s across a 384-bit memory with up to 48 GB VRAM and 448 GB/s across a 256-bit bus with up to 16 GB VRAM. Previously, we have seen both flagship and high-end PCB leaks with 12 dies and 8 dies respectively. The board with 12 dies was using the Micron provided VRAM and you can learn more details here. We also mentioned the overclocking potential of GDDR6 memory a while back, reaching up to 20 GB/s, more details here.
If NVIDIA was to use even higher end memory chips from Samsung, then the upcoming GeForce RTX parts would be the go-to graphics solution as they'll be targeting the graphics performance hungry masses in the gaming world who will need higher VRAM and faster memory speeds for unprecedented gaming performance.
GPU Memory Technology Updates
|Graphics Card Name||Memory Technology||Memory Speed||Memory Bus||Memory Bandwidth||Release|
|AMD Radeon R9 Fury X||HBM1||1.0 Gbps||4096-bit||512 GB/s||2015|
|NVIDIA GTX 1080||GDDR5X||10.0 Gbps||256-bit||320 GB/s||2016|
|NVIDIA Tesla P100||HBM2||1.4 Gbps||4096-bit||720 GB/s||2016|
|NVIDIA Titan Xp||GDDR5X||11.4 Gbps||384-bit||547 GB/s||2017|
|AMD RX Vega 64||HBM2||1.9 Gbps||2048-bit||483 GB/s||2017|
|NVIDIA Titan V||HBM2||1.7 Gbps||3072-bit||652 GB/s||2017|
|NVIDIA Tesla V100||HBM2||1.7 Gbps||4096-bit||901 GB/s||2017|
|NVIDIA RTX 2080 Ti||GDDR6||14.0 Gbps||384-bit||672 GB/s||2018|
|AMD Instinct MI100||HBM2||2.4 Gbps||4096-bit||1229 GB/s||2020|
|NVIDIA A100 80 GB||HBM2e||3.2 Gbps||5120-bit||2039 GB/s||2020|
|NVIDIA RTX 3090||GDDR6X||19.5 Gbps||384-bit||936.2 GB/s||2020|
|AMD Instinct MI200||HBM2e||3.2 Gbps||8192-bit||3200 GB/s||2021|
|NVIDIA RTX 3090 Ti||GDDR6X||21.0 Gbps||384-bit||1008 GB/s||2022|