hybrid memory cube | KitGuru https://www.kitguru.net KitGuru.net - Tech News | Hardware News | Hardware Reviews | IOS | Mobile | Gaming | Graphics Cards Wed, 09 Sep 2015 01:37:46 +0000 en-US hourly 1 https://wordpress.org/?v=6.4.3 https://www.kitguru.net/wp-content/uploads/2021/06/cropped-KITGURU-Light-Background-SQUARE2-32x32.png hybrid memory cube | KitGuru https://www.kitguru.net 32 32 Micron to unveil third-gen hybrid memory cube in 2016 https://www.kitguru.net/components/memory/anton-shilov/micron-to-unveil-third-gen-hybrid-memory-cube-in-2016/ https://www.kitguru.net/components/memory/anton-shilov/micron-to-unveil-third-gen-hybrid-memory-cube-in-2016/#comments Tue, 08 Sep 2015 19:42:08 +0000 http://www.kitguru.net/?p=266781 Micron Technology is working on the third generation of its hybrid memory cube technology, which will be unveiled next year. If the third-gen HMC doubles data rate of the memory from 15Gb/s today, then the new memory technology will offer unprecedented bandwidth. HMC uses advanced through-silicon vias (TSVs) – vertical conduits that electrically connect a …

The post Micron to unveil third-gen hybrid memory cube in 2016 first appeared on KitGuru.]]>
Micron Technology is working on the third generation of its hybrid memory cube technology, which will be unveiled next year. If the third-gen HMC doubles data rate of the memory from 15Gb/s today, then the new memory technology will offer unprecedented bandwidth.

HMC uses advanced through-silicon vias (TSVs) – vertical conduits that electrically connect a stack of individual chips – to combine Micron’s high-performance logic with Micron's dynamic random access memory. At present Micron offers 2GB and 4GB HMC devices based on 4Gb DRAM dies with up to 15Gb/s data-rates and up to 160GB/s peak bandwidth per device.

ibm_micron_hmc

At present, Micron is working on next-generation HMC, which could improve density and bandwidth, reports HPC Wire. Nothing particular is known about the third-gen HMC, but it is logical to expect Micron to improve performance and capacity of HMC.

“To be frank, we cannot achieve the applications and system needs without developing a really good packaging technology,” said Scott Graham, Micron’s general manager of Hybrid Memory at the Intel Developer Forum last month. “We’re not going to achieve these bandwidth capabilities. We’re not going to achieve the reliability needs. We’re not going to overcome some of the scaling challenges without developing some of these new technology methods. If you look at Hybrid Memory Cube, that’s been the lead vehicle for Micron in order to develop these package technologies for future emerging memories.”

micron_altera_hmc_chip

HMC is supported by various special-purpose microprocessors. In addition, HMC will be used by Intel’s next-generation Xeon Phi co-processor code-named “Knights Landing”. HMC competes against high-bandwidth memory (HBM), but is based on different principles. Instead of using ultra-wide interface, HMC features up to 16-bit serial interconnect operating at a very high clock-rate. Maximum bandwidth supported by one HBM chip is up to 128GB/s, but second-generation HBM will have bandwidth of up to 256GB/s.

“If we have the ability to take DRAM and stack it on top of a logic layer and SoC and be able to control that DRAM with that SoC, it allows us to overcome scaling challenges,” said Mr. Graham. “Being able to combine these technologies together, gives us unprecedented memory bandwidth that keeps pace with multiple CPU cores, and DRAM alone is not going to do that. This all allows for increased savings in energy/bit, density in a small form factor, higher performance and lower energy, and compelling RAS features.”

Discuss on our Facebook page, HERE.

KitGuru Says: HMC makes a great business sense for Micron, who is the only producer of such memory and can control pricing. However, for developers of bandwidth-demanding applications it makes a lot of sense to use HBM instead of HMC because of pricing concerns. HMC has a number of advantages over HBM, but for those, who do not need features like RAS, its advantages are not important. The arrival of HBM will affect popularity of HMC.

The post Micron to unveil third-gen hybrid memory cube in 2016 first appeared on KitGuru.]]>
https://www.kitguru.net/components/memory/anton-shilov/micron-to-unveil-third-gen-hybrid-memory-cube-in-2016/feed/ 2
Nvidia ‘Pascal’ GPUs to offer up to 10X higher speed than ‘Maxwell’ https://www.kitguru.net/components/graphic-cards/anton-shilov/nvidia-next-gen-pascal-gpus-to-offer-up-to-10-times-higher-performance-than-maxwell/ https://www.kitguru.net/components/graphic-cards/anton-shilov/nvidia-next-gen-pascal-gpus-to-offer-up-to-10-times-higher-performance-than-maxwell/#comments Wed, 18 Mar 2015 01:55:00 +0000 http://www.kitguru.net/?p=240589 At its GPU Technology Conference Nvidia Corp. revealed some details about its next-generation code-named “Pascal” architecture of graphics processing units. As expected, the new GPUs will feature numerous innovations that will provide significant benefits in performance in various types of applications. Nvidia noted three key technologies that the “Pascal” GPUs will have: mixed precision computing, support for …

The post Nvidia ‘Pascal’ GPUs to offer up to 10X higher speed than ‘Maxwell’ first appeared on KitGuru.]]>
At its GPU Technology Conference Nvidia Corp. revealed some details about its next-generation code-named “Pascal” architecture of graphics processing units. As expected, the new GPUs will feature numerous innovations that will provide significant benefits in performance in various types of applications.

Nvidia noted three key technologies that the “Pascal” GPUs will have: mixed precision computing, support for stacked multi-layer 3D memory and NVLink GPU bus. As reported previously, the “Pascal” GPUs will be made using 16nm FinFET process technology, therefore, expect increased count of stream processors, and higher clock-rates in addition to architectural enhancements. According to Nvidia, in peak cases, when all improvements come into play, “Pascal” GPUs can be 10 times faster than “Maxwell” GPUs. In typical cases expect next-gen GPUs to be around two times faster than contemporary graphics chips.
nvidia_artworklatesteyeweb_mid
Mixed-precision computing enables “Pascal” architecture-based GPUs to compute at 16-bit floating point accuracy at twice the rate of 32-bit floating point accuracy, which is useful for a number of GPGPU tasks. In certain cases GPUs could do graphics work with 16-bit FP precision without degradation of quality, but not in all of them.

Stacked multi-layer 3D memory will increase memory bandwidth available to new GPUs. Nvidia does not reveal what kind of memory it plans to use, but depending on the Pascal’s availability timeframe, it could be first-generation HBM (with up to 640GB/s bandwidth) or second-generation HBM with unprecedented capacities and north from 1TB/s bandwidth. Extreme memory bandwidth brings benefits to virtually all types of applications, including video games. Graphics cards featuring “Pascal” GPUs and second-gen HBM will carry up to 32GB of memory, according to Nvidia.

NVLink is an energy-efficient, high-bandwidth bus that will be used for communications between Nvidia GPUs and IBM Power processors in supercomputers as well as for multi-GPU communications. Initial NVLink data-rates will be “at least” 80GB/s, but eventually NVLink’s bandwidth will be increased to 192GB/s or even higher.

Nvidia plans to release its first “Pascal” GPUs in 2016.

Discuss on our Facebook page, HERE.

KitGuru Says: While “Pascal” GPUs will not be 10 times faster than “Maxwell” graphics processors in all types of applications, expect the upcoming GPUs to offer significantly higher performance than predecessors due to increased amount of execution units, higher clock-rates, massively increased memory bandwidth and architectural enhancements. The majority of innovations will be enabled by thinner manufacturing process.

The post Nvidia ‘Pascal’ GPUs to offer up to 10X higher speed than ‘Maxwell’ first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/nvidia-next-gen-pascal-gpus-to-offer-up-to-10-times-higher-performance-than-maxwell/feed/ 26
Nvidia is ‘excited’ about ‘Pascal’ and next-gen process technologies https://www.kitguru.net/components/graphic-cards/anton-shilov/nvidia-we-are-excited-about-pascal-and-next-generation-process-technologies/ https://www.kitguru.net/components/graphic-cards/anton-shilov/nvidia-we-are-excited-about-pascal-and-next-generation-process-technologies/#comments Sat, 08 Nov 2014 13:09:21 +0000 http://www.kitguru.net/?p=221054 Jen-Hsen Huang, chief executive officer of Nvidia Corp. said this week that he is excited about the company’s next-generation graphics processing units code-named “Pascal” as well as next-generation process technologies. Nevertheless, while the CEO of Nvidia is confident of the company’s roadmap, he notes that current-gen “Maxwell” family of GPUs is only beginning its journey. …

The post Nvidia is ‘excited’ about ‘Pascal’ and next-gen process technologies first appeared on KitGuru.]]>
Jen-Hsen Huang, chief executive officer of Nvidia Corp. said this week that he is excited about the company’s next-generation graphics processing units code-named “Pascal” as well as next-generation process technologies. Nevertheless, while the CEO of Nvidia is confident of the company’s roadmap, he notes that current-gen “Maxwell” family of GPUs is only beginning its journey.

“We have got lot of great surprises for you guys and I am excited about our next generation GPUs,” said Jen-Hsun Huang during quarterly conference call with investors and financial analysts. “But right now we are enjoying ramping Maxwell. This is a brand new product cycle.”

NVIDIA_GeForce_GTX_900series_KeyVisual_HD_003

Right now Maxwell mainly addresses the market of consumer gaming PCs with GeForce graphics cards. Nvidia plans to introduce professional-grade Quadro graphics cards as well as Tesla accelerators for high-performance computing applications sometime in 2015.

At present there are only two graphics processing units – GM107 and GM204 – based on the Maxwell architecture. Nvidia is expected to unveil two more chips based on the latest graphics processing technology, which will take a quarter or two. It is believed that one of the forthcoming Maxwell GPUs – code-named GM200 – will address the markets of high-performance computing, professional graphics as well as ultra-high-end gaming PCs.

Nvidia’s next-generation graphics processors are code-named “Pascal”. Based on the company’s roadmap that it demonstrated back in March, Pascal GPUs are due sometime in 2016. Next-generation graphics chips from Nvidia will support stacked high-bandwidth dynamic random access memory (DRAM) (SK Hynix's high-bandwidth memory (HBM) or Micron's hybrid memory cube (HMC)), unified memory addressing for CPU and GPU, NVLink interconnection for high-performance computing platforms as well as new graphics, compute and multimedia features that will be a part of DirectX 12, OpenGL 5.0 and other forthcoming application programming interfaces.

nvidia_pascal_module

In 2016 displays with ultra-high-definition (UHD) resolutions like 4K (3840*2160, 4096*2160) or 5K (5120*2160) will get much more popular than they are today. Therefore, dramatically improved graphics processing horsepower of Pascal GPUs as well as extreme bandwidth provided by stacked HMC or HBM DRAM devices (we are talking about 1TB/s – 2TB/s bandwidth here) will be appreciated by the market.

Given the availability timeframe of the “Pascal” family of graphics processors, it is very likely that they will be manufactured using 16nm FinFET+ process technology at Taiwan Semiconductor Manufacturing Co. Although Jen-Hsun Huang has not confirmed anything about Pascal, he did indicate that he is happy with the forthcoming fabrication processes.

“We are excited about the next generation FinFET [manufacturing technologies],” said Mr. Huang. “I can tell you that for the next couple of nodes, I feel pretty good about [them].”

Discuss on our Facebook page, HERE.

KitGuru Says: While Nvidia’s Pascal architecture looks like another major step in the evolution of graphics processors in general, it is at least 1.5 years away. Therefore, from an end-user point of view it is more interesting to know, what the GM200 is and how fast it is. The GM200 will power Nvidia’s next-generation GeForce GTX Titan graphics cards and it is not a secret that they are performance monsters.

The post Nvidia is ‘excited’ about ‘Pascal’ and next-gen process technologies first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/nvidia-we-are-excited-about-pascal-and-next-generation-process-technologies/feed/ 17