- 精华
- 0
- 帖子
- 6906
- 威望
- 0 点
- 积分
- 7471 点
- 种子
- 11 点
- 注册时间
- 2005-11-11
- 最后登录
- 2019-3-28
|
发表于 2013-3-20 16:10 · 新加坡
|
显示全部楼层
本帖最后由 key39 于 2013-3-20 16:13 编辑
这坛子里很多笑话,看的人姚明和侏儒都分不清了。
NVIDIA Updates GPU Roadmap with "Volta"
NVIDIA updated its GPU micro-architecture roadmap at the 2013 GPU Technology Conference (GTC). Currently spearheaded by the "Kepler" micro-architecture, which drives its GeForce, Quadro, and Tesla product lines, and which will drive Tegra mobile SoCs in 2014; NVIDIA's next-generation "Maxwell" could make its debut some time in 2014. Going by NVIDIA's graph that puts performance-per-Watt against time, "Maxwell" should nearly double performance. Maxwell GPUs feature unified virtual memory, which lets CPUs treat graphics card memory as system memory, for faster general-purpose performance.
Although not backed by a tentative launch year, and assuming "Maxwell" has its run for another two years, 2016 could see the launch of NVIDIA's "Volta" GPU micro-architecture. In addition to advancements by its predecessors, "Volta" could introduce stacked DRAM technology. It would enable GPU memory bandwidths as high as 1 TB/s. Current high-end graphics cards such as GeForce Titan and Radeon HD 7970 GHz Edition, are capable of breaching the 300 GB/s mark, so NVIDIA's claims don't sound far-fetched.
With Tegra 4i capping NVIDIA's SoC lineup for now, the company is looking forward to future generations. Its currently successful "Kepler" GPU micro-architecture missed the bus when designing Tegra 4 "Wayne" and "Grey" series, but won't repeat it with "Logan."
Designed to form foundation of NVIDIA's SoCs for 2014, "Logan," as detailed by CEO Jen-Hsun Huang at NVIDIA's GPU Technology Conference, will integrate "Kepler" GPU micro-architecture, and the company's CUDA GPU compute technology.
NVIDIA's move to push CUDA on mobile platforms could help app developers take advantage of idle GPU compute resources, in addition to the limited performance envelope of ARM CPU cores. It looks like "Logan" could make do with whatever high-performance ARM CPU technologies exist in 2014.
Moving on, NVIDIA's SoC lineup for 2015 could be led by "Parker." These chips could integrate the company's next-generation "Maxwell" GPU micro-architecture, and 64-bit "Project Denver" CPU cores based on the ARM machine-architecture. These chips could be built on foundry processes with FinFET technology, which reduces performance-per-Watt, which can be exchanged for higher transistor counts.
|
|