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.
|Topics||NVIDIA, Tegra, Logan, Parker, Kepler, Maxwell|