Microprocessor maker Nvidia has unveiled the fourth- and fifth-generation chips in its Tegra line, code-named Logan and Parker, respectively. The announcement comes only months after Tegra 4 and 4i, the company's latest chips, have hit the market.
Nvidia's newest chips were announced by CEO Jen-Hsun Huang at the Nvidia GPU developers' conference. Huang said the Tegra chip line will be more than 100-times more powerful from the first generation through the fifth generation, CNET reports.
Nvidia began as a graphics processing unit chip maker for computers and video game consoles and has tried to make inroads with smartphones and tablets. Only Google Nexus 7 and Microsoft Surface currently have them, as other manufacturers opt for other chips.
Nvidia showcased Tegra 4 at CES in January and announced Tegra 4i the next month. The latter integrates the app processor and 4G LTE, which Nvidia hopes will increase its smartphone market share.
Logan will be released later this year and include Nvidia's Kepler GPU, which is popular in the discrete graphics market, and will come with CUDA, Nvidia's programming model for GPUs that lets users multitask. Parker will be Nvidia's first processor from its Project Denver push, which includes full 64-bit capabilities, CNET reports. Nvidia introduced Project Denver during the International Consumer Electronics Show in 2011. Parker also will incorporate a Maxwell GPU, Nvidia's next-generation architecture.
Huang also unveiled Kayla, a development platform for CUDA and OpenGL, an API for rendering 2D and 3D computer graphics. Kayla is powered by the Tegra 3 quad-core ARM processor and a next-generation Kepler GPU. It will be available this spring from ARM-based PC providers.
The Kepler architecture, which is currently shipping in devices, will be followed by Maxwell in 2014. That architecture has a unified virtual memory that makes it possible for GPU operations to read and see the CPU memory, and vice versa. All memory is visible to all processors.
Volta GPU would arrive after that and featuring stacked memory, a new technology for Nvidia that resolves memory bandwidth issues for the GPU. Volta will stack the DRAM on the same silicon chip.
"I love that name, because it would suggest that Volta will be even more energy-efficient," Huang said.
Huang also introduced the GRID "Visual Computing Appliance," which is designed to let businesses deliver ultrafast GPU performance to any Windows, Linux, or Mac client on their network.
GRID VCA lets businesses store graphics-related tasks in the cloud and provides "enormous flexibility to small- and medium-size businesses with limited IT infrastructures," the company said.
