NVIDIA announced that it plans to integrate a high-speed interconnect, called NVIDIA NVLink, into its future GPUs, enabling GPUs and CPUs to share data five to 12 times faster than they can today. According to the company, this will help pave the way for a new generation of exascale supercomputers that are 50-100 times faster.
The company also unveiled the Jetson TK1 DevKit.
NVIDIA will add NVLink technology into its Pascal GPU architecture ” expected to be introduced in 2016 ” following this year’s new NVIDIA Maxwell compute architecture. The new interconnect was co-developed with IBM, which is incorporating it in future versions of its POWER CPUs.
“NVLink technology unlocks the GPU’s full potential by dramatically improving data movement between the CPU and GPU, minimizing the time that the GPU has to wait for data to be processed,” said Brian Kelleher, senior vice president of GPU Engineering at NVIDIA.
According to the company, with NVLink technology tightly coupling IBM POWER CPUs with NVIDIA Tesla GPUs, the POWER data center ecosystem will be able to fully leverage GPU acceleration for a diverse set of applications, such as high performance computing, data analytics and machine learning.
According to NVIDIA, GPUs are connected to x86-based CPUs through the PCI Express (PCIe) interface, which limits the GPU’s ability to access the CPU memory system and is four- to five-times slower than typical CPU memory systems. As the NVLink interface will match the bandwidth of typical CPU memory systems, it will enable GPUs to access CPU memory at its full bandwidth.
Faster data movement, coupled with another feature known as Unified Memory, will simplify GPU accelerator programming. Unified Memory allows the programmer to treat the CPU and GPU memories as one block of memory. The programmer can operate on the data without worrying about whether it resides in the CPU’s or GPU’s memory.
Although future NVIDIA GPUs will continue to support PCIe, NVLink technology will be used for connecting GPUs to NVLink-enabled CPUs as well as providing high-bandwidth connections directly between multiple GPUs.
NVIDIA has designed a module to house GPUs based on the Pascal architecture with NVLink. This new GPU module is one-third the size of the standard PCIe boards used for GPUs today. Connectors at the bottom of the Pascal module enable it to be plugged into the motherboard, improving system design and signal integrity.
NVIDIA also launched a developer platform based on the world’s first mobile supercomputer for embedded systems. The NVIDIA Jetson TK1 Developer Kit boasts 326-gigaflop performance, and includes a full C/C++ toolkit based on NVIDIA CUDA architecture.
“Jetson TK1 fast tracks embedded computing into a future where machines interact and adapt to their environments in real time,” said Ian Buck, vice president of Accelerated Computing at NVIDIA. “This platform enables developers to fully harness computer vision in handheld devices, bringing supercomputing capabilities to low-power devices.”
The kit is based on the Tegra K1 mobile processor, NVIDIA’s 192-core super chip built on the Kepler architecture. It supports the NVIDIA VisionWorks toolkit, which provides a set of computer vision and image processing algorithms to create applications quickly.
The Jetson TK1 Developer Kit comes with the full support of the CUDA 6.0 developer tool suite, including debuggers and profilers to develop massively parallel applications.
It comes with a board support package and software stack, including OpenGL4.4, as well as CUDA and the VisionWorks toolkit. It also includes a complete suite of development and profiling tools, out-of-the-box support for cameras and other peripherals, and NVIDIA’s partner support networking including Avionic Design, GE Intelligent Platforms, ICD, SECO and Toshiba DME.
For more information, visit NVIDIA.
Sources: Press materials received from the company and additional information gleaned from the company’s website.