我们超算用GPU，美国把已经把GPU用在军用载具里了

GPU用于超算中的通用计算有很多问题，但是对于信号处理，图像处理等军事中常用的专门应用往往可以发挥更高的效率。
目前已知的使用GPU的军用设备：M2A2车载训练设备，RQ-8无人直升机，MQ-9无人机
主要用于可视化，图像增强，图像降噪

GE to Revolutionize Military with NVIDIA CUDA Technology
Brings GPU-Based Supercomputing to Small, Lightweight, Rugged Embedded Platforms

GE Fanuc Intelligent Platforms, a unit of GE Enterprise Solutions, today announced that it had signed an agreement with NVIDIA® Corporation for GE Fanuc to develop new hardware products using NVIDIA graphics processing units (GPUs) based on the award-winning CUDA architecture, for military and aerospace applications. These new products will deliver substantial increases in processing capability for applications and environments that require leading edge computing such as radar, signals intelligence and video surveillance and interpretation.

"There has long been interest in taking the processing performance inherent in state-of-the-art GPUs - such as their massively parallel computing capability - and applying that to problems that have historically been solved using complex DSP and FPGA processor architectures," said Peter Cavill, General Manager, Military & Aerospace Products at GE Fanuc Intelligent Platforms. "The CUDA architecture allows us to offer our customers a level of processing performance that surpasses anything else in the industry by a significant margin. NVIDIA GPUs, in effect, bring the power of supercomputing and parallel processing to applications that are size-, weight- and power-constrained, and will enable us to create new generations of powerful mobile military platforms."

NVIDIA's CUDA Technology delivers up to 100x increase in speed in a broad range of applications that lend themselves to parallel computing. Early tests at GE Fanuc have shown that military applications will benefit from similar increases in speed. A major prime contractor in the military/aerospace industry has evaluated the CUDA architecture in a radar system, and found that performance improvement of 15x is achievable with minimal reprogramming effort. Other prime contractors are expressing substantial interest in the technology.

"CUDA is becoming increasingly pervasive in a broad range of environments and applications, and has reached a tipping point," said Taner Ozcelik, General Manager, Embedded Business at NVIDIA. "We're delighted to help GE Fanuc revolutionize mission critical embedded computing with CUDA in demanding military and aerospace applications, which have been historically constrained by compute performance."

In addition to having potential applications in radar, signals intelligence, and video surveillance and interpretation, GPUs based on the CUDA architecture represent outstanding potential in other application areas including target tracking, image stabilization, SAR (synthetic aperture radar) simulation, pattern recognition, video encoding/decoding, graphics rendering, object recognition, in-crowd behavioral monitoring and analysis, cryptography, sensor processing and software defined radio. Traditional graphics applications will also benefit greatly from high performance NVIDIA GPUs.

New GE Fanuc hardware products featuring CUDA-based GPUs will be announced in the fourth quarter. The first board will be 3U VPX-based and will benefit from a broad-ranging supporting infrastructure of other GE Fanuc 3U VPX solutions and services, allowing customers to specify tailored multi-board solutions. Alternatively, a CUDA-enabled 3U VPX rugged graphics subsystem will also be available.

A family of 6U VPX products will feature combinations of Intel® dual core processors and NVIDIA CUDA-enabled GPUs, allowing designers to create highly sophisticated, powerful multi-board solutions for the most demanding applications. This family, as well as the new 3U VPX platform, will additionally support OpenCL.

The CUDA architecture enables programmers to write programs in conventional computing languages to access the massively parallel processing capabilities of the GPU. This architecture, in tandem with the CUDA C language - the same as conventional C with minor extensions - allows developers to achieve transformative increases in performance.

The ease of CUDA development reduces customers' time to market, enabling substantial performance increases to be gained for minimal investment of time and effort. Application- or porting development can be achieved on a commercial desktop system and transferred to rugged deployable hardware from GE Fanuc.

About GE Fanuc Intelligent Platforms

GE Fanuc Intelligent Platforms, a joint venture between General Electric Company (NYSE:GE) and FANUC LTD of Japan, is an experienced high-performance technology company and a global provider of hardware, software, services, and expertise in automation and embedded computing. We offer a unique foundation of agile, advanced and ultra-reliable technology that provides customers a sustainable advantage in the industries they serve, including energy, water, consumer packaged goods, government & defense, and telecommunications. GE Fanuc Intelligent Platforms is a worldwide company headquartered in Charlottesville, VA and is part of GE Enterprise Solutions. For more information, visit www.gefanuc.com.

About GE Enterprise Solutions

GE Enterprise Solutions elevates customers' productivity and profitability with integrated solutions using sensors and non-destructive testing; security and life safety technologies; power system protection and control; and plant automation and embedded computing systems. Enterprise Solutions' high-tech, high-growth businesses include Sensing & Inspection Technologies, Security, Digital Energy, and GE Fanuc Intelligent Platforms. The business has 17,000 problem-solving employees in more than 60 countries around the world.

GPU用于超算中的通用计算有很多问题，但是对于信号处理，图像处理等军事中常用的专门应用往往可以发挥更高的效率。
目前已知的使用GPU的军用设备：M2A2车载训练设备，RQ-8无人直升机，MQ-9无人机
主要用于可视化，图像增强，图像降噪

GE to Revolutionize Military with NVIDIA CUDA Technology
Brings GPU-Based Supercomputing to Small, Lightweight, Rugged Embedded Platforms

GE Fanuc Intelligent Platforms, a unit of GE Enterprise Solutions, today announced that it had signed an agreement with NVIDIA® Corporation for GE Fanuc to develop new hardware products using NVIDIA graphics processing units (GPUs) based on the award-winning CUDA architecture, for military and aerospace applications. These new products will deliver substantial increases in processing capability for applications and environments that require leading edge computing such as radar, signals intelligence and video surveillance and interpretation.

"There has long been interest in taking the processing performance inherent in state-of-the-art GPUs - such as their massively parallel computing capability - and applying that to problems that have historically been solved using complex DSP and FPGA processor architectures," said Peter Cavill, General Manager, Military & Aerospace Products at GE Fanuc Intelligent Platforms. "The CUDA architecture allows us to offer our customers a level of processing performance that surpasses anything else in the industry by a significant margin. NVIDIA GPUs, in effect, bring the power of supercomputing and parallel processing to applications that are size-, weight- and power-constrained, and will enable us to create new generations of powerful mobile military platforms."

NVIDIA's CUDA Technology delivers up to 100x increase in speed in a broad range of applications that lend themselves to parallel computing. Early tests at GE Fanuc have shown that military applications will benefit from similar increases in speed. A major prime contractor in the military/aerospace industry has evaluated the CUDA architecture in a radar system, and found that performance improvement of 15x is achievable with minimal reprogramming effort. Other prime contractors are expressing substantial interest in the technology.

"CUDA is becoming increasingly pervasive in a broad range of environments and applications, and has reached a tipping point," said Taner Ozcelik, General Manager, Embedded Business at NVIDIA. "We're delighted to help GE Fanuc revolutionize mission critical embedded computing with CUDA in demanding military and aerospace applications, which have been historically constrained by compute performance."

In addition to having potential applications in radar, signals intelligence, and video surveillance and interpretation, GPUs based on the CUDA architecture represent outstanding potential in other application areas including target tracking, image stabilization, SAR (synthetic aperture radar) simulation, pattern recognition, video encoding/decoding, graphics rendering, object recognition, in-crowd behavioral monitoring and analysis, cryptography, sensor processing and software defined radio. Traditional graphics applications will also benefit greatly from high performance NVIDIA GPUs.

New GE Fanuc hardware products featuring CUDA-based GPUs will be announced in the fourth quarter. The first board will be 3U VPX-based and will benefit from a broad-ranging supporting infrastructure of other GE Fanuc 3U VPX solutions and services, allowing customers to specify tailored multi-board solutions. Alternatively, a CUDA-enabled 3U VPX rugged graphics subsystem will also be available.

A family of 6U VPX products will feature combinations of Intel® dual core processors and NVIDIA CUDA-enabled GPUs, allowing designers to create highly sophisticated, powerful multi-board solutions for the most demanding applications. This family, as well as the new 3U VPX platform, will additionally support OpenCL.

The CUDA architecture enables programmers to write programs in conventional computing languages to access the massively parallel processing capabilities of the GPU. This architecture, in tandem with the CUDA C language - the same as conventional C with minor extensions - allows developers to achieve transformative increases in performance.

The ease of CUDA development reduces customers' time to market, enabling substantial performance increases to be gained for minimal investment of time and effort. Application- or porting development can be achieved on a commercial desktop system and transferred to rugged deployable hardware from GE Fanuc.

About GE Fanuc Intelligent Platforms

GE Fanuc Intelligent Platforms, a joint venture between General Electric Company (NYSE:GE) and FANUC LTD of Japan, is an experienced high-performance technology company and a global provider of hardware, software, services, and expertise in automation and embedded computing. We offer a unique foundation of agile, advanced and ultra-reliable technology that provides customers a sustainable advantage in the industries they serve, including energy, water, consumer packaged goods, government & defense, and telecommunications. GE Fanuc Intelligent Platforms is a worldwide company headquartered in Charlottesville, VA and is part of GE Enterprise Solutions. For more information, visit www.gefanuc.com.

About GE Enterprise Solutions

GE Enterprise Solutions elevates customers' productivity and profitability with integrated solutions using sensors and non-destructive testing; security and life safety technologies; power system protection and control; and plant automation and embedded computing systems. Enterprise Solutions' high-tech, high-growth businesses include Sensing & Inspection Technologies, Security, Digital Energy, and GE Fanuc Intelligent Platforms. The business has 17,000 problem-solving employees in more than 60 countries around the world.