TENSOR PROCESSING UNIT

-
Tensor Processing Unit (TPU) is an AI accelerator application-specific integrated circuit (ASIC) developed by Google specifically for neural network machine learning, particularly using Google's own TensorFlow software. Google began using TPUs internally in 2015, and in 2018 made them available for third party use, both as part of its cloud infrastructure and by offering a smaller version of the chip for sale.

The tensor processing unit was announced in May 2016 at Google I/O, when the company said that the TPU had already been used inside their data centers for over a year. The chip has been specifically designed for Google's TensorFlow framework, a symbolic math library which is used for machine learning applications such as neural networks. However, as of 2017 Google still used CPUs and GPUs for other types of machine learning. Other AI accelerator designs are appearing from other vendors also and are aimed at embedded and robotics markets.

Google's TPUs are proprietary. Some models are commercially available, and on February 12, 2018, The New York Times reported that Google "would allow other companies to buy access to those chips through its cloud-computing service." Google has said that they were used in the AlphaGo versus Lee Sedol series of man-machine Go games, as well as in the AlphaZero system, which produced Chess, Shogi and Go playing programs from the game rules alone and went on to beat the leading programs in those games. Google has also used TPUs for Google Street View text processing and was able to find all the text in the Street View database in less than five days. In Google Photos, an individual TPU can process over 100 million photos a day. It is also used in RankBrain which Google uses to provide search results.

Compared to a graphics processing unit, it is designed for a high volume of low precision computation (e.g. as little as 8-bit precision) with more input/output operations per joule, and lacks hardware for rasterisation/texture mapping. The TPU ASICs are mounted in a heatsink assembly, which can fit in a hard drive slot within a data center rack, according to Norman Jouppi. Different types of processors are suited for different types of machine learning models, TPUs are well suited for CNNs while GPUs have benefits for some fully-connected neural networks, and CPUs can have advantages for RNNs.

Google provides third parties access to TPUs through its Cloud TPU service as part of the Google Cloud Platform and through its notebook-based service Kaggle.

Comments

Post a Comment

Popular posts from this blog

Policy based design in programming.

-
Policy-based design, also known as policy-based class design or policy-based programming, is the term used in Modern C++ Design for a design approach based on an idiom for C++ known as policies. It has been described as a compile-time variant of the strategy pattern, and has connections with C++ template metaprogramming. It was first popularized in C++ by Andrei Alexandrescu with Modern C++ Design and with his column Generic<Programming> in the C/C++ Users Journal, and it is currently closely associated with C++ and D as it requires a compiler with highly robust support for templates, which was not common before about 2003. Previous examples of this design approach, based on parameterized generic code, include parametric modules (functors) of the ML languages,and C++ allocators for memory management policy. The central idiom in policy-based design is a class template (called the host class), taking several type parameters as input, which are instantiated with types selected by th
Read more

What is artificial empathy

-
Artificial empathy (AE) or computational empathy is the development of AI systems − such as companion robot or virtual agents − that are able to detect and respond to human emotions in an empathic way.According to scientists, although the technology can be perceived as scary or threatening by many people, it could also have a significant advantage over humans in professions which are traditionally involved in emotional role-playing such as the health care sector.From the care-giver perspective for instance, performing emotional labor above and beyond the requirements of paid labor often results in chronic stress or burnout, and the development of a feeling of being desensitized to patients. However, it is argued that the emotional role-playing between the care-receiver and a robot can actually have a more positive outcome in terms of creating the conditions of less fear and concern for one's own predicament best exemplified by the phrase: "if it is just a robot taking care of
Read more

Nvidia software

-
Nvidia DGX is a line of Nvidia produced servers and workstations which specialize in using GPGPU to accelerate deep learning applications. DGX-1 DGX-1 servers feature 8 GPUs based on the Pascal or Volta daughter cards with HBM 2 memory, connected by an NVLink mesh network. The product line is intended to bridge the gap between GPUs and AI accelerators in that the device has specific features specializing it for deep learning workloads.The initial Pascal based DGX-1 delivered 170 teraflops of half precision processing,while the Volta-based upgrade increased this to 960 teraflops. DGX-2 The successor of the Nvidia DGX-1 is the Nvidia DGX-2, which uses 16 32GB V100 (second generation) cards in a single unit. This increases performance of up to 2 Petaflops with 512GB of shared memory for tackling larger problems and uses NVSwitch to speed up internal communication. Additionally, there is a higher performance version of the DGX-2, the DGX-2H with a notable difference being the replacement o
Read more