Extended precisionExtended precision refers to floating-point number formats that provide greater precision than the basic floating-point formats. Extended precision formats support a basic format by minimizing roundoff and overflow errors in intermediate values of expressions on the base format. In contrast to extended precision, arbitrary-precision arithmetic refers to implementations of much larger numeric types (with a storage count that usually is not a power of two) using special software (or, rarely, hardware).
AI acceleratorAn AI accelerator is a class of specialized hardware accelerator or computer system designed to accelerate artificial intelligence and machine learning applications, including artificial neural networks and machine vision. Typical applications include algorithms for robotics, Internet of Things, and other data-intensive or sensor-driven tasks. They are often manycore designs and generally focus on low-precision arithmetic, novel dataflow architectures or in-memory computing capability.
Double-precision floating-point formatDouble-precision floating-point format (sometimes called FP64 or float64) is a floating-point number format, usually occupying 64 bits in computer memory; it represents a wide dynamic range of numeric values by using a floating radix point. Floating point is used to represent fractional values, or when a wider range is needed than is provided by fixed point (of the same bit width), even if at the cost of precision. Double precision may be chosen when the range or precision of single precision would be insufficient.
Microprocessor chronologyThe first microprocessors were designed and manufactured in the 1970s. Intel's 4004 of 1971 is widely regarded as the first commercial microprocessor. Designers predominantly used MOSFET transistors with pMOS logic in the early 1970s, switching to nMOS logic after the mid-1970s. nMOS had the advantage that it could run on a single voltage, typically +5V, which simplified the power supply requirements and allowed it to be easily interfaced with the wide variety of +5V transistor-transistor logic (TTL) devices.
Digital signal processorA digital signal processor (DSP) is a specialized microprocessor chip, with its architecture optimized for the operational needs of digital signal processing. DSPs are fabricated on MOS integrated circuit chips. They are widely used in audio signal processing, telecommunications, , radar, sonar and speech recognition systems, and in common consumer electronic devices such as mobile phones, disk drives and high-definition television (HDTV) products. The goal of a DSP is usually to measure, filter or compress continuous real-world analog signals.
Language modelA language model is a probabilistic model of a natural language that can generate probabilities of a series of words, based on text corpora in one or multiple languages it was trained on. Large language models, as their most advanced form, are a combination of feedforward neural networks and transformers. They have superseded recurrent neural network-based models, which had previously superseded the pure statistical models, such as word n-gram language model.
Transformer (machine learning model)A transformer is a deep learning architecture that relies on the parallel multi-head attention mechanism. The modern transformer was proposed in the 2017 paper titled 'Attention Is All You Need' by Ashish Vaswani et al., Google Brain team. It is notable for requiring less training time than previous recurrent neural architectures, such as long short-term memory (LSTM), and its later variation has been prevalently adopted for training large language models on large (language) datasets, such as the Wikipedia corpus and Common Crawl, by virtue of the parallelized processing of input sequence.
Floating-point arithmeticIn computing, floating-point arithmetic (FP) is arithmetic that represents subsets of real numbers using an integer with a fixed precision, called the significand, scaled by an integer exponent of a fixed base. Numbers of this form are called floating-point numbers. For example, 12.345 is a floating-point number in base ten with five digits of precision: However, unlike 12.345, 12.3456 is not a floating-point number in base ten with five digits of precision—it needs six digits of precision; the nearest floating-point number with only five digits is 12.
Transistor countThe transistor count is the number of transistors in an electronic device (typically on a single substrate or "chip"). It is the most common measure of integrated circuit complexity (although the majority of transistors in modern microprocessors are contained in the cache memories, which consist mostly of the same memory cell circuits replicated many times). The rate at which MOS transistor counts have increased generally follows Moore's law, which observed that the transistor count doubles approximately every two years.
3DNow!3DNow! is a deprecated extension to the x86 instruction set developed by Advanced Micro Devices (AMD). It adds single instruction multiple data (SIMD) instructions to the base x86 instruction set, enabling it to perform vector processing of floating-point vector operations using vector registers, which improves the performance of many graphics-intensive applications. The first microprocessor to implement 3DNow! was the AMD K6-2, which was introduced in 1998. When the application was appropriate, this raised the speed by about 2–4 times.
