 | |
| Type | Private |
|---|---|
| Industry | Semiconductors |
| Founded | 2016 |
| Founders |
|
| Headquarters | , |
Key people |
|
| Products | IPU, Poplar |
| Revenue | US$2.7 million (2022) [1] |
| US$−205 million (2022) [1] | |
Number of employees | 494 (2023) [1] |
| Website | www |
Graphcore Limited is a British semiconductor company that develops accelerators for AI and machine learning. It has introduced a massively parallel Intelligence Processing Unit (IPU) that holds the complete machine learning model inside the processor. [2]
Graphcore was founded in 2016 by Simon Knowles and Nigel Toon. [3]
In the autumn of 2016, Graphcore secured a first funding round led by Robert Bosch Venture Capital. Other backers include Samsung, Amadeus Capital Partners, C4 Ventures, Draper Esprit, Foundation Capital, and Pitango. [4] [5]
In July 2017, Graphcore secured a round B funding led by Atomico, [6] which was followed a few months later by $50 million in funding from Sequoia Capital. [7]
In December 2018, Graphcore closed its series D with $200 million raised at a $1.7 billion valuation, making the company a unicorn. Investors included Microsoft, Samsung and Dell Technologies. [8]
On 13 November 2019, Graphcore announced that their Graphcore C2 IPUs are available for preview on Microsoft Azure. [9]
Meta Platforms acquired the AI networking technology team from Graphcore in early 2023. [10]
In 2016, Graphcore announced the world's first graph tool chain designed for machine intelligence called Poplar Software Stack. [11] [12] [13]
In July 2017, Graphcore announced their first chip, called the Colossus GC2, a "16 nm massively parallel, mixed-precision floating point processor", first available in 2018. [14] [15] Packaged with two chips on a single PCI Express card called the Graphcore C2 IPU (an Intelligence Processing Unit), it is stated to perform the same role as a GPU in conjunction with standard machine learning frameworks such as TensorFlow. [14] The device relies on scratchpad memory for its performance rather than traditional cache hierarchies. [16]
In July 2020, Graphcore presented their second generation processor called GC200 built in TSMC's 7nm FinFET manufacturing process. GC200 is a 59 billion transistor, 823 square-millimeter integrated circuit with 1,472 computational cores and 900 Mbyte of local memories. [17] In 2022, Graphcore and TSMC presented the Bow IPU, a 3D package of a GC200 die bonded face to face to a power-delivery die that allows for higher clock rate at lower core voltage. [18] Graphcore aims at a Good machine, named after I.J. Good, enabling AI models with more parameters than the human brain has synapses. [18]
| Release date | Product | Process node | Cores | Threads | Transistors | teraFLOPS (FP16) |
|---|---|---|---|---|---|---|
| July 2017 | Colossus™ MK1 - GC2 IPU | 16 nm TSMC | 1216 | 7296 | ? | ~100-125 [19] |
| July 2020 | Colossus™ MK2 - GC200 IPU | 7 nm TSMC | 1472 | 8832 | 59 billion | ~250-280 [20] |
| Colossus™ MK3 | ~500 [21] |
Both the older and newer chips can use 6 threads per tile (for a total of 7,296 and 8,832 threads, respectively) "MIMD (Multiple Instruction, Multiple Data) parallelism and has distributed, local memory as its only form of memory on the device" (except for registers). The older GC2 chip has 256 KiB per tile while the newer GC200 chip has about 630 KiB per tile that are arranged into islands (4 tiles per island), [22] that are arranged into columns, and latency is best within tile. The IPU uses IEEE FP16, with stochastic rounding, and also single-precision FP32, at lower performance. [23] Code and data executed locally must fit in a tile, but with message-passing, all on-chip or off-chip memory can be used, and software for AI makes it transparently possible, e.g. has PyTorch support.
IPU may refer to:
Xilinx, Inc. was an American technology and semiconductor company that primarily supplied programmable logic devices. The company is known for inventing the first commercially viable field-programmable gate array (FPGA) and creating the first fabless manufacturing model.
The transistor count is the number of transistors in an electronic device. It is the most common measure of integrated circuit complexity. The rate at which MOS transistor counts have increased generally follows Moore's law, which observes that transistor count doubles approximately every two years. However, being directly proportional to the area of a chip, transistor count does not represent how advanced the corresponding manufacturing technology is: a better indication of this is transistor density.
The 22 nm node is the process step following 32 nm in CMOS MOSFET semiconductor device fabrication. The typical half-pitch for a memory cell using the process is around 22 nm. It was first demonstrated by semiconductor companies for use in RAM memory in 2008. In 2010, Toshiba began shipping 24 nm flash memory chips, and Samsung Electronics began mass-producing 20 nm flash memory chips. The first consumer-level CPU deliveries using a 22 nm process started in April 2012 with the Intel Ivy Bridge processors.
CUDA is a proprietary and closed source parallel computing platform and application programming interface (API) that allows software to use certain types of graphics processing units (GPUs) for general purpose processing, an approach called general-purpose computing on GPUs (GPGPU). CUDA is a software layer that gives direct access to the GPU's virtual instruction set and parallel computational elements, for the execution of compute kernels.
The 14 nm process refers to the MOSFET technology node that is the successor to the 22 nm node. The 14 nm was so named by the International Technology Roadmap for Semiconductors (ITRS). Until about 2011, the node following 22 nm was expected to be 16 nm. All 14 nm nodes use FinFET technology, a type of multi-gate MOSFET technology that is a non-planar evolution of planar silicon CMOS technology.
Achronix Semiconductor Corporation is an American fabless semiconductor company based in Santa Clara, California with an additional R&D facility in Bangalore, India, and an additional sales office in Shenzhen, China. Achronix is a diversified fabless semiconductor company that sells FPGA products, embedded FPGA (eFPGA) products, system-level products and supporting design tools. Achronix was founded in 2004 in Ithaca, New York based on technology licensed from Cornell University. In 2006, Achronix moved its headquarters to Silicon Valley.
Volta is the codename, but not the trademark, for a GPU microarchitecture developed by Nvidia, succeeding Pascal. It was first announced on a roadmap in March 2013, although the first product was not announced until May 2017. The architecture is named after 18th–19th century Italian chemist and physicist Alessandro Volta. It was NVIDIA's first chip to feature Tensor Cores, specially designed cores that have superior deep learning performance over regular CUDA cores. The architecture is produced with TSMC's 12 nm FinFET process. The Ampere microarchitecture is the successor to Volta.
Annapurna Labs is an Israeli microelectronics company. Since January 2015 it has been a wholly-owned subsidiary of Amazon.com. Amazon reportedly acquired the company for its Amazon Web Services division for US$350–370M.
A vision processing unit (VPU) is an emerging class of microprocessor; it is a specific type of AI accelerator, designed to accelerate machine vision tasks.
Tensor Processing Unit (TPU) is an AI accelerator application-specific integrated circuit (ASIC) developed by Google for neural network machine learning, 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.
AMD Instinct is AMD's brand of professional GPUs. It replaced AMD's FirePro S brand in 2016. Compared to the Radeon brand of mainstream consumer/gamer products, the Instinct product line is intended to accelerate deep learning, artificial neural network, and high-performance computing/GPGPU applications.
SiFive, Inc. is a fabless semiconductor company and provider of commercial RISC-V processor IP and silicon chips based on the RISC-V instruction set architecture (ISA). SiFive's products include cores, SoCs, IPs, and development boards.
The Apple A11 Bionic is a 64-bit ARM-based system on a chip (SoC), designed by Apple Inc. and manufactured by TSMC. It first appeared in the iPhone 8 and 8 Plus, and iPhone X which were introduced on September 12, 2017. Apple states that the two high-performance cores are 25% faster than the Apple A10's and the four high-efficiency cores are up to 70% faster than the two corresponding cores in the A10. The A11 Bionic chip was discontinued on April 15, 2020, following the discontinuation of the iPhone 8 and 8 Plus. The latest software update for the iPhone 8 & 8 Plus and iPhone X using this chip was iOS 16.7, released on September 21, 2023.
The Pixel Visual Core (PVC) is a series of ARM-based system in package (SiP) image processors designed by Google. The PVC is a fully programmable image, vision and AI multi-core domain-specific architecture (DSA) for mobile devices and in future for IoT. It first appeared in the Google Pixel 2 and 2 XL which were introduced on October 19, 2017. It has also appeared in the Google Pixel 3 and 3 XL. Starting with the Pixel 4, this chip was replaced with the Pixel Neural Core.
In semiconductor manufacturing, the 3 nm process is the next die shrink after the 5 nanometer MOSFET technology node. South Korean chipmaker Samsung started shipping its 3 nm gate all around (GAA) process, named 3GAA, in mid-2022. On 29 December 2022, Taiwanese chip manufacturer TSMC announced that volume production using its 3 nm semiconductor node termed N3 is under way with good yields. An enhanced 3 nm chip process called N3E may have started production in 2023. American manufacturer Intel planned to start 3 nm production in 2023.
Ampere Computing LLC is an American fabless semiconductor company based in Santa Clara, California that develops processes for servers operating in large scale environments. Ampere also has offices in: Portland, Oregon; Taipei, Taiwan; Raleigh, North Carolina; Bangalore, India; Warsaw, Poland; and Ho Chi Minh City, Vietnam.
Cerebras Systems is an American artificial intelligence company with offices in Sunnyvale and San Diego, Toronto, Tokyo and Bangalore, India. Cerebras builds computer systems for complex artificial intelligence deep learning applications.
Meta AI is an artificial intelligence laboratory that belongs to Meta Platforms Inc. Meta AI intends to develop various forms of artificial intelligence, improving augmented and artificial reality technologies. Meta AI is an academic research laboratory focused on generating knowledge for the AI community. This is in contrast to Facebook's Applied Machine Learning (AML) team, which focuses on practical applications of its products.
Shanghai Biren Intelligent Technology Co. is a Chinese fabless semiconductor design company. The company was founded in 2019 by Lingjie Xu and others, all of whom were previously employed at NVIDIA or Alibaba. Biren has advertised two general-purpose graphics processing units (GPGPUs), the BR100 and BR104. Both cards are aimed at artificial intelligence and high-performance computing.
