DSP, Micros & Memory


1000-core processor developed

13 July 2016 DSP, Micros & Memory Computer/Embedded Technology

A microchip containing 1000 independent programmable processors has been designed by a team at the University of California, Davis’ department of electrical and computer engineering. The energy-efficient ‘KiloCore’ chip has a maximum computation rate of 1,78 trillion instructions per second and contains 621 million transistors.

“To the best of our knowledge, it is the world’s first 1000-processor chip and it is the highest clock-rate processor ever designed in a university,” said Bevan Baas, professor of electrical and computer engineering, who led the team that designed the chip architecture. While other multiple-processor chips have been created, none exceed about 300 processors, according to an analysis by Baas’ team. Most were created for research purposes and few are sold commercially. The KiloCore chip was fabricated by IBM using its 32 nm CMOS technology.

Each processor core can run its own small program independently of the others, which is a fundamentally more flexible approach than so-called ‘single-instruction-multiple-data’ approaches utilised by processors such as GPUs (graphics processing units). The idea is to break an application up into many small pieces, each of which can run in parallel on different processors, enabling high throughput with lower energy use, Baas said.

Because each processor is independently clocked, it can shut itself down to further save energy when not needed, said graduate student Brent Bohnenstiehl, who developed the principal architecture. Cores operate at an average maximum clock frequency of 1,78 GHz, and they transfer data directly to each other rather than using a pooled memory area that can become a bottleneck for data.

The chip is the most energy-efficient ‘many-core’ processor ever reported, Baas said. For example, the 1000 processors can execute 115 billion instructions per second while dissipating only 0,7 Watts, low enough to be powered by a single AA battery. The KiloCore chip executes instructions more than 100 times more efficiently than a modern laptop processor.

Applications already developed for the chip include wireless coding/decoding, video processing, encryption, and others involving large amounts of parallel data such as scientific data applications and data centre record processing. The team has completed a compiler and automatic program mapping tools for use in programming the chip.





Share this article:
Share via emailShare via LinkedInPrint this page

Further reading:

KIOXIA pioneer new 3D Flash technology
EBV Electrolink DSP, Micros & Memory
KIOXIA Corporation and Sandisk Corporation have pioneered a state-of-the-art 3D flash memory technology, setting the industry benchmark with a 4,8 Gb/s NAND interface speed, superior power efficiency, and heightened density.

Read more...
Artificial intelligence meets embedded development
Avnet Silica DSP, Micros & Memory
Microchip Technology is leveraging the power of artificial intelligence (AI) to assist software developers and embedded engineers in writing and debugging code with the launch of its MPLAB AI Coding Assistant.

Read more...
Embedded module for AI vision applications
Rugged Interconnect Technologies DSP, Micros & Memory
The TQMa95xxSA supports AI/ML with vision applications through an integrated NPU and an image processor unit.

Read more...
High-speed Flash for SoC applications
NuVision Electronics DSP, Micros & Memory
GigaDevice has unveiled the GD25NE series of dual-power supply SPI NOR Flash chips, designed specifically for 1,2 V system-on-chip (SoC) applications.

Read more...
Super-fast H.264 encoder FPGA core
EBV Electrolink DSP, Micros & Memory
An ITAR-compliant H.264 core designed for AMD FPGAs provides baseline H.264 support and is currently the smallest and fastest FPGA core in the industry.

Read more...
ST MCUs extend ultra-low power innovation
Altron Arrow DSP, Micros & Memory
STMicroelectronics has introduced new STM32U3 microcontrollers with cutting-edge power-saving innovations that ease deployment of smart connected tech, especially in remote locations.

Read more...
Chipset enables ultra-wide signal capture
RFiber Solutions DSP, Micros & Memory
Jariet Technologies has developed Electra, a chipset that enables ultra-wide, multi-function and multi-band signal capture and generation from a single component.

Read more...
SoC for real-time AI at the edge
Future Electronics DSP, Micros & Memory
Ambiq’s Apollo330 Plus series is purpose-built to enable always-on and real-time AI inferencing on devices.

Read more...
Evaluation kit for ML applications
Future Electronics DSP, Micros & Memory
The hardware kit includes radar, acoustic, pressure and motion sensors and integrates dual Arm Cortex-M4 and Cortex-M0+ CPU cores.

Read more...
Microprocessors with advanced graphics and connectivity
Avnet Silica DSP, Micros & Memory
Microchip’s SAMA7D65 MPU runs a 1 GHz Arm Cortex-A7 core and integrates MIPI DSI, LVDS display interfaces and 2D GPU for HMI applications.

Read more...