Tag Archives: Intel

HiFive Unleashed – The First RISC-V-based Linux development board

RISC-V is an open specification of an Instruction Set Architecture (ISA). That is, it describes the way in which software talks to an underlying processor – just like the x86 ISA for Intel/AMD processors and the ARM ISA for ARM processors. Unlike those, however, the RISC-V ISA is open so that anyone can build a processor that supports it. Just as Linux revolutionize the software world, RISC-V could create a substantial impact on the hardware world. This open-source chip project is might just go out to break the dominance of proprietary chips offered by Intel, AMD, and ARM.

hifive-unleashed-board
Hi-Five Unleashed-board

Silicon Valley-based company SiFive has released the world first RISC-V based Linux development board called Hi-Five Unleashed. SiFive which has previously released the HiFive1, a RISC-V-based, Open-Source, Arduino-Compatible Development Kit. The HiFive Unleashed is powerful enough to run Linux distributions.

HiFive Unleased Block Diagram

Hi-Five Unleashed was designed around the RISC-V based, quad-core, 1.5GHz U540 SoC (Freedom U540). The Freedom U540 is the first multi-core SoC featuring the open source RISC-V ISA with 4x 1.5GHz “U54” cores and a management core, fabricated with TSMC’s 28nm HPC process, and also the first to offer cache coherence. The U54-MC Core’s high-performance and flexible memory system make it ideal for applications such as AI, machine learning, networking, gateways, and smart IoT devices. It has no GPUs or other coprocessors, but the open source hardware design is intended to encourage third parties to collaborate to develop one.

The Hi-Five Unleashed is a minimalist board that uses one Freedom U540 paired with 8GB DDR4 ECC RAM, as well as 32MB Quad SPI Flash, a microSD card slot for external storage, a Gigabit Ethernet port, and an FMC connector for future expansion cards. The development board is still barebone for now and mostly intended for developers and not the general public; it lacks hobbyist helpful resources like a video output and USB support, none of those are available on the board.

The following are some of the HiFive Unleashed specifications:

  • SoC – SiFive Freedom U540 with 4x U54 RV64GC application cores @ up to 1.5GHz with Sv39 virtual memory support
    • 1x E51 RV64IMAC Management Core
    • 2 MB L2 cache
    • 28 nm TSMC process
  • System Memory – 8GB DDR4 with ECC
  • Storage –  32MB Quad SPI Flash from ISSI
    • MicroSD card for removable storage
  • Connectivity – Gigabit Ethernet port
  • Debugging – Micro USB port connector to FTDI chip
  • Expansion – FMC Connector for future add-in cards
  • Misc – On-off switch, various configuration jumpers
  • Power Supply – 12V DC input

The board is currently available for order at Crowd Supply for $999 and is expected to ship on June 30th. An earlier access board goes for $1250, which will ship on March 31st. RISC-V has grown from an academic project which first started in 2006 at UC Berkely, and now to a welcome, acceptable alternative to existing ISA and a potential game-changer in the long run.

In the future, we are not only going to build powerful open source based system but also understand their internal working and avoid something like the Spectre and Meltdown bugs that affected the likes of Intel processor.

New Powerful Nano-ITX Form Factor ADL120S Single Board Computer For IoT

USA based ADL Embedded Solutions has introduced a new rugged, Nano-ITX form factor ADL120S single board computer (SBC). It is mainly produced for IoT, networking, and cyber-security applications. The highlighted feature of this SBC is its wide variety of PCIe expansion slots. The SBC includes 8x stackable PCIe interfaces, as well as optional custom expansion board services. Also, you get dual M/2 Key-B 2280 interfaces that support PCIe/SATA with USB 3.0. Networking is taken care with 4x Gigabit Ethernet ports (1x with PXE boot and WoL).

ADL120S Single Board Computer by ADL Embedded Solutions

 

The ADL120S runs Linux or Windows OS on dual- or quad-core Intel 6th Gen (“Skylake“) processor and Celeron CPUs that support an LGA1151 socket. There’s an Intel Q170 chipset on ADL120S instead of a Q170HDS. The supported SKUs include the quad-core 2.4GHz Core i7-6700TE, the dual-core 2.7GHz i3-6100TE, and 2.3GHz Celeron G3900TE.

The board has a compact dimension of 120 x 120mm in a Nano-ITX form factor but has a high vertical profile with 4x USB 3.0 ports piled on a single column. This high-rise board also includes 4x GbE ports, one of which has WoL and PXE Boot, and a pair of DisplayPort 1.2 ports with 4096 x 2304 resolution at 60Hz refresh rate.

The ADL120S comes with up to 32GB DDR4 RAM and offers a wide-range 20-30VDC (optional 12-24V or 20-36V) input and RTC (Real time clock) with battery. The boards with -20 to 70°C or -40 to 85°C temperature range of usability are available.

The SBC is also praised for its high MTBF, long-life availability, hardware and firmware revision control, obsolescence management, and technical, engineering and design support, on their website’s product page.

No pricing or availability information was provided for the ADL120S.

The ezPixel is an Upcoming FPGA based WS2812B Controller Board

FPGAs are field programmable gate arrays which basically means they are reconfigurable hardware chips. FPGAs have found applications in different industries and engineering fields from the defence, telecommunications to automotive and several others but little application in the maker’s world. Mostly, as a result of being largely difficult and high cost as compared to the likes of Arduino, but the introduction of the ezPixel and other similar FPGA boards is making this a possibility.

Prototype modules.

The ezPixel board, by Thomas Burke of MakerLogic, is a small size FPGA based circuit board that can be used to drive up to 32 strings of WS2812Bs, for up to 9,216 LEDs in total, a very first of its kind. These WS2812B programmable color LEDs have been a phenomenon in the maker’s world, being used in various Led Lights and creating of various Light Artworks. These popular LEDs comes in strings that can be cut to any length, and only require a single wire serial data connection to control all the lights in the string individually, and multiple strings can be stacked together to create large two-dimensional displays.

ezPixel description.

Most WS2812B controller boards can be used to control up to hundreds of these LEDs, but not thousands of them. The ezPixel board is a perfect fit for applications that use thousands of these LEDs. The ezPixel board is powered by the Intel MAX FPGA, a single chip small form factor programmable logic device with full-featured FPGA capabilities, and it’s designed to interface with other Micro-controllers or any SPI/UART host device. The ezPixel board serves as bridge between microcontrollers and long WS2812B strings. A user sets the length of each string using simple commands that are sent via the SPI or USB/UART communication link.

The following below are the features of the ezPixel:

  • WS2812B Smart Pixel Controller.
  • Up to 32 Strings can be controlled independently.
  • Up to 9216 LEDs can be controlled.
  • Communication:
    • USB/UART Interface.
    • SPI Interface.
  • Read/Write Pixel Memory.
  • FPGA – Intel MAX10M08 FPGA.
  • Dimension:
    • 1” x 3” (25mm x 76mm).
  • SPI Flash.

The ezPixel can run as a standalone display controller as a result of its serial flash memory chip, and this board is slated for a crowdfunding campaign in early 2018.

LattePanda – Hackable Single Board Computer runs Win 10

LattePanda, has announced the launch of its next-gen LattePanda, LattePanda Delta, what the company claims to be the first hackable computer pre-installed Windows 10 and compatible with Linux. It offers onboard Intel 7th Gen Dual-core, Four-Thread processor, and the general performance is four times higher than the first generation. Additional it integrates an Arduino Compatible coprocessor to support the access of thousands of sensors and controllers. The project is live on kickstarter and has 59 days to go.

This is why we redesigned the LattePanda – to make it even easier for these talented and eager individuals to have a tool that can power nearly anything they want to build, whether a video game console, a 4K movie player, an in-home fire sensor, or even a digital instrument.

Key specifications:

  • Windows 10 Pro preinstalled, support Linux
  • CPU Up to Intel Core 7th generation M3-7Y30, 2.6Ghz
  • Up to 8GB dual-channel RAM
  • Compatibility with NVMe SSDs
  • Gigabit Ethernet, Wake on lan enable
  • Intel Dual Band Wireless-AC 3165, support 2.4G/5G WiFi, support Bluetooth V4.2
  • Software that includes AI and IoT developer kits, allowing students to explore these advanced technologies in an easy, user-friendly way
  • Hardware to support creations that leverage Artificial Intelligence (AI), Augmented Reality (AR), Virtual Reality (VR) and Machine Learning (ML)
  • Arduino-enabled, support all of arduino IDE and software library, compatible with Arduino sensor and Actuator.

Intel Introduces Loihi – A Self Learning Processor That Mimics Brain Functions

Intel has developed a first-of-its-kind self-learning neuromorphic chip – codenamed Loihi. It mimics the animal brain functions by learning to operate based on various modes of feedback from the environment. Unlike convolutional neural network (CNN) and other deep learning processors, Intel’s Loihi uses an asynchronous spiking model to mimic neuron and synapse behavior in a much closer analog to animal brain behavior.

loihi - Intel's self-learning chip
Loihi – Intel’s self-learning chip

Machine learning models based on CNN use large training sets to set up recognition of objects and events. This extremely energy-efficient chip, which uses the data to learn and make inferences, gets smarter over time and does not need to be trained in the traditional way. The Loihi chip includes digital circuits that mimic the brain’s basic mechanics, making machine learning faster and more efficient while requiring much lower computing power.

The chip offers highly flexible on-chip learning and combines training and inference on a single chip. This allows machines to be autonomous and to adapt in real time instead of waiting for the next update from the cloud. Compared to convolutional neural networks and deep learning neural networks, the Loihi test chip uses many fewer resources on the same task. Researchers have demonstrated learning at a rate that is a 1 million times improvement compared with other typical neural network devices.

The self-learning capabilities prototyped by this test chip have huge potential to improve automotive and industrial applications as well as personal robotics – any application that would benefit from the autonomous operation and continuous learning in an unstructured environment. For example, recognizing the movement of a car or bike for an autonomous vehicle. More importantly, it is up to 1,000 times more energy-efficient than general purpose computing.

Features

  • Fully asynchronous neuromorphic many core mesh.
  • Each neuron capable of communicating with thousands of other neurons.
  • Each neuromorphic core includes a learning engine that can be programmed to adapt network parameters during operation.
  • Fabrication on Intel’s 14 nm process technology.
  • A total of 130,000 neurons and 130 million synapses.
  • Development and testing of several algorithms with high algorithmic efficiency for problems including path planning, constraint satisfaction, sparse coding, dictionary learning, and dynamic pattern learning and adaptation.

Overclocked Intel CPU draws 1kW

by Thomas Scherer @ elektormagazine.com

The impressively powerful i9-7980XE CPU from Intel boasts not just 18 cores and 36 threads but also an unlocked clock multiplier. The spec was clearly an open invitation to Roman Hartung who has something of a reputation when it comes to overclocking processors. In tests he was able to crank up the clock of this beast to 5.7 GHz at which point the CPU draws around 1kW of power.

Overclocked Intel CPU draws 1kW – [Link]

Inside Intel’s first product: the 3101 RAM chip held just 64 bits

Ken Shirriff takes a look inside the 3110 RAM chip from Intel. He writes:

Intel’s first product was not a processor, but a memory chip: the 31011 RAM chip, released in April 1969. This chip held just 64 bits of data (equivalent to 8 letters or 16 digits) and had the steep price tag of $99.50. The chip’s capacity was way too small to replace core memory, the dominant storage technology at the time, which stored bits in tiny magnetized ferrite cores. However, the 3101 performed at high speed due to its special Schottky transistors, making it useful in minicomputers where CPU registers required fast storage. The overthrow of core memory would require a different technology—MOS DRAM chips—and the 3101 remained in use in the 1980s.3

Inside Intel’s first product: the 3101 RAM chip held just 64 bits – [Link]

Intel Optane, Intel’s Next-Generation SSD Technology

In July 2015, Intel and Micron Technology announced a new technology for memory and storage solutions called “3D XPoint™ technology“. It is a new category of nonvolatile memory that addresses the need for high-performance, high-endurance, and high-capacity memory and storage.

Now Intel had produced its Optane™ technology that provides an unparalleled combination of high throughput, low latency, high quality of service, and high endurance. The new technology is a special combination of 3D XPoint™ memory media, Intel Memory and Storage Controllers, Intel Interconnect IP and Intel® software.

From system acceleration and fast caching to storage and memory expansion, Intel Optane delivers a revolutionary leap forward in decreasing latency and accelerating systems for workloads demanding large capacity and fast storage.

3D-Xpoint memory structure, Source: Intel Corp

The first product with this technology is the Intel Optane SSD DC P4800X. It is a 375GB add-in card that communicates via NVMe over a four-lane PCIe 3.0 link, and it is available for $1,520 or $4.05 per GB.

Optane™ storage could be used in many sectors and domains. It will help healthcare researchers to work with larger data sets in real-time, financial institutions to speed trading, and retailers to identify fraud detection patterns more quickly. Optane™ technology can also be used at home to optimize personal computer for immersive gaming experience.

The 3D XPoint innovative, transistor-less cross point architecture creates a three-dimensional checkerboard where memory cells sit at the intersection of words lines and bit lines, allowing the cells to be addressed individually. As a result, data can be written and read in small sizes, leading to fast and efficient read/write processes.

Memory cells are written or read by varying the amount of voltage sent to each selector. This eliminates the need for transistors, increasing capacity and reducing cost. The initial technology stores 128Gb per die across two stacked memory layers. Future generations of this technology can increase the number of memory layers and/or use traditional lithographic pitch scaling to increase die capacity.

3D XPoint Technology Wafer

You can get more detailed information about 3D Xpoint and Intel Optane technologies through their official websites. You can also take a look at these two Intel P4800X reviews; Billy Tallis fromAnandTech and Paul Alcorn from Tom’s Hardware.

tinyTILE, An Intel Development Board Based on Intel Curie Module

In the past year, Intel announced the low power development board “tinyTILE” which was built based on Intel Curie Module, offering quick and easy identification of actions and motions, features needed by always-on applications.

tinyTile was designed for use in wearable devices and rapid prototyping. It is a 35 x 26 mm board and has an Intel Curie Module on the top and a flat reverse side. There are 20 general purpose I/O pins (four of them are PWM output pins) operate at 3.3V with a maximum of 20 mA current.

The Intel Curie Module is a low-power compute module featuring the low-power 32-bit Intel Quark microcontroller with 384kB flash memory and 80kB SRAM, low-power integrated DSP sensor hub and pattern matching technology, Bluetooth® Low Energy (BLE), and 6-axis combo sensor with accelerometer and gyroscope.

Intel Curie Module Block Diagram

Features of the tinyTILE include:

  • Intel® Curie™ module dual-core (Intel® Quark* processor core and ARC* core)
  • Bluetooth® low energy, 6-axis combo sensor and pattern matching engine
  • 14 digital input/output pins (four can be used as PWM output pins)
  • Four PWM output pins
  • Six analog input pins
  • Strictly 3.3 V I/Os only
  • 20 mA DC current per I/O pin
  • 196 kB Flash memory
  • 24 kB SRAM
  • 32 MHz clock speed
  • USB connector for serial communication and firmware updates (DFU protocol)
  • 35 mm length and 26 mm width

tinyTILE can be powered using the USB connection or by an external battery, and it is compatible with three development environments:

The board is available for around $40 on element14. All related documents, specifications, BOM, BSP and other needed information are available at the official page.

You can view this project that invades your dog’s privacy with impressive ease while you’re at work!

Analyzing the vintage 8008 processor from die photos

Ken Shirriff writes:

The revolutionary Intel 8008 microprocessor is 45 years old today (March 13, 2017), so I figured it’s time for a blog post on reverse-engineering its internal circuits. One of the interesting things about old computers is how they implemented things in unexpected ways, and the 8008 is no exception. Compared to modern architectures, one unusual feature of the 8008 is it had an on-chip stack for subroutine calls, rather than storing the stack in RAM. And instead of using normal binary counters for the stack, the 8008 saved a few gates by using shift-register counters that generated pseudo-random values. In this article, I reverse-engineer these circuits from die photos and explain how they work.

Analyzing the vintage 8008 processor from die photos – [Link]