Microprocessor Report Subscribe

Current Articles

October 15, 2018

  • Turing T4 Targets AI Inference
    Nvidia’s new Turing architecture boosts AI inferencing performance by adding integer capability to its tensor cores. The Tesla T4 accelerator brings Turing to data centers as a 70W PCIe card.
  • Cadence Mutates Its DNA to Boost AI
    Cadence’s new DNA 100 IP core integrates a sparse-compute engine that supports applications ranging from low-power IoT devices to high-performance video surveillance and autonomous vehicles.
  • Titan IC Floats 100Gbps Reg-Ex Engine
    The company’s RXP core delivers leading regular-expression-search throughput for SoC designs and FPGAs. The primary application is in network-security appliances such as intrusion-detection systems and next-generation firewalls.

October 8, 2018

  • Turing Accelerates Ray Tracing
    An upgrade to the two-year-old Pascal, Nvidia’s new Turing architecture delivers a big performance boost, AI-enhanced imaging, and real-time ray tracing for PC and professional graphics.
  • Xilinx Versal Surpasses UltraScale+
    Scheduled to sample in mid-2019, Versal chips will combine Arm Cortex-A72 CPUs and new AI Engines with field-programmable logic, redefining FPGAs as full-fledged SoCs.

October 1, 2018

  • NRAM Brings Nanotubes to Silicon
    NRAM uses carbon nanotubes (CNTs) in silicon to offer DRAM-like performance and density with nearly unlimited endurance and retention. Products could reach production in 2020.
  • NetSpeed Disappears Into Intel
    Network-on-a-chip (NoC) vendor NetSpeed Systems is now part of Intel, giving it a good exit but leaving its customers without a roadmap and consolidating the NoC market.
  • Marvell Reveals Post-Cavium Roadmap
    As Marvell works to integrate its Cavium acquisition, it’s paring unneeded and overlapping product lines. The changes affect both Cavium and Marvell roadmaps.

September 24, 2018

  • CPU Performance for the Next Decade
    A comprehensive analysis of a decade’s worth of processor data reveals the approaches that have enabled CPU and GPU performance to double every two years and how they will change over time.
  • Fujitsu Raises Arm Over SPARC
    Fujitsu’s Post-K exascale supercomputer will bring Arm into the HPC world with its new 52-core A64FX, an extreme processor for an extreme machine.
  • Editorial: Intel Customizes Cloud Chips
    More than half of Intel’s cloud shipments are custom models that add or delete features from standard products. This approach satisfies customer needs while giving Intel pricing flexibility.
  • Marvell Connects SSDs to Ethernet
    Marvell is sampling the 88SN2400, a unique controller chip that connects an SSD to Ethernet, enabling a new storage-array architecture based on Ethernet instead of PCI Express.

September 17, 2018

  • Graphcore Makes Big AI Splash
    One of the best-funded AI startups is sampling its first product, an accelerator chip that packs 1,216 independent CPUs and matches the performance of Nvidia’s V100 at half the power.
  • DeePhi Accelerates Xilinx AI Strategy
    Xilinx recently acquired DeePhi, a developer of FPGA-based accelerators for computer vision and speech recognition, to add to its large library of reference designs that it can offer to its FPGA customers.
  • Broadcom First With 200Gbps NIC
    Broadcom is first to sample Ethernet adapters for new 50Gbps-per-lane standards, including 50GbE and 200GbE. The NICs use the new Thor controller chip, the company’s third-generation NetXtreme-E design.
  • Wear 3100 Boosts Smartwatch Life
    Qualcomm has added a real-time controller to its next-generation smartwatch platform, creating a big-small-tiny architecture that extends battery life for Wear OS watches.

September 10, 2018

  • Xilinx Everest Outclimbs FPGAs
    Xilinx is pitching its next-generation Everest devices as SoCs with programmable logic, not as traditional FPGAs. They’ll have ARM cores, new programmable engines, and PCI Express Gen4.
  • 5G Raises Handset-RF Complexity
    RF architectures will diverge between the new 3.5GHz and millimeter-wave bands being allocated for 5G New Radio. RF-module vendors are slowly disclosing their plans.

September 3, 2018

  • Cascade Lake Speeds Deep Learning
    Intel’s next-generation Xeon refreshes the Purley platform, adding instruction extensions for neural networks as well as support for Optane DC persistent memory.
  • Intel Pours Whiskey Lake for Laptops
    The new Whiskey Lake (U-series) and Amber Lake (Y-series) processors bring greater CPU speeds and the Cannon Point south bridge to premium thin-and-light and 2-in-1 PCs.
  • AlphaICs Employs AI Special Agents
    This small startup, fronted by “The Father of Pentium,” has developed what it calls the Real AI Processor, which employs an array of special-purpose compute “agents” to power autonomous systems.

August 27, 2018

  • Mythic Multiplies in a Flash
    Mythic is an AI-processor startup that uses embedded flash memory to store neural-network weights as analog parameters. The technique can store a complete network on-chip.
  • Threadripper 2 Grows to 32 Cores
    AMD’s second-generation Ryzen Threadripper chips offer more CPUs than Intel’s best competing products at any price. The 32-core model is the most powerful PC processor available.
  • Broadcom, Mellanox Target NVMe-oF
    Broadcom and Mellanox announced storage-controller cards for flash arrays that support the RoCE flavor of NVMe-oF. These cards employ Stingray and BlueField SoCs, respectively.
  • Snapdragon 670 Extends Midrange
    Qualcomm’s newest smartphone processor brings Cortex-A75, 10nm technology, and better AI acceleration to a new low price, strengthening the company in the mid-premium segment.

August 20, 2018

  • Samsung M3 Flexes Arm Muscles
    Samsung’s third-generation mobile CPU nearly doubles performance using a massive microarchitecture that challenges Intel’s Skylake in complexity and throughput.
  • Alibaba Looks to C-Sky for CPU IP
    Chinese vendor C-Sky has been quietly designing 32-bit embedded CPUs since its founding in 2001, compiling a customer list that includes 70 licensees. Among them is its new parent, Alibaba.

August 13, 2018

  • Intel to Offer Structured ASICs
    Intel’s FPGA group (formerly Altera) has acquired eASIC, a small vendor of structured ASICs, to expand its portfolio and offer its customers a path to “harden” their FPGA designs.
  • IBM Trains in Analog to Save AI Power
    IBM is using phase-change memories to build analog neural networks. The architecture enables area- and power-efficient in-memory computing, which is suitable for training as well as low-power inference engines. 
  • Microchip Debuts Dual-Core DSC
    The dsPIC33CH combines the functions of a 16-bit microcontroller and digital signal controller (DSC). This dual-core design competes with 32-bit DSCs that use Arm’s Cortex-M4F CPU.

August 6, 2018

  • Foundries Head to 5nm and Beyond
    Even as the first 7nm chips reach production, TSMC and Samsung have a roadmap to 3nm that includes EUV, new materials such as cobalt, and gate-all-around (GAA) transistors.
  • Helio A-Series Targets Low End
    The Helio brand started as MediaTek’s premium smartphone-processor line, but with the introduction of the Helio A22, it now covers all price tiers. This new chip runs four Cortex-A53 CPUs at up to 2.0GHz.

July 30, 2018

  • Microchip L10/L11 Bolster Security
    The Microchip SAM L10 and SAM L11 are the first microcontrollers to use Arm’s Cortex-M23, which supersedes the popular Cortex-M0+. With its TrustZone isolation and other features, the L11 is an unusually secure MCU.
  • General Processor Commands IP Unity
    General Processor has developed a heterogeneous processor-IP platform it calls Unity. This Sino-American platform includes a configurable deep-learning accelerator (DLA), a 64-bit CPU, and a vector DSP.
  • Wear 2500 Targets Kid Watches
    After a two-year hiatus, Qualcomm announced the first of two new smartwatch chipsets. The Snapdragon Wear 2500 targets the emerging kid-watch segment of the rapidly growing smartwatch market.

July 23, 2018

  • Snapdragon 400-Series Shrinks to 12nm
    Qualcomm is bringing advanced 12nm FinFET technology to its low-cost Snapdragon 400-series. It also announced the Snapdragon 632, offering OEMs a Big.Little upgrade for midrange smartphones.
  • Flex Logix Diversifies eFPGA
    OEMs and chip vendors are adopting embedded FPGAs in a variety of applications. Flex Logix has responded to this demand with improved cores and new process nodes.
  • Editorial: Challenges for New Intel CEO
    Whomever Intel chooses as its next CEO must fix the execution problems that have led to product and technology delays across several business units as well as diminished customer confidence.
  • MediaTek Advances in 5G
    The Helio M70, MediaTek’s first 5G chip, is a multimode modem that should enter production next year. The company plans to follow quickly with an integrated processor for 5G smartphones.

More Articles

Purchase an Article


 

Events

Linley Fall Processor Conference 2018
Covers processors and IP cores used in embedded, communications, automotive, IoT, and server designs.
October 31 - November 1, 2018
Hyatt Regency, Santa Clara, CA
Register Now!
More Events »

Newsletter

Linley Newsletter
Analysis of new developments in microprocessors and other semiconductor products
Subscribe to our Newsletter »