Microprocessor Report (MPR) Subscribe

Current MPR Articles

December 5, 2016

  • Everspin MRAM Targets Enterprise (MPR)
    Everspin’s new non-volatile memory offers DRAM-like performance as well as greater endurance and retention than flash memory, targeting embedded and enterprise storage.

November 28, 2016

  • Editorial: Nanometer Madness (MPR)
    The foundries no longer follow traditional metrics in labeling their process nodes, making IC-manufacturing progress more difficult to accurately assess.

November 21, 2016

  • New Standards Open Server Platform (MPR)
    Non-Intel servers will benefit as OpenCAPI and CCIX compete to become the standard coherent interconnect while Gen-Z aims to simplify deployment of innovative memory and storage technologies.
  • DeepBench Measures Deep Learning (MPR)
    Baidu has released a collection of over 150 neural-network kernels designed to evaluate the performance of various processors, along with performance data for Intel and Nvidia hardware.

November 14, 2016

  • Qualcomm-NXP: A New Goliath (MPR)
    Qualcomm’s proposed $47 billion acquisition of NXP will strengthen its mobile offering while diversifying the company, giving it strong positions in automotive, embedded, and IoT.
  • Cortex-M23/M33 Bolster IoT Security (MPR)
    ARM has rolled out the first Cortex-M CPUs to implement the ARMv8-M ISA, as well as a new CoreLink system interconnect, a security-IP core, and a complete subsystem for IoT processors.

November 7, 2016

October 31, 2016

  • Adjusting SPEC CPU2006 Scores (MPR)
    Advanced compilers inflate SPEC benchmark scores by 8–23% using optimizations that are irrelevant to most server users. Adjusting these scores enables more accurate comparisons of server processors.

October 24, 2016

  • Editorial: Intel Unarmed in M&A Battle (MPR)
    Intel’s ARM-avoidance policy constrains its acquisition strategy, as recent purchases of Movidius, Nervana, and Soft Machines demonstrate. Qualcomm’s proposed NXP deal provides a stark contrast.
  • Adapteva’s Million-Dollar Epiphany (MPR)
    Adapteva’s 1,024-core Epiphany-V should deliver 2Tflop/s of double-precision performance at 30W. More remarkably, the 16nm FinFET design took less than $1 million to tape out.

October 17, 2016

  • Apple A10 Bruises Other CPUs (MPR/MCR)
    The iPhone 7 uses two new custom ARM CPU designs to deliver better performance than any other smartphone, although the big Hurricane CPU consumes plenty of die area.
  • Nvidia Tunes Pascal for Learning (MPR)
    The Tesla P4 and P40, due to enter production in 4Q16, are second-generation machine-learning accelerators that use the new Pascal architecture for up to 10x performance gains.

October 10, 2016

  • Adesto Executes in Place (MPR)
    The new EcoXIP memory combines standard NOR flash with a custom high-speed interface designed specifically for streaming instructions in MCU-based IoT applications.
  • Flex Logix Adds 40nm for MCUs (MPR/NWR)
    Flex Logix, a startup specializing in FPGA intellectual property, has designed cores for a mature 40nm TSMC process (40ULP), even as it simultaneously characterizes its FinFET cores.
  • Ceva XM6 Accelerates Neural Nets (MPR)
    The new XM6 DSP core enables deep learning in embedded computer-vision processors, targeting self-driving cars, augmented and virtual reality, surveillance cameras, drones, and robotics.

October 3, 2016

  • Wave Accelerates Deep Learning (MPR)
    Startup Wave Computing has created an innovative dataflow architecture, implemented in a processor with 16,384 cores, that offers a 10x speedup for training neural networks.
  • Andes E830 Extends Processor IP (MPR)
    The new Andes E830 is a user-extensible CPU core with an updated and more compact instruction set. The company has also solidified its interconnect-design portfolio by adding the AE300.
  • Cortex-R52: Safer Real-Time Control (MPR)
    ARM’s new core supersedes the Cortex-R5 by adding virtualization, greater throughput, better lockstepping, and optional Neon extensions while increasing real-time deterministic performance.
  • GlobalFoundries Offers 7nm Roadmap (MPR)
    For its FinFET technology, GlobalFoundries is skipping 10nm and moving to a 7nm process targeting for 2018 production. Its new 12nm FD-SOI process offers an alternative path forward.

September 26, 2016

  • Samsung Unveils Custom M1 Core (MPR/MCR)
    Taking a page from rival Qualcomm’s book, Samsung designed a custom ARM CPU for the Exynos 8890, its first smartphone processor to forgo using a standard Cortex core.
  • Phytium Samples 64-Core ARMv8 (MPR)
    The Chinese startup is sampling its FT-2000/64—the world’s biggest ARM-compatible server processorand disclosed 4- and 16-core ARM chips that are already in production.
  • Editorial: ADAS Opportunities Expand (MPR)
    Despite the attention on self-driving cars, automotive-processor vendors will find that active-safety systems present a bigger and fast-growing opportunity over the next several years.
  • Synopsys Debuts Secure ARC Cores (MPR)
    Two new DesignWare cores improve security in IoT devices and embedded systems using features such as secure containers and countermeasures against side-channel attacks.

September 19, 2016

  • Oracle Sparc Accelerates Big Data (MPR)
    Oracle’s recent Sparc processors integrate hardware acceleration for database software, big-data analytics, and security. They also enable compression of in-memory databases.

September 12, 2016

Purchase an Article

Events

Linley Cloud Hardware Conference 2017
Covers system design for cloud computing and networking
February 8 - 9, 2017
Hyatt Regency Hotel, Santa Clara, CA
Register Now!
More Events »

Newsletters

Linley Wire
Analysis and news on processors for networking and communications
Linley on Mobile
Analysis and news on semiconductors for mobile and wireless
Processor Watch
Analysis of high-performance microprocessor developments
Subscribe to our Newsletters »