» Archived Articles | Login | Activate My Subscription | Subscribe | Free Sample Articles | Purchase an Article

Current MPR Articles

June 24, 2019

• Broadcom Samples Trident 4 Switch
  Broadcom’s first 7nm switch chip is also its first to offer compiler programmability. It marks the debut of the company’s Network Programming Language (NPL).
  

• Hailo Illuminates Low-Power AI Chip
  Israeli startup Hailo is entering the highly competitive AI inference-engine market with a chip that runs the entire ResNet-50 neural network using only on-chip SRAM and consuming just 1.5W.
  

• Knowles Adds AI to IA8201
  The IA8201 adds a midrange audio processor to the Knowles AISonic line, which includes neural-network functions for voice recognition in smart speakers, appliances, and other consumer gear.
  

• Unisoc Launches Tiger T310
  The Tiger 310 is the first low-cost smartphone processor to include a big CPU to boost performance, helping the four-core design compete against eight-core products.
  

June 17, 2019

• Habana Offers Gaudi for AI Training
  The startup expects its second AI chip to deliver better performance than Nvidia’s V100 GPU at half the operating power. It plans to sample Gaudi-based cards and systems this year.
  

• MediaTek AI Engine Earns Top Marks
  The Helio P90 integrates a custom deep-learning accelerator, enabling it to take the top spot on the new AI Benchmark. MediaTek’s forthcoming 5G SoC will feature an enhanced version of this accelerator.
  

• Silicon Labs Upgrades Wireless MCUs
  New Wireless Gecko Series 2 microcontrollers for IoT offer stronger security, enhanced radios, and Arm Cortex-A33 CPUs. These EFR32-series chips also feature the smallest packages in their class.
  

June 10, 2019

• DSP-IP Vendors Target 3D Navigation
  DSPs are well suited to simultaneous localization and mapping (SLAM). Cadence’s new Vision Q7 improves SLAM performance, and Ceva is also offering a new SLAM SDK that works with its DSPs. 
  

• Editorial: AI Needs Flexibility…For Now
  AI accelerators must handle the myriad types of neural networks available now and in the future, but over time, chip designers will focus on efficiently executing a smaller set of models.
  

June 3, 2019

• Arm Mali-G77 Goes to Valhall
  Arm’s new Mali-G77 GPU boosts area and power efficiency by 30% and machine-learning performance by 60%. The new Mali-D77 display unit includes features that target VR headsets.
  

• Achronix Debuts FPGAs for AI
  The new Speedster7t FPGA family from Achronix competes with Intel and Xilinx by offering faster DSP blocks optimized for machine learning, optional GDDR6 memory, 400G Ethernet, PCI Express Gen5, and novel internal routing.
  

• Arm CPUs Approach Intel Complexity
  Our die-photo analysis reveals that the largest Arm-compatible CPUs, such as the Samsung M4, consume up to 70% of the area of the Intel Skylake CPU after adjusting for IC-process differences.
  

May 27, 2019

• Cortex-A77 Improves IPC
  Arm’s next-generation big core offers more per-clock performance than Cortex-A76 by increasing the reorder window and by adding two new function units and a level-zero cache.
  

• Arm Machine-Learning Core Scales Up
  Arm’s machine-learning processor core is now available for general licensing, although it has yet to receive a brand name such as Cortex or Mali. A single core delivers up to four trillion operations per second. 
  

• Xilinx Enters Smart-NIC Market
  With its $400 million acquisition of Solarflare, Xilinx is bringing important server-networking intellectual property in house. The move enables it to offer FPGA-based network interface cards.
  

May 20, 2019

• EUV Processes Reach Mass Production
  After many years of research, semiconductor foundries finally in 1Q19 brought extreme-ultraviolet (EUV) lithography to production, as Samsung and TSMC delivered 7nm wafers using that technology.
  

• Lattice Lessens Power With SensAI
  Lattice offers SensAI RTL for its low-power Ice40 and ECP5 FPGAs that enable them to perform image recognition using neural networks while consuming as little as 10mW.
  

• Ambarella Expands Vision to ADAS
  Using its experience in video processing, Ambarella has developed the new CV2-series chips for advanced driver-assistance systems (ADAS) that employ custom logic for machine learning and image processing.
  

May 13, 2019

• Tesla Rolls Its Own Self-Driving Chip
  By building a custom ASIC that delivers up to 74 trillion operations per second (TOPS) of neural-network acceleration, Tesla set a new high-performance mark for autonomous-driving processors.
  

• Intel Warms Up Coffee Lake
  A broad line of 9th Generation processors exhibits only minor improvements over previous Coffee Lake parts. A leaked PC roadmap relies mainly on 14nm chips through 2020.
  

• Huawei Ascends in AI Accelerators
  Huawei is shipping the first deep-learning accelerators based on its in-house Ascend 310 chip. These Atlas modules target smart cameras and edge compute with up to 64 TOPS of peak performance.
  

May 6, 2019

• Fabu Aims to Deliver ADAS Processors
  The autonomous-vehicle-technology startup is preparing to tape out a Level 3 ADAS processor that integrates a 5.5-TOPS inference engine. It targets cameras, lidar, and radar sensors.
  

• AMD Accelerates Ryzen Embedded
  The new dual-core Ryzen Embedded R1000 processors, now sampling, improve CPU throughput, graphics performance, and Ethernet connectivity at the same power as the current V1000 models.
  

• Editorial: Apple Shuffles 5G Landscape
  Qualcomm won a major victory by settling its long-running legal feud with Apple and forcing Intel out of the modem market. But Apple may have the last laugh.
  

April 29, 2019

• Marvell Brings 400GbE to Enterprises
  Marvell’s new Prestera CX 8500 family upgrades the company’s Ethernet switching portfolio with 400Gbps Ethernet and PAM4-based network interfaces, scaling from 2.0Tbps to 12.8Tbps.
  

• Qualcomm Advances Into AI Chips
  Taking another run at the lucrative data-center market, Qualcomm disclosed plans to offer the Cloud AI 100, an AI-inference accelerator for servers, and claimed industry-leading performance per watt.
  

• Cortus FPS69V Uses 64-Bit RISC-V
  Cortus has added five new CPUs to its RISC-V lineup, ranging from the tiny APS1V to its first multicore and 64-bit designs. All except the FPS69V are already in production.
  

April 22, 2019

• Horizon Robotics Eyes ADAS
  Chinese startup Horizon Robotics is shipping two vision processors for smart cameras and autonomous vehicles and has improved products on its roadmap. Well funded by Chinese and American investors, it specializes in machine-learning-accelerated object recognition.
  

• Snapdragon 730 Pushes Gaming
  Qualcomm has introduced the Snapdragon 665, the Snapdragon 730, and, for gamers, the Snapdragon 730G, bringing premium features such as computer vision to mid-premium smartphones.
  

• Wave to License TritonAI IP
  Wave Computing’s AI-accelerator platform comprises three components: WaveFlow compute clusters, WaveTensor MAC arrays, and new MIPS CPUs based on technology it acquired last year.
  

April 15, 2019

• Flex Logix Moves Into Chips
  The new Flex Logix InferX X1 is an AI coprocessor chip designed to connect to a host CPU via PCIe. It integrates four NNMax tiles, delivering a total of 8.5 trillion operations per second.
  

• Xeon D-1600 Tackles NFV, 5G Systems
  Intel’s newest embedded processors include new Xeon D (Hewitt Lake) and Xeon Scalable (Cascade Lake) models that boost performance for networking and storage applications.
  

• Andes Strengthens Its RISC-V Arsenal
  The new A25MP and AX25MP RISC-V CPUs from Andes add cache-coherent multicore support and an optional DSP extension. The company also rolled out the tiny N22, which is compatible with the RV32C ISA.
  

April 8, 2019

• 2nd-Gen Xeon Scalable Adds Cores
  Intel’s new server processors, code-named Cascade Lake, offer workload optimizations such as DL Boost and introduce Optane support. Many of the popular models pack more cores at the same price.
  

• Intel 10nm FPGAs Add Chiplets
  Intel’s next-generation Agilex FPGAs can copackage programmable logic with chiplets that add high-speed memory, new I/O interfaces, and even customer-designed functions.
  

• First Optane DIMMs Disappoint
  Intel’s first persistent-memory modules are suitable only for Cascade Lake servers with terabyte memory systems and, on the basis of estimated pricing, offer relatively small cost savings.
  

• Qualcomm Amps Up Smart Speakers
  Enabling in-device speech recognition of more than 100 phrases, the new smart-audio platform includes the QCS400 processor and the CSRA6640, which integrates an audio DSP and a class-D amplifier. 
  

• Editorial: Nvidia to Acquire Mellanox
  The GPU vendor is bringing its data-center partner in house, enabling more-complete solutions for large-scale accelerated computing.
  

April 1, 2019

• MIPS Openly Challenges RISC-V
  MIPS is offering its instruction-set architecture without license fees or royalties under the new MIPS Open program. The ISA is more complete and production tested than the open-source RISC-V.
  

• ST MCUs Make a Stellar Debut
  STMicroelectronics’ new Stellar microcontrollers provide security for wireless communications and in-vehicle networks. They’re the first commercial MCUs with phase-change memory.
  

More Articles

Purchase an Article