Sample Articles from Microprocessor Report

Microprocessor Report articles are available only to paid subscribers. The following articles are available as samples to show the breadth and depth of our coverage. Please note that, because these articles are several months old, some of the information and opinions may be out of date. Subscribers get access to these articles as soon as they are posted.


Untether Delivers At-Memory AI  — November 2, 2020
Using what it calls an at-memory architecture, Untether AI has created a highly power-efficient PCIe card that can achieve a stunning two petaop/s for neural-network inferencing using nearly 800MB of SRAM.

Jericho2c+ Brings 7nm to Routers  — September 14, 2020
Broadcom is sampling its first 7nm router chip, the Jericho2c+ packet processor. The new product serves in line cards for chassis-based routers, pairing with the shipping Ramon fabric chip.

Blaize Ignites Edge-AI Performance  — September 7, 2020
Edge-AI startup Blaize is sampling modules that integrate its El Cano inference processor. The chip can run Yolo v3 on five separate HD-video streams, delivering results at 10fps.

MediaTek Adds Midrange Dimensity  — August 17, 2020
The new Dimensity 700-series represents the third (and lowest) tier in MediaTek’s lineup of 5G-smartphone processors. The first product is the Dimensity 720, which targets phones selling for less than $300.

GlobalFoundries Wins AI Chips  — July 27, 2020
Even as its 12nm customers deliver industry-leading AI accelerators, GF has created new 12LP+ technology with ultra-low-voltage operation as well as optimized SRAM and MAC-unit designs.

Tom Halfhill Retires, Aakash Jani Joins  — June 29, 2020
After 20 years, Tom is retiring from his senior editor role at Microprocessor Report but will join the editorial board. New senior editor Aakash Jani is joining Microprocessor Report from AMD.

Pensando, Xilinx Debut Smart NICs  — June 15, 2020
Seeking to increase demand for merchant smart NICs, two new entrants plan to serve the broader market beyond hyperscale data centers.

Editorial: Publishing Under a Quarantine  — April 20, 2020
Many technology companies are struggling to develop new products during the unprecedented lockdowns, but The Linley Group delivers online articles and a virtual conference.

Tenstorrent Scales AI Performance  — April 13, 2020
Startup Tenstorrent is sampling an AI-inference accelerator that exceeds the performance of all other data-center inference chips while using just 65W, a fraction of their power.

Lattice First With FPGA in FD-SOI  — February 3, 2020
CrossLink-NX is the first chip in the company’s new Nexus line developed in 28nm FD-SOI technology. It targets embedded-vision applications in IoT and automotive markets.

Groq Rocks Neural Networks  — January 6, 2020
The startup has created a new AI architecture that implements a single massive programmable engine rated at an industry-leading 1,000 TOPS. It runs ResNet-50 with extremely low latency.

Tomahawk 4 Switch First to 25.6Tbps  — December 16, 2019
Broadcom is sampling a 400Gbps Ethernet switch that packs an unprecedented 512 serdes to double bandwidth relative to the shipping Tomahawk 3. 

BrainChip Akida Is a Fast Learner  — October 28, 2019
BrainChip has announced a new spiking-neural-network processor called Akida, which it plans to tape out by the end of the year. It also offers Akida’s core as licensable IP.

SiFive U8 Takes RISC-V Out of Order  — October 28, 2019
SiFive has revealed its U8-series, which builds on the 64-bit superscalar U7-series by adding out-of-order (OOO) execution, a first for commercial RISC-V intellectual property. 

Ceva and Synopsys Spin More TOPS  — October 7, 2019
To support neural-network inference in autonomous vehicles and other high-performance edge devices, new multicore deep-learning accelerators can generate 100 TOPS or more.

Silicon Labs Upgrades Wireless MCUs  — June 17, 2019
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.

Syntiant Knows All the Best Words  — March 18, 2019
The NDP10x processors can recognize a 64-word vocabulary while consuming less than a milliwatt of active power. They target always-on keyword and speaker recognition in battery-powered devices.

Habana Wins Cigar for AI Inference  — February 18, 2019
The Goya accelerator from Habana Labs offers industry-leading AI performance on ResNet-50 inference, but the company won’t disclose its architecture. We try to discern its secrets...

Intel Turns Graphics up to (Gen) 11  — January 21, 2019
The upcoming 10nm Ice Lake processors will employ Intel’s first mainstream GPU with 1Tflop/s of single-precision compute capability. The Gen11 graphics architecture also boosts power efficiency.

Mythic Multiplies in a Flash  — August 27, 2018
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.


If you have any further questions about our journals, please contact our customer service.

Subscribe »

Free Newsletter

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

Events

Linley Fall Processor Conference 2021
Coming October 20-21, 2021
Hyatt Regency Hotel, Santa Clara, CA
Register Now!
Linley Spring Processor Conference 2021
April 19 - 23, 2021
Proceedings Available
More Events »