Providing An AI Accelerator Ecosystem


A key design area for AI systems is the creation of Machine Learning (ML) algorithms that can be accelerated in hardware to meet power and performance goals. Teams designing these algorithms find out quickly that a traditional RTL design flow will no longer work if they want to meet their delivery schedules. The algorithms are often subject to frequent changes, the performance requirements may ... » read more

Formally Ensuring Equivalence Between C++ And RTL Designs


Moving untimed C++ design descriptions through a High-Level Synthesis (HLS) flow, designers wonder if the generated, timed RTL is functionally equivalent to the original, high-level description. When they make refinements or optimize RTL for power, they naturally are concerned that these changes no longer meet their original specifications. They could create testbenches and run verification at ... » read more

CEO Outlook: Rising Costs, Chiplets, And A Trade War


Semiconductor Engineering sat down to discuss what's changing across the semiconductor industry with Wally Rhines, CEO emeritus at Mentor, a Siemens Business; Jack Harding, president and CEO of eSilicon; John Kibarian, president and CEO of PDF Solutions; and John Chong, vice president of product and business development for Kionix. What follows are excerpts of that discussion, which was held in... » read more

Machine Learning Drives High-Level Synthesis Boom


High-level synthesis (HLS) is experiencing a new wave of popularity, driven by its ability to handle machine-learning matrices and iterative design efforts. The obvious advantage of HLS is the boost in productivity designers get from working in C, C++ and other high-level languages rather than RTL. The ability to design a layout that should work, and then easily modify it to test other confi... » read more

Building An Efficient Inferencing Engine In A Car


David Fritz, who heads corporate strategic alliances at Mentor, a Siemens Business, talks about how to speed up inferencing by taking the input from sensors and quickly classifying the output, but also doing that with low power. » read more

How To Integrate An Embedded FPGA


Choosing to add programmable logic into an SoC with an eFPGA is just the beginning. Other choices follow involving how many lookup tables (LUTs), how much routing and what topology, how will data be transferred in and out of the fabric, does data need to be coherent with system memory, how will it be programmed and tested, and what RTL functions need to be embedded into the programmable fabric ... » read more

AI Accelerator Ecosystem: An Overview


Companies worldwide trust the Catapult HLS Platform for designing and verifying machine learning accelerators and connecting them to systems. But, Mentor has taken a big step farther and offers an AI accelerator ecosystem that provides AI designers with an environment to jumpstart their projects. Based on years of working with designers, this ecosystem provides resources from IP libraries to fu... » read more

Challenges In Using HLS For FPGA Design


High-level synthesis (HLS) tools, which transform C/C++ source code to Verilog/VHDL, have been commercially available for over 15 years. HLS tools from FPGA vendors and EDA companies promise improved productivity through a higher-level of abstraction, faster verification and quicker design iterations. For example, simulating your design in C/C++ can be 10 to 100x faster than simulating in RTL (... » read more

Finding Code Problems Before High-Level Synthesis


In order to significantly speed up verification and to handle complex algorithms that change daily, many companies are turning to a High-Level Synthesis (HLS) methodology. But, it is extremely important that the high-level C++ model is correct. In addition, the C++ language has ambiguities that can be tough to catch during simulation. Even if correctly written, the high-level model could be cod... » read more

Closing Functional And Structural Coverage On RTL Generated By High-Level Synthesis


Most hardware design teams have a verification methodology that requires a deep understanding of the RTL to reach their verification goals, but this type of methodology is difficult to apply to the machine generated RTL from High-level Synthesis (HLS). This paper describes innovative techniques to use with existing methodologies, for example the Universal Verification Methodology (UVM), to clos... » read more

← Older posts