Dynamic/Leakage Power Reduction in Memories – European/India Webinar

A Webinar on Slashing your Dynamic/Leakage Memory Power in your Verilog/SystemVerilog/VHDL RTL

 

Thursday September 12

UK (10:00 AM) | Europe (11:00 AM) | Finland (12:00 PM) | India (2:30 PM)

 

Abstract

 

Given the complexity of today’s SoCs, efficient power management requires a holistic approach where the control logic, data paths, and memories are analyzed together and optimized for both dynamic and static power. However, identifying memory-gating opportunities is beyond the scope of RTL synthesis tools. Power conscious designers try to analyze the registers for redundant accesses and look for conditions under which such accesses can be shut off. There is no single known method of achieving this, and designers mostly develop this expertise over time. Even so, the process can get very tedious and error prone without suitable assistance.

 

Memory vendors provide several capabilities to reduce leakage power in memories that are not in use, and various flavors of sleep modes are now available in embedded memories, but using these modes requires the creation of controllers to generate the sleep and wake signals. In addition, the leakage power savings gained during sleep mode must be greater than the dynamic power dissipation associated with transitioning the memory in and out of sleep mode. The memory must be in sleep mode for a minimum number of cycles to actually save power. Finally, creating the sleep mode control signals and ensuring that sleep modes are triggered only during periods when the memory is quiet for an extended period require analysis of the design functionality over multiple cycles.

 

In this webinar, Calypto will show how its patented sequential analysis technology can be applied to reduce memory power. Deep sequential analysis examines the read and write operation of memories over several cycles and automatically optimizes the memories for both dynamic and leakage power. It also implements optimized sleep modes for the memory.

 

 

Thursday September 12

Register Now!

 

UK 1000 hours (10:00 AM)

Europe 1100 hours (11:00 AM)
Finland 1200 hours (12:00 PM)
India 1430 hours (2:30 PM)

A Practical Comparison Between C++ and SystemC for High Level Synthesis – European/India Webinar

 A Practical Comparison Between C++ and SystemC for High Level Synthesis

 

Thursday June 20

UK (10:00 AM) | Europe (11:00 AM) | Finland (12:00 PM) | India (2:30 PM)

 

Abstract

 

Have you ever wondered the difference between C++ and SystemC for high level synthesis (HLS)? This 50 minute webinar will provide a practical overview of the differences between the two most common ESL hardware description languages. The webinar will show side by side coding examples of the two languages for basic hardware concepts such as: hierarchy, IO, numerical precision and timing. As the only company to support both SystemC and C++ for synthesis with the industry’s most successful HLS tool (Catapult Synthesis), Calypto is uniquely placed to discuss the differences between the two languages.

 

In this 50 minute webinar, we will cover the basics of designing for hardware with each language, covering what you can, and can’t do:

 

*    Bit-accurate datatypes

*    Architecture design

*    Interfacing

*    Hierarchy

*    Verification

 

 

Thursday June 20

Register Now!

 

UK 1000 hours (10:00 AM)

Europe 1100 hours (11:00 AM)
Finland 1200 hours (12:00 PM)
India 1430 hours (2:30 PM)

Minimizing RTL Power Through Sequential Analysis – European/India Webinar

A Webinar on the Latest Techniques for Power Optimization at RTL
 

 

Thursday May 23

UK (10:00 AM) | Europe (11:00 AM) | Finland (12:00 PM) | India (2:30 PM)

 

Abstract

 

Analyzing and optimizing power at RTL can significantly reduce power but is challenging especially when done manually. The widely used practice of inserting clock gating may not be very effectivewithout considering the sequential nature of the design and representative switching activity.

 

In this 50 minute webinar, Calypto will review the requirements for a comprehensive methodology to reduce power at the RTL level. The webinar will cover more advance topics such as how to analyze the RTL for wasted power and show optimization techniques to reduce power on real designs. The latest technique of sequential analyses will be described including stability based and the more difficult observability based sequential clock gating that provides maximum power optimization.

 

 

Thursday May 23

Register Now!

 

UK 1000 hours (10:00 AM)

Europe 1100 hours (11:00 AM)
Finland 1200 hours (12:00 PM)
India 1430 hours (2:30 PM)

RTL Power Reduction and High Level Synthesis Report 2013

Download Report

 

 

Register for DAC Suite Sessions

 

 

 

This year’s annual report has two sections based on an independent worldwide survey: 1) RTL power reduction; 2) High Level Synthesis.

 

648 SoC, IC, and FPGA design professionals responded to the survey, which was executed in December 2012. By analyzing this comprehensive feedback from engineers and engineering management, we can better understand key trends for these two technology areas.

 

The topics covered in this report are:

I. Survey methodology and demographics

II. Top methods used to reduce power

III. Engineering time spent on specific RTL power reduction tasks

IV. Plans to implement RTL power reduction tools in 2013

V. Methods to verify High Level Synthesis output RTL

VI. Important technologies to integrate with High Level Synthesis

VII. Summary

 

Download Report

 

 

DAC 2013 Suite Sessions – Austin Texas:

AMD’s Methodology Reduces Power by 20% (Customer Presentation)

Catapult & SLEC HLS Methodology

DAC 2013: Renesas Formal Flow Cuts Verification Time (Customer Presentation)

Presenter: Shintaro Imamura-san, Engineer, Front-end Design Technology Development, of Renesas

Description: Shintaro Imamura-san, Engineer, Front-end Design Technology Development, of Renesas, will describe how they have deployed a C to C and HLS formal equivalency flow using Calypto’s SLEC product.

 
There will be one presentation given in English and the other in Japanese.

 

Bio: Shintaro Imamura received BS and MS degree from Hiroshima City University in 2006 and 2008 respectively. Since 2008 Imamura has worked as an engineer on HLS design methodology development to improve SOC/MCU design productivity at Renesas. His area of research is in front-end design technologies and front-end hardware design for SystemC-HLS.

 

 

Click on your preferred time to register:

 

Tuesday, June 4th: 10:00 AM CDT (Presented in Japanese)

or 2:00 PM CDT (Presented in English)

 

View All DAC Sessions

DAC 2013: Insight Presentation – Reducing Design and Debug Time with Synthesizable TLM

Topic Area: High-Level and Logic Synthesis

Speaker: Bryan Bowyer, Calypto Design Systems


Summary: For teams designing hardware accelerators on an SoC, debugging and integrating the new block is often the most difficult task. For new standards, such as H.265 and Ultra HD TV, companies have moved to synthesizable, transaction-level SystemC to reduce design and debug time.

 

This session describes an approach to reduce design and debug time of hardware accelerators by 50%. The approach includes:

  • Designing synthesizable TLMs in SystemC
  • Meeting functional coverage goals in TLMs by using assertions
  • What to debug in transactions vs. RTL
  • Synthesizing the TLM model into RTL using HLS
  • How to use SLEC to formally prove that TLM and RTL match
Date/Time: Wednesday June 5, 2:00 PM — 4:00 PM CDT

Low Power RTL Report 2012

This report covers trends in the area of low power design, based on an independent, global RTL power analysis and optimization survey.

 

The survey was executed in late 2011 and had 744 SoC, IC, and FPGA design professionals respond; this report will analyze the survey results and identify relevant year-to-year trends.

 

Calypto RTL Report

 

The topics covered in this report are:

  • Survey methodology and demographics
  • Top methods used to reduce power
  • Percent of engineering time spent meeting power specifications
  • Top criteria for selecting RTL power optimization tools
  • Process nodes where RTL power optimization becomes important
  • Plans to implement power optimization tools in 2012
  • Conclusion

 

Click Here to download full report
(you must be a registered user to view report)

DAC 2013: AMD’s Methodology Reduces Power by 20% (Customer Presentation)

Presenter: Steve Kommrusch – Sr. Fellow Design Engineer, AMD

 

Description: AMD is building a reputation for designing power-efficient chips, which helps its end customers deliver lower-power products. In this private suite presentation, Steve Kommrusch from AMD will discuss AMD’s methodology for reducing power on the Jaguar SoC and will show how AMD used PowerPro to improve clock-gating efficiency. Steve will also share the results and advantages of doing power analysis and optimization at the RTL stage rather than waiting until post-gate synthesis.

 

Bio: Steve Kommrusch received his BS from University of Illinois in 1987 and his Masters degree from Massachusetts Institute of Technology in 1989.  Steve has worked as a lead engineer on low power processors for over 15 years.  At Hewlett Packard, Steve worked on a 3 ARM core ASIC for the CapShare 910 handheld scanner.  With National Semiconductor Steve worked on the Geode LX, an SOC with 2D graphics, X86 processor, and integrated display control, which was in the OLPC laptop (One Laptop Per Child). Most recently Steve architected the clock, reset, and power control signals for the AMD Jaguar processor.   All of these products made extensive use of clock gating to improve battery life.

 

 

Click on your preferred time to register:

 

Monday, June 3rd: 3:00 PM CDT

Wednesday, June 5th: 11:00 AM CDT

 

View All DAC Sessions