Ultra-low power memory generators silicon proven at TSMC 55 nm uLP and uLP eFlash
Grenoble, France – March 6, 2017 -- The ultra-low power targets of a battery-powered SoC - be it for IoT, Wearables, Wireless audio, BLE, SmartHome, Sensor hubs, Wireless automotive, MCUs... - now benefit from the widest panoply of low-power and dense memories proven to safely operate down to 0.81 V and to retain data down to 0.6 V.
Granting up to 70 % power consumption savings compared to conventional memory generators at 55 nm LP, the following set of memory generators has successfully passed all stages of TSMC9000 silicon qualification, both in 55 nm uLP and 55 nm uLP eFlash:
- Single-port RAM, SpRAM RHEA
- 1-port Register File, 1PRF AURA
- 2-port Register File, 2PRF ERA
- Dual-port RAM, DpRAM ERA
- Late programmable via ROM, sROMet TITAN
SoC designers have the flexibility to get the best performance trade-off, between speed and low-power, by selecting any operation voltage between 1.2 V and 0.9 V thanks to off-the-shelf available characterizations at 1.2 V +/- 10%, 1.1 V +/- 10%, 1.0 V +/- 10% and 0.9 V+/- 10% as well as additional user-specific characterization corners.
As facing the increasing architectural complexity of SoCs to lower their power consumption is challenging, Dolphin Integration streamlines SoC integration by proposing its RAMs with multiple power supply schemes - single rail, dual active rails, dual retention rails - with and without embedded power switches.
Most of the memory generators are provided in the frame of the TSMC sponsorship program, i.e. free of license fee. Register right away on MyDolphin private space to assess the achievable savings for your coming SoC using our on-line memory generators.
For further information on these memories, and on the complete and consistent set of silicon IPs for TSMC 55 nm uLP / uLP-eFlash, click here or or meet us at the TSMC symposiums in Santa-Clara (USA) on March 15th and in Shanghai (China) on March 28th.
About Dolphin Integration
Dolphin Integration contributes to "enabling low-power Systems-on-Chip" for worldwide customers - up to the major actors of the semiconductor industry - with high-density Silicon IP components best at low-power consumption.
"Foundation IPs" includes innovative libraries of standard cells, register files and memory generators as well as an ultra-low power cache controller. "Fabric IPs" of voltage regulators, Power Island Construction Kit and their control network MAESTRO enable to safely implement low-power SoCs with the smallest silicon area. They also star the "Feature IP": from ultra-low power Voice Activity Detector with high-resolution converters for audio and measurement applications to power-optimized 8 or 16 and 32 bit micro-controllers.
Over 30 years of experience in the integration of silicon IP components, providing services for ASIC/SoC design and fabrication with its own EDA solutions, make DOLPHIN Integration a genuine one-stop shop addressing all customers' needs for specific requests.
It is not just one more supplier of Technology, but the provider of the DOLPHIN Integration know-how!
|
Dolphin Design Hot IP
Related News
- Dolphin Integration sets up a large range of sponsored IPs at 55 nm to reduce SoC power consumption by up to 70%
- 12bit 2Msps Silicon proven SAR ADC IP Core with Ultra-low power is available in different technology nodes for various applications that includes IoT, Medical, Consumer, etc
- Dolphin Integration augments the TSMC IP Ecosystem at 40 nm ULP eFlash with new TITAN Read Only Memory
- Dolphin Integration's memories silicon proven at TSMC 90 nm eFlash
- sureCore announces ultra-low power memory IP for AI applications
Breaking News
- Jury is out in the Arm vs Qualcomm trial
- Ceva Seeks To Exploit Synergies in Portfolio with Nano NPU
- Synopsys Responds to U.K. Competition and Markets Authority's Phase 1 Announcement Regarding Ansys Acquisition
- Alphawave Semi Scales UCIe™ to 64 Gbps Enabling >20 Tbps/mm Bandwidth Density for Die-to-Die Chiplet Connectivity
- RaiderChip Hardware NPU adds Falcon-3 LLM to its supported AI models
Most Popular
E-mail This Article | Printer-Friendly Page |