Analog Bits Provides Enabling IP for Graphcore IPU-Machine M2000
Wide-range PLL and low-power, small footprint PVT sensor deployed in new machine Intelligence compute blade on 7nm technology
Sunnyvale, California -- September 17, 2020 -- Graphcore recently introduced its second-generation IPU platform with greater processing power, more memory and built-in scalability for handling extremely large machine intelligence workloads. The IPU-Machine M2000 is a plug-and-play machine intelligence compute blade that has been designed for easy deployment and supports systems that can grow to massive scale. Each IPU-Machine M2000 is powered by four new 7nm Colossus™ Mk2 GC200 IPU processors. GC200 integrates 1,472 separate IPU-cores and is capable of executing 8,832 separate parallel computing threads.
Each IPU processor core gets a performance boost from a set of novel floating-point technologies developed by Graphcore, called AI-Float. By tuning arithmetic implementations for energy and performance in machine intelligence computation, Graphcore is able to serve up one PetaFlop of AI compute in each IPU-Machine M2000 1U blade.
The Colossus Mk2 GC200 IPU processor required a reliable and precise clocking scheme. The Analog Bits low power, wide-range integer/fractional, ultra-low jitter PLL in 7nm was chosen because of its low jitter, reliability and support for the required frequency range to clock the IPU processor. Analog Bits’ small footprint, integrated sensor for PVT and power supply monitoring in 7nm was used to ensure the device maintained the required thermal profile. The sensor also helped to ensure the integrity of the entire power delivery subsystem.
“The Mk2 IPU is a highly complex, challenging design. We needed to count on a reliable, low jitter PLL so we could focus on its unique requirements. Power dissipation for a chip this large was also a focus for us,” said Phil Horsfield, vice president silicon at Graphcore. “The Analog Bits high-performance PLL addressed our clocking needs, and their small, integrated PVT sensor ensured power dissipation stayed in spec. Access to proven IP that is easy to integrate from a reliable vendor like Analog Bits helped our design process quite a bit.”
“Every new product release from Graphcore sets a new standard for performance and scalability,” said Mahesh Tirupattur, executive vice president at Analog Bits. “We’re excited to help enable the new frontiers being opened by Graphcore’s IPU-Machine M2000.”
To learn more about Analog Bits’ PLLs and PVT sensors, visit www.analogbits.com or email us at: info@analogbits.com.
About Analog Bits
Founded in 1995, Analog Bits, Inc. (www.analogbits.com), is the leading supplier of mixedsignal IP with a reputation for easy and reliable integration into advanced SOCs. Products include precision clocking macros such as PLLs & DLLs, programmable interconnect solutions such as multi-protocol SERDES and programmable I/O’s as well as specialized Sensors. With billions of IP cores fabricated in customer silicon, from 0.35-micron to 7-nm processes, Analog Bits has an outstanding heritage of "first-time-working” with foundries and IDMs
|
Related News
- Analog Bits Introduces Design Kits for 16nm FinFET Enabling next generation devices with SERDES, Sensors and PLLs
- Analog Bits to Demonstrate Pinless PLL and Sensor IP in TSMC N4 and N5 Processes at TSMC 2022 North America Open Innovation Platform® Ecosystem Forum
- Analog Bits to Demonstrate Pinless PLL and Sensor IP's in TSMC N5 Process at TSMC 2022 North America Technology Symposium
- Analog Bits and GLOBALFOUNDRIES Deliver Differentiated Analog and Mixed Signal IP for High-Performance Mobile and Compute Applications
- Analog Bits to Provide Precision PLL and SERDES IP to DesignShare for SiFive Freedom Platform
Breaking News
- Frontgrade Gaisler Unveils GR716B, a New Standard in Space-Grade Microcontrollers
- Blueshift Memory launches BlueFive processor, accelerating computation by up to 50 times and saving up to 65% energy
- Eliyan Ports Industry's Highest Performing PHY to Samsung Foundry SF4X Process Node, Achieving up to 40 Gbps Bandwidth at Unprecedented Power Levels with UCIe-Compliant Chiplet Interconnect Technology
- CXL Fabless Startup Panmnesia Secures Over $60M in Series A Funding, Aiming to Lead the CXL Switch Silicon Chip and CXL IP
- Cadence Unveils Arm-Based System Chiplet
Most Popular
- Cadence Unveils Arm-Based System Chiplet
- CXL Fabless Startup Panmnesia Secures Over $60M in Series A Funding, Aiming to Lead the CXL Switch Silicon Chip and CXL IP
- Esperanto Technologies and NEC Cooperate on Initiative to Advance Next Generation RISC-V Chips and Software Solutions for HPC
- Eliyan Ports Industry's Highest Performing PHY to Samsung Foundry SF4X Process Node, Achieving up to 40 Gbps Bandwidth at Unprecedented Power Levels with UCIe-Compliant Chiplet Interconnect Technology
- Arteris Selected by GigaDevice for Development in Next-Generation Automotive SoC With Enhanced FuSa Standards
E-mail This Article | Printer-Friendly Page |