Application convergence
Carl Schlachte
(05/03/2004 9:00 AM EDT)
We are experiencing a phenomenon that profoundly affects the industry, particularly the silicon intellectual property portion: application convergence-the combining of electronic subsystems that meld voice, data and video into all sorts of electronic equipment. This convergence is helping to dictate how silicon IP vendors define, develop and market their products.
Driven by the consumer's hunger for features, various technologies are coming together in single appliances. Not far down the road will be cell phones with video capability.
Convergence can also mean different technologies combining for one application. Convergence is also vital in cars, where silicon vendors are developing processor-based chips that deal with several functions concurrently.
But application convergence poses a formidable challenge to silicon IP providers. Designing systems that deal with multiple technologies is not as simple as combining single application-specific subsystems within the same package. Such designs can result in systems with unnecessary redundancy. They also put an unnecessary strain on system resources, such as the OS, and require a larger memory footprint. Vendors must be able to integrate technologies efficiently.
One way to accomplish integration is via configurable-processing engines. One example is a soft microprocessor core that can process both video and audio information by using instruction-set extensions. Such a core results in a system that has a lower clock frequency and, hence, lower power, than one that uses two processor cores to handle audio and video separately. Configurable and extendable processor cores also allow you to choose the best combination of speed, area and power for a specific application.
The challenge of successfully designing silicon IP for application convergence goes beyond the technology you need to integrate application-specific subsystems. Vendors must also deal with the realities of shrinking design cycles and leaner design teams. To exponentially increase design complexity, you need a design team that can work with different technologies concurrently.
Those companies that wish to excel as silicon IP providers must adopt a business model that addresses the technological convergence of products and companies. The successful silicon IP providers will morph into silicon system providers and will offer a complete package: silicon; software; and, most important, end-use knowledge. The silicon IP provider that has proven knowledge of vertical markets is an invaluable member of the customer's team and, in fact, extends the customer's design expertise without additional head count.
Carl Schlachte is chief executive officer of ARC International (San Jose, Calif.).
Related Semiconductor IP
- Simulation VIP for Ethernet UEC
- CAN-FD Controller
- Bluetooth® Low Energy 6.2 PHY IP with Channel Sounding
- Simulation VIP for UALink
- General use, integer-N 4GHz Hybrid Phase Locked Loop on TSMC 28HPC
Related News
- Artisan Components' Libraries Selected By empowerTel Networks For Use In Industry's First Convergence Processors
- Compal Communication Adopts Motorola’s Innovative Convergence Platform
- Toshiba Launches First SoCMosaic Custom Chip, An Arm-Based Controller For Low-End Networking And Consumer Convergence Applications
- Trinity Convergence And ARM Announce Single Chip Solution For VoIP Enabled Soho/Residential Devices
Latest News
- Quintauris releases RT-Europa, the first RISC-V Real-Time Platform for Automotive
- PQShield's PQCryptoLib-Core v1.0.2 Achieves CAVP Certification for a broad set of classical and post-quantum algorithms
- M31 Debuts at ICCAD 2025, Empowering the Next Generation of AI Chips with High-Performance, Low-Power IP
- Perceptia Begins Port of pPLL03 to Samsung 14nm Process Technology
- Spectral Design and Test Inc. and BAE Systems Announce Collaboration in RHBD Memory IP Development