Analysis: CEVA's ''Lite'' Mobile Multimedia Platform
In March CEVA unveiled "Mobile-Media-Lite" (MMLite), a family of multimedia processing solutions comprising licensable silicon IP and software. The family is aimed at low-end multimedia-enabled devices such as mobile TV players, portable multimedia players, and multimedia phones. CEVA also announced the first family member, the MM2200, a single-processor multimedia engine (shown in Figure 1). CEVA's intent is to provide highly integrated, application-optimized solutions; the company states that the MM2200 is area and energy optimized for cost-constrained consumer electronics products.
Figure 1. Block diagram of the MM2200 hardware platform.
The MM2200, like CEVA's earlier MM2000 platform, is based on the CEVA-X1620 DSP core (see BDTI's analysis excerpts and benchmark scores), and features a DMA engine and peripherals. Like the MM2000, the MM2200 also includes a range of optimized software for video, audio, imaging, and voice encoding and decoding; audio/video synchronization, file parsing, and protocol encoding/decoding; video conferencing, and media player and recorder functionality. However, unlike the MM2000, which targets mid- to high-end multimedia applications, the MM2200 is specialized for low-end multimedia—it has less memory, fewer peripherals, and lower performance. With both platforms, CEVA offers single-core, programmable, application-optimized engines.
For more BDTI analysis of CEVA's offering, see the full article at InsideDSP.
Related Semiconductor IP
- Link Acceleration Unit
- 64-bit, RISC-V, ultra-high performance processors
- 64-bit, RISC-V, performance and data computation processors
- 32-bit, RISC-V, deeply embedded processors
- Verification IP for eUSB 2 v2 and USB 2.0
Related Articles
- PowerVR MBX - Creating an IP standard for advanced mobile multimedia
- Mobile apps should be developed with platform independence
- Analysis: CEVA's 32-bit, Dual-MAC TeakLite-III DSP
- Analysis: ZSP800 and VZ.AudioHD platform
Latest Articles
- Design and Development of a Neuromorphic Silicon Suite: PVT Sensing, Stochastic LIF Inference, On-Chip STDP Learning, and Crossbar Programming
- LLM4RTL: Tool-Assisted LLM for RTL Generation
- Towards Delta Aware Training: Efficient DNN Weight Storage for Resource-Constrained FPGAs
- CHERI-D: Secure and efficient inline object ID for CHERI temporal memory safety
- AIA: A 16nm Multicore SoC for Approximate Inference Acceleration Exploiting Non-normalized Knuth-Yao Sampling and Inter-Core Register Sharing