MIPS Enhances Two Architectures
MIPS Enhances Two Architectures
By Embedded.com
October 31, 2001 (5:39 p.m. EST)
URL: http://www.eetimes.com/story/OEG20011026S0050
San Jose, CA - MIPS Technologies recently enhanced its MIPS32 and MIPS64 RISC microprocessor architectures. Among other changes, MIPS tried to reduce the architecture's interrupt latency by implementing general purpose register (GPR) shadow sets, which eliminate the need to save and restore GPRs when servicing an exception or interrupt. This reduces register save time to the duration of a pipeline flush. In addition, the architectures were endowed with vectored interrupts, which can save up to 20 cycles, thereby decreasing interrupt latency. MIPS also enabled the architectures to manipulate bits within data packets and device registers. The enhanced architectures allow MIPS64-compliant coprocessors, such as floating processor units (FPUs), to be combined with a 32-bit CPU. The architectures' MMUs are capable of managing pages as small as 1KB or as large as 256MB. The support for small page sizes is useful in memory-constrained ap plications. Large page support allows regions of virtual memory to be mapped with a single transition look-aside buffer entry allowing, for example, network applications to map and protect a memory-resident database. The enhanced architectures will support all legacy IP and will be compatible with third-party tools, operating systems, and application software supporting the MIPS architecture. The MIPS32 and MIPS64 architectures with the enhancement described above are available for licensing now.
Related Semiconductor IP
- USB 20Gbps Device Controller
- Ultra-High-Speed Time-Interleaved 7-bit 64GSPS ADC on 3nm
- Fault Tolerant DDR2/DDR3/DDR4 Memory controller
- 25MHz to 4.0GHz Fractional-N RC PLL Synthesizer on TSMC 3nm N3P
- AGILEX 7 R-Tile Gen5 NVMe Host IP
Related News
- RF Engines Grant Development Licence to Advanced Architectures
- Design costs for complex chip architectures reaching $100 million
- Advanced Architectures' Floating Point Accelerator Selected for XML Parallel Processing Architecture
- Architectures: On-chip interconnect gets off the bus
Latest News
- BrainChip Expands Global Reach, Announces Akida Boards and AI Development Kits Available at DigiKey
- Qualitas Semiconductor Successfully Demonstrates Live UCIe PHY IP at AI Infra Summit 2025
- Silicon Creations Announces 1000th Production FinFET Tapeout at TSMC and Immediate Availability of Full IP Library on TSMC N2 Technology
- Intel and NVIDIA to Jointly Develop AI Infrastructure and Personal Computing Products
- Comcores MACsec IP is compliant with the OPEN Alliance Standard