AI Processor IP
Filter
Compare
301
IP
from
42
vendors
(1
-
10)
-
AI Processor Accelerator
- Universal Compatibility: Supports any framework, neural network, and backbone.
- Large Input Frame Handling: Accommodates large input frames without downsizing.
-
Powerful AI processor
- SiFive Intelligence Extensions for ML workloads
- 512-bit VLEN
- Performance benchmarks
- Built on silicon-proven U7-Series core
-
AI DSA Processor - 9-Stage Pipeline, Dual-issue
- NI900 is a DSA processor based on 900 Series.
- NI900 is optimized with features specifically targeting AI applications.
-
High-performance AI dataflow processor with scalable vector compute capabilities
- Matrix Engine
- 4 X-Cores per cluster
- 1 Cluster = 16 TOPS (INT8)
-
High-performance 64-bit RISC-V architecture multi-core processor with AI vector acceleration engine
- Instruction set: RISC-V RV64GC/RV 64GCV;
- Multi-core: Isomorphic multi-core with 1 to 4 optional clusters. Each cluster can have 1 to 4 optional cores;
-
High-performance 32-bit multi-core processor with AI acceleration engine
- Instruction set: T-Head ISA (32-bit/16-bit variable-length instruction set);
- Multi-core: Isomorphic multi-core, with 1 to 4 optional cores;
- Pipeline: 12-stage;
- Microarchitecture: Tri-issue, deep out-of-order;
-
AI inference processor IP
- High Performance, Low Power Consumption, Small Foot Print IP for Deep Learning inference processing.
-
Low-power high-speed reconfigurable processor to accelerate AI everywhere.
- Multi-Core Number: 4
- Performance (INT8, 600MHz): 0.6TOPS
- Achievable Clock Speed (MHz): 600 (28nm)
- Synthesis Logic Gates (MGates): 2
-
Neural Video Processor IP
- The NVP300, AI-based Neural Video Processing IP push video quality to the next level by leveraging the advanced features and benefits of AI based video processing technologies.
- The NVP300 IP features an optimized hardware implementation to deliver real-time AI processing of 4K video whithin best-in-class silicon area and power budget suitable for embedded products.
-
64-bit application processor for energy-efficient computation
- Dubhe-80 processor features a 9+ stage, 3-issue, out-of-order pipeline, fully compliant with a rich set of RISC-V extensions of RV64GCBH_Zicond_Zicbom_Zicboz_Zicbop.
- With a score of 8.5 SPECInt2006/GHz, Dubhe-80 is designed for mobile, desktop, AI, and automotive applications that require highly energy-efficient computation.
