A Programmable Heterogeneous Microprocessor Based on Bit-Scalable In-Memory Computing

Computer Science

• Noise-to-Signal Ratio 100%
• Sparsity 33%
• Energy Consumption 33%
• Software Stack 33%
• Heterogeneous Architecture 33%
• Programmability 33%
• Energy Efficient 33%
• Image Classification 33%
• Software Library 33%
• Digital Conversion 33%
• Convolutional Neural Network 33%
• Quantization Level 33%

Keyphrases

• Near-memory Computing 28%
• Application Mapping 14%
• Primary Restriction 14%