ESE: Efficient Speech Recognition Engine with Sparse LSTM on FPGA
원문 초록
Long Short-Term Memory (LSTM) is widely used in speech recognition. In order to achieve higher prediction accuracy, machine learning scientists have built larger and larger models. Such large model is both computation intensive and memory intensive. Deploying such bulky model results in high power consumption and leads to high total cost of ownership (TCO) of a data center. In order to speedup the prediction and make it energy efficient, we first propose a load-balance-aware pruning method that can compress the LSTM model size by 20x (10x from pruning and 2x from quantization) with negligible loss of the prediction accuracy. The pruned model is friendly for parallel processing. Next, we propose scheduler that encodes and partitions the compressed model to each PE for parallelism, and schedule the complicated LSTM data flow. Finally, we design the hardware architecture, named Efficient Speech Recognition Engine (ESE) that works directly on the compressed model. Implemented on Xilinx XCKU060 FPGA running at 200MHz, ESE has a performance of 282 GOPS working directly on the compressed LSTM network, corresponding to 2.52 TOPS on the uncompressed one, and processes a full LSTM for speech recognition with a power dissipation of 41 Watts. Evaluated on the LSTM for speech recognition benchmark, ESE is 43x and 3x faster than Core i7 5930k CPU and Pascal Titan X GPU implementations. It achieves 40x and 11.5x higher energy efficiency compared with the CPU and GPU respectively.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Task-Specific Audio Coding for Machines: Machine-Learned Latent Features Are Codes for That Machine
MNN-LLM: A Generic Inference Engine for Fast Large Language Model Deployment on Mobile Devices
any4: Learned 4-bit Numeric Representation for LLMs
MathOptAI.jl: Embed trained machine learning predictors into JuMP models
First Steps Towards Voice Anonymization for Code-Switching Speech
MambAttention: Mamba with Multi-Head Attention for Generalizable Single-Channel Speech Enhancement
토론
이 논문과 연결된 포럼 글이 아직 없습니다.