.png){kind=icon}
返回
A Reconfigurable Processing Element for Multiple-Precision Floating/Fixed-Point HPC
.png){kind=icon}
PRE
AI
DOI：10.1109/TCSII.2023.3322259.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
High-performance computing (HPC) can facilitate deep neural network (DNN) training and inference. Previous works have proposed multiple-precision floating- and fixed-point designs, but most can only handle either one independently. This brief proposes a novel reconfigurable processing element (PE) supporting both energy-efficient floating-point and fixed-point multiply-accumulate (MAC) operations. This PE can support $9\times $ BFloat16 (BF16), 4 $\times $ half-precision (FP16), $4\times $ TensorFloat-32 (TF32) and $1\times $ single-precision (FP32) MAC operation with 100% multiplication hardware utilization in one clock cycle. Besides, it can also support 72 $\times $ INT2, 36 $\times $ INT4 and 9 $\times $ INT8 dot product plus one 32-bit addend. The design is realized in a 28nm-process at a 1.471GHz slow-corner clock frequency. Compared with state-of-the-art (SOTA) multiple-precision PEs, the proposed work exhibits the best energy efficiency of 834.35GFLOPS/W and 1761.41GFLOPS/W at TF32 and BF16 with at least 10 $\times $ and 4 $\times $ improvement, respectively, for deep learning training. Meanwhile, this design supports energy-efficient fixed-point computing with a small hardware overhead for deep learning inference.
Keyword:
Multiple-precision
floating-point
fixed-point
PE
MAC
HPC
期刊
I
IF:
4.9
论文数:
8.8K
被引数:
2.5W
机构
引用论文
.png){kind=icon}
Phyto-mediated synthesis of ZnO/attapulgite nanocomposites using C. limon peel extract for enhancing the resistance against multidrug-resistant bacteria and fungi利用C. limon果皮提取物进行植物介导的ZnO/凹凸棒土纳米复合材料的合成，以增强对多重耐药细菌和真菌的抵抗性
PREAI
分享收藏
分享收藏
查看更多内容