首页> 外文期刊>IEEE transactions on very large scale integration (VLSI) systems >GreenTPU: Predictive Design Paradigm for Improving Timing Error Resilience of a Near-Threshold Tensor Processing Unit
【24h】

GreenTPU: Predictive Design Paradigm for Improving Timing Error Resilience of a Near-Threshold Tensor Processing Unit

机译:Greentpu:预测设计范式,用于改善近阈值张量处理单元的定时误差弹性

获取原文
获取原文并翻译 | 示例

摘要

The emergence of hardware accelerators has brought about several orders of magnitude improvement in the speed of the deep neural-network (DNN) inference. Among such DNN accelerators, the Google tensor processing unit (TPU) has transpired to be the best-in-class, offering more than 15x speedup over the contemporary GPUs. However, the rapid growth in several DNN workloads conspires to escalate the energy consumptions of the TPU-based data-centers. In order to restrict the energy consumption of TPUs, we propose GreenTPU-a low-power near-threshold (NTC) TPU design paradigm. To ensure a high inference accuracy at a low-voltage operation, GreenTPU identifies the patterns in the error-causing activation sequences in the systolic array, and prevents further timing errors from similar patterns by intermittently boosting the operating voltage of the specific multiplier-and-accumulator units in the TPU. Compared to a cutting-edge timing error mitigation technique for TPUs, GreenTPU enables 2x to 3x higher performance (TOPS) in an NTC TPU, with a minimal loss in the prediction accuracy.
机译:硬件加速器的出现已经带来了深度神经网络(DNN)推断的速度的几个数量级改善。在此类DNN加速器中,谷歌张量处理单元(TPU)已将其送至最佳,在当代GPU上提供超过15倍的加速。然而,若干DNN工作量的快速增长始终升级基于TPU的数据中心的能量消耗。为了限制TPU的能量消耗,我们提出了Greentpu-A低功率近阈值(NTC)TPU设计范式。为了确保低电压操作的高推理精度,GreentPU通过间歇地提高特定乘法器的工作电压,防止在收缩系统阵列中的错误导致激活序列中的模式识别出误差的激活序列中的模式。 TPU中的蓄能器单元。与TPU的尖端定时误差缓解技术相比,GREENTPU在NTC TPU中启用2X到3x的高性能(上部),预测精度最小损耗。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号