# GoogleWorkloads for Consumer Devices: Mitigating Data Movement Bottlenecks
###### tags: `PIM` `Onur Mutlu` `ASPLOS '18`
###### papers: [link](https://people.inf.ethz.ch/omutlu/pub/Google-consumer-workloads-data-movement-and-PIM_asplos18.pdf)
###### slides: [link](https://people.inf.ethz.ch/omutlu/pub/Google-consumer-workloads-data-movement-and-PIM_asplos18-talk.pptx)
## 0. ABSTRACT
* data movement 是 consumer-device 能量消耗的主要來源，希望能透過 PIM 技巧減少這方面的overhead
* 分析以下 workloads:
* Chrome web browser
* TensorFlow mobile
* video plaback
* video capture
* 分析結果發現透過 PIM 技巧可以減少整體系統耗能 (平均 55.4%) 及執行時間 (平均 54.2%)
## 1. INTRODUCTION
*
## 2. BACKGROUND
## 3. ANALYZING AND MITIGATING DATA MOVEMENT
## 4. CHROME WEB BROWSER
## 5. TENSORFLOW MOBILE
## 6. VIDEO PLAYBACK
## 7. VIDEO CAPTURE
## 8. SYSTEM INTEGRATION
## 9. METHODOLOGY
## 10. EVALUATION
## 11. OTHER RELATED WORK
## 12. CONCLUSION