Large-scale Media Processing on Cloud - Cloud Asia 2016 PANEL DISCUSSION
-
Upload
anand-bhojan -
Category
Software
-
view
97 -
download
0
Transcript of Large-scale Media Processing on Cloud - Cloud Asia 2016 PANEL DISCUSSION
![Page 1: Large-scale Media Processing on Cloud - Cloud Asia 2016 PANEL DISCUSSION](https://reader031.fdocuments.in/reader031/viewer/2022021813/589ae6fa1a28abee708b5f7f/html5/thumbnails/1.jpg)
+
Large-scale Media Processing on Cloud
(Discussion Panel - Introduction)
Dr BHOJAN ANAND (Panel Moderator)
![Page 2: Large-scale Media Processing on Cloud - Cloud Asia 2016 PANEL DISCUSSION](https://reader031.fdocuments.in/reader031/viewer/2022021813/589ae6fa1a28abee708b5f7f/html5/thumbnails/2.jpg)
+Let's Make this Interactive
![Page 3: Large-scale Media Processing on Cloud - Cloud Asia 2016 PANEL DISCUSSION](https://reader031.fdocuments.in/reader031/viewer/2022021813/589ae6fa1a28abee708b5f7f/html5/thumbnails/3.jpg)
+Large-Scale Media Processing in Cloud
Storage
Search
Retrieve
Encrypt
quality control
Transcode
Analytics
DRM
File Transfer Stream
Ever increasing Media Data: 400 hours of video uploaded/min & 3 trillion views/year in Youtube
Compress
![Page 4: Large-scale Media Processing on Cloud - Cloud Asia 2016 PANEL DISCUSSION](https://reader031.fdocuments.in/reader031/viewer/2022021813/589ae6fa1a28abee708b5f7f/html5/thumbnails/4.jpg)
+Large-Scale Media Processing in Cloud
Consumer Demand (choices
and control)
Time pressures
(more OTT providers)
Cost Pressures
(resources)
Eg. Media – Entertainment Industry
scalability, agility and
cost flexibility
and
Calling for
Cloud
![Page 5: Large-scale Media Processing on Cloud - Cloud Asia 2016 PANEL DISCUSSION](https://reader031.fdocuments.in/reader031/viewer/2022021813/589ae6fa1a28abee708b5f7f/html5/thumbnails/5.jpg)
+Discussions ….
PANEL MEMBERS INTRODUCTION… PANEL MEMBERS PRESENTATION… DISCUSSIONS… Q&A
![Page 6: Large-scale Media Processing on Cloud - Cloud Asia 2016 PANEL DISCUSSION](https://reader031.fdocuments.in/reader031/viewer/2022021813/589ae6fa1a28abee708b5f7f/html5/thumbnails/6.jpg)
+
CLOUD GAMES
- Multiplayer Cloud Games
- Mobile or Resource limited devices
![Page 7: Large-scale Media Processing on Cloud - Cloud Asia 2016 PANEL DISCUSSION](https://reader031.fdocuments.in/reader031/viewer/2022021813/589ae6fa1a28abee708b5f7f/html5/thumbnails/7.jpg)
+ Multiplayer Games
client
![Page 8: Large-scale Media Processing on Cloud - Cloud Asia 2016 PANEL DISCUSSION](https://reader031.fdocuments.in/reader031/viewer/2022021813/589ae6fa1a28abee708b5f7f/html5/thumbnails/8.jpg)
+Multiplayer Games
n Mobile Games and Game Maps
n Characteristics (FPS games) n Highly interactive, Closed maps with occlusions, 40-80
fps
n ~20 pps server to client (in
regular interval, cannot burst!)
n ~40 pps client to server (in regular interval, cannot burst!)
n Latency more than 180ms makes the game play annoying and not playable
![Page 9: Large-scale Media Processing on Cloud - Cloud Asia 2016 PANEL DISCUSSION](https://reader031.fdocuments.in/reader031/viewer/2022021813/589ae6fa1a28abee708b5f7f/html5/thumbnails/9.jpg)
+Multiplayer Games
n Characteristics (MMORPG games) n Slow speed games, with few high interactive areas n Huge (100’s of square miles) open maps with few
occlusions. [Estimated – time taken to run from one end to another].
n 100s to few 1000s of players per server
n 40-60 fps n ~15 pps server to client n ~20 pps client to server n Latency more than 400ms
makes the game play annoying and not playable
![Page 10: Large-scale Media Processing on Cloud - Cloud Asia 2016 PANEL DISCUSSION](https://reader031.fdocuments.in/reader031/viewer/2022021813/589ae6fa1a28abee708b5f7f/html5/thumbnails/10.jpg)
+Multiplayer Games
n Client side Latency Hiding Techniques
Immediate Response Prediction
Local Perception
Filters
Require Intelligent
Clients!
![Page 11: Large-scale Media Processing on Cloud - Cloud Asia 2016 PANEL DISCUSSION](https://reader031.fdocuments.in/reader031/viewer/2022021813/589ae6fa1a28abee708b5f7f/html5/thumbnails/11.jpg)
+ Mobile Multiplayer Cloud Games
• No download, no patches, no disks, no installations
• CPU/GPU load is reduced to save energy
• Centralized control. Hard to cheat
• Scalable
• Portable
![Page 12: Large-scale Media Processing on Cloud - Cloud Asia 2016 PANEL DISCUSSION](https://reader031.fdocuments.in/reader031/viewer/2022021813/589ae6fa1a28abee708b5f7f/html5/thumbnails/12.jpg)
+Mobile Multiplayer Cloud Games Key Challenges
- All these operations should happen serially in few ms!
- Requires
high sever bandwidth for Video Streaming
Inte
ract
ion
Del
ay
![Page 13: Large-scale Media Processing on Cloud - Cloud Asia 2016 PANEL DISCUSSION](https://reader031.fdocuments.in/reader031/viewer/2022021813/589ae6fa1a28abee708b5f7f/html5/thumbnails/13.jpg)
+Multiplayer Cloud Games
n Could Games need to handle additional latencies n Cloud Processing (Cloud Overhead) n Encoding Video n Compression n Worse in Mobile Environments due to prevailing
Network Latency and Jitter n Even with LTE it takes 70ms to closest data
center, Goes upto 200ms
Key Challenges
Conventional Client Side Latency Hiding Techniques are not Possible! – Client is Dump!
![Page 14: Large-scale Media Processing on Cloud - Cloud Asia 2016 PANEL DISCUSSION](https://reader031.fdocuments.in/reader031/viewer/2022021813/589ae6fa1a28abee708b5f7f/html5/thumbnails/14.jpg)
+Multiplayer Cloud Games
n “the company had deployed thousands of servers that were sitting unused, and only ever had 1,600 concurrent users of the service worldwide.”
http://www.theverge.com/2012/8/28/3274739/onlive-report
Active cloud gaming providers GameNow, GameFly Streaming, G-cluster, Gface, Kalydo, LoudPlay, Leap Computing, Liquidsky, PlayGiga, PlayKey, PlayStation Now, NVIDIA GeForce Now, Turbo Games
![Page 15: Large-scale Media Processing on Cloud - Cloud Asia 2016 PANEL DISCUSSION](https://reader031.fdocuments.in/reader031/viewer/2022021813/589ae6fa1a28abee708b5f7f/html5/thumbnails/15.jpg)
+ Possible Approaches: Gamelet System (case for micro-cloud!)
n Gamelet is a minimal-set hardware required to run, render and stream 3D games placed in the same local network or few hops (most of the time one or two hops) away from the mobile client.
n Uses distributed rendering to counter the limitations of renderer HW resources
Render at next hop!
Bhojan Anand, Aw Jia Hao Edwin , "Gamelets - Multiplayer Mobile Games with Distributed Micro-Clouds,” IEEE-ICMU 2014
![Page 16: Large-scale Media Processing on Cloud - Cloud Asia 2016 PANEL DISCUSSION](https://reader031.fdocuments.in/reader031/viewer/2022021813/589ae6fa1a28abee708b5f7f/html5/thumbnails/16.jpg)
+Demo
n Look for “Gamelets - Multiplayer Mobile Games with Distributed Micro-Clouds” in Youtube
![Page 17: Large-scale Media Processing on Cloud - Cloud Asia 2016 PANEL DISCUSSION](https://reader031.fdocuments.in/reader031/viewer/2022021813/589ae6fa1a28abee708b5f7f/html5/thumbnails/17.jpg)
+Speculative Rendering in Cloud
n Speculation/Prediction for Navigation and Camera Movement
n Impulse Events - Explore multiple outcomes in parallel and render for all possibilities
Outatime: Using Speculation to Enable Low-Latency Continuous Interaction for Mobile Cloud Gaming, Kyungmin Lee, David Chu, Eduardo Cuervo, Johannes Kopf, Yury Degtyarev, Sergey Grizan, Alec Wolman, Jason Flinn, Univeristy of Michigan, Microsoft Research, Mobisys 2015
![Page 18: Large-scale Media Processing on Cloud - Cloud Asia 2016 PANEL DISCUSSION](https://reader031.fdocuments.in/reader031/viewer/2022021813/589ae6fa1a28abee708b5f7f/html5/thumbnails/18.jpg)
+
THANK YOU Questions?