Private:progress-neshat

Spring 2011 (GF)

• Courses: None

working on: Large Scale data processing with MapReduce on GPU/CPU hybrid systems

the report is available here or from this adddress: \students\neshat\reports\large_scale_data_processing\doc\doc.pdf

Feb 15

• Started to work on more advance version of advertising on video. report.
• revised predicting quality work. Report is accessible from here.

Feb 8

• continued to revise predicting quality work. Report is accessible from here.
• Went over some papers to find solutions for creating dynamic thread in GPU.

Feb 1

• Revised predicting quality work. Report is accessible from here.
• Started to implement proposed system for using Hadoop over Hybrid CPU/GPU systems

Jan 24

• (On Going)Designing high-level architecture of proposed approach for using Hadoop over Hybrid CPU/GPU systems
• Read one example of large scale data proc. with map reduce
• Read papers about GPU clusters for HPC
• Explored Hadoop and its properties like HDFS
• Explored Architecture of NVIDIA GPU cluster's arch and specs

Jan 17

• read two papers about Phoenix, a mapreduce implementation for multi-core processors.
• spent some days to figure out how to use Mark framework and run some samples, but couldn't fully understand. These works has been done:
  • Configured system (windows) to run Mars, including cuda and SDK installation as well as VS9 configuring.
  • Corrected some typos in the code (library mismatching)
  • Asking authors about problems, and got this answer: "I must apologize that mars_v2 is buggy and complex, and we don't maintain the code base any more, I strongly recommend you to try the latest version on linux"
  • tried to install mars_v2 on Linux, but it is still buggy and complex. It seems this frame work could run only with certaing configuration, and with older versions of CUDA.
• Explored Mars to find its algorithm, and found in co-processing mode (Hybrid) they partition input data into two parts, one for CPU processing, the other for GPU processing. After the map stage, they merge data on CPU side, then dispatch data again to CPU workers and GPU workers.
• Looked at phonix, another System for MapReduce Programming from Stanford. It was the comparison base for Mars.
  • Spent 2 days for writing resume and being prepared for YouTube interview.

Jan 10

• Explored related works and potential ideas

Fall 2010 (TA)

• Courses:
  • CMPT-820: Multimedia Systems
  • CMPT-825: NLP

• worked on:
  • effective advertising in video

• Submissions:
  • SmartAd: a smart autonomous system for effective advertising in video (ICME 11)

Summer 2010 (RA)

• • Writing for publication

• worked on:
  • Estimating the click-through rate for new ads with semantic and feature based similarity

algorithms

Spring 2010 (RA)

• Courses:
  • CMPT-886: Special topics in operation systems

• worked on:
  • Accelarting online auction using GPU
  • Estimating the click-through rate for new ads with semantic and feature based similarity

algorithms

• submitted
  • Accelerating online auctions with Optimized Parallel GPU based algorithms: Accelerating Vickrey-Clarke-Groves (VCG) Mechanism (proposal for GPU Gem book)

Fall 2009 (TA)

• Courses:
  • CMPT-705: Algorithm
  • CMPT-771: Internet Architecture and Protocols

• worked on:
  • implementing FEC on mobile tv testbed