As a part of resource-aware data systems team, and under prof. Pınar Tözün's supervision, I worked on developing mechanisms for higher utilization and efficiency of GPUs for deep learning training tasks.
Thesis: "Collocation and Memory Estimation for Efficient GPU Resource Management in Deep Learning Training"
★ ★ ★
Working under the supervision of prof. Hamid Sarbazi-Azad, my research's focus was to introduce an energy efficeint on-chip memories design with negligible performance overhead for GPUs. I experienced working with GPGPU-sim, and further developed c and Python codes for evaluation goals.
Thesis: "Unifying L1 Data Cache and Shared Memory in GPUs"
GPA: 17.20/ 20
★ ★ ★
During my bachelor's, my focus was on learning and understanding the basics of computer science through taking courses and conducting extensive self-study.
GPA: 18.42/ 20