ACADEMICS
Indian Institute of Technology, Kanpur 2020-22
M.Tech (Computer Science and Engineering)[CGPA:8.3]
| CS610 : Programming for Performance | CS633 : Parallel Computing |
| CS622 : Advanced Computer Architecture | CS628 : Computer Systems Security |
| CS641 : Modern Cryptology | CS711 : Introduction to Machine Learning |
| CS738 Advanced Compiler Optimizations |
University Institute of Technology, RGPV, Bhopal 2016-20
B.E. (Information Technology)[CGPA: 8.39]
RESEARCH EXPERIENCE
Exploring Techniques to Improve Cross-Device Data Sharing via Unified Shared Memory
Unified Shared Memory in CUDA primarily focuses on improving programmer productivity, possibly at the cost of diminished
program performance.
The CUDA programming model introduces mechanisms that can only be properly exploited by sophisticated GPU programmers.
Studying and Evaluating techniques to automatically reduce the overhead in accessing data via Unified Shared memory
through compiler and runtime transformations
PROJECTS
Modeled a multi-core Cache Hierarchy Simulator, Prof. Mainak Chauduri| Oct'20-Nov'20
Developed a multicore hierarchy cache simulator in C++ which implements directory based cache coherence protocol.
Used Queues to handle multiple access requests and recorded L1, L2 cache access, cache misses and simulated cycles.
Implemented Haloexchange, Prof. Preeti Malakar| Jan'21-Feb'21
Performed Haloexchange with neighbouring MPI processes using MPICH library functions.
Did rigorous analysis on it to compare performance using MPI Sends, MPI Pack/Unpack and MPI Derived Datatypes.
Optimized CUDA Kernel for Matrix Multiplication, Prof. Swarnendu Biswas| Sept'20-Oct'20
Performed Haloexchange with neighbouring MPI processes using MPICH library functions.
Did rigorous analysis on it to compare performance using MPI Sends, MPI Pack/Unpack and MPI Derived Datatypes.
Optimization of collective blocking calls based on Topoaware Network, Prof. Preeti Malakar| Feb'21-Mar'21
Optimized collective blocking calls on in-built functions viz. MPI Bcast, MPI Reduce, MPI Gather and MPI AlltoAllv based on collective algorithms viz. Binary Algorithm, Binomial Algorithm, Ring Algorithm and Topoaware Network.
Advanced Cache Simulation using Cache Trace, Prof. Mainak Chauduri| Sept'20-Oct'20
Given L1 memory trace-file, simulated cache to count L2 & L3 hits/misses using Inclusive, NINE and Exclusive policy.
Implemented Belady and LRU Replacement Policy to classify Cold, Con
ict and Capacity misses for Inclusive L3 cache.
Escaping the Caves|Cryptanalysis on numerous Cryptosystems, Prof. Manindra Agrawal| Jan'21-Apr'21
Performed Cryptanalysis on different Cryptosystems viz. Substitution Cipher, Playfair, 6-round DES,EAEAE and RSA.
TECHNICAL SKILLS
Languages
C, C++, Python
Others
Git, MySQL, LaTeX , HTML, CSS
ACHIEVEMENTS & EXTRA-CURRICULAR
- All India Rank 312 in GATE 2020
- 3rd Rank in Intra-College Coding Competition CodeAdept 2.0 (2018)
- Regular Volunteer for Blood Donation
- Winner of Inter-House Cricket Competition(2012)