aayush-ankit Goto Github PK

aayush-ankit.github.io

Personal website

bme595-deep-learning

cutlass-gpgpu-sim

ece573-compiler

Implemented a compiler for toy language (Tiny) to a simplified ISA (Micro) - scanner & parser, symbol table, expressions, control structures, functions, register allocation, loop optimization

ece595z-design-automation

ece666-parallelarch-gaussianelimination

Gaussian Implementation using pipelined and non-pipelined approach using shared memory (Pthreads) and message passing (MPI) programming models

ece666-parallelarch-gem5

Implementation of MSI directory coherence protocol and Dynamic Self Invalidation (Lebeck and Wood, ISCA'95)

ece695-accelarch

Implemented Iterative Jacobi algorithm in CUDA (and optimizations) and Register File Caching in GPGPUSim.

gpgpu-sim_distribution

GPGPU-Sim provides a detailed simulation model of a contemporary GPU running CUDA and/or OpenCL workloads and now includes an integrated (and validated) energy model, GPUWattch.

ml-inference-benchmarks

GPU and CPU measurements for ML inference workloads for power, latency and throughput

onnxruntime

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

puma-compiler

PUMA Compiler

puma-functional-model

puma-simulator

[ASPLOS 2019] PUMA-simulator provides a detailed simulation model of a dataflow architecture built with NVM (non-volatile memory), and runs ML models compiled using the puma compiler.

puma-tensorflow

Modelling PUMA computations in tensorflow

pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

resparc-plc

shrinkbench

PyTorch library to facilitate development and standardized evaluation of neural network pruning methods.

trannsformers

Structured clustering for memristive crossbar based neuromorphic architectures