yeonan Goto Github PK

accel-sim-framework

This is the top-level repository for the Accel-Sim framework.

accelerating-recsys-training

Accelerating Recommender model training by leveraging popular choices -- VLDB 2022

accelergy

Accelergy is an energy estimation infrastructure for accelerator energy estimations

altis

A benchmarking suite for heterogeneous systems. The primary goal of this project is to improve and update aspects of existing benchmarking suites which are either insufficient or outdated.

ann-processor

Documentation and example programs for custom-developed instruction set architecture of the ANN Processor.

aws-fpga

Official repository of the AWS EC2 FPGA Hardware and Software Development Kit

axi-pcie-core

cactus

condensa

Programmable Neural Network Compression

corundum

Open source FPGA-based NIC and platform for in-network compute

cuda-gdb

CUDA GDB

cuda-gpu-tlb

TLB Benchmarks

deeplearningexamples

Deep Learning Examples

deeprecsys

http://vlsiarch.eecs.harvard.edu/research/recommendation/

deepspeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

dissectingtensorcores

dlrm_datasets

Set of datasets for the deep learning recommendation model (DLRM).

dnnweaver2

Open Source Specialized Computing Stack for Accelerating Deep Neural Networks.

dsa-framework

Release of stream-specialization software/hardware stack.

ev-store-dlrm

fbtt-embedding

This is a Tensor Train based compression library to compress sparse embedding tables used in large-scale machine learning models such as recommendation and natural language processing. We showed this library can reduce the total model size by up to 100x in Facebook’s open sourced DLRM model while achieving same model quality. Our implementation is faster than the state-of-the-art implementations. Existing the state-of-the-art library also decompresses the whole embedding tables on the fly therefore they do not provide memory reduction during runtime of the training. Our library decompresses only the requested rows therefore can provide 10,000 times memory footprint reduction per embedding table. The library also includes a software cache to store a portion of the entries in the table in decompressed format for faster lookup and process.

fio

Flexible I/O Tester

firesim

FireSim: Easy-to-use, Scalable, FPGA-accelerated Cycle-accurate Hardware Simulation in the Cloud

fpga-network-stack

Scalable Network Stack for FPGAs (TCP/IP, RoCEv2)

fpga-recommendation-accelerator

MLSys 2021 paper: MicroRec: efficient recommendation inference by hardware and data structure solutions

fpgaemu

Introduction to FPGA emulation and digital design. This capstone project was part of the 2021 University of San Diego Shiley-Marcos School of Engineering & Computing Showcase.

fpganic

FpgaNIC is an FPGA-based Versatile 100Gb SmartNIC for GPUs

galois

Galois: C++ library for multi-core and multi-node parallelization

galoisgpu

LonestarGPU: Irregular algorithms parallelized for GPUs

gem5-gpu