bismo

Matrix accelerator

An FPGA accelerator designed to speed up matrix multiplication in neural networks and other applications

BISMO: A Scalable Bit-Serial Matrix Multiplication Overlay for Reconfigurable Computing

GitHub

131 stars
6 watching
30 forks
Language: Scala
last commit: almost 5 years ago
Linked from 1 awesome list


Backlinks from these awesome lists:

Related projects:

Repository Description Stars
mitsuba-renderer/enoki Enables automatic transformations of numerical code to create vectorized and differentiated implementations on modern processor architectures. 1,261
linghaosong/sextans An FPGA-based accelerator for accelerating sparse matrix dense matrix multiplication 73
versilov/matrex A fast and efficient matrix library for Elixir/Erlang with C implementation using CBLAS. 479
marksbench/mb_47x16 A MicroPython module for interacting with SRAM and EEPROM on Microchip 47x16 EERAM devices. 1
linghaosong/serpens An accelerator design for fast sparse matrix-vector multiplication on an HBM FPGA 9
apache/tvm-vta A comprehensive hardware design stack for accelerating deep learning models 258
biddata/bidmat A high-performance matrix library with CPU and GPU acceleration for data mining applications. 265
brainelectronics/micropython-eeprom Provides a driver for interacting with EEPROM memory on MicroPython devices 5
nbronson/scala-stm A library-based Software Transactional Memory for concurrent data access and updates in Scala 249
denosaurs/neo A matrix and linear algebra library accelerated by WebGPU and WASM for JavaScript development. 67
peterhinch/micropython_eeprom A set of drivers for accessing various types of memory chips from MicroPython 76
a115/exmatrix An Elixir library implementing parallel matrix multiplication and other utilities for working with matrices. 58
microsoft/bitblas A library to support efficient mixed-precision matrix multiplications on GPUs for deep learning model deployment 445
tlk00/bitmagic A C++ library for compact data structures and algorithms optimized for memory efficiency and high performance 413
nickovs/uumpy A compact implementation of essential matrix and linear algebra operations for microcontrollers. 2