FPGA acceleration lifecycle
made simple.


Deploy. Scale. Orchestrate. Monitor.



What is InAccel

InAccel offers 1-click deployment of FPGA workloads on premises, on cloud, using Docker, Podman, Singularity or Kubernetes. By taking care of the whole FPGA acceleration lifecycle we make it possible for you to focus on the application. The limit is your imagination!


Trusted By


Products



Ready to Use FPGA Accelerators

InAccel started as an IP core production company and later on transformed to the company it is today to help the adoption of FPGAs. InAccel still develops IP cores for customers and has a pool of available IP cores mainly targeting the domain of Machine Learning.


Store and version FPGA binaries.

InAccel offers an end-to-end Bitstream repository solution covering the deployment lifecycle of your FPGA binaries to manage target platforms, allow artifact versioning and accelerator distribution.


A reliable, scalable and distributed acceleration system

Coral is a framework that allows the distributed acceleration of large data sets across clusters of FPGA resources using simple programming models. It abstracts away the FPGA resources to a pool of accelerators and takes care of scheduling and orchestrating jobs for acceleration.


A unique Monitor to get valuable insight of your FPGAs

Coral monitor is a real-time monitoring tool designed specifically for custom resources like FPGAs and GPUs. It can provide power, thermal and structural information as well as details for all the running tasks.

FPGA IP Cores


Ready to Use FPGA Accelerators


InAccel started as an IP core production company and later on transformed to the company it is today to help the adoption of FPGAs. InAccel still develops IP cores for customers and has a pool of available IP cores mainly targeting the domain of Machine Learning.

Bitstream Repository


Store and version FPGA binaries.


InAccel offers an end-to-end Bitstream repository solution covering the deployment lifecycle of your FPGA binaries to manage target platforms, allow artifact versioning and accelerator distribution.

Coral Resource Manager


A reliable, scalable and distributed acceleration system


Coral is a framework that allows the distributed acceleration of large data sets across clusters of FPGA resources using simple programming models. It abstracts away the FPGA resources to a pool of accelerators and takes care of scheduling and orchestrating jobs for acceleration.

Coral Monitor


A unique Monitor to get valuable insight of your FPGAs


Coral monitor is a real-time monitoring tool designed specifically for custom resources like FPGAs and GPUs. It can provide power, thermal and structural information as well as details for all the running tasks.

Deploy Anywhere



Docker

Docker plugin


Kubernetes CSI driver and device plugin


Podman rootles and rootful support


Singularity is perfect for rootless client containers

Use Cases


Machine Learning

You can find machine learning almost everywhere nowadays. Data scientists train multiple models until they get what they are looking for in terms of accuracy and performance and then they need a very fast inference system. FPGAs are a perfect match for machine learning inference and they can also provide reasonable speedup for the training part.



Logistic Regression

Intel/Xilinx

train

KMeans

Intel/Xilinx

train

XGBoost

Xilinx

train

Naive Bayes

Intel/Xilinx

inference


Deep Learning

FPGAs are a natural choice for implementing neural networks as they can handle different algorithms in computing, logic, and memory resources in the same device. Try out our ResNet50 online demo



ResNet50

Intel/Xilinx

inference

MobileNet

Xilinx

inference


Genomics

Genomics is fundamental to diagnosis and cure of rare, inherited diseases but applications need a lot of computational power to produce results. Try now online our Smith-Waterman accelerator or contact us to learn how you can accelerate your BWA and PairHMM applications.


BWA Mem

Intel

PairHMM

Intel

Smith Waterman

Intel/Xilinx



Financial

Stock price


BlackScholes

Intel/Xilinx

Binomial

Xilinx

PDE

Intel

Monte Carlo

Intel/Xilinx



Computer Vision

Computer vision stuff


Color Detect

Xilinx

Stero BM

Xilinx



Compression

GZip and Lz4 compression acceleration through an easy to use GUI on a cluster of FPGAs.


Lz4

Xilinx

Compress
Decompress

GZip

Xilinx

Compress


Encryption/Decryption

Accelerating encryption and decryption

AES

Intel/Xilinx

256bit CBC


Solutions



1

Login to InAccel Studio



Navigate to InAccel Studio and select one from the available options to login.
2

Select an application


Ready to use examples include:

  • Genomics (Intel)
  • Machine Learning (InAccel)
  • Deep Learning (Xilinx)
  • Compression (Vitis)
  • Encryption (Vitis)
  • Quantitative Finance (Intel + Vitis)
  • Computer Vision (Vitis)
3

Run on your browser



Run your applications right from your browser, using a terminal or a Python notebook.
InAccel Studio

Speed up your applications from your browser

InAccel’s Accelerated Machine Learning Studio (AML) is a fully integrated framework that allows to speedup your C/C++, Python, Java and Scala applications with zero code changes.

It aims to maintain the practical and easy to use interface of other open-source frameworks and at the same time to accelerate the training or the classification part of machine learning models.

The accelerators can achieve up to 15x speedup compared to multi-threaded high performance processors. InAccel provides all the required APIs in Python, C/C++ and Java for the seamless integration of the accelerators with your applications.

InAccel studio is a managed cloud platform for data scientists and software developers. We provide the tools to utilize the power of FPGA accelerators in the most efficient way.
Accelerated Apache Spark ML

Seamless integration with RDD and Dataframe

Logistic
Accelerated Scikit Learn

Zero code changes, instant acceleration

Scikit Learn

White Papers


Machine Learning


Accelerated XGBOOST on Xilinx FPGA cards


Genomics


Acceleration of Sequence Alignment and Variant Calling Using Intel FPGAs

Quantitative Finance


High-Frequency Trading with Intel PAC FPGAs


Deep Learning


Scalable Deployment of Inspur Accelerator on Multi-tenant Intel FPGA Cluster

Simple, transparent pricing


Free

Community

APIs in Scala, Java, Python and C++
Up to 2 nodes
Unlimited FPGAs per node
Native CLI automation tool
Bitstream packaging and versioning
-
-
-
300$/node/month

Enterprise

APIs in Scala, Java, Python and C++
Unlimited nodes
Unlimited FPGAs per node
Native CLI automation tool
Bitstream packaging and versioning
Web UI to monitor your FPGA resources
Bitstream deployment pipelines
24x7 uptime support