Coral FPGA cluster manager is a framework that allows the distributed acceleration of large data sets across clusters of FPGA resources using simple programming models.
It is designed to scale up from single devices to multiple FPGAs, each offering local computation and storage. It also allows sharing of the resources from multiple applications, processes and users automatically.
It facilitates the easy deployment, scaling and resource management of FPGA clusters.
InAccel orchestration platform helps organizations manage FPGA resource allocation and increase cluster utilization. InAccel Coral manager pools FPGA resources and then applies advanced scheduling to dynamically set policies and orchestrate jobs.
Scale-out your applications to multiple FPGAs on the same server or to multiple servers (using Kubernetes plug-in) without changing your code.
InAccel’s Coral FPGA cluster manager dispatches the accelerated functions to the FPGA cluster automatically.
It also allows automatically scaling to multiple kernels on the same FPGA.
InAccel’s Coral FPGA cluster manager allows seamless sharing of the FPGA resources. from:
– Multiple threads
– Multiple processes
– Multiple applications
– Multiple users
It allows dynamic resource management and scheduling of the accelerated function to the FPGA cluster automatically.
It also allows automatic management of the bitstreams.
InAccel offers all the required high-level functions (APIs) that make it easy to accelerate your applications by offloading the most computationally intensive tasks to the FPGAs.
No need to modify your application or to use an unfamiliar parallel programming language (like OpenCL).
And you can use it interactively from C/C++, Scala and Python shells. No need for OpenCL directives.
InAccel decouples the bitstreams from the Software developer.
SW developers do not need any more to work with bitstreams.
FPGA Resource Manager automatically fetch the right bitstream based on the requested function invoking and handles the programming and scheduling of the FPGAs.
Deploy FPGAs as easy as any other software library.
InAccel FPGA orchestrator comes with a unique Monitor tool that allows to get valuable insight on the performance of the kernels in the FPGAs.
The monitor tool can be used to get information for the execution of the accelerators in the FPGAs helping optimize the performance of your applications.
Launch a container with InAccel’s Docker image or even deploy it as a daemonset on a Kubernetes cluster and enjoy acceleration services at the drop of a hat.
Deploy your accelerators from Apache Spark, Scikit-learn, Keras, Jupyter notebooks and H2O.
Instant deployment with zero code changes.
Kubernetes on FPGA extends the industry standard container orchestration platform with FPGA acceleration capabilities.
With first class support for FPGA resources scheduling, developers and DevOps engineers can now build, deploy, orchestrate and monitor FPGA-accelerated application deployments on heterogeneous, multi-cloud clusters.
InAccel supports all the FPGA boards compatible with the OpenCL frameworks from Xilinx and Intel.
“InAccel framework gives you a great abstraction layer resulting in less code. It has a monitoring tool and other language bindings like Python, etc. making it very easy to integrate with our applications.”
“…this is where InAccel’s framework helps immensely: we don’t need to code MT C++, rather we call the FPGA from multiple workers and we let the InAccel framework schedule the FPGA workloads as fast as possible”
“We found it very useful as it allows high-level abstracted kernel calls instead of OpenCL which requires complex implementation of FPGA kernel calls.”
Click to download the white paper