Questions & Answers

Contact us for more

What are hardware IP cores?
Hardware IP cores are IP (Intellectual Property) cores that are used to program (configure) hardware accelerators like FPGA devices. The IP cores can be in several forms like source code, netlist or configuration files.
What kind of IP cores are provided by InAccel?
InAccel provides any required form of IP cores (source code (HLS or OpenCL), netlist or configuration file) depending on the application's requirements.
Can I use the IP cores to accelerate my applications if I don't own an FPGA?
Yes. Amazon and Accelize allow users to rent FPGA modules as a service through Amazon AWS. The user can rent the FPGA resources per hour and then can instantiate the IP cores for the configuration of the FPGAs. The pricing model for the use of the IP cores is similar to Amazon AWS (cost is allocated per hour).
What is the cost of the IP cores?
The cost of the IP cores depends on the format that is required. The purchase of the source code allow users to modify the core based on the application requirements and can be used in many projects but it has higher initial cost. The use of IP cores as a service (e.g. through Amazon AWS) allow users to pay as much as the IP core is used (pay-as-you-go).
How I connect my application with the IP core?
InAccel provides all the required APIs for the seamless integration of the IP cores for your application. The current supported APIs include C/C++, Java, Python, and Scala. InAccel also provides the required libraries for the integration of the IP cores from widely-used programming frameworks like Apache Spark and Mahout. These APIs allow integration of the IP cores without any changes of your source code.
How can I use the IP cores from Apache Spark?
InAccel provides the required library, compatible with Spark, that allow users to utilize the IP cores without any changes in the Spark application. The only change that is required is the replacement of the MLlib library with the InAccel library for the use of the IP core.
Do I need to rent also typical compute units to run the IP cores?
No. When the users rent the FPGA units, they also have access to the host device that is communicating with the FPGA. That means, that the users can run their applications in the host processors that is also located in the same resources as the FPGA machine. However, the users can also rent additional typical compute units and to communicate with the FPGAs.
How is the speedup measured?
The speedup of the accelerator (IP core) is evaluated compared to a single thread contemporary processor (e.g. C4 compute unit from Amazon AWS).
Does the IP core support any type of machine learning algorithm/parameters?
Hardware IP cores have lower flexibility compared to software as they are made to map directly into hardware circuits. That means that if the user need to change some of the parameters of the code a new design (core) may be required. However, most of the cores support a maximum number of parameters that satisfy most of the applications. For example, the LR (Logistic Regression) IP core supports up to 24 classes.
What is the license agreement?
You can find here the license agreement for the InAccel IP cores.