MXNet Extensions
Since I joined Amazon and started working on the Apache (incubating) MXNet open source deep learning framework I kept looking for ways to integrate hardware acceleration. The main problem is […]
Building MXNet on EC2 ARM instances
Recently AWS announced the availability of ARM based EC2 instances. So I thought id try out compiling MXNet to run on one of these instances since MXNet has already been […]
Back to basics: Linear Algebra – Calculating the diagonal of a multi-dimensional matrix
Recently I had the need to calculate the diagonal of a matrix. Initially I thought, wow, here we go again: And initially this worked. But then I realized that it […]
Getting started with cuDNN
I was in need of getting familiar with calling cuDNN routines, but the descriptor interface was a little confusing. So I put together this example calling the pooling operator for […]
Paper Accepted: Python + HLS + SDSoC
This paper is a new direction looking at how we can take advantage of the C-based HLS tools that are currently available by translating Python functions to C so that […]
Serializing Python objects to JSON
Python is great, and there are a lot of tools and libraries for all sorts of functionality available now. But sometimes you need to stitch tools together and use some […]
Poster Presented: Hot & sPyC: Improving Productivity with Python
At the 2017 Reconfig conference I presented some work-in-progress on a set of Python tools that ive been developing to help with implementing Python Applications with FPGAs. A PDF version […]
A Xilinx-familiar user’s experience on Amazon AWS F1/AMI
I am an avid FPGA enthusiast and have worked with FPGAs for years, programming VHDL, Verilog, and C/C++ with High Level Synthesis (HLS) tools like Impulse-C and Vivado HLS. I […]
Paper Accepted: Custom ISA processors w/ HLS
This paper is sort of an offshoot of our previous work on estimating the performance of computations using scheduling. To get a better understanding of the performance we started looking […]
Paper Accepted: Parallelizing Matlab Compiler
Continuing with our previous work on heterogeneous systems, in this paper we describe the compilation framework to take an initial sequential Matlab program and parallelize it automatically across a CPU+GPU+FPGA system. […]
Sam Skalicky 