<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Hardware Acceleration on Muk's Blog</title><link>https://jcmk77.github.io/categories/hardware-acceleration/</link><description>Recent content in Hardware Acceleration on Muk's Blog</description><generator>Hugo -- gohugo.io</generator><language>en-us</language><managingEditor>mca307@sfu.ca (Mukun)</managingEditor><webMaster>mca307@sfu.ca (Mukun)</webMaster><lastBuildDate>Thu, 02 Apr 2026 11:05:00 -0600</lastBuildDate><atom:link href="https://jcmk77.github.io/categories/hardware-acceleration/index.xml" rel="self" type="application/rss+xml"/><item><title>Hardware Acceleration: Likelihood Kernel</title><link>https://jcmk77.github.io/post/ensc453likelihoodkernel/</link><pubDate>Thu, 02 Apr 2026 11:05:00 -0600</pubDate><author>mca307@sfu.ca (Mukun)</author><guid>https://jcmk77.github.io/post/ensc453likelihoodkernel/</guid><description>A retrospective on an ENSC 453 likelihood-kernel project, and how the real breakthrough came from redesigning the FPGA pipeline around data movement instead of forcing the original irregular access pattern onto the hardware.</description></item><item><title>Hardware Acceleration: GEMM Performance Engineering</title><link>https://jcmk77.github.io/post/ensc453gemm/</link><pubDate>Thu, 02 Apr 2026 10:15:00 -0600</pubDate><author>mca307@sfu.ca (Mukun)</author><guid>https://jcmk77.github.io/post/ensc453gemm/</guid><description>A retrospective on five ENSC 453 labs, from OpenMP GEMM on CPU to HLS on FPGA and CUDA on GPU, and how each one changed how I think about performance.</description></item></channel></rss>