Mark Gottscho, Ph.D.

A Template for Writing a Microarchitecture Specification

Tue, 20 Feb 2024 00:00:00 +0000

Figure 1. My prompt to Gemini: "please generate a banner image suitable for a 'how to write a microarchitecture specification' blog post."

Architecture and microarchitecture are two different levels of abstraction. The former is about the hardware/software interface; the latter is about the hardware implementation. The microarchitect crafts a source of truth for the hardware team to anchor their work on.

Why Codesign is Important (Architecture Spec Series, Part 1)

Sat, 02 Dec 2023 00:00:00 +0000

Computer architecture is all about balance. Nail it, and you’ve got yourself a rock-solid, one-of-a-kind platform with some seriously cool features and a lot of developers. Maybe even a $1T cap. But if you trip up even a little, you could end up wasting years of work into a pricey silicon paperweight. That’s why we need codesign.

New Wikipedia Article on Energy Proportionality

Sun, 25 Jan 2015 00:00:00 +0000

I’ve started a new Wikipedia article on basic concepts and research efforts in energy proportionality. You can read and contribute to it here.

A Brief Git Tutorial for Collaborative Research

Sat, 24 Jan 2015 00:00:00 +0000

Continuing in the trend I’ve established with some technical tutorials that have proven to be useful to others, I’ve decided to write another brief one, this time focusing on Git version control for researchers. Why the emphasis on researchers? One often comes across academic code that is poorly documented, or there are various copies of the code being developed simultaneously by different people, none of whom communicate their changes to one another, making collaboration and follow-up work harder.

Easily Running SPEC CPU2006 Benchmarks in the gem5 Simulator

Sat, 20 Sep 2014 00:00:00 +0000

It appears that a good number of people found my articles from 2013 on building gem5 and SPEC CPU2006 benchmarks for Alpha useful! So due to some requests I’ve decided to make an additional post on how to get the SPEC benchmarks and gem5 you set up actually running.

Is the Internet of Things What You Think It Is?

Tue, 10 Dec 2013 00:00:00 +0000

Ron Wilson of Altera posted a short piece about the IoT and two contrasting viewpoints about its structure. This is worth a look!

Cross-Compiling SPEC2006 benchmarks for Alpha ISA on Ubuntu 12.04 x86-64

Thu, 31 Oct 2013 00:00:00 +0000

This guide will show you how to cross-compile SPEC2006 for Alpha using your regular old Ubuntu machine running on Intel. In particular, I have done this so that they can be run in gem5 for the Alpha ISA. I assume that you have a copy of the SPEC benchmarks and the input vectors.

Quick gem5 Build Guide for Alpha ISA on Ubuntu 12.04 x86-x64 Host

Fri, 25 Oct 2013 00:00:00 +0000

In this guide, I will walk you through a quick way to get gem5 built for the Alpha ISA using a Ubuntu 12.04 64-bit host. I have not tried these methods on any other platform. If you get stuck, you can always refer to the documentation at gem5.org. Nothing is presented here that doesn’t already exist somewhere else, but I found that some other methods did not work for me. These steps are based on gem5 revision f75ee4849c40 and the website as of 10/24/13. Please refer to the website for any specific version requirements. Make sure you have the following tools:

Anandtech's Look at Altera OpenCL SDK for FPGAs

Tue, 22 Oct 2013 00:00:00 +0000

If you’re into hardware acceleration and heterogeneous computing, this is a good read. Currently, FPGAs are not commonly used by programmers to accelerate their workloads due to the difficulty of hardware design compared to software. OpenCL support potentially changes the game by allowing FPGA accelerators to be used in a manner similar to GPGPUs. This will be interesting!

Richard Hamming's 1986 Talk at Bell Labs: 'You and Your Research'

Thu, 17 Oct 2013 00:00:00 +0000

Today, while working on my fellowship application, I was pondering the nature of graduate research and how one comes up with truly novel ideas. My friend and colleague, Lucas Wanner, sent me this transcription of a talk Richard Hamming gave many years ago on how one does great research. I found it enlightening; hopefully you will, too.

Hello World

Sun, 29 Sep 2013 00:00:00 +0000

First post! I’ll be blogging about my experiences as a Ph.D student in electrical engineering at UCLA. It may just be thoughts and insights about grad school, tips for other engineers and students on specific topics, and other stuff. We’ll see! For now, here’s a picture of a LeafLabs Maple board that I used a few years ago. Yay electronics!