It's recently been a year since I started working on my pet OS project, and I often end up looking backwards at what I have done, wondering what made things difficult in the beginning. One of my conclusions is that while there's a lot of documentation on OS development from a technical point of view, more should be written about the project management aspect of it. Namely, how to go from a blurry "I want to code an OS" vision to either a precise vision of what you want to achieve, or the decision to stop following this path before you hit a wall. This article series aims at putting those interested in hobby OS development on the right track, while keeping this aspect of things in mind.
To view parent comment, click here.
To read all comments associated with this story, please click here.
Member since:2006-02-15
As for your last sentence, isn't the consensus that GCC output performs poorly compared to other commercial compilers such as intel's?
I would be interested in seeing a fair comparison.
Apparently this is true. I googled a bit and found three benchmarks:
http://macles.blogspot.com/2010/08/intel-atom-icc-gcc-clang.html
http://multimedia.cx/eggs/intel-beats-up-gcc/
http://www.luxrender.net/forum/viewtopic.php?f=21&t=603
They're all from 2009 or 2010 and in all of them icc beats GCC by quite a large margin, not to mention icc is much faster at doing the actual compiling, too. Quite surprising. What could the reason be then, why does an open-source compiler fare so poorly against a commercial one?
Edited 2011-01-30 03:58 UTC
Member since:2011-01-28
"What could the reason be then, why does an open-source compiler fare so poorly against a commercial one?"
Without looking at the assembly, it's just speculation on my part.
I've read that GCC is rather ignorant of code & data locality and cpu cache lines; therefor binary code placement is arbitrary rather than optimal. In theory, this could make a huge difference.
Function inlining is usually good, but only until the cache lines are full, further inlining is detrimental. This may be a weakness for GCC.
The compilers inject prefetch hints into the code, maybe GCC predicts the branches less accurately at compile time?
GLIBC is notoriously bloated. I don't know if intel links in it's own streamlined c library? That might make a difference.
As for compilation time, ICC has an "unfair" advantage. If GCC had been compiled under ICC, then GCC itself might perform much better - though I'm not sure the GCC folks would want to admit to that.
Member since:2011-01-28
Thinking about it further... the GCC bottleneck may not be the compiler at all but just the malloc implementation.
In an earlier post, I had mentioned that I made my own malloc which performs much better than GNU's malloc in multithreaded apps.
I think my implementation fits somewhere between ptmalloc and Hoard on the following chart.
http://developers.sun.com/solaris/articles/multiproc/multiproc.html
I developed mine from scratch, so I have no idea why GNU's malloc is slow, but I'm baffled as to why GNU continues to use a slow implementation?
Member since:2010-02-15
Member since:2005-07-06
Well *I* am not surprised: remember that very recently distribution have changed their JPEG rendering libraries with a 20% performance improvement.
You can see this in two ways:
- the optimistic view: nice a 20% improvement!
- the realistic view: JPEG are very old, the improved library use ISA which are very old too, why only now do we have the 20% improvement?
My view is that: open-source developpers like to have very flexible software combinations so GCC compiles many language on many architecture, but from a performance POV the situation isn't very good..
Member since:2006-11-02
1) Because GCC is *old* in terms of computer software. It has decades of cruft to take along for the ride.
2) GCC is portable. It's optimizations can only take the optimization so far, if not to break compatibility with, say, the 68040.
3) Exactly because it is open source. That model means gradual evolution, almost never rewriting/reinvention.
Official Apple statement on PRISM and privacy: "Regardless of the circumstances, our Legal team conducts an evaluation of each request and, only if appropriate, we retrieve and deliver the narrowest possible set of information to the authorities. In fact, from time to time when we see inconsistencies or inaccuracies in a request, we will refuse to fulfill it." This is basically Apple re-publishing their earlier statement in a more official manner. You either believe it, or you don't.The open source Contiki operating system and its commercial Thingsquare distribution are making strides towards the connected home. According to a Computerworld article, a new LED light bulb manufacturer is putting small computers into their light bulbs. Each computer runs the Contiki OS, which gives each bulb an IP address and allows them to be controlled with a smartphone application. To connect the bulbs to the application, the bulbs use both Wi-Fi and the much lower power IEEE 802.15.4 mesh technology.
"Google asked the secretive Foreign Intelligence Surveillance Court on Tuesday to ease long-standing gag orders over data requests it makes, arguing that the company has a constitutional right to speak about information it's forced to give the government. The legal filing, which cites the First Amendment's guarantee of free speech, is the latest move by the California-based tech giant to protect its reputation in the aftermath of news reports about sweeping National Security Agency surveillance of Internet traffic." Draining the ditch after the cow has drowned in it."I can't find one person who has been using the Nexus 7 for an extended period of time, and hasn't seen a massive downgrade in performance. Just what kind of downgrade are we talking here? I cannot pick up my Nexus 7 without experiencing problems like a lag of ten seconds, or more, just to rotate the display; touches refusing to acknowledged; stuttering notification panel actions; and unresponsive apps." Fully and utterly agreed. My Nexus 7 was blazing-fast and awesome for a few months, and at some point, it just started sucking. Just like that. I've tried loads of ROMs, and nothing helps.A new release of the hobby operating system MenuetOS! The release notes are a bit non-descript, but you'll have to take what you can get: "updates and improvements (picview, httpc, ehci, ...)"."The Internet is one of the most transformative technologies of our lifetimes. But for 2 out of every 3 people on earth, a fast, affordable Internet connection is still out of reach. And this is far from being a solved problem. There are many terrestrial challenges to Internet connectivity - jungles, archipelagos, mountains. There are also major cost challenges. Right now, for example, in most of the countries in the southern hemisphere, the cost of an Internet connection is more than a month's income. Solving these problems isn't simply a question of time: it requires looking at the problem of access from new angles. So today we're unveiling our latest moonshot from Google[x]: balloon-powered Internet access." Insane.
"MineAssemble is a tiny bootable Minecraft clone written partly in x86 assembly. I made it first and foremost because a university assignment required me to implement a game in assembly for a computer systems course. Because I had never implemented anything more complex than a 'Hello World' bootloader before, I decided I wanted to learn about writing my own kernel code at the same time. Note that the goal of this project was not to write highly efficient hand-optimized assembly code, but rather to have fun and write code that balances readability and speed. This is primarily accomplished by proper commenting and consistent code structuring." Just cool.
Jon Rubinstein, former CEO of Palm: "Well, I'm not sure I would have sold the company to HP. That's for sure. Talk about a waste. Not that I had any choice because when you sell a company you don't get to decide that. Obviously, the board and shareholders decide that. If we had known they were just going to shut it down and never really give it a chance to flourish, what would have been the point of selling the company? I think the deal we had with Verizon really hurt us, but who knew that at the time? These things are all hindsight.""And so it is with Dell's Alienware X51 R2, a small form factor gaming PC in console digs. It's shaped similar to Microsoft's Xbox 360 Slim, and though it's slightly larger than either a 360 or PlayStation 3, the X51 R2 would be right at home in a living room setting nestled next to a large screen TV. Indeed, it's adept at running Steam's Big Picture mode, and if your primary objective is to play games in the living room, go ahead and consider the X51 R2 a hybrid game console." This is obviously not the only machine like this - still, these are very valid console alternatives even for those that don't like being hunched over with a cramped WASD-claw. Also, PC gamers among us: could you get away with the $699 model for gaming?
From Bloomberg: "Microsoft, the world's largest software company, provides intelligence agencies with information about bugs in its popular software before it publicly releases a fix, according to two people familiar with the process. That information can be used to protect government computers and to access the computers of terrorists or military foes." The lid has officially been blown off.
Member since:
2011-01-28
"Even to this day it's often easy to beat a compiler's output"
"I quite doubt that. There's been plenty of discussion of this and the general consensus nowadays is that it's really, really hard to beat atleast GCC's optimizations anymore."
I feel you've copied my phrase entirely out of context. I want to re-emphasize my point that c compilers are constrained to strict calling conventions which imply shifting more variables between registers and the stack than would be possible to do by hand.
I'm not blaming GCC or any other compiler for this, after all calling conventions are very important for both static and dynamic linking. However it can result in code which performs worse than if done by hand.
As for your last sentence, isn't the consensus that GCC output performs poorly compared to other commercial compilers such as intel's?
I would be interested in seeing a fair comparison.
Edited 2011-01-30 03:37 UTC