The End of Architecture
Burton Smith, Tera Computer Company
17th Annual Symposium on Computer Architecture
Seattle, Washington
May 29, 1990
(Thanks, Wendy!)
Archive for the 'Software' Category
Here’s my contribution to the lore of software development:
Any piece of software larger than a screenful is a steaming pile of crap.
Pessimistic, yes, but perhaps also liberating in a way. Think about it.
Update:
Apparently I’m not the only one with this sentiment.
Here is a quote from Chris Hecker at GDC 2005:
Modern CPUs use out-of-order execution, which is there to make crappy code run fast. This was really good for the industry when it happened, although it annoyed many assembly language wizards in Sweden.
I first heard this when Chris was quoted by Pete Isensee (from the XBOX 360 team) in his NWCPP talk a year ago. Maybe Chris was kidding. I don’t know. What I do know is:
- He is wrong
- Smart people are believing him
- It’s time to set the record straight
Processors implement dynamic scheduling because sometimes the ideal order for a given sequence of instructions can only be known at runtime. In fact, the ideal order can change each time the instructions are executed.
Imagine your binary contains the following very simple code:
mov rax, [foo]
mov rbx, [bar]
Two loads — that’s all. Lets assume that each of the loads misses cache 10% of the time. Often, one will miss but the other will hit. If you have an in-order machine, and the first load misses, you are forced to wait — you cannot proceed to the 2nd load, and you cannot hide any of the miss latency.
No matter how much of an uber assembly coder you are, you are going to be forced to choose an order for these two loads. More likely, your compiler will make this choice for you. Either way, that choice will be wrong at least some of the time.
An OoO processor can do the right thing every time.
If you haven’t heard of Sun’s ZFS file system, here are the two important summary bullets:
- It is freaking bad ass
- OSX Leopard will support it
For slightly more info, check out these screencasts, this slide deck, or this set of vids.
I can’t even begin to describe how much I lust for Linux support (currently difficult due to CDDL incompatibility with GPL). With a little effort, one could combine ZFS and something like S3 or rsync.net to get easy off-site backup on the cheap.
Update:
Much of the power behind ZFS comes from its copy-on-write philosophy. The parallels with software transactional memory are stark. One outstanding question re transaction size: are they limited by free disk space? Traditional file systems use in-place modification, but it sounds as though ZFS may require additional free storage proportional to the size of the change.
Update 2:
I just learned about the clone ability in ZFS and my eyes just about fell out of my head. I mean seriously, this is constant time file copying. I’d have half a mind to alias cp zfs clone.
Update 3:
Man the ZFS hits just keep on coming. I’ve got a RAID-5 at home, but I’d never heard of the “RAID-5 write hole” until I read Jeff Bonwick’s blog article. Don’t miss this war story featuring ZFS’s end-to-end checksumming.
For you command-line junkies, I present size.exe. You can use it to resize a console window programmatically. Here’s an example:
C:\scripts >type vimdiff.cmd
@echo off
size 60 120
vim -d %*
size 60 80
I wrote this in C++ using Boost. If you’re interested, the source is available here.
Update 4/8/2008:
Turns out that Windows actually does have built-in support for this, it’s just hidden in a dusty corner as usual. Good thing, too, because my program didn’t work worth a damn. Here’s the official method:
mode 120,60
(Credit to Sahil Malik)
Despite the cheezy website, Foxit is a great PDF reader.
It starts up freaking instantly. Multiple documents open in multiple windows by default. Better still, there is no installation required because it’s just a single .EXE.
This is what Acrobat would be if it weren’t too busy moonlighting as the posterchild for software bloat. I wish I had discovered this a long time ago.
What would a system with no volatile memory look like? Imagine a PC without DRAMs or a HDD — instead, what if we could have a terabyte hunk of very fast nonvolatile flash, or something?
I’ve been thinking about this question, on and off, for a few years now.
I think software would change a lot. What would it mean to install software? To load a program? To open a file?
Marketwatch.com uses AJAX to embed real-time stock quotes* into its articles. For example, see this MarketWatch article about an analyst downgrade of AMD.
I’m not an expert on web development, but I think this sort of thing may be the killer app for AJAX. There was really no reasonable way to do this this well before AJAX. It would have been obscene to use a Java applet, for example.
* Technically the quotes are delayed 20 minutes, but they update in real-time.
If you know x86 assembly, you know that it’s pretty quirky and irregular. Instructions are between one and fifteen bytes long. You need to know the length of current instruction in order to find the beginning of the next.
I’ve often wondered, if one got lost in the middle of an x86 byte stream, is there any way to get back on track? Well, I did an experiment and the results were sort-of surprising.
I took a 4k chunk of assembly from the middle of a C++ hello world program, and began disassembling it at arbitrary offsets. Well over half the time, the disassembler recovered in less than three instructions. In other words, it got zero, one, or two instructions wrong. It was never confused for more than 12 instructions.
I investigated a little further, and here’s my explanation: quite often, if you lop off the first byte or two of an x86 instruction, you get another valid x86 instruction which ends on the same byte.
It struck me today that I’m prone to doing too much preparation and not enough application. I’m like a farmer who spends all day sharpening his blade, and never gets around to harvesting. Others have the opposite problem. They are farmers who spend all day hacking away with a dull blade.
The trick is to strike the proper balance, I suppose. If I tried to err on the side of too much application, at least I’d be accomplishing something.
Still, there’s something about being totally prepared that I like. I love having a tool that does exactly what I need. I love putting systems in place so “I’ll never make that mistake again!” For any given question, I love being equipped to find the answer faster than anyone else.
Latest Comments
RSS