Valve Hardware Day 2006 - Multithreaded Edition
by Jarred Walton on November 7, 2006 6:00 AM EST- Posted in
- Trade Shows
What Is Multithreading?
Before we get into discussion of how to go about multithreading, it may be beneficial for some if we explain what multithreading means. Most people who use computers are now familiar with the term multitasking. As the name implies, this involves running multiple tasks at the same time. This can be done either in the real world or on computers, and depending on what you're doing you may experience an overall increase in productivity by multitasking.
For example, let's say you're cooking dinner and it will consist of three dishes: roasted chicken, mashed potatoes, and green beans. If you were to tackle this task without any multitasking, you would first cook the chicken, then the potatoes, and finally the green beans. Unfortunately, by the time you're finished cooking the green beans, you might discover that the chicken and potatoes are already cold. So you decide to multitask and do all three at once: first you start boiling some water on the stove for the potatoes, while doing that you pull the chicken out of the refrigerator and place it into a pan and start heating the oven. Then you peel the potatoes. By now the water is boiling, so you put the potatoes into the water and let them cook. The oven is also preheated now, so you put the chicken in and let it begin cooking. The beans won't take too long to cook, so just wash them off and set them to the side for now. Eventually the potatoes are finished cooking, but before finishing those you put the green beans in a steamer and put them on the stove. Then you drain the potatoes and mash them up, add butter and whatever else you want, and now both the beans and chicken are done as well. You put everything onto plates, serve it up, and you're finished.
What's interesting to note is that the above description does not actually involve doing two things at once. Instead, you are actually doing portions of each task and then while you're waiting for certain things to complete you work on other tasks. On the classic single processor computer system, the same situation applies: the processor never really does two things at once; it just switches rapidly between various applications giving each of them a portion of the computational power of available. In order to actually do more than one thing at a time, you need more cooks in the kitchen, or else you need more processors. In the case of our example, you might have two people working on dinner, allowing more elaborate dishes to be prepared along with additional courses. Now while one person works on preparing the main three dishes we mentioned above, a second person could work on something like an appetizer and a dessert.
You could potentially even add more people, so you might have five people each preparing a single dish for a five course meal. Slightly trickier would be to have multiple people working on each dish. Rather than doing something mundane like grilled chicken, you could have a chicken dish with various other items to liven it up, along with a sauce. In extremely complex dishes, you could even break down a dish into more steps that various individuals could work on completing. Obviously, more can be accomplished as you add additional people, but you also run the risk of becoming less efficient so that some people might only be busy half the time.
We started with talking about multitasking, but the last example began to get into the concept of multithreading. In computer terminology, a "thread" is basically a portion of a program that needs to be executed. If you have a task that is computationally intensive and it is written as a single threaded application, it can only take advantage of a single processor core. Running two instances of such an application would allow you to use two processor cores, but if you only need to run one instance you need to figure out a way to take advantage of the additional computational power available. Multithreading is what is required, and in essence it involves breaking a task into two or more pieces which can be solved simultaneously.
Where multitasking can be important whether or not you have multiple processor cores available, multithreading really only begins to become important when you have the ability to execute more than one thread at a time. If you have a single core processor, multithreading simply adds additional overhead while the processor spends time switching between threads, and it is often better to run most tasks as a single thread on such systems. It's also worth noting that it becomes much easier to write and debug programming code when it is running as a single threaded application, because you know exactly in what order each task will execute.
We will return to this "cooks in the kitchen" example a bit more when we talk about the various types of threading environments. It's a bit simplistic, but hopefully it gives you a bit better idea about what goes on inside computer programs and what it means to break up a task into threads.
Before we get into discussion of how to go about multithreading, it may be beneficial for some if we explain what multithreading means. Most people who use computers are now familiar with the term multitasking. As the name implies, this involves running multiple tasks at the same time. This can be done either in the real world or on computers, and depending on what you're doing you may experience an overall increase in productivity by multitasking.
For example, let's say you're cooking dinner and it will consist of three dishes: roasted chicken, mashed potatoes, and green beans. If you were to tackle this task without any multitasking, you would first cook the chicken, then the potatoes, and finally the green beans. Unfortunately, by the time you're finished cooking the green beans, you might discover that the chicken and potatoes are already cold. So you decide to multitask and do all three at once: first you start boiling some water on the stove for the potatoes, while doing that you pull the chicken out of the refrigerator and place it into a pan and start heating the oven. Then you peel the potatoes. By now the water is boiling, so you put the potatoes into the water and let them cook. The oven is also preheated now, so you put the chicken in and let it begin cooking. The beans won't take too long to cook, so just wash them off and set them to the side for now. Eventually the potatoes are finished cooking, but before finishing those you put the green beans in a steamer and put them on the stove. Then you drain the potatoes and mash them up, add butter and whatever else you want, and now both the beans and chicken are done as well. You put everything onto plates, serve it up, and you're finished.
What's interesting to note is that the above description does not actually involve doing two things at once. Instead, you are actually doing portions of each task and then while you're waiting for certain things to complete you work on other tasks. On the classic single processor computer system, the same situation applies: the processor never really does two things at once; it just switches rapidly between various applications giving each of them a portion of the computational power of available. In order to actually do more than one thing at a time, you need more cooks in the kitchen, or else you need more processors. In the case of our example, you might have two people working on dinner, allowing more elaborate dishes to be prepared along with additional courses. Now while one person works on preparing the main three dishes we mentioned above, a second person could work on something like an appetizer and a dessert.
You could potentially even add more people, so you might have five people each preparing a single dish for a five course meal. Slightly trickier would be to have multiple people working on each dish. Rather than doing something mundane like grilled chicken, you could have a chicken dish with various other items to liven it up, along with a sauce. In extremely complex dishes, you could even break down a dish into more steps that various individuals could work on completing. Obviously, more can be accomplished as you add additional people, but you also run the risk of becoming less efficient so that some people might only be busy half the time.
We started with talking about multitasking, but the last example began to get into the concept of multithreading. In computer terminology, a "thread" is basically a portion of a program that needs to be executed. If you have a task that is computationally intensive and it is written as a single threaded application, it can only take advantage of a single processor core. Running two instances of such an application would allow you to use two processor cores, but if you only need to run one instance you need to figure out a way to take advantage of the additional computational power available. Multithreading is what is required, and in essence it involves breaking a task into two or more pieces which can be solved simultaneously.
Where multitasking can be important whether or not you have multiple processor cores available, multithreading really only begins to become important when you have the ability to execute more than one thread at a time. If you have a single core processor, multithreading simply adds additional overhead while the processor spends time switching between threads, and it is often better to run most tasks as a single thread on such systems. It's also worth noting that it becomes much easier to write and debug programming code when it is running as a single threaded application, because you know exactly in what order each task will execute.
We will return to this "cooks in the kitchen" example a bit more when we talk about the various types of threading environments. It's a bit simplistic, but hopefully it gives you a bit better idea about what goes on inside computer programs and what it means to break up a task into threads.
Facebook
Twitter
RSS
55 Comments
View All Comments
JarredWalton - Tuesday, November 7, 2006 - link
What's with the octal posting? Too many CPU cores running? ;)I deleted the other 7 identical posts for you. Careful with that Post Comment button!
saratoga - Tuesday, November 7, 2006 - link
Server kept timing out when I hit post, so I assumed it wasn't committing :)exdeath - Tuesday, November 7, 2006 - link
You can see my recent comments on this topic here:http://www.dailytech.com/Article.aspx?newsid=4847&...">http://www.dailytech.com/Article.aspx?newsid=4847&...
In my experience relying on atomic CPU swap operations isn't enough as it only works with a single value (32 bit word for example).
While you lock and swap a 32 bit Y value, someone else has just finished reading the newly written X value but beat you to the lock to read the old Y value before you've updated. Clearly whole data structures need to be coherent, not just small atomic values.
Also it’s unusual to modify objects observable states mid frame. Even if you avoided the above example so that the X,Y pair was always updated together, you'd still have different objects interpreting the position as a whole of that object in different places at different times. State data must be held constant to all observers throughout the context of a single frame.
exdeath - Tuesday, November 7, 2006 - link
Even if you avoided the above example so that the X,Y pair was always updated together, you'd still have different objects interpreting the position as a whole of that object in different places at different times in the same frame.JarredWalton - Tuesday, November 7, 2006 - link
I'm assuming your comment is in regards to the PS3/Cell comments on the last page? It's sort of sounds like you're arguing about the way Valve has chosen to go about doing things, or that you disagree with some of the opinions they've expressed concerning other hardware. We have only tried to provide a very high-level overview of what Valve is doing, and we hardly touched the low-level details -- Valve didn't spend a lot of time on specific implementation issues either. All they did was provide us with some information about what they are doing, and a bit of opinion on what they think of the rest of the hardware options.Preventing anything else from doing write operations to the world state during an entire frame in order to keep things coherent is a big problem with multithreading. Apparently Valve has found a way around that, or at least found a way to do it more efficiently, using lock free and wait free algorithms. No, I can't honestly say I really understand what those algorithms do, but if they say it worked better for their code base I'm willing to trust them.
As far as the PS3/Cell processor goes, Valve did say that they have various thoughts on how to properly utilize the architecture. It is simply going to be more difficult to do relative to Xbox 360 and PC. It's not impossible, and companies are definitely going to tackle this problem. As far as how they tackle it, I'm more than a bit rusty on my coding background, and other than high-level details I'm not too concerned how they improve their multithreading code on any specific platform, just that they do it.
exdeath - Tuesday, November 7, 2006 - link
The other issue is OS support.Compiler add-on's or third party APIs can only serve to hide the details or make things look cleaner. But no matter what, the final barrier between the application and the OS are the API calls provided by the OS threading model. Thus no third party implementation can be better than the OS thread model itself in terms of performance and overhead. All those can do is make it easier to use at the top by handling the OS details.
I imagine threading APIs on popular OSes will start to evolve, just like graphics APIs have, once everyone gets on the multi-core bandwagon and starts to get a feel for what's available in the OS APIs and what they'd rather have. So far, Vista's thread pool API looks good, but I still don't see an API to determine such basic things as checking if the work queue is empty and all threads are idle, etc.
Currently I find it's easier to implement my own thread pool manager which does atomic increments and decrements on a 'task count' variable as tasks are entered or completed in the queue. Checking if all tasks are done involves testing that task count against 0 and signaling an event flag that wakes any management threads sleeping until all its work tasks to complete. It also allows for more flexibility in 'before and after' housekeeping as work threads move from task to task and that kind of control isn't offered in the XP’s built in thread pool API, nor Vista’s as far as I can tell.
exdeath - Tuesday, November 7, 2006 - link
Not arguing their methods, a lot of things in this article are in line with my own opinions on multithreading, pretty much the best way to got about it. I'm just pointing out that atomic lock/swap operations in hardware are very primitive and typically operate only on CPU word size values, not entire data structures. Thus it's possible between doing two atomic operations on two variables on one core, another core can get an old version of one variable and a new version of another.core1: compute X
core2: ...
core1: lock/write x
core2: read x, get newly written version
core1: compute Y
core2: read Y, get old y before the update
core1: lock/write Y
core2: ...
The task on core2 is working with inconsistent data, the new X and the old Y. If the task on core2 only uses the data as input, i.e.: AI tracking another AI entity, it has the wrong position, and won't know about it since it has no need to perform its own lock/write (so it never gets the exception that says the value changed). Even if it did, it would have to throw out all work and redo it with the new Y, and then it could possibly change again.
Looping and retrying seems wasteful. And I’m thinking the only way to catch such a hardware error on a failed lock/write update is via exceptions, and handling a thrown exception on an attempt to write a single 32 bit value is very wasteful of CPU cycles.
In my own research I have had excellent results with double buffering any modified data. Each threaded task only updates its hidden internal working state for frame n+1 while all reads to the object are read from its external current state for frame n. At the end of the frame when all parallel tasks have completed, the current/working states are swapped, and the work queue is filled again to start the next frame.
This ensures that throughout the entire computation of frame n+1, the current frame n state will be available to all threads, and guaranteed to not be modified through the duration of current frame. So basically all threads can read anything they want and modify their own data. On PC/360 the time to swap everything is basically nothing; you just swap a few pointers, or a single pointer to an array/structure of current/working data for the frame.
On the PS3 some data copying and moving will be required, but this is mandatory due to design anyway and assisted by an extremely smart and powerful DMAC.
One place to be critical about is message passing between objects since it requires posting (writing) data to be picked up by another object. But the time to lock/post/unlock a queue is negligible compared to the time it takes to process the results leading up to the creation of the message. This is similar to the D3D notion of doing as much as you can before you lock and only do the minimal work needed inside the lock and unlock as quickly as possible.
GhandiInstinct - Tuesday, November 7, 2006 - link
Jarred Walton,My question: Will Valve's games in 2007 be released with specificaitons such as: "For minimum requirements you need a dual-core cpu, for maximum results you need a quad-core" or anything to that nature? Because I seem to be confused in what Valve is working on dual or quad or both or neither or something different, and what I should get to best utilize their games and multi-core software in general.
Thanks.
JarredWalton - Tuesday, November 7, 2006 - link
Episode Two should come out sometime in 2007, and before that happens you will get the multithreading patch affecting previous Source engine titles. Right now, it doesn't sound like anything released in the next year or so from valve is going to require dual cores. That's what I was trying to get out on the conclusion page where I mentioned that they are targeting an "equivalent experience" regardless of what sort of processor you are running.So just like you could turn down the level of detail in Half-Life 2 and run it on DX8 or even DX7 hardware, Source engine should be able to accommodate single core processors all the way up through N-core processors. The engine will spawn as many threads as you have processor cores, with one main thread serving as the controller and N - 1 helper threads. Xbox 360 for example would have 5 helper threads plus the master thread, because it has three course each capable of executing to threads simultaneously.
Patrese - Tuesday, November 7, 2006 - link
Great article, good to see dual-quad cores being used for something in games. By the way, the kitchen examples made me hungry... :)