Multithreading (computer architecture)
||This article has multiple issues. Please help improve it or discuss these issues on the talk page.
Multithreading computer central processing units have hardware support to efficiently execute multiple threads. These are distinguished from multiprocessing systems (such as multi-core systems) in that the threads have to share the resources of a single core: the computing units, the CPU caches and the translation lookaside buffer (TLB). Where multiprocessing systems include multiple complete processing units, multithreading aims to increase utilization of a single core by using thread-level as well as instruction-level parallelism. As the two techniques are complementary, they are sometimes combined in systems with multiple multithreading CPUs and in CPUs with multiple multithreading cores.
The multithreading paradigm has become more popular as efforts to further exploit instruction level parallelism have stalled since the late-1990s. This allowed the concept of throughput computing to re-emerge to prominence from the more specialized field of transaction processing:
- Even though it is very difficult to further speed up a single thread or single program, most computer systems are actually multi-tasking among multiple threads or programs.
- Techniques that would allow speedup of the overall system throughput of all tasks would be a meaningful performance gain.
The two major techniques for throughput computing are multiprocessing and multithreading.
Some advantages include:
- If a thread gets a lot of cache misses, the other thread(s) can continue, taking advantage of the unused computing resources, which thus can lead to faster overall execution, as these resources would have been idle if only a single thread was executed.
- If a thread cannot use all the computing resources of the CPU (because instructions depend on each other's result), running another thread can avoid leaving these idle.
- If several threads work on the same set of data, they can actually share their cache, leading to better cache usage or synchronization on its values.
Some criticisms of multithreading include:
- Multiple threads can interfere with each other when sharing hardware resources such as caches or translation lookaside buffers (TLBs).
- Execution times of a single thread are not improved but can be degraded, even when only one thread is executing. This is due to slower frequencies and/or additional pipeline stages that are necessary to accommodate thread-switching hardware.
- Hardware support for multithreading is more visible to software, thus requiring more changes to both application programs and operating systems than multiprocessing.
The mileage thus varies; Intel claims up to 30 percent improvement with its HyperThreading technology, while a synthetic program just performing a loop of non-optimized dependent floating-point operations actually gains a 100 percent speed improvement when run in parallel. On the other hand, hand-tuned assembly language programs using MMX or Altivec extensions and performing data pre-fetches (as a good video encoder might), do not suffer from cache misses or idle computing resources. Such programs therefore do not benefit from hardware multithreading and can indeed see degraded performance due to contention for shared resources.
- Thread scheduling is also a major problem in multithreading.
Types of multithreading 
Block multi-threading 
The simplest type of multi-threading occurs when one thread runs until it is blocked by an event that normally would create a long latency stall. Such a stall might be a cache-miss that has to access off-chip memory, which might take hundreds of CPU cycles for the data to return. Instead of waiting for the stall to resolve, a threaded processor would switch execution to another thread that was ready to run. Only when the data for the previous thread had arrived, would the previous thread be placed back on the list of ready-to-run threads.
- Cycle i : instruction j from thread A is issued
- Cycle i+1: instruction j+1 from thread A is issued
- Cycle i+2: instruction j+2 from thread A is issued, load instruction which misses in all caches
- Cycle i+3: thread scheduler invoked, switches to thread B
- Cycle i+4: instruction k from thread B is issued
- Cycle i+5: instruction k+1 from thread B is issued
Conceptually, it is similar to cooperative multi-tasking used in real-time operating systems in which tasks voluntarily give up execution time when they need to wait upon some type of the event.
This type of multi threading is known as Block or Cooperative or Coarse-grained multithreading.
Hardware cost 
The goal of multi-threading hardware support is to allow quick switching between a blocked thread and another thread ready to run. To achieve this goal, the hardware cost is to replicate the program visible registers as well as some processor control registers (such as the program counter). Switching from one thread to another thread means the hardware switches from using one register set to another.
Such additional hardware has these benefits:
- The thread switch can be done in one CPU cycle.
- It appears to each thread that it is executing alone and not sharing any hardware resources with any other threads[dubious ]. This minimizes the amount of software changes needed within the application as well as the operating system to support multithreading.
In order to switch efficiently between active threads, each active thread needs to have its own register set. For example, to quickly switch between two threads, the register hardware needs to be instantiated twice.
- Many families of microcontrollers and embedded processors have multiple register banks to allow quick context switching for interrupts. Such schemes can be considered a type of block multithreading among the user program thread and the interrupt threads.
Interleaved multi-threading 
- Cycle i+1: an instruction from thread B is issued
- Cycle i+2: an instruction from thread C is issued
The purpose of interleaved multithreading is to remove all data dependency stalls from the execution pipeline. Since one thread is relatively independent from other threads, there's less chance of one instruction in one pipe stage needing an output from an older instruction in the pipeline.
Conceptually, it is similar to pre-emptive multi-tasking used in operating systems. One can make the analogy that the time-slice given to each active thread is one CPU cycle.
This type of multithreading was first called Barrel processing, in which the staves of a barrel represent the pipeline stages and their executing threads. Interleaved or Pre-emptive or Fine-grained or time-sliced multithreading are more modern terminology.
Hardware costs 
In addition to the hardware costs discussed in the Block type of multithreading, interleaved multithreading has an additional cost of each pipeline stage tracking the thread ID of the instruction it is processing. Also, since there are more threads being executed concurrently in the pipeline, shared resources such as caches and TLBs need to be larger to avoid thrashing between the different threads.
Simultaneous multi-threading 
The most advanced type of multi-threading applies to superscalar processors. A normal superscalar processor issues multiple instructions from a single thread every CPU cycle. In Simultaneous Multi-threading (SMT), the superscalar processor can issue instructions from multiple threads every CPU cycle. Recognizing that any single thread has a limited amount of instruction level parallelism, this type of multithreading tries to exploit parallelism available across multiple threads to decrease the waste associated with unused issue slots.
- Cycle i : instructions j and j+1 from thread A; instruction k from thread B all simultaneously issued
- Cycle i+1: instruction j+2 from thread A; instruction k+1 from thread B; instruction m from thread C all simultaneously issued
- Cycle i+2: instruction j+3 from thread A; instructions m+1 and m+2 from thread C all simultaneously issued
To distinguish the other types of multithreading from SMT, the term Temporal multithreading is used to denote when instructions from only one thread can be issued at a time.
Hardware costs 
In addition to the hardware costs discussed for interleaved multithreading, SMT has the additional cost of each pipeline stage tracking the Thread ID of each instruction being processed. Again, shared resources such as caches and TLBs have to be sized for the large number of active threads being processed.
- DEC (later Compaq) EV8 (not completed)
- Intel Hyper-Threading
- IBM POWER5
- Sun Microsystems UltraSPARC T2
- MIPS MT
- CRAY XMT
Implementation specifics 
A major area of research is the thread scheduler which must quickly choose among the list of ready-to-run threads to execute next as well as maintain the ready-to-run and stalled thread lists. An important sub-topic is the different thread priority schemes that can be used by the scheduler. The thread scheduler might be implemented totally in software, totally in hardware, or as a hardware/software combination.
Another area of research is what type of events should cause a thread switch - cache misses, inter-thread communication, DMA completion, etc.
If the multithreading scheme replicates all software visible state, include privileged control registers, TLBs, etc., then it enables virtual machines to be created for each thread. This allows each thread to run its own operating system on the same processor. On the other hand, if only user-mode state is saved, less hardware is required which would allow for more threads to be active at one time for the same die-area/cost.
See also