The speed and efficiency of computer network and database servers could increase as much as 400 percent because of an idea developed by two 91探花computer scientists that is reaching mainstream computing.
The technique, known as simultaneous multithreading, was first proposed in the mid-1990s by Susan Eggers and Hank Levy, 91探花professors in the Department of Computer Science & Engineering. Compaq Computers was the first to announce a processor using that idea on its Alpha computer, but that line was discontinued before Compaq鈥檚 merger with Hewlett-Packard. However, Sun Microsystems announced in December that it would produce microprocessors using simultaneous multithreading and Intel Corp. made a similar announcement shortly afterward. Other companies appear likely to follow suit.
The new concept will have a major impact on high-end computer users, such as Internet service providers and businesses with server-administered databases and networks, Eggers and Levy predict.
鈥淎t computer conferences, presenters talk about new ideas that will boost speed by 15 or 20 percent, and people get really excited,鈥� Eggers said. 鈥淲e鈥檙e talking about an increase of 300 to 400 percent.鈥�
Ideas that fuel momentous forward leaps in computing come along about once every 10 years, Levy added. 鈥淭his, we think, is one of those ideas.鈥�
Burton Smith, chief scientist at world supercomputing leader Cray Inc. and a pioneer of multithreading technology, agreed, adding that he expects simultaneous multithreading, or SMT, to become an industry standard.
鈥淪MT fits multithreading into the architecture that microprocessor manufacturers are using in a relatively painless way,鈥� said Smith, who was the first person to use multithreading in the central processing unit of a computer. 鈥淚t provides them with a much better use of the hardware and much better performance as well, with minimal impacts on the way they do business. It鈥檚 quite a nice thing.鈥�
The concept of multithreading was first proposed in the 1960s and is used in supercomputers. Eggers and Levy鈥檚 technique shows how the idea can be applied to mass-market computing. The key to SMT involves making better use of a chip鈥檚 computing power.
Modern computers are capable of doing a lot of work simultaneously. For example, some processors can perform 10 arithmetic operations (like adding or subtracting) every clock tick, which is every billionth of a second on a one-gigahertz processor. In practice, however, they do only two or three operations per tick, wasting the potential for much higher performance. That鈥檚 because modern computers work on only one program, or thread, at a time, and there鈥檚 a limit to the number of arithmetic operations a single program can present to the computer in one clock tick.
Imagine a chef who is cooking dinner for four people, standing in front of a four-burner cooktop. If the chef prepares one meal at a time using one frying pan on one burner, he鈥檚 wasting three-fourths of his potential. On the other hand, if he places one frying pan on each of the four burners and prepares the meals all at once, he鈥檒l be finished in about one-quarter the time. SMT is like the efficient chef 鈥� it takes instructions from many programs and loads them all into the computer at once, using the full arithmetic potential of the computer to process many programs in parallel, like the chef who鈥檚 sauteing in all the frying pans simultaneously. This is particularly useful for Web servers, which are trying to cook thousands or millions of 鈥渕eals鈥� at the same time.
The trick lies in keeping close track of each thread. To do that, some additional hardware is required so that the state of each thread can be stored and updated.
That extra hardware requirement highlights the advantages of SMT, according to Eggers. The additional circuitry for a chip that can run four threads at once is estimated at about
10 percent. But the boost in performance far outstrips the hardware need because when one thread is stalled, waiting for data, the other threads keep running. That鈥檚 what makes SMT so advantageous for database and Web servers, which generally process user requests as separate threads. According to Eggers and Levy鈥檚 research, an eight-thread SMT chip can run database software three times faster than a normal chip. For Web-server software, performance jumps fourfold. And that鈥檚 with unmodified software, Eggers said. Fine-tuning programs with SMT specifically in mind could make things even faster.
鈥淚t gives you a huge bang for your buck,鈥� she said.
Ultimately, Cray鈥檚 Smith predicts, multithreading of one sort or another will be needed for all types of computing, from personal computing to the very highest performance computing we do.
鈥淭he circuitry is getting so much faster and transistors are getting less expensive,鈥� he said. 鈥淭o take advantage of the opportunities that presents, multithreading is the only way to go in the long run.鈥�
In that sense, SMT is a start.
鈥淚t鈥檚 a beginning for the mainstream of computing in exploring a whole new kind of architecture,鈥� he said. 鈥淚t will become standard and there will be further evolution of these ideas. It opens all sorts of possibilities.鈥�