MICROPROCESSOR ARCHITECTURE

Transcription

1 MICROPROCESSOR ARCHITECTURE UOP S.E.COMP (SEM-I) MULTICORE DESIGN Prof.P.C.Patil Department of Computer Engg Matoshri College of Engg.Nasik

2 History 2

3 History The most important part of the computer is the chip i.e. "microprocessor or processor" that is the brain of the computer. The earlier processors were single core processors. The core is part of the processor that is responsible for correctly reading and executing the instructions. The single core processors are capable of executing only one instruction at a time. 3

4 History As we move from one generation to the other i.e. from 8086, 80186, 80286, towards Pentium IV we see that the processor clock frequency increases. The faster clock speeds typically require additional transistors and higher input voltages, It results in greater power consumption. The increasing clock speed is creating a power dissipation problem for semiconductor manufacturers. 4

5 History The latest semiconductor technologies support more and more transistors. The downside is that every transistor leaks a small amount of current, and the sum of which is problematic. Therefore... Instead of pushing chips to run faster, CPU designers are adding resources, such as more cores i.e. multicore and more cache to provide comparable or better performance at lower power. 5

6 History Adding a core will double the system performance, and dissipate less heat. A multicore processor consists of two or more independent cores. The previously used single core designs have been replaced by multicore designs that are nowadays used. 6

7 History In the early 1970 s the first Microprocessor was developed by Intel. It was a 4 bit machine that was named the 4004 The 4004 was followed by Intel s 8008 and 8080, as well as motorola s 6800 and 68000

8 Growth GROWTH With each new generation of processors there were several developments such as: Smaller size Faster speed Increased heat dissipation Greater Consumption of power

9 Single Core Performance SINGLE CORE PERFORMANCE Technique used to increase single core performance was: Pipelining: beginning other waiting instructions before the first finishes

10 Single Core Performance Another technique was multithreading Multithreading involves execution of two separate threads. Time is divided and interlaced between the two threads in order to simulate simultaneous execution

11 Problems with Single Core PROBLEMS WITH SINGLE CORE To execute the tasks faster you must increase the clock time. Increasing clock times too high drastically increases power consumption and heat dissipation to extremely high levels, making the processor inefficient.

12 Multi Core solution 12

13 Multi Core solution MULTI CORE SOLUTION Creating two cores or more on the same Disc increases processing power while keeping clock speeds at an efficient level. A processor with 2 cores running at efficient clock speeds can process instructions with similar speed to a single core processor running at twice the clock speed, yet the dual core processor would still consume less energy.

14 Multi Core solution MULTI-CORE ADVANTAGES While working with many threads, a Multi Core processor with n cores can execute n threads simultaneously by assigning a core to each thread. If it must process more than n threads, say x, it can apply multithreading procedures with each core working with an average of x/n threads. A Single core processor must multithread with every single thread.

15 Multi Core solution OTHER INCENTIVES Improving an existing single core design or creating a better one is problematic in that it: Is time consuming to design Is risky to modify existing designs Creating multi core processors is convenient in that: The name core dual and similar names are good for marketing. It has lower manufacturing costs. Uses proven processor designs.

16 What is multicore 16

17 What is Multicore Processor A multicore architecture is an architecture where on a single computer chip multiple processors are integrated. A multicore processor has two or more independent cores. Each of the processor is referred to as a core. 17

18 What is Multicore Processor A processor with two cores is called as a dual core e.g. Intel Core Duo, AMD Phenom II X2 etc. A processor with four cores is called as a quad core e.g. Intel 2010 core line, AMD Phenom II X4. A processor with six cores is called as a hexa core e.g. Intel Core i7 Extreme Edition,AMD phenom II X6. A processor with eight cores is called as a octa core e.g. Intel Xeon E7 Edition 2820, AMD Phenom II X8. A processor with ten cores is called as a deca core e.g. Intel Xeon E7 Edition

19 Implementations 19

20 Implementations IMPLEMENTATIONS Two main ways to have multiple cores interact are Shared memory model, Distributed memory model. In the shared memory model, all cores share the same cache memory. In the distributed memory model, each core has its own cache memory.

21 Implementations The Intel core duo design has a separate L1 cache memory for each core, but both cores share an L2 cache.

22 Implementations The AMD Athlon 64 X2 implementation has separate L1 and L2 cache memory for each core.

23 Multicore Architectures 23

24 Multicore Architectures Depending on the type of core the CMPs (Chip Multiprocessors) are classified as : 1. Dual Core (two processors) 2. Quad Core (four processors) 3. Hexa Core (six processors) 4. Octa Core (eight processors) 5. Deca Core (ten processors). 24

25 Multicore Architectures All these systems are multithreaded (a thread is a small sequence of programmed instuctions that can be executed individually.) Presently in the multicore systems the cores may or may not share the cache or They may implement shared memory inter-core communication methods. Each CMP implemented handles the Front side bus (FSB) and I/O bus in a different way. 25

26 Problems with multicore 26

27 Problems PROBLEMS Some of the current problems found with multi core processors include: Memory/Cache coherence. some implementations have distributed L1 caches but must share an L2 cache. This poses the problem of making sure each core keeps the other updated with changes in the data in its own cache.

28 Problems Multi threading is also a problem when the software being run is not designed to take advantage of the multi core processor. This may mean that one core does most of the work which means that the processor is running no more efficiently than a single core.