PDF-Multiprocessor Design I:

Page 1 SnoopBased Multiprocessor Design I Base DesignTodd C Mowry CS 418 CS 418 Feb 23 24 2011 Design Goalscostdepend on CorrectnessHigh PerformanceOften at oddsHigh Performance multiple ou. Mooney Georgia Institute of Technology Electrical and Computer Engineering Atlanta GA 30332 kkryu eung mooneyecegatechedu Abstract The performance of a system especially a multiprocessor system heavily depends upon the efficiency of its bus architec 1 Multiprocessor System Interconnects Generalized Multiprocessor System Generalized Multiprocessor System Each processor Pi is attached to its own local memory and private cache Multiple processors connected to shared memory through interprocessor me The architecture consists of powerful processing nodes each with a portion of the sharedmemory connected to a scalable interconnection network A key feature of DASH is its dis tributed directorybased cache coherence protocol Unlike tra ditional snoo For each of the approaches the associated protocol is outlined The simulation model is described and results from that model are presented The magnitude of the potential performance difference between the various approaches indicates that the choice 142 brPage 2br Taxonomy SISD single instruction and sing le data stream uniprocessor MISD no commercial multiprocessor imagine data going through a pipeline of execution engines SIMD vector architectures lower flexibility MIMD most multiprocessors to coprocessor 8087 2 closely coupled 8089 3 loosely coupled Multibus Coprocessors and closely coupled configurations are similar in that both the CPU and the external processor share Memory IO system Bus bus control logic Clock generator Closely Tullsen University of California San Diego asvenkattullsencsucsdedu Abstract Heterogeneous multicore architectures have the potential for high performance and energy ef64257ciency These architec tures may be composed of small poweref64257cient cores A method is proposed for deriving the necessary commands from a correctness proof of the underlying algorithm in a formalism based on temporal relations among operation executions index terms concurrency memory consistency multiprocessor syn chroniz Companion slides for. The Art of Multiprocessor Programming. by Maurice . Herlihy. & . Nir. . Shavit. TexPoint fonts used in EMF. . Read the TexPoint manual before you delete this box.: . A. A. Companion slides for. The Art of Multiprocessor Programming. by Maurice Herlihy & Nir Shavit. Art of Multiprocessor Programming. 2. Focus so far: Correctness and Progress. Models. Accurate . (we never lied to you). 2. Mutual Exclusion. We will clarify our understanding of mutual exclusion. We will also show you how to reason about various properties in an asynchronous concurrent setting. Art of Multiprocessor Programming. Companion slides for. The Art of Multiprocessor Programming. by Maurice . Herlihy. & . Nir. . Shavit. Turing Computability. A mathematical model of computation. Computable = Computable on a T-Machine. Companion slides for. The Art of Multiprocessor Programming. by Maurice Herlihy & Nir Shavit. Art of Multiprocessor Programming. 2. Last Lecture: Spin-Locks. CS. Resets lock . upon exit. spin . lock. Companion slides for. The Art of Multiprocessor Programming. by Maurice Herlihy & Nir Shavit. Art of Multiprocessor Programming. 2. 2. The Five-Fold Path. Coarse-grained locking. Fine-grained locking.