The Sun Fireplane System Interconnect

  title={The Sun Fireplane System Interconnect},
  author={A. Charlesworth},
  journal={ACM/IEEE SC 2001 Conference (SC'01)},
  • A. Charlesworth
  • Published 2001
  • Computer Science
  • ACM/IEEE SC 2001 Conference (SC'01)
System interconnect is a key determiner of the cost, performance, and reliability of large cache-coherent, shared-memory multiprocessors. Interconnect implementations have to accommodate ever greater numbers of ever faster processors. This paper describes the Sun™ Fireplane two-level cache-coherency protocol, and its use in the medium and large-sized UltraSPARC-III-based Sun Fire™ servers. 
The Sun Fireplane Interconnect
The Sun Fireplane Interconnect, used inside the Sun Microsystems Ultrasparc III generation of servers and workstations, builds on three generations of interconnects, and provides a significant increase in performance and system bandwidth. Expand
Scalability port: a coherent interface for shared memory multiprocessors
The scalability port (SP) is a point-to-point cache consistent interface to build scalable shared memory multiprocessors for the Intel Itanium/sup /spl reg//2 processor and future generations of the Itanium processor family. Expand
Efficient synchronization and coherence for nonuniform communication architectures
In large multiprocessors, the access to shared memory is often n orders of magnitude smaller than in previous generations of computers, so the need for uniformity in the design of these systems is important. Expand
Reconfigurable optical interconnection networks for shared-memory multiprocessor architectures
Current technologies, using electrical signaling, are reaching the end of their capabilities. Moreover, the traffic on such networks is very irregular, making some parts of the network highlyExpand
The architecture of the HP Superdome shared-memory multiprocessor
This paper offers an overview of the HP Superdome shared memory multiprocessor, along with a detailed description of the cache coherence implementation, and microarchitectural details on the sx1000 chipset, codenamed Pinnacles. Expand
SMP System Interconnect Instrumentation for Performance Analysis
The instrumentation supports sophisticated programmable filtering of event counters, allowing to construct histograms of system interconnect activity, and a FIFO to capture trace sequences, and results in a very small hardware footprint, making it appropriate for inclusion in commodity hardware. Expand
SMP System Interconnect Instrumentation for Performance Analysis
The system interconnect is often the performance bottleneck in SMP computers. Although modern SMPs include event counters on processors and interconnects, these provide limited information about theExpand
Memory Subsystem Characterization in a 16-Core Snoop-Based Chip-Multiprocessor Architecture
A taxonomy of the L1 cache misses found in CMPs is proposed which subsequently is used to determine where the hot spots of the memory hierarchy are and, thus, where computer architects have to place special emphasis to improve the performance of future dense single-chip multiprocessors, which will integrate 16 or more processor cores. Expand
Assessment of Cache Coherence Protocols in Shared-memory Multiprocessors
This dissertation provides a framework for evaluating the coherence communication traffic of different protocols and considers using more than one protocol in a DSM multiprocessor, and shows that no single protocol is best suited for all communication patterns. Expand
A Power-Aware Prediction-Based Cache Coherence Protocol for Chip Multiprocessors
Speculative supplier identification (SSI) is proposed to reduce power dissipation in binary tree interconnects in snoopy cache coherence implementations and reduces interconnect power by 23% in a 4-way multiprocessor. Expand


Parallel Computer Architecture
Computer architecture is a truly fascinating field in tha improvements in the basic echnology and innovations how to make best use of he underlying tech- nology has yielded a performance growthExpand
UltraSPARC-III: designing third-generation 64-bit performance
The UltraSPARC-III is the third generation of Sun Microsystems' most powerful microprocessors, which are at the heart of Sun's computer systems and ensures compatibility with all existing SPARC applications and the Solaris operating system. Expand
Parallel computer architecture - a hardware / software approach
This book explains the forces behind this convergence of shared-memory, message-passing, data parallel, and data-driven computing architectures and provides comprehensive discussions of parallel programming for high performance and of workload-driven evaluation, based on understanding hardware-software interactions. Expand
lmbench: Portable Tools for Performance Analysis
lmbench is a micro-benchmark suite designed to focus attention on the basic building blocks of many common system applications, such as databases, simulations, software development, and networking.Expand
Architecture and Design of AlphaServer GS 320
  • Latest Quarterly Server Tracker spreadsheet , June
  • 2001
International Data Corp, Latest Quarterly Server Tracker spreadsheet
  • International Data Corp, Latest Quarterly Server Tracker spreadsheet
  • 2001
Architecture and design of AlphaServer GS320
This paper describes the architecture and implementation of the AlphaServer GS320, a cache-coherent non-uniform memory access multiprocessor developed at Compaq. The AlphaServer GS320 architecture isExpand
SGI, SGI 3000 Family Reference Guide
  • SGI, SGI 3000 Family Reference Guide
  • 2000
The IBM pSeries 680 Technology and Architecture White Paper
  • IBM
  • 2000
The UltraSPARC Port Architecture
  • Hot Interconnects III
  • 1995