• DocumentCode
    110074
  • Title

    The Next Generation 64b SPARC Core in a T4 SoC Processor

  • Author

    Jinuk Luke Shin ; Golla, Robert ; Hongping Li ; Dash, Shishir ; Youngmoon Choi ; Smith, A. ; Sathianathan, Hari ; Joshi, Madhura ; Heechoul Park ; Elgebaly, M. ; Turullols, Sebastian ; Song Kim ; Masleid, R. ; Konstadinidis, Georgios K. ; Doherty, Mary Jo

  • Author_Institution
    Oracle, Santa Clara, CA, USA
  • Volume
    48
  • Issue
    1
  • fYear
    2013
  • fDate
    Jan. 2013
  • Firstpage
    82
  • Lastpage
    90
  • Abstract
    The SPARC T4 processor introduces the next generation multi-threaded 64b core to deliver up to 5x integer and 7x floating-point single-thread performance improvement over its predecessor. The chip integrates eight cores, an 8-Bank 4 MB L3 Cache, a 768 GB/sec crossbar, a memory controller, PCI Gen2.0, 10 Gb Ethernet and cache coherency with 2.4 Tb/s bandwidth high-speed I/Os. The dual-issue, out-of-order execution core (S3) features a new 16-stage integer pipeline, extensive branch predictions, dynamic threading and an enhanced cryptographic processing unit. The 406 mm2 die contains 855 million transistors and 2.6 million flip-flops in TSMC´s 40nm process utilizing 11 Cu metals and four transistor types. Enhanced physical design methodologies and extensive power management features enable 3.0 GHz operation in the same power envelope of its predecessor. Logically complex SRAMs deploy techniques to support out-of-order execution core while addressing area, timing and power challenges. The power supply calibration circuit improves yield by reducing 70% of conventional voltage guard-band for the speed and power constrained design.
  • Keywords
    SRAM chips; cache storage; cryptography; flip-flops; floating point arithmetic; integrated circuit design; multi-threading; pipeline processing; system-on-chip; transistor circuits; 16-stage integer pipeline; 8-bank L3 cache; Ethernet; PCI Gen2.0; SPARC T4 SoC processor; SRAM; TSMC process; branch prediction; cache coherency; crossbar; cryptographic processing unit; dynamic threading; flip-flop; floating-point single-thread performance; frequency 3 GHz; high-speed I/O; memory controller; next generation SPARC core; next generation multithreaded core; out-of-order execution core; power constrained design; power envelope; power management; power supply calibration circuit; size 40 nm; storage capacity 10 Gbit; storage capacity 64 bit; transistor; voltage guard-band; Clocks; Out of order; Pipelines; Registers; System-on-a-chip; Timing; Body-bias; L3 Cache; SPARC; SerDes; System-On-Chip (SoC); clocking; coherency; idle power; interconnect crossbar; multi-core; multi-threaded; power management; single-thread performance; throughput performance;
  • fLanguage
    English
  • Journal_Title
    Solid-State Circuits, IEEE Journal of
  • Publisher
    ieee
  • ISSN
    0018-9200
  • Type

    jour

  • DOI
    10.1109/JSSC.2012.2223036
  • Filename
    6399578