Systems Disappeared from the List

Introduction
HPC Architecture
  1. Shared-memory SIMD machines
  2. Distributed-memory SIMD machines
  3. Shared-memory MIMD machines
  4. Distributed-memory MIMD machines
  5. ccNUMA machines
  6. Clusters
  7. Processors
    1. AMD Opteron
    2. IBM POWER7
    3. IBM BlueGene/Q processor
    4. Intel Xeon
    5. The SPARC processors
  8. Accelerators
    1. GPU accelerators
      1. ATI/AMD
      2. nVIDIA
    2. General computational accelerators
      1. Intel Xeon Phi
    3. FPGA accelerators
      1. Convey
      2. Kuberre
      3. SRC
  9. Interconnects
    1. Infiniband
Available systems
  • The Bull bullx system
  • The Cray XC30
  • The Cray XE6
  • The Cray XK7
  • The Eurotech Aurora
  • The Fujitsu FX10
  • The Hitachi SR16000
  • The IBM BlueGene/Q
  • The IBM eServer p775
  • The NEC SX-9
  • The SGI Altix UV series
  • Systems disappeared from the list
    Systems under development
    Glossary
    Acknowledgments
    References

    As already stated in the introduction the list of systems is not complete. On one hand this is caused by the sheer number of systems that are presented to the market and are often very similar to systems described above (for instance, the Volvox system not listed is very similar but not equivalent to the listed C-DAC system and there are numerous other examples). On the other hand there many systems that are still in operation around the world, often in considerable quantities that for other reasons are excluded. The most important reasons are:

    • The system is not marketed anymore. This is generally for one of two reasons:
      • The manufacturer is out of business.
      • The manufacturer has replaced the system by a newer model of the same type or even of a different type.

    • The system has become technologically obsolete in comparison to others of the same type. Therefore, listing them is not sensible anymore.
    Below we present a table of systems that fall into one of the categories mentioned above. We think this may have some sense to those who come across machines that are still around but are not the latest in their fields. It may be interesting at least to have an indication how such systems compare to the newest ones and to place them in context.

    It is good to realise that although systems have disappeared from the section above they still may exist and are actually sold. However, their removal stems in such cases mainly from the fact that they are not serious candidates for high-performance computing anymore.

    The table is, again, not complete and admittedly somewhat arbitrary. The data are in a highly condensed form: the system name, system type, theoretical maximum performance of a fully configured system, and the reason for their disappearance is given. The arbitrariness lies partly in the decision which systems are still sufficiently of interest to include and which are not.

    We include also both the year of introduction and the year of exit of the systems when they were readily accessible. These time-spans could give a hint of the dynamics that governs this very dynamical branch of the computer industry.

    Recently disappeared systems

    We want to discuss some developments that led to the disappearance of systems that have been of interest the last few years. Some of these are logical in the sense that other systems have replaced them. Others have left the market because of commercial shifts in the area.

    Cray XMT
    This system has been replaced by the Cray uRIKA system. It is essentially the same as the former Cray XMT, be it that the proprietary Threadstorm processor is replaced by the Threadstorm+ processor with the same clock cycle (500 MHz) but with a few improvements. As the uRIKA system now is marketed completely for the High Performance Data Analysis (HPA), we do not include it in this report anymore because it is primarily directed to HPC.

    Disappeared systems


    Machine: The Alex AVX 2.
    Year of introduction: 1992.
    Year of exit: 1997.
    Type: RISC-based distributed-memory multi-processor.
    Theoretical Peak performance: 3.84 Gflop/s.
    Reason for disappearance: System is obsolete, there is no new system planned.


    Machine: Alliant FX/2800.
    Year of introduction: 1989.
    Year of exit: 1992.
    Type: Shared memory vector-parallel, max. 28 processors.
    Theoretical Peak performance: 1120 Mflop/s.
    Reason for disappearance: Manufacturer out of business.


    Machine: Avalon A12.
    Year of introduction: 1996.
    Year of exit: 2000.
    Type: RISC-based distributed memory multi-processor, max. 1680 processors.
    Theoretical Peak performance: 1.3 Tflop/s.
    Reason for disappearance: Avalon is not in business anymore.


    Machine: The AxilSCC.
    Year of introduction: 1996.
    Year of exit: 1997.
    Type: RISC-based distributed-memory system, max. 512 processors.
    Theoretical Peak performance: 76.8 Gflop/s.
    Reason for disappearance: System is not marketed anymore by Axil.


    Machine: BBN TC2000.
    Year of introduction: ---
    Year of exit: 1990.
    Type: Virtual shared memory parallel, max. 512 processors.
    Theoretical Peak performance: 1 Gflop/s
    Reason for disappearance: Manufacturer has discontinued marketing parallel computer systems.


    Machine: Cambridge Parallel Processing DAP Gamma.
    Year of introduction: 1986.
    Year of exit: 1995.
    Type: Distributed memory processor array system, max. 4096 processors.
    Theoretical Peak performance: 1.6 Gflop/s (32-bit)
    Reason for disappearance: replaced by newer Gamma II Plus series.


    Machine: Cambridge Parallel Processing DAP Gamma II Plus.
    Year of introduction: 1995.
    Year of exit: 2003.
    Type: Distributed memory processor array system, max. 4096 processors.
    Theoretical Peak performance: 2.4 Gflop/s (32-bit)
    Reason for disappearance: system became too slow, even for its specialised tasks.


    Machine: C-DAC PARAM 9000/SS.
    Year of introduction: 1995.
    Year of exit: 1997.
    Type: RISC-based distributed-memory system, max. 200 processors.
    Theoretical Peak performance: 12.0 Gflop/s.
    Reason for disappearance: replaced by newer OpenFrame series (see below).


    Machine: C-DAC PARAM Openframe series.
    Year of introduction: 1996.
    Year of exit: 1999.
    Type: RISC-based distributed-memory system, max. 1024 processors.
    Theoretical Peak performance: Unspecified.
    Reason for disappearance: The system is not actively marketed anymore by C-DAC.


    Machine: C-DAC PARAM 10000 Openframe series.
    Year of introduction: 2000.
    Year of exit: 2002.
    Type: RISC-based distributed-memory system, max. processors: :unspecified.
    Theoretical Peak performance: Unspecified.
    Reason for disappearance: The system was replaced by the C-DAC PARAM Padma.


    Machine: C-DAC PARAM Padma.
    Year of introduction: 2003.
    Year of exit: 2010.
    Type: RISC-based distributed-memory system, max. processors: :unspecified.
    Theoretical Peak performance: 992 Gflop/s.
    Reason for disappearance: The system might be still in production but its performance has become too low to be relevant.


    Machine: Convex SPP-1000/1200/1600.
    Year of introduction: 1995 (SPP-1000).
    Year of exit: 1996 (SPP-1600).
    Type: Distributed memory RISC based system, max. 128 processors.
    Theoretical Peak performance: 25.6 Gflop/s
    Reason for disappearance: replaced by newer HP 9000 Superdome series.


    Machine: Cray Computer Corporation Cray-2.
    Year of introduction: 1982.
    Year of exit: 1992.
    Type: Shared memory vector-parallel, max. 4 processors.
    Theoretical Peak performance: 1.95 Gflop/s
    Reason for disappearance: Manufacturer out of business.


    Machine: Cray Computer Corporation Cray-3.
    Year of introduction: 1993.
    Year of exit: 1995.
    Type: Shared memory vector-parallel, max. 16 processors.
    Theoretical Peak performance: 16 Gflop/s
    Reason for disappearance: Manufacturer out of business.


    Machine: Cray Research Inc. APP.
    Year of introduction: 1994.
    Year of exit: 1996.
    Type: Shared memory RISC based system, max. 84 processors.
    Theoretical Peak performance: 6.7 Gflop/s
    Reason for disappearance: Product line discontinued, gap was expected to be filled by the Cray J90 (see below).


    Machine: Cray J90.
    Year of introduction: 1994.
    Year of exit: 1998.
    Type: Shared memory vector-parallel, max. 32 processors.
    Theoretical Peak performance: 6.4 Gflop/s
    Reason for disappearance: replaced by newer Cray Inc. SV1ex (see below).


    Machine: Cray Research Inc. MTA-2.
    Year of introduction: 2001.
    Year of exit: 2005.
    Type: Distributed memory multi-processor, max. 256 processors.
    Theoretical Peak performance: 192 Gflop/s
    Reason for disappearance: The system is not actively marketed anymore by Cray.


    Machine: Cray Research Inc. XMT.
    Year of introduction: 2007.
    Year of exit: 2005.
    Type: Distributed memory multi-processor, max. 8024 processors.
    Theoretical Peak performance: 120 Tflop/s
    Reason for disappearance: The system is re-branded to the Cray uRIKA system that is entirely directed at High Performance Data Analysis.


    Machine: Cray SV-1(ex).
    Year of introduction: 2000.
    Year of exit: 2004.
    Type: Shared memory vector-parallel, max. 32 processors.
    Theoretical Peak performance: 64 Gflop/s
    Reason for disappearance: replaced by newer Cray Inc. X1.


    Machine: Cray T3D.
    Year of introduction: 1994.
    Year of exit: 1996.
    Type: Distributed memory RISC based system, max. 2048 processors.
    Theoretical Peak performance: 307 Gflop/s
    Reason for disappearance: replaced by newer Cray T3E (see below).


    Machine: Cray T3E Classic.
    Year of introduction: 1996.
    Year of exit: 1997.
    Type: Distributed memory RISC based system, max. 2048 processors.
    Theoretical Peak performance: 1228 Gflop/s
    Reason for disappearance: replaced by Cray T3Es with faster clock (see below).


    Machine: Cray T3E 1350.
    Year of introduction: 2000.
    Year of exit: 2003.
    Type: Distributed memory RISC based system, max. 2048 processors.
    Theoretical Peak performance: 2938 Gflop/s
    Reason for disappearance: Cray does not market the system anymore.


    Machine: Cray Research Inc. Cray Y-MP, Cray Y-MP M90.
    Year of introduction: 1989 (Cray Y-MP).
    Year of exit: 1994 (Cray Y-MP M90)..
    Type: Shared memory vector-parallel, max. 8 processors.
    Theoretical Peak performance: 2.6 Gflop/s
    Reason for disappearance: replaced by newer C90 (see below).


      Machine: Cray Y-MP C90.
    Year of introduction: 1994.
    Year of exit: 1996.
    Type: Shared memory vector-parallel, max. 16 processors.
    Theoretical Peak performance: 16 Gflop/s
    Reason for disappearance: replaced by newer T90 (see below).


    Machine: Cray T90.
    Year of introduction: 1995.
    Year of exit: 1998.
    Type: Shared memory vector-parallel, max. 32 processors.
    Theoretical Peak performance: 58 Gflop/s
    Reason for disappearance: replaced by newer Cray Inc. SV1ex (see below).


    Machine: Cray X1.
    Year of introduction: 2000.
    Year of exit: 2004.
    Type: Shared memory vector-parallel, max. 64 MSP processors.
    Theoretical Peak performance: 819 Gflop/s
    Reason for disappearance: replaced by newer Cray Inc. X2.


    Machine: Cray X1E.
    Year of introduction: 2004.
    Year of exit: 2007.
    Type: Shared memory vector-parallel, max. 8192 MSP processors.
    Theoretical Peak performance: 147.2 Tflop/s
    Reason for disappearance: replaced by newer (see below).


    Machine: Cray X2.
    Year of introduction: 2007.
    Year of exit: 2009.
    Type: Shared memory vector-parallel, max. 32576 MSP processors.
    Theoretical Peak performance: 3.3 Pflop/s
    Reason for disappearance: Cray considers vector-based systems not economically viable anymore.


    Machine: Cray XD1.
    Year of introduction: 2004.
    Year of exit: 2006.
    Type: Distributed-memory multi-processor, max. 144 processors.
    Theoretical Peak performance: 663 Gflop/s
    Reason for disappearance: recomponents will re-appear in Cray's heterogeneous systems in the near future.


    Machine: Cray XR1.
    Year of introduction: 2007.
    Year of exit: 2009.
    Type: Distributed-memory multi-processor, maximum configuration not specified.
    Theoretical Peak performance: 12 Tflops/s/cabinet
    Reason for disappearance: Superseeded by Cray XE6.


    Machine: Cray XT5.
    Year of introduction: 2008.
    Year of exit: 2010.
    Type: .
    Theoretical Peak performance: variable
    Reason for disappearance: Cray deems it not economically viable anymore.


    Machine: Digital Equipment Corp. Alpha farm.
    Year of introduction: ---
    Year of exit: 1994.
    Type: Distributed memory RISC based system, max. 4 processors.
    Theoretical Peak performance: 0.8 Gflop/s
    Reason for disappearance: replaced by newer HP/Compaq GS series.


    Machine: Digital Equipment Corp. Alpha AlphaServer 8200 & 8400.
    Year of introduction: ---
    Year of exit: 1998.
    Type: Distributed memory RISC based system, max. 6 processors (AlphaServer 8200) or 14 (AlphaServer 8400).
    Theoretical Peak performance: 7.3 Gflop/s, resp. 17.2 Gflop/s.
    Reason for disappearance: replaced by newer Integrity Superdome.


    Machine: Fujitsu AP1000.
    Year of introduction: 1991.
    Year of exit: 1996.
    Type: Distributed memory RISC based system, max. 1024 processors.
    Theoretical Peak performance: 5 Gflop/s
    Reason for disappearance: replaced by the Fujitsu AP3000 (see below).


    Machine: Fujitsu AP3000.
    Year of introduction: 1996.
    Year of exit: 2003.
    Type: Distributed memory RISC based system, max. 1024 processors.
    Theoretical Peak performance: 614 Gflop/s
    Reason for disappearance: Fujitsu does not market the system anymore in favour of its PRIMEPOWER series.


    Machine: Fujitsu VPP500 series.
    Year of introduction: 1993.
    Year of exit: 1995.
    Type: Distributed memory multi-processor vectorprocessors, max. 222 processors.
    Theoretical Peak performance: 355 Gflop/s
    Reason for disappearance: replaced by the VPP300/700 series (see below).


    Machine: Fujitsu VPP300/700 series.
    Year of introduction: 1995/1996.
    Year of exit: 1999.
    Type: Distributed memory multi-processor vectorprocessors, max. 256 processors.
    Theoretical Peak performance: 614 Gflop/s
    Reason for disappearance: replaced by the Fujitsu VPP5000 series (see below).


    Machine: Fujitsu VPP5000 series.
    Year of introduction: 1999.
    Year of exit: 2002.
    Type: Distributed memory multi-processor vectorprocessors, max. 128 processors.
    Theoretical Peak performance: 1.22 Tflop/s
    Reason for disappearance: Fujitsu does not market vector systems anymore, this machine line is replaced by the PRIMEPOWER series (see below).


    Machine: Fujitsu VPX200 series.
    Year of introduction: ---
    Year of exit: 1995.
    Type: Single-processor vectorprocessors.
    Theoretical Peak performance: 5 Gflop/s
    Reason for disappearance: replaced by the VPP300/700 series (see above).


    Machine: Fujitsu PRIMEPOWER series.
    Year of introduction: 2002.
    Year of exit: 2006.
    Type: RISC-based shared-memory multi-processor. max. 128 processors.
    Theoretical Peak performance: 466 Gflop/s
    Reason for disappearance: Succeeded by the Fujitsu PRIMEQUEST 500 (see below).


    Machine: Fujitsu PRIMEQUEST 500.
    Year of introduction: 2006.
    Year of exit: 2010.
    Type: Distributed-memory multi-processor vectorprocessors, max. 32 processors.
    Theoretical Peak performance: 409.6 Gflop/s
    Reason for disappearance: Fujitsu does not target this system to the HPC market anymore.


    Machine: Fujitsu-Siemens M9000.
    Year of introduction: 2008.
    Year of exit: 2009.
    Type: Distributed-memory multi-processor vectorprocessors, max. 128 processors.
    Theoretical Peak performance: 2.58 Tflop/s
    Reason for disappearance: Fujitsu does not target this system to the HPC market anymore.


    Machine: Hitachi S-3800 series.
    Year of introduction: 1993.
    Year of exit: 1998.
    Type: Shared-memory multi-processor vectorprocessors, max. 4 processors.
    Theoretical Peak performance: 32 Gflop/s
    Reason for disappearance: Replaced by the newer SR16000 system.


    Machine: Hitachi S-3600 series.
    Year of introduction: 1994.
    Year of exit: 1999.
    Type: Single-processor vectorprocessor.
    Theoretical Peak performance: 2 Gflop/s
    Reason for disappearance: Replaced by the newer SR16000 system.


    Machine: Hitachi SR2001 series.
    Year of introduction: 1994.
    Year of exit: 1996.
    Type: Distributed memory RISC based system, max. 128 processors.
    Theoretical Peak performance: 23 Gflop/s
    Reason for disappearance: Replaced by the successor SR2201 (see below).


    Machine: Hitachi SR2201 series.
    Year of introduction: 1996.
    Year of exit: 1998.
    Type: Distributed memory RISC based system, max. 1024 processors.
    Theoretical Peak performance: 307 Gflop/s
    Reason for disappearance: Replaced by the newer SR8000 (see below).


    Machine: Hitachi SR8000 series.
    Year of introduction: 1998.
    Year of exit: 1998—2003 (different models).
    Type: Distributed memory RISC based system, max. 512 processors.
    Theoretical Peak performance: 7.3 Tflop/s
    Reason for disappearance: Replaced by the newer FSR11000.


    Machine: Hitachi SR11000 series.
    Year of introduction: 2005.
    Year of exit: 2009.
    Type: Distributed memory RISC based system, max. 512 processors.
    Theoretical Peak performance: 68.8 Tflop/s
    Reason for disappearance: Replaced by the newer
    SR16000.


    Machine: Hitachi BladeSymphony.
    Year of introduction: 2005.
    Year of exit: 2010.
    Type: Distributed memory RISC based system, max. 64 processors.
    Theoretical Peak performance: 850 Gflop/s
    Reason for disappearance: Hitachi does not target this system to the HPC market anymore.


    Machine: HP/Convex C4600.
    Year of introduction: 1994.
    Year of exit: 1997.
    Type: Shared memory vector-parallel, max. 4 processors (C4640).
    Theoretical Peak performance: 3.2 Gflop/s
    Reason for disappearance: The C4600 is not marketed by HP/Convex anymore.


    Machine: The HP Exemplar V2600.
    Year of introduction: 1999.
    Year of exit: 2000.
    Type: Distributed-memory RISC based system, max. 128 processors.
    Theoretical Peak performance: 291 Gflop/s
    Reason for disappearance: Replaced by the HP 9000 SuperDome.


    Machine: The HP 9000 Superdome.
    Year of introduction: 2004.
    Year of exit: 2005.
    Type: Distributed-memory RISC based system, max. 64 processors.
    Theoretical Peak performance: 512 Gflop/s
    Reason for disappearance: Replaced by the HP Integrity Superdome.
    Machine: The HP Integrity Superdome.
    Year of introduction: 2000.
    Year of exit: 2005.
    Type: Distributed-memory RISC based system, max. 128 processors.
    Theoretical Peak performance: 819.2 Gflop/s
    Reason for disappearance: HP does not market Itanium-based ccNUMA systems anymore.


    Machine: IBM ES/9000 series.
    Year of introduction: 1991.
    Year of exit: 1994.
    Type: Shared memory vector-parallel system, max. 6 processors.
    Theoretical Peak performance: 2.67 Gflop/s
    Reason for disappearance: IBM does not pursue high-performance computing by this product line anymore.


    Machine: IBM SP1 series.
    Year of introduction: 1992.
    Year of exit: 1994.
    Type: Distributed memory RISC based system, max. 64 processors.
    Theoretical Peak performance: 8 Gflop/s
    Reason for disappearance: Replaced by the newer RS/6000 SP series (see below).


    Machine: IBM RS/6000 SP series.
    Year of introduction: 1999.
    Year of exit: 2001.
    Type: Distributed memory RISC based system, max. 2048 processors.
    Theoretical Peak performance: 24 Gflop/s
    Reason for disappearance: Replaced by the newer IBM eServer p575.


    Machine: IBM IBM eServer p575.
    Year of introduction: 2008.
    Year of exit: 2011.
    Type: Distributed memory RISC based system, max. size unspecified.
    Theoretical Peak performance: unspecified.
    Reason for disappearance: Replaced by the newer
    IBM eServer p775.


    Machine: IBM Bluegene/P
    Year of introduction: 2007.
    Year of exit: 2013.
    Type: Distributed-memory RISC system, max 2×65,536 processors.
    Theoretical Peak Performance: 367 Tflops.
    Reason for disappearance: Replaced by BlueGene/Q, see IBM Bluegen/Q


    Machine: Intel Paragon XP.
    Year of introduction: 1992.
    Year of exit: 1996.
    Type: Distributed memory RISC based system, max. 4000 processors.
    Theoretical Peak performance: 300 Gflop/s.
    Reason for disappearance: Except for a non-commercial research system (the ASCI Option Red system at Sandia National Labs.) Intel is not in the business of high-performance computing anymore.


    Machine: Kendall Square Research KSR2.
    Year of introduction: 1992.
    Year of exit: 1994.
    Type: Virtually shared memory parallel, max. 1088 processors.
    Theoretical Peak performance: 400 Gflop/s
    Reason for disappearance: Kendall Square has terminated its business.


    Machine: Kongsberg Informasjonskontroll SCALI.
    Year of introduction: 1996.
    Year of exit: 1997.
    Type: Distributed memory RISC based system, max. 512 processors.
    Theoretical Peak performance: 76.8 Gflop/s
    Reason for disappearance: Kongsberg does not market the system anymore.


    Machine: The Liquid Computing LiquidIQ system.
    Year of introduction: 2006.
    Year of exit: 2009.
    Type: Distributed memory multi-processor system, max. 960 processors.
    Theoretical Peak performance: 20 Tflop/s
    Reason for disappearance: Liquid does not market the system anymore.


    Machine: MasPar MP-1, MP-2.
    Year of introduction: 1991 (MP-1).
    Year of exit: 1996.
    Type: Distributed memory processor array system, max. 16384 processors.
    Theoretical Peak performance: 2.4 Gflop/s (64-bit, MP-2)
    Reason for disappearance: Systems are not marketed anymore.


    Machine: Matsushita ADENART.
    Year of introduction: 1991.
    Year of exit: 1997.
    Type: Distributed memory RISC based system, 256 processors.
    Theoretical Peak performance: 2.56 Gflop/s.
    Reason for disappearance: Machine is obsolete and no new systems are developed in this line.


    Machine: Meiko CS-1 series.
    Year of introduction: 1989.
    Year of exit: 1995.
    Type: Distributed memory RISC based system.
    Theoretical Peak performance: 80 Mflop/s per processor
    Reason for disappearance: Meiko does not build complete systems anymore (but see below).


    Machine: Meiko CS-2 series.
    Year of introduction: 1994.
    Year of exit: 1999.
    Type: Distributed memory RISC based system, max. 1024 processors.
    Theoretical Peak performance: 200 Mflop/s per processor
    Theoretical Peak performance: 204.8 Gflop/s
    Reason for disappearance: Quadrics Supercomputers World Ltd. does not market the system anymore. The updated network technology was offered for other systems like HP/Compaq's AlphaServer SC45.


    Machine: nCUBE 2S.
    Year of introduction: 1993. Year of exit: 1998.
    Type: Distributed memory system, max. 8192 processors.
    Theoretical Peak performance: 19.7 Gflop/s.
    Reason for disappearance: NCUBE has withdrawn from the scientific and technical market. The nCUBE2S is now offered as a parallel multimedia server.


    Machine: nCUBE 3.
    Year of introduction: --- (see remarks at nCUBE 2S).
    Year of exit: ---
    Type: Distributed memory system, max. 10244 processors.
    Theoretical Peak performance: 1 Tflop/s.
    Reason for disappearance: Was announced several times but was never finished.


    Machine: NEC Cenju-3.
    Year of introduction: 1994.
    Year of exit: 1996.
    Type: Distributed-memory system, max. 256 processors.
    Theoretical Peak performance: 12.8 Gflop/s
    Reason for disappearance: replaced by newer Cenju-4 series (see below).


    Machine: NEC Cenju-4.
    Year of introduction: 1998.
    Year of exit: 2002.
    Type: Distributed-memory system, max. 1024 processors.
    Theoretical Peak performance: 410 Gflop/s
    Reason for disappearance: NEC has withdrawn this machine in favour of a possible successor. Specifics are not known, however.


    Machine: NEC SX-3R.
    Year of introduction: 1993.
    Year of exit: 1996.
    Type: Shared memory multi-processor vector processors, max. 4 processors.
    Theoretical Peak performance: 25.6 Gflop/s
    Reason for disappearance: replaced by newer SX-4 series (see below).


    Machine: NEC SX-4.
    Year of introduction: 1995.
    Year of exit: 1998.
    Type: Shared memory multi-processor vector processors, max. 256 processors.
    Theoretical Peak performance: 1 Tflop/s
    Reason for disappearance: replaced by newer SX-5 series (see below).


    Machine: NEC SX-5.
    Year of introduction: 1998.
    Year of exit: 2002.
    Type: Shared memory multi-processor vector processors, max. 512 processors.
    Theoretical Peak performance: 5.12 Tflop/s
    Reason for disappearance: replaced by newer SX-6 (see below).


    Machine: NEC SX-6.
    Year of introduction: 2002.
    Year of exit: 2005.
    Type: Shared memory multi-processor vector processors, max. 1024 processors.
    Theoretical Peak performance: 9.2 Tflop/s
    Reason for disappearance: replaced by newer SX-8 series (see below).


    Machine: NEC SX-8.
    Year of introduction: 2004.
    Year of exit: 2008.
    Type: Shared memory multi-processor vector processors, max. 1024 processors.
    Theoretical Peak performance: 90.1 Tflop/s
    Reason for disappearance: replaced by newer SX-9 series.


    Machine: NEC Express5800/1000.
    Year of introduction: 2006.
    Year of exit: 2010.
    Type: Distributed-memory multi-processor vectorprocessors, max. 32 processors
    Theoretical Peak performance: 409.6 Gflop/s
    Reason for disappearance: NEC does not target this system to the HPC market anymore.


    Machine: Parsys SN9000 series.
    Year of introduction: 1993.
    Year of exit: 1995.
    Type: Distributed memory RISC based system, max. 2048 processors.
    Theoretical Peak performance: 51.2 Gflop/s
    Reason for disappearance: Replaced by the newer TA9000 (but see below).


    Machine: Parsys TA9000 series.
    Year of introduction: 1995.
    Year of exit: 1996.
    Type: Distributed memory RISC based system, max. 512 processors.
    Theoretical Peak performance: 119.3 Gflop/s
    Reason for disappearance: Parsys does not offer complete system anymore. Instead it sells node cards based on the TA9000 for embedded systems.


    Machine: Parsytec GC/Power Plus.
    Year of introduction: 1993.
    Year of exit: 1996.
    Type: Distributed memory RISC based system.
    Theoretical Peak performance: 266.6 Mflop/s per processor.
    Reason for disappearance: System has been replaced by the Parsytec CC systems (see below).


    Machine: Parsytec CC series.
    Year of introduction: 1996.
    Year of exit: 1998.
    Type: Distributed memory RISC based system.
    Theoretical Peak performance: unspecified.
    Reason for disappearance: Vendor has withdrawn from the High-Performance computing market.


    Machine: Quadrics Appemille.
    Year of introduction: 1999.
    Year of exit: 2004.
    Type: Processor array, max. 2048 processors.
    Theoretical Peak performance: 1 Tflop/s.
    Reason for disappearance: Not marketed anymore.


    Machine: Siemens-Nixdorf VP2600 series.
    Year of introduction: ---
    Year of exit: 1995.
    Type: Single-processor vectorprocessors.
    Theoretical Peak performance: 5 Gflop/s
    Reason for disappearance: eventually replaced by the PRIMEPOWER series.


    Machine: Silicon Graphics PowerChallenge.
    Year of introduction: 1994.
    Year of exit: 1996.
    Type: Shared memory multi-processor, max. 36 processors.
    Theoretical Peak performance: 14.4 Gflop/s
    Reason for disappearance: replaced by the SGI Origin 2000 (see below).


    Machine: SGI Origin 2000.
    Year of introduction: 1996.
    Year of exit: 2000.
    Type: Shared memory multi-processor, max. 128 processors.
    Theoretical Peak performance: 102.4 Gflop/s
    Reason for disappearance: replaced by the SGI Origin 3900.


    Machine: SGI Origin 3000.
    Year of introduction: 2003.
    Year of exit: 2005.
    Type: Shared memory multi-processor, max. 512 processors.
    Theoretical Peak performance: 819 Gflop/s
    Reason for disappearance: replaced by the SGI Altix 4700 and later the Altix UV 2000.


    Machine: Stern Computing Systems SSP.
    Year of introduction: 1994.
    Year of exit: 1996.
    Type: Shared memory multi-processor, max. 6 processors.
    Theoretical Peak performance: 2 Gflop/s
    Reason for disappearance: Vendor terminated its business just before delivering first systems.


    Machine: SUN E10000 Starfire.
    Year of introduction: 1997.
    Year of exit: 2001.
    Type: Shared memory multi-processor, max. 64 processors.
    Theoretical Peak performance: 51.2 Gflop/s
    Reason for disappearance: replaced by the SUN Fire 3800-15K (see below).


    Machine: SUN Fire 3800-15K.
    Year of introduction: 2001.
    Year of exit: 2004.
    Type: Shared memory multi-processor, max. 106 processors.
    Theoretical Peak performance: 254 Gflop/s
    Reason for disappearance: replaced by the newer SUN Fire E25K.


    Machine: SUN Fire 25K.
    Year of introduction: 2004.
    Year of exit: 2007.
    Type: Shared memory multi-processor, max. 72 processors.
    Theoretical Peak performance: 432 Gflop/s
    Reason for disappearance: Sun does not market SMP-type systems anymore.


    Machine: Thinking Machine Corporation CM-2(00).
    Year of introduction: 1987.
    Year of exit: 1991.
    Type: SIMD parallel machine with hypercube structure, max. 64K processors.
    Theoretical Peak performance: 31 Gflop/s
    Reason for disappearance: was replaced by the newer CM-5 (but see below).


    Machine: Thinking Machine Corporation CM-5.
    Year of introduction: 1991.
    Year of exit: 1996.
    Type: Distributed memory RISC based system, max. 16K processors.
    Theoretical Peak performance: 2 Tflop/s
    Reason for disappearance: Thinking Machine Corporation has stopped manufacturing hardware and hopes to keep alive as a software vendor.