Active | Two-Thirds Operational March 1997, Fully Operational June 1997, [1] decommissioned 2006 [2] |
---|---|
Sponsors | Intel Corporation [1] |
Operators | Sandia National Laboratories, US Department of Energy |
Location | Sandia National Laboratories, United States |
Power | 850 kW |
Operating system | Cougar / TOS (a Mach kernel derivative) |
Space | 1,600 sq ft (150 m2) [3] |
Memory | 1212 gigabytes |
Speed | 1.3 teraflops (peak) [1] |
Ranking | TOP500 : 1, June 2000 [4] |
Purpose | nuclear materials testing, other |
Legacy | First Supercomputer to achieve over 1.0 teraflops on LINPACK test |
Website | web.archive.org |
ASCI Red (also known as ASCI Option Red or TFLOPS) was the first computer built under the Accelerated Strategic Computing Initiative (ASCI), [5] [6] the supercomputing initiative of the United States government created to help the maintenance of the United States nuclear arsenal after the 1992 moratorium on nuclear testing.
ASCI Red was built by Intel and installed at Sandia National Laboratories in late 1996. The design was based on the Intel Paragon computer. The original goals to deliver a true teraflop machine by the end of 1996 that would be capable of running an ASCI application using all memory and nodes by September 1997 were met. [7] It was used by the US government from the years of 1997 to 2005 and was the world's fastest supercomputer until late 2000. [4] [6] It was the first ASCI machine that the Department of Energy acquired, [6] and also the first supercomputer to score above one teraflops on the LINPACK benchmark, a test that measures a computer's calculation speed. Later upgrades to ASCI Red allowed it to perform above two teraflops.
ASCI Red earned a reputation for reliability that some veterans say has never been beaten. Sandia director Bill Camp said that ASCI Red had the best reliability of any supercomputer ever built, and “was supercomputing’s high-water mark in longevity, price, and performance.” [8]
ASCI Red was decommissioned in 2006. [2]
The ASCI Red supercomputer was a distributed memory MIMD (Multiple Instruction, Multiple Data) message-passing computer. The design provided high degrees of scalability for I/O, memory, compute nodes, storage capacity, and communications; standard parallel interfaces also made it possible to port parallel applications to the machine. The machine was structured into four partitions: Compute, Service, I/O, and System. Parallel applications executed in the Compute Partition which contained nodes optimized for floating point performance. The compute nodes had only the features required for efficient computation – they were not purposed for general interactive services. The Service Partition provided an integrated, scalable host that supported interactive users (log-in sessions), application development, and system administration. The I/O Partition supported disk I/O, a scalable parallel file system and network services. The System Partition supported initial booting and system Reliability, Availability, and Serviceability (RAS) capabilities. [7]
The Service partition helps integrate all of the different parts of ASCI Red together. It provides a scalable host for users, and it is used for general system administration. [1] The I/O Partition provides a file system and network services, and the Service partition is made up of the log-in screens, tools for application development, and utilities for network connections. [5] The Compute partition contains nodes that are designed for floating point performance. This is where the actual computing takes place. [5] Every one of the compute nodes accommodated two 200 MHz Pentium Pro processors, each with a 16 KB level-1 cache and a 256 KB level-2 cache, which were upgraded later to two 333 MHz Pentium II OverDrive processors, each with a 32 KB level-1 cache and a 512 KB level-2 cache. [9] According to Intel, the ASCI Red Computer is also the first large scale supercomputer to be built entirely of common commercially available components. [10]
All of ASCI Red's partitions are interconnected to form one supercomputer, however at the same time none of the nodes support global shared memory. Each of the nodes works in its own memory, and each shares data with the others through "explicit message-passing". [11]
The computer itself took up almost 1,600 square feet (150 m2) of space, [3] and was made up of 104 "cabinets". Of those cabinets, 76 are computers (processors), 8 are switches, and 20 are disks. It had a total of 1212 GB of RAM, and 9298 separate processors. The original machine used Intel Pentium Pro processors each clocked at 200 MHz. These were later upgraded to specially packaged Pentium II Xeon processors, each clocked at 333 MHz. Overall, it required 850 kW of power (not including air conditioning). What sets ASCI Option Red aside from all of its predecessors in supercomputing is its high I/O bandwidth. Previous supercomputers had multi-GFLOPS performance, yet their slow I/O speeds would slow down, or bottleneck the systems. Intel's TFLOPS PFS is an extremely efficient "Parallel File System" that can sustain transfer speeds of up to 1 GB/s, eliminating bottlenecks. [12]
In December, 1996, three quarters of ASCI Red was measured at a world record 1.06 TFLOPS on MP LINPACK and held the record for fastest supercomputer in the world for several consecutive years, maxing out at 2.38 TFLOPS after a processor and memory upgrade in 1999. [4] [7] The system used Pentium Pro processors when initially constructed and when it recorded performance above one TFLOPS. In that configuration, when fully built it recorded 1.6 TFLOPS of performance. Upgrades later in 1999, to specially packaged Pentium II Xeon processors, pushed performance to 3.1 TFLOPS. [8]
The different partitions of ASCI Red run on different operating systems. For example, users of the computer work in an environment called "Teraflops OS", an operating system (once called Paragon OS) that was originally developed for the Intel Paragon XP/S Supercomputer. [5] ASCI Red's Compute partition runs on an operating system named Cougar. [11] Cougar is a Sandia Labs and University of New Mexico collaboration; it is a lightweight OS based on PUMA and SUNMOS, two systems that were also designed for use on the Paragon supercomputer. [11] It consists of a light weight kernel, the Process Control Thread, and other utilities and libraries. The Linux 2.4 kernel was ported to the system and a custom CNIC driver was written, but the heavy weight OS did not perform as well as the Cougar lightweight kernel on many benchmarks. [11]
A supercomputer is a type of computer with a high level of performance as compared to a general-purpose computer. The performance of a supercomputer is commonly measured in floating-point operations per second (FLOPS) instead of million instructions per second (MIPS). Since 2017, supercomputers have existed which can perform over 1017 FLOPS (a hundred quadrillion FLOPS, 100 petaFLOPS or 100 PFLOPS). For comparison, a desktop computer has performance in the range of hundreds of gigaFLOPS (1011) to tens of teraFLOPS (1013). Since November 2017, all of the world's fastest 500 supercomputers run on Linux-based operating systems. Additional research is being conducted in the United States, the European Union, Taiwan, Japan, and China to build faster, more powerful and technologically superior exascale supercomputers.
Floating point operations per second is a measure of computer performance in computing, useful in fields of scientific computations that require floating-point calculations.
Blue Gene was an IBM project aimed at designing supercomputers that can reach operating speeds in the petaFLOPS (PFLOPS) range, with low power consumption.
The Pentium Pro is a sixth-generation x86 microprocessor developed and manufactured by Intel and introduced on November 1, 1995. It introduced the P6 microarchitecture and was originally intended to replace the original Pentium in a full range of applications. Later, it was reduced to a more narrow role as a server and high-end desktop processor. The Pentium Pro was also used in supercomputers, most notably ASCI Red, which used two Pentium Pro CPUs on each computing nodes and was the first computer to reach over one teraFLOPS in 1996, holding the number one spot in the TOP500 list from 1997 to 2000.
The Pentium OverDrive was a microprocessor marketing brand name used by Intel, to cover a variety of consumer upgrade products sold in the mid-1990s. It was originally released for 486 motherboards, and later some Pentium sockets. Intel dropped the brand, as it failed to appeal to corporate buyers, and discouraged new system sales.
SUNMOS is an operating system jointly developed by Sandia National Laboratories and the Computer Science Department at the University of New Mexico. The goal of the project, started in 1991, is to develop a highly portable, yet efficient, operating system for massively parallel-distributed memory systems.
Scalable POWERparallel (SP) is a series of supercomputers from IBM. SP systems were part of the IBM RISC System/6000 (RS/6000) family, and were also called the RS/6000 SP. The first model, the SP1, was introduced in February 1993, and new models were introduced throughout the 1990s until the RS/6000 was succeeded by eServer pSeries in October 2000. The SP is a distributed memory system, consisting of multiple RS/6000-based nodes interconnected by an IBM-proprietary switch called the High Performance Switch (HPS). The nodes are clustered using software called PSSP, which is mainly written in Perl.
Red Storm was a supercomputer architecture designed for the US Department of Energy’s National Nuclear Security Administration Advanced Simulation and Computing Program. Cray, Inc developed it in 2004 based on the contracted architectural specifications provided by Sandia National Laboratories. The architecture was later commercially produced as the Cray XT3.
The Cray XT3 is a distributed memory massively parallel MIMD supercomputer designed by Cray Inc. with Sandia National Laboratories under the codename Red Storm. Cray turned the design into a commercial product in 2004. The XT3 derives much of its architecture from the previous Cray T3E system, and also from the Intel ASCI Red supercomputer.
The TOP500 project ranks and details the 500 most powerful non-distributed computer systems in the world. The project was started in 1993 and publishes an updated list of the supercomputers twice a year. The first of these updates always coincides with the International Supercomputing Conference in June, and the second is presented at the ACM/IEEE Supercomputing Conference in November. The project aims to provide a reliable basis for tracking and detecting trends in high-performance computing and bases rankings on HPL benchmarks, a portable implementation of the high-performance LINPACK benchmark written in Fortran for distributed-memory computers.
The QCDOC is a supercomputer technology focusing on using relatively cheap low power processing elements to produce a massively parallel machine. The machine is custom-made to solve small but extremely demanding problems in the fields of quantum physics.
The National Center for Computational Sciences (NCCS) is a United States Department of Energy (DOE) Leadership Computing Facility that houses the Oak Ridge Leadership Computing Facility (OLCF), a DOE Office of Science User Facility charged with helping researchers solve challenging scientific problems of global interest with a combination of leading high-performance computing (HPC) resources and international expertise in scientific computing.
Portals is a low-level network API for high-performance networking on high-performance computing systems developed by Sandia National Laboratories and the University of New Mexico. Portals is currently the lowest-level network programming interface on the commercially successful XT line of supercomputers from Cray.
A lightweight kernel (LWK) operating system is one used in a large computer with many processor cores, termed a parallel computer.
This list compares various amounts of computing power in instructions per second organized by order of magnitude in FLOPS.
Japan operates a number of centers for supercomputing which hold world records in speed, with the K computer being the world's fastest from June 2011 to June 2012, and Fugaku holding the lead from June 2020 until June 2022.
The history of supercomputing goes back to the 1960s when a series of computers at Control Data Corporation (CDC) were designed by Seymour Cray to use innovative designs and parallelism to achieve superior computational peak performance. The CDC 6600, released in 1964, is generally considered the first supercomputer. However, some earlier computers were considered supercomputers for their day such as the 1954 IBM NORC in the 1950s, and in the early 1960s, the UNIVAC LARC (1960), the IBM 7030 Stretch (1962), and the Manchester Atlas (1962), all of which were of comparable power.
Several centers for supercomputing exist across Europe, and distributed access to them is coordinated by European initiatives to facilitate high-performance computing. One such initiative, the HPC Europa project, fits within the Distributed European Infrastructure for Supercomputing Applications (DEISA), which was formed in 2002 as a consortium of eleven supercomputing centers from seven European countries. Operating within the CORDIS framework, HPC Europa aims to provide access to supercomputers across Europe.
Xeon Phi is a discontinued series of x86 manycore processors designed and made by Intel. It was intended for use in supercomputers, servers, and high-end workstations. Its architecture allowed use of standard programming languages and application programming interfaces (APIs) such as OpenMP.
The Cray XC40 is a massively parallel multiprocessor supercomputer manufactured by Cray. It consists of Intel Haswell Xeon processors, with optional Nvidia Tesla or Intel Xeon Phi accelerators, connected together by Cray's proprietary "Aries" interconnect, stored in air-cooled or liquid-cooled cabinets. The XC series supercomputers are available with the Cray DataWarp applications I/O accelerator technology.