Menu
Home Explore People Places Arts History Plants & Animals Science Life & Culture Technology
On this page
Floating point operations per second
Measure of computer performance

Floating point operations per second (FLOPS) is a key measure of computer performance in computing, especially important for scientific computations requiring floating-point calculations. This metric provides a more precise evaluation of a system’s capability in handling complex arithmetic than traditional measures such as instructions per second, making it essential for assessing performance in environments where floating-point accuracy and speed are critical.

Related Image Collections Add Image
Profiles
1 Image
We don't have any YouTube videos related to Floating point operations per second yet.
We don't have any PDF documents related to Floating point operations per second yet.
We don't have any Books related to Floating point operations per second yet.
We don't have any archived web articles related to Floating point operations per second yet.

Floating-point arithmetic

Multipliers for flops
NameUnitValue
kiloFLOPSkFLOPS103
megaFLOPSMFLOPS106
gigaFLOPSGFLOPS109
teraFLOPSTFLOPS1012
petaFLOPSPFLOPS1015
exaFLOPSEFLOPS1018
zettaFLOPSZFLOPS1021
yottaFLOPSYFLOPS1024
ronnaFLOPSRFLOPS1027
quettaFLOPSQFLOPS1030

Floating-point arithmetic is needed for very large or very small real numbers, or computations that require a large dynamic range. Floating-point representation is similar to scientific notation, except computers use base two (with rare exceptions), rather than base ten. The encoding scheme stores the sign, the exponent (in base two for Cray and VAX, base two or ten for IEEE floating point formats, and base 16 for IBM Floating Point Architecture) and the significand (number after the radix point). While several similar formats are in use, the most common is ANSI/IEEE Std. 754-1985. This standard defines the format for 32-bit numbers called single precision, as well as 64-bit numbers called double precision and longer numbers called extended precision (used for intermediate results). Floating-point representations can support a much wider range of values than fixed-point, with the ability to represent very small numbers and very large numbers.2

Dynamic range and precision

The exponentiation inherent in floating-point computation assures a much larger dynamic range – the largest and smallest numbers that can be represented – which is especially important when processing data sets where some of the data may have extremely large range of numerical values or where the range may be unpredictable. As such, floating-point processors are ideally suited for computationally intensive applications.3

Computational performance

FLOPS and MIPS are units of measure for the numerical computing performance of a computer. Floating-point operations are typically used in fields such as scientific computational research, as well as in machine learning. However, before the late 1980s floating-point hardware (it's possible to implement FP arithmetic in software over any integer hardware) was typically an optional feature, and computers that had it were said to be "scientific computers", or to have "scientific computation" capability. Thus the unit MIPS was useful to measure integer performance of any computer, including those without such a capability, and to account for architecture differences, similar MOPS (million operations per second) was used as early as 19704 as well. Note that besides integer (or fixed-point) arithmetics, examples of integer operation include data movement (A to B) or value testing (If A = B, then C). That's why MIPS as a performance benchmark is adequate when a computer is used in database queries, word processing, spreadsheets, or to run multiple virtual operating systems.56 In 1974 David Kuck coined the terms flops and megaflops for the description of supercomputer performance of the day by the number of floating-point calculations they performed per second.7 This was much better than using the prevalent MIPS to compare computers as this statistic usually had little bearing on the arithmetic capability of the machine on scientific tasks.

FLOPS on an HPC-system can be calculated using this equation:8

FLOPS = racks × nodes rack × sockets node × cores socket × cycles second × FLOPs cycle . {\displaystyle {\text{FLOPS}}={\text{racks}}\times {\frac {\text{nodes}}{\text{rack}}}\times {\frac {\text{sockets}}{\text{node}}}\times {\frac {\text{cores}}{\text{socket}}}\times {\frac {\text{cycles}}{\text{second}}}\times {\frac {\text{FLOPs}}{\text{cycle}}}.}

This can be simplified to the most common case: a computer that has exactly 1 CPU:

FLOPS = cores × cycles second × FLOPs cycle . {\displaystyle {\text{FLOPS}}={\text{cores}}\times {\frac {\text{cycles}}{\text{second}}}\times {\frac {\text{FLOPs}}{\text{cycle}}}.}

FLOPS can be recorded in different measures of precision, for example, the TOP500 supercomputer list ranks computers by 64-bit (double-precision floating-point format) operations per second, abbreviated to FP64.9 Similar measures are available for 32-bit (FP32) and 16-bit (FP16) operations.

Floating-point operations per clock cycle for various processors

Floating-point operations per clock cycle per core10
MicroarchitectureInstruction set architectureFP64FP32FP16
Intel CPU
Intel 80486x87 (32-bit)?0.12811?
x87 (32-bit)?0.512?
MMX (64-bit)?113?
Intel P6 Pentium IIISSE (64-bit)?214?
Intel NetBurst Pentium 4 (Willamette, Northwood)SSE2 (64-bit)24?
Intel P6 Pentium MSSE2 (64-bit)12?
SSE3 (64-bit)24?
48?
Intel Atom (Bonnell, Saltwell, Silvermont and Goldmont)SSE3 (128-bit)24?
Intel Sandy Bridge (Sandy Bridge, Ivy Bridge)AVX (256-bit)8160
AVX2 & FMA (256-bit)16320
Intel Xeon Phi (Knights Corner)IMCI (512-bit)16320
AVX-512 & FMA (512-bit)32640
AMD CPU
AMD BobcatAMD64 (64-bit)240
AVX (128-bit)480
AMD K10SSE4/4a (128-bit)480
AMD Bulldozer17(Piledriver, Steamroller, Excavator)
  • AVX (128-bit)(Bulldozer, Steamroller)
  • AVX2 (128-bit) (Excavator)
  • FMA3 (Bulldozer)18
  • FMA3/4 (Piledriver, Excavator)
480
  • AMD Zen(Ryzen 1000 series, Threadripper 1000 series, Epyc Naples)
  • AMD Zen+19202122(Ryzen 2000 series, Threadripper 2000 series)
AVX2 & FMA(128-bit, 256-bit decoding)238160
  • AMD Zen 224(Ryzen 3000 series, Threadripper 3000 series, Epyc Rome)
  • AMD Zen 3(Ryzen 5000 series, Epyc Milan)
AVX2 & FMA (256-bit)16320
AVX-512 & FMA (256-bit)16320
  • AMD Zen 526(Ryzen 9000 series, Threadripper 9000 series, Epyc Turin)
AVX-512 & FMA (512-bit)32640
ARM CPU
ARM Cortex-A7, A9, A15ARMv7180
ARM Cortex-A32, A35ARMv8280
ARM Cortex-A53, A55, A57,27 A72, A73, A75ARMv8480
ARM Cortex-A76, A77, A78ARMv88160
ARM Cortex-X1ARMv81632?
Qualcomm KraitARMv8180
Qualcomm Kryo (1xx - 3xx)ARMv8280
Qualcomm Kryo (4xx - 5xx)ARMv88160
Samsung Exynos M1 and M2ARMv8280
Samsung Exynos M3 and M4ARMv83120
IBM PowerPC A2 (Blue Gene/Q)?88(as FP64)0
Hitachi SH-42829SH-4170
Nvidia GPU
Nvidia Curie (GeForce 6 series and GeForce 7 series)PTX?8?
Nvidia Tesla 2.0 (GeForce GTX 260–295)PTX?2?
Nvidia Fermi

(only GeForce GTX 465–480, 560 Ti, 570–590)

PTX1⁄4(locked by driver,1 in hardware)20
Nvidia Fermi

(only Quadro 600–2000)

PTX1⁄820
Nvidia Fermi

(only Quadro 4000–7000, Tesla)

PTX120
Nvidia Kepler

(GeForce (except Titan and Titan Black), Quadro (except K6000), Tesla K10)

PTX1⁄12(for GK110:locked by driver,2⁄3 in hardware)20
Nvidia Kepler

(GeForce GTX Titan and Titan Black, Quadro K6000, Tesla (except K10))

PTX2⁄320
  • Nvidia Maxwell
  • Nvidia Pascal(all except Quadro GP100 and Tesla P100)
PTX1⁄1621⁄32
Nvidia Pascal (only Quadro GP100 and Tesla P100)PTX124
Nvidia Volta30PTX12 (FP32) + 2 (INT32)16
Nvidia Turing (only GeForce 16XX)PTX1⁄162 (FP32) + 2 (INT32)4
Nvidia Turing (all except GeForce 16XX)PTX1⁄162 (FP32) + 2 (INT32)16
Nvidia Ampere3132 (only Tesla A100/A30)PTX22 (FP32) + 2 (INT32)32
PTX1⁄322 (FP32) + 0 (INT32)or1 (FP32) + 1 (INT32)8
Nvidia HopperPTX22 (FP32) + 1 (INT32)32
AMD GPU
AMD TeraScale 1 (Radeon HD 4000 series)TeraScale 10.42?
AMD TeraScale 2 (Radeon HD 5000 series)TeraScale 212?
AMD TeraScale 3 (Radeon HD 6000 series)TeraScale 314?
AMD GCN(only Radeon Pro W 8100–9100)GCN12?
AMD GCN(all except Radeon Pro W 8100–9100, Vega 10–20)GCN1⁄824
AMD GCN Vega 10GCN1⁄824
AMD GCN Vega 20(only Radeon VII)GCN1⁄2(locked by driver,1 in hardware)24
AMD GCN Vega 20(only Radeon Instinct MI50 / MI60 and Radeon Pro VII)GCN124
RDNA1⁄824
AMD RDNA3RDNA1⁄8?48?
AMD CDNACDNA14(Tensor)3516
AMD CDNA 2CDNA 24(Tensor)4(Tensor)16
Intel GPU
Intel Xe-LP (Iris Xe MAX)36Xe1⁄2?24
Intel Xe-HPG (Arc Alchemist)37Xe0216
Intel Xe-HPC (Ponte Vecchio)38Xe2232
Intel Xe2 (Arc Battlemage)Xe21⁄8216
Qualcomm GPU
Qualcomm Adreno 5x0Adreno 5xx124
Qualcomm Adreno 6x0Adreno 6xx124
Graphcore
Graphcore Colossus GC23940?01664
  • Graphcore Colossus GC200 Mk241
  • Graphcore Bow-200042
?032128
Supercomputer
ENIAC @ 100 kHz in 19450.00443(~3×10−8 FLOPS/W)
48-bit processor @ 208 kHz in CDC 1604 in 1960
60-bit processor @ 10 MHz in CDC 6600 in 19640.3(FP60)
60-bit processor @ 10 MHz in CDC 7600 in 19671.0(FP60)
Cray-1 @ 80 MHz in 19762(700 FLOPS/W)
CDC Cyber 205 @ 50 MHz in 1981

FORTRAN compiler (ANSI 77 with vector extensions)

816
Transputer IMS T800-20 @ 20 MHz in 19870.0844
Parallella E16 @ 1000 MHz in 2012245(5.0 GFLOPS/W)46
Parallella E64 @ 800 MHz in 2012247(50.0 GFLOPS/W)48
MicroarchitectureInstruction set architectureFP64FP32FP16

Performance records

Single computer records

In June 1997, Intel's ASCI Red was the world's first computer to achieve one teraFLOPS and beyond. 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".49

NEC's SX-9 supercomputer was the world's first vector processor to exceed 100 gigaFLOPS per single core.

In June 2006, a new computer was announced by Japanese research institute RIKEN, the MDGRAPE-3. The computer's performance tops out at one petaFLOPS, almost two times faster than the Blue Gene/L, but MDGRAPE-3 is not a general purpose computer, which is why it does not appear in the Top500.org list. It has special-purpose pipelines for simulating molecular dynamics.

By 2007, Intel Corporation unveiled the experimental multi-core POLARIS chip, which achieves 1 teraFLOPS at 3.13 GHz. The 80-core chip can raise this result to 2 teraFLOPS at 6.26 GHz, although the thermal dissipation at this frequency exceeds 190 watts.50

In June 2007, Top500.org reported the fastest computer in the world to be the IBM Blue Gene/L supercomputer, measuring a peak of 596 teraFLOPS.51 The Cray XT4 hit second place with 101.7 teraFLOPS.

On June 26, 2007, IBM announced the second generation of its top supercomputer, dubbed Blue Gene/P and designed to continuously operate at speeds exceeding one petaFLOPS, faster than the Blue Gene/L. When configured to do so, it can reach speeds in excess of three petaFLOPS.52

On October 25, 2007, NEC Corporation of Japan issued a press release announcing its SX series model SX-9,53 claiming it to be the world's fastest vector supercomputer. The SX-9 features the first CPU capable of a peak vector performance of 102.4 gigaFLOPS per single core.

On February 4, 2008, the NSF and the University of Texas at Austin opened full scale research runs on an AMD, Sun supercomputer named Ranger,54 the most powerful supercomputing system in the world for open science research, which operates at sustained speed of 0.5 petaFLOPS.

On May 25, 2008, an American supercomputer built by IBM, named 'Roadrunner', reached the computing milestone of one petaFLOPS. It headed the June 2008 and November 2008 TOP500 list of the most powerful supercomputers (excluding grid computers).5556 The computer is located at Los Alamos National Laboratory in New Mexico. The computer's name refers to the New Mexico state bird, the greater roadrunner (Geococcyx californianus).57

In June 2008, AMD released ATI Radeon HD 4800 series, which are reported to be the first GPUs to achieve one teraFLOPS. On August 12, 2008, AMD released the ATI Radeon HD 4870X2 graphics card with two Radeon R770 GPUs totaling 2.4 teraFLOPS.

In November 2008, an upgrade to the Cray Jaguar supercomputer at the Department of Energy's (DOE's) Oak Ridge National Laboratory (ORNL) raised the system's computing power to a peak 1.64 petaFLOPS, making Jaguar the world's first petaFLOPS system dedicated to open research. In early 2009 the supercomputer was named after a mythical creature, Kraken. Kraken was declared the world's fastest university-managed supercomputer and sixth fastest overall in the 2009 TOP500 list. In 2010 Kraken was upgraded and can operate faster and is more powerful.

In 2009, the Cray Jaguar performed at 1.75 petaFLOPS, beating the IBM Roadrunner for the number one spot on the TOP500 list.58

In October 2010, China unveiled the Tianhe-1, a supercomputer that operates at a peak computing rate of 2.5 petaFLOPS.5960

As of 2010 the fastest PC processor reached 109 gigaFLOPS (Intel Core i7 980 XE)61 in double precision calculations. GPUs are considerably more powerful. For example, Nvidia Tesla C2050 GPU computing processors perform around 515 gigaFLOPS62 in double precision calculations, and the AMD FireStream 9270 peaks at 240 gigaFLOPS.63

In November 2011, it was announced that Japan had achieved 10.51 petaFLOPS with its K computer.64 It has 88,128 SPARC64 VIIIfx processors in 864 racks, with theoretical performance of 11.28 petaFLOPS. It is named after the Japanese word "kei", which stands for 10 quadrillion,65 corresponding to the target speed of 10 petaFLOPS.

On November 15, 2011, Intel demonstrated a single x86-based processor, code-named "Knights Corner", sustaining more than a teraFLOPS on a wide range of DGEMM operations. Intel emphasized during the demonstration that this was a sustained teraFLOPS (not "raw teraFLOPS" used by others to get higher but less meaningful numbers), and that it was the first general purpose processor to ever cross a teraFLOPS.6667

On June 18, 2012, IBM's Sequoia supercomputer system, based at the U.S. Lawrence Livermore National Laboratory (LLNL), reached 16 petaFLOPS, setting the world record and claiming first place in the latest TOP500 list.68

On November 12, 2012, the TOP500 list certified Titan as the world's fastest supercomputer per the LINPACK benchmark, at 17.59 petaFLOPS.6970 It was developed by Cray Inc. at the Oak Ridge National Laboratory and combines AMD Opteron processors with "Kepler" NVIDIA Tesla graphics processing unit (GPU) technologies.7172

On June 10, 2013, China's Tianhe-2 was ranked the world's fastest with 33.86 petaFLOPS.73

On June 20, 2016, China's Sunway TaihuLight was ranked the world's fastest with 93 petaFLOPS on the LINPACK benchmark (out of 125 peak petaFLOPS). The system was installed at the National Supercomputing Center in Wuxi, and represented more performance than the next five most powerful systems on the TOP500 list did at the time combined.74

In June 2019, Summit, an IBM-built supercomputer now running at the Department of Energy's (DOE) Oak Ridge National Laboratory (ORNL), captured the number one spot with a performance of 148.6 petaFLOPS on High Performance Linpack (HPL), the benchmark used to rank the TOP500 list. Summit has 4,356 nodes, each one equipped with two 22-core Power9 CPUs, and six NVIDIA Tesla V100 GPUs.75

In June 2022, the United States' Frontier was the most powerful supercomputer on TOP500, reaching 1102 petaFlops (1.102 exaFlops) on the LINPACK benchmarks. 76[circular reference]

In November 2024, the United States’ El Capitan exascale supercomputer, hosted at the Lawrence Livermore National Laboratory in Livermore, displaced Frontier as the world's fastest supercomputer in the 64th edition of the Top500 (Nov 2024).

Distributed computing records

Distributed computing uses the Internet to link personal computers to achieve more FLOPS:

  • As of April 2020, the Folding@home network has over 2.3 exaFLOPS of total computing power.77787980 It is the most powerful distributed computer network, being the first ever to break 1 exaFLOPS of total computing power. This level of performance is primarily enabled by the cumulative effort of a vast array of powerful GPU and CPU units.81
  • As of December 2020, the entire BOINC network averages about 31 petaFLOPS.82
  • As of June 2018, SETI@home, employing the BOINC software platform, averages 896 teraFLOPS.83
  • As of June 2018, Einstein@Home, a project using the BOINC network, is crunching at 3 petaFLOPS.84
  • As of June 2018, MilkyWay@home, using the BOINC infrastructure, computes at 847 teraFLOPS.85
  • As of June 2020, GIMPS, searching for Mersenne primes, is sustaining 1,354 teraFLOPS.86

Cost of computing

Hardware costs

DateApproximate USD per GFLOPSPlatform providing the lowest cost per GFLOPSComments
Unadjusted202487
1945$1.265T$22.094TENIAC: $487,000 in 1945 and $8,506,000 in 2023.$487,000 / 0.000000385 GFLOPS. First-generation (vacuum tube-based) electronic digital computer.
1961$18.672B$196.472BA basic installation of IBM 7030 Stretch had a cost at the time of US$7.78 million each.The IBM 7030 Stretch performs one floating-point multiply every 2.4 microseconds.88 Second-generation (discrete transistor-based) computer.
1964$2.3B$23.318BBase model CDC 6600 price: $6,891,300.The CDC 6600 is considered to be the first commercially-successful supercomputer.
1984$18,750,000$56,748,479Cray X-MP/48$15,000,000 / 0.8 GFLOPS. Third-generation (integrated circuit-based) computer.
1997$30,000$58,762Two 16-processor Beowulf clusters with Pentium Pro microprocessors89
April 2000$1,000$1,855Bunyip Beowulf clusterBunyip was the first sub-US$1/MFLOPS computing technology. It won the Gordon Bell Prize in 2000.
May 2000$640$1,169KLAT2KLAT2 was the first computing technology which scaled to large applications while staying under US$1/MFLOPS.90
August 2003$83.86$143.34KASY0KASY0 was the first sub-US$100/GFLOPS computing technology. KASY0 achieved 471 GFLOPS on 32-bit HPL. At a cost of less than $39,500, that makes it the first supercomputer to break $100/GFLOPS.91
August 2007$48.31$73.26MicrowulfAs of August 2007, this 26 GFLOPS "personal" Beowulf cluster can be built for $1256.92
March 2011$1.80$2.52HPU4ScienceThis $30,000 cluster was built using only commercially available "gamer" grade hardware.93
August 201275¢$1.03Quad AMD Radeon 7970 SystemA quad AMD Radeon 7970 desktop computer reaching 16 TFLOPS of single-precision, 4 TFLOPS of double-precision computing performance. Total system cost was $3000; built using only commercially available hardware.94
June 201321.68¢29.26¢Sony PlayStation 4The Sony PlayStation 4 is listed as having a peak performance of 1.84 TFLOPS, at a price of $39995
November 201316.11¢21.75¢AMD Sempron 145 & GeForce GTX 760 systemBuilt using commercially available parts, a system using one AMD Sempron 145 and three Nvidia GeForce GTX 760 reaches a total of 6.771 TFLOPS for a total cost of US$1,090.66.96
December 201312.41¢16.75¢Pentium G550 & Radeon R9 290 systemBuilt using commercially available parts. Intel Pentium G550 and AMD Radeon R9 290 tops out at 4.848 TFLOPS grand total of US$681.84.97
January 20157.85¢10.41¢Celeron G1830 & Radeon R9 295X2 systemBuilt using commercially available parts. Intel Celeron G1830 and AMD Radeon R9 295X2 tops out at over 11.5 TFLOPS at a grand total of US$902.57.9899
June 20176¢7.7¢AMD Ryzen 7 1700 & AMD Radeon Vega Frontier Edition systemBuilt using commercially available parts. AMD Ryzen 7 1700 CPU combined with AMD Radeon Vega FE cards in CrossFire tops out at over 50 TFLOPS at just under US$3,000 for the complete system.100
October 20172.73¢3.5¢Intel Celeron G3930 & AMD RX Vega 64 systemBuilt using commercially available parts. Three AMD RX Vega 64 graphics cards provide just over 75 TFLOPS half precision (38 TFLOPS SP or 2.6 TFLOPS DP when combined with the CPU) at ~$2,050 for the complete system.101
November 20203.14¢3.82¢AMD Ryzen 3600 & 3× NVIDIA RTX 3080 systemAMD Ryzen 3600 @ 484 GFLOPS & $199.99

3× NVIDIA RTX 3080 @ 29,770 GFLOPS each & $699.99

Total system GFLOPS = 89,794 / TFLOPS = 89.794

Total system cost incl. realistic but low cost parts; matched with other example = $2839102

US$/GFLOP = $0.0314

November 20203.88¢4.71¢PlayStation 5The Sony PlayStation 5 Digital Edition is listed as having a peak performance of 10.28 TFLOPS (20.56 TFLOPS at half precision) at a retail price of $399.103
November 20204.11¢4.99¢Xbox Series XMicrosoft's Xbox Series X is listed as having a peak performance of 12.15 TFLOPS (24.30 TFLOPS at half precision) at a retail price of $499.104
September 20221.94¢2.08¢RTX 4090Nvidia's RTX 4090 is listed as having a peak performance of 82.6 TFLOPS (1.32 PFLOPS at 8-bit precision) at a retail price of $1599.105
May 20231.25¢1.29¢Radeon RX 7600AMD's RX 7600 is listed as having a peak performance of 21.5 TFLOPS at a retail price of $269.106

See also

References

  1. "Understand measures of supercomputer performance and storage system capacity". kb.iu.edu. Retrieved March 23, 2024. https://kb.iu.edu/d/apeq ↩

  2. Floating Point Retrieved on December 25, 2009. http://www.dspguide.com/ch4/3.htm ↩

  3. Summary: Fixed-point (integer) vs floating-point Archived December 31, 2009, at the Wayback Machine Retrieved on December 25, 2009. http://www.analog.com/en/embedded-processing-dsp/content/Fixed-Point_vs_Floating-Point_DSP/fca.html ↩

  4. NASA Technical Note. National Aeronautics and Space Administration. 1970. https://books.google.com/books?id=ARwaAQAAMAAJ&pg=RA7-PA7 ↩

  5. Fixed versus floating point. Retrieved on December 25, 2009. http://www.dspguide.com/ch28/4.htm ↩

  6. Data manipulation and math calculation. Retrieved on December 25, 2009. http://www.dspguide.com/ch28/1.htm ↩

  7. Kuck, D. J. (1974). Computer System Capacity Fundamentals. U.S. Department of Commerce, National Bureau of Standards. https://books.google.com/books?id=PFqzjuXL4YgC&pg=PA1 ↩

  8. ""Nodes, Sockets, Cores and FLOPS, Oh, My" by Dr. Mark R. Fernandez, Ph.D." Archived from the original on February 13, 2019. Retrieved February 12, 2019. https://web.archive.org/web/20190213005604/https://www.dell.com/support/article/fr/fr/frbsdt1/sln310893/nodes-sockets-cores-and-flops-oh-my ↩

  9. "FREQUENTLY ASKED QUESTIONS". top500.org. Retrieved June 23, 2020. https://www.top500.org/resources/frequently-asked-questions/ ↩

  10. "Floating-Point Operations Per Second (FLOPS)". https://en.wikichip.org/wiki/flops ↩

  11. "home.iae.nl". http://home.iae.nl/users/mhx/flops_4.tbl ↩

  12. "home.iae.nl". http://home.iae.nl/users/mhx/flops_4.tbl ↩

  13. "Computing Power throughout History". alternatewars.com. Retrieved February 13, 2021. https://www.alternatewars.com/BBOW/Computing/Computing_Power.htm ↩

  14. "Computing Power throughout History". alternatewars.com. Retrieved February 13, 2021. https://www.alternatewars.com/BBOW/Computing/Computing_Power.htm ↩

  15. Dolbeau, Romain (2017). "Theoretical Peak FLOPS per instruction set: a tutorial". Journal of Supercomputing. 74 (3): 1341–1377. doi:10.1007/s11227-017-2177-5. S2CID 3540951. /wiki/Doi_(identifier) ↩

  16. Dolbeau, Romain (2017). "Theoretical Peak FLOPS per instruction set: a tutorial". Journal of Supercomputing. 74 (3): 1341–1377. doi:10.1007/s11227-017-2177-5. S2CID 3540951. /wiki/Doi_(identifier) ↩

  17. Dolbeau, Romain (2017). "Theoretical Peak FLOPS per instruction set: a tutorial". Journal of Supercomputing. 74 (3): 1341–1377. doi:10.1007/s11227-017-2177-5. S2CID 3540951. /wiki/Doi_(identifier) ↩

  18. "New instructions support for Bulldozer (FMA3) and Piledriver (FMA3+4 and CVT, BMI, TB M)" (PDF). https://developer.amd.com/wordpress/media/2012/10/New-Bulldozer-and-Piledriver-Instructions.pdf ↩

  19. Dolbeau, Romain (2017). "Theoretical Peak FLOPS per instruction set: a tutorial". Journal of Supercomputing. 74 (3): 1341–1377. doi:10.1007/s11227-017-2177-5. S2CID 3540951. /wiki/Doi_(identifier) ↩

  20. "Agner's CPU blog - Test results for AMD Ryzen". http://www.agner.org/optimize/blog/read.php?i=838 ↩

  21. https://arstechnica.com/gadgets/2017/03/amds-moment-of-zen-finally-an-architecture-that-can-compete/2/ "each core now has a pair of 128-bit FMA units of its own" https://arstechnica.com/gadgets/2017/03/amds-moment-of-zen-finally-an-architecture-that-can-compete/2/ ↩

  22. Mike Clark (August 23, 2016). A New x86 Core Architecture for the Next Generation of Computing (PDF). HotChips 28. AMD. Archived from the original (PDF) on July 31, 2020. Retrieved October 8, 2017. page 7 https://web.archive.org/web/20200731171730/https://www.hotchips.org/wp-content/uploads/hc_archives/hc28/HC28.23-Tuesday-Epub/HC28.23.90-High-Perform-Epub/HC28.23.930-X86-core-MikeClark-AMD-final_v2-28.pdf#page=7 ↩

  23. "The microarchitecture of Intel and AMD CPUs" (PDF). https://www.agner.org/optimize/microarchitecture.pdf ↩

  24. "AMD CEO Lisa Su's COMPUTEX 2019 Keynote". youtube.com. May 27, 2019. Archived from the original on December 11, 2021. https://www.youtube.com/watch?v=_96stDCb-mk&t=3299 ↩

  25. "Leadership HPC Performance with 5th Generation AMD EPYC Processors". https://community.amd.com/t5/server-processors/leadership-hpc-performance-with-5th-generation-amd-epyc/ba-p/739498 ↩

  26. "Leadership HPC Performance with 5th Generation AMD EPYC Processors". https://community.amd.com/t5/server-processors/leadership-hpc-performance-with-5th-generation-amd-epyc/ba-p/739498 ↩

  27. Dolbeau, Romain (2017). "Theoretical Peak FLOPS per instruction set: a tutorial". Journal of Supercomputing. 74 (3): 1341–1377. doi:10.1007/s11227-017-2177-5. S2CID 3540951. /wiki/Doi_(identifier) ↩

  28. "Entertainment Systems and High-Performance Processor SH-4" (PDF). Hitachi Review. 48 (2). Hitachi: 58–63. 1999. Retrieved June 21, 2019. https://retrocdn.net/images/f/fa/Entertainment_Systems_and_High-Performance_Processor_SH-4.pdf ↩

  29. "SH-4 Next-Generation DSP Architecture for VoIP" (PDF). Hitachi. 2000. Retrieved June 21, 2019. https://retrocdn.net/images/b/b3/SH-4_Next-Generation_DSP_Architecture.pdf ↩

  30. "Inside Volta: The World's Most Advanced Data Center GPU". May 10, 2017. https://devblogs.nvidia.com/inside-volta/ ↩

  31. "NVIDIA Ampere Architecture In-Depth". May 14, 2020. https://devblogs.nvidia.com/nvidia-ampere-architecture-in-depth/ ↩

  32. "NVIDIA A100 GPUs Power the Modern Data Center". NVIDIA. https://www.nvidia.com/en-us/data-center/a100/ ↩

  33. Schilling, Andreas (June 10, 2019). "Die RDNA-Architektur - Seite 2". Hardwareluxx. https://www.hardwareluxx.de/index.php/artikel/hardware/grafikkarten/49892-alles-zu-navi-radeon-rx-5700-xt-ist-rdna-mit-gddr6.html ↩

  34. "AMD Radeon RX 5700 XT Specs". TechPowerUp. https://www.techpowerup.com/gpu-specs/radeon-rx-5700-xt.c3339 ↩

  35. "AMD Instinct MI100 Accelerator". https://www.amd.com/en/products/server-accelerators/instinct-mi100 ↩

  36. "Introduction to the Xe-HPG Architecture". https://www.intel.com/content/www/us/en/developer/articles/technical/introduction-to-the-xe-hpg-architecture.html ↩

  37. "Introduction to the Xe-HPG Architecture". https://www.intel.com/content/www/us/en/developer/articles/technical/introduction-to-the-xe-hpg-architecture.html ↩

  38. "Intel Data Center GPU Max". November 9, 2022. https://allinfo.space/2022/11/09/intel-data-center-gpu-max-ponte-vecchio-starts-in-3-variants-for-supercomputers/ ↩

  39. "250 TFLOPs/s for two chips with FP16 mixed precision". youtube.com. October 26, 2018. https://www.youtube.com/watch?v=2IOyQEIlN6Y&t=1361 ↩

  40. Archived at Ghostarchive and the Wayback Machine: "Estimation via power consumption that FP32 is 1/4 of FP16 and that clock frequency is below 1.5GHz". youtube.com. October 25, 2017. https://ghostarchive.org/varchive/youtube/20211211/7XtBZ4Hsi_M ↩

  41. Archived at Ghostarchive and the Wayback Machine: "Introducing Graphcore's Mk2 IPU systems". youtube.com. July 15, 2020. https://ghostarchive.org/varchive/youtube/20211211/_zvU0uwIafQ ↩

  42. "Bow-2000 IPU-Machine". docs.graphcore.ai/. https://docs.graphcore.ai/projects/bow-2000-datasheet/en/latest/product-description.html#technical-specifications ↩

  43. ENIAC @ 100 kHz with 385 Flops "Computers of Yore". clear.rice.edu. Retrieved February 26, 2021. https://www.clear.rice.edu/comp201/08-spring/lectures/lec02/computers.shtml ↩

  44. "IMS T800 Architecture". transputer.net. Retrieved December 28, 2023. https://www.transputer.net/tn/06/tn06.html#x1-150005 ↩

  45. Epiphany-III 16-core 65nm Microprocessor (E16G301) // admin (August 19, 2012) http://www.adapteva.com/products/silicon-devices/e16g301/ ↩

  46. Feldman, Michael (August 22, 2012). "Adapteva Unveils 64-Core Chip". HPCWire. Retrieved September 3, 2014. http://www.hpcwire.com/2012/08/22/adapteva_unveils_64-core_chip/ ↩

  47. Epiphany-IV 64-core 28nm Microprocessor (E64G401) // admin (August 19, 2012) http://www.adapteva.com/products/silicon-devices/e64g401/ ↩

  48. Feldman, Michael (August 22, 2012). "Adapteva Unveils 64-Core Chip". HPCWire. Retrieved September 3, 2014. http://www.hpcwire.com/2012/08/22/adapteva_unveils_64-core_chip/ ↩

  49. "Sandia's ASCI Red, world's first teraflop supercomputer, is decommissioned" (PDF). Archived from the original (PDF) on November 5, 2010. Retrieved November 17, 2011. https://web.archive.org/web/20101105131112/http://www.jacobsequity.com/ASCI%20Red%20Supercomputer.pdf ↩

  50. Richard Swinburne (April 30, 2007). "The Arrival of TeraFLOP Computing". bit-tech.net. Retrieved February 9, 2012. http://www.bit-tech.net/hardware/2007/04/30/the_arrival_of_teraflop_computing/2 ↩

  51. "29th TOP500 List of World's Fastest Supercomputers Released". Top500.org. June 23, 2007. Archived from the original on May 9, 2008. Retrieved July 8, 2008. https://web.archive.org/web/20080509064814/http://www.top500.org/news/2007/06/23/29th_top500_list_world_s_fastest_supercomputers_released ↩

  52. "June 2008". TOP500. Retrieved July 8, 2008. http://www.top500.org/lists/2008/06 ↩

  53. "NEC Launches World's Fastest Vector Supercomputer, SX-9". NEC. October 25, 2007. Retrieved July 8, 2008. http://www.nec.co.jp/press/en/0710/2501.html ↩

  54. "University of Texas at Austin, Texas Advanced Computing Center". Archived from the original on August 1, 2009. Retrieved September 13, 2010. Any researcher at a U.S. institution can submit a proposal to request an allocation of cycles on the system. https://web.archive.org/web/20090801102108/http://www.tacc.utexas.edu/resources/hpcsystems/ ↩

  55. Sharon Gaudin (June 9, 2008). "IBM's Roadrunner smashes 4-minute mile of supercomputing". Computerworld. Archived from the original on December 24, 2008. Retrieved June 10, 2008. https://web.archive.org/web/20081224001155/http://www.computerworld.com/action/article.do?command=viewArticleBasic&taxonomyName=hardware&articleId=9095318&taxonomyId=12&intsrc=kc_top ↩

  56. "Austin ISC08". Top500.org. November 14, 2008. Archived from the original on February 22, 2012. Retrieved February 9, 2012. https://web.archive.org/web/20120222023827/http://www.top500.org/lists/2008/11/press-release ↩

  57. Fildes, Jonathan (June 9, 2008). "Supercomputer sets petaflop pace". BBC News. Retrieved July 8, 2008. http://news.bbc.co.uk/1/hi/technology/7443557.stm ↩

  58. Greenberg, Andy (November 16, 2009). "Cray Dethrones IBM in Supercomputing". Forbes. https://www.forbes.com/2009/11/15/supercomputer-ibm-jaguar-technology-cio-network-cray.html?feed=rss_popstories ↩

  59. "China claims supercomputer crown". BBC News. October 28, 2010. https://www.bbc.co.uk/news/technology-11644252 ↩

  60. Dillow, Clay (October 28, 2010). "China Unveils 2507 Petaflop Supercomputer, the World's Fastest". Popsci.com. Retrieved February 9, 2012. http://www.popsci.com/technology/article/2010-10/china-unveils-2507-petaflop-supercomputer-worlds-fastest ↩

  61. "Intel's Core i7-980X Extreme Edition – Ready for Sick Scores?: Mathematics: Sandra Arithmetic, Crypto, Microsoft Excel". Techgage. March 10, 2010. Retrieved February 9, 2012. http://techgage.com/article/intels_core_i7-980x_extreme_edition_-_ready_for_sick_scores/8 ↩

  62. "NVIDIA Tesla Personal Supercomputer". Nvidia.com. Retrieved February 9, 2012. http://www.nvidia.com/object/product_tesla_C2050_C2070_us.html ↩

  63. "AMD FireStream 9270 GPU Compute Accelerator". Amd.com. Retrieved February 9, 2012. https://www.amd.com/us/products/workstation/firestream/firestream-9270/pages/firestream-9270.aspx ↩

  64. "'K computer' Achieves Goal of 10 Petaflops". Fujitsu.com. Retrieved February 9, 2012. http://www.fujitsu.com/global/news/pr/archives/month/2011/20111102-02.html ↩

  65. See Japanese numbers /wiki/Japanese_numerals#Large_numbers ↩

  66. "Intel's Knights Corner: 50+ Core 22nm Co-processor". November 16, 2011. Retrieved November 16, 2011. http://www.tomshardware.com/news/intel-knights-corner-mic-co-processor,14002.html ↩

  67. "Intel unveils 1 TFLOP/s Knight's Corner". Retrieved November 16, 2011. http://www.eetimes.com/electronics-news/4230654/Intel-unveils-1-TFLOP-s-Knight-s-Corner ↩

  68. Clark, Don (June 18, 2012). "IBM Computer Sets Speed Record". The Wall Street Journal. Retrieved June 18, 2012. https://www.wsj.com/articles/SB10001424052702303379204577472773983130902 ↩

  69. "US Titan supercomputer clocked as world's fastest". BBC. November 12, 2012. Retrieved February 28, 2013. https://www.bbc.co.uk/news/technology-20272810 ↩

  70. "Oak Ridge Claims No. 1 Position on Latest TOP500 List with Titan | TOP500 Supercomputer Sites". Top500.org. November 12, 2012. Retrieved February 28, 2013. http://top500.org/blog/lists/2012/11/press-release/ ↩

  71. Montalbano, Elizabeth (October 11, 2011). "Oak Ridge Labs Builds Fastest Supercomputer". Informationweek. Retrieved February 9, 2012. http://www.informationweek.com/news/government/enterprise-architecture/231900554 ↩

  72. Tibken, Shara (October 29, 2012). "Titan supercomputer debuts for open scientific research | Cutting Edge". News.CNet.com. Retrieved February 28, 2013. http://news.cnet.com/8301-11386_3-57541791-76/titan-supercomputer-debuts-for-open-scientific-research/ ↩

  73. "Chinese Supercomputer Is Now The World's Fastest – By A Lot". Forbes Magazine. June 17, 2013. Retrieved June 17, 2013. https://www.forbes.com/sites/alexknapp/2013/06/17/chinese-supercomputer-is-now-the-worlds-fastest-by-a-lot/ ↩

  74. Feldman, Michael. "China Races Ahead in TOP500 Supercomputer List, Ending US Supremacy". Top500.org. Retrieved December 31, 2016. https://www.top500.org/news/china-races-ahead-in-top500-supercomputer-list-ending-us-supremacy/ ↩

  75. "June 2018". Top500.org. Retrieved July 17, 2018. https://www.top500.org/lists/2018/06/ ↩

  76. "TOP500". https://en.wikipedia.org/wiki/TOP500 ↩

  77. "Folding@Home Active CPUs & GPUs by OS". foldingathome.org. Retrieved April 8, 2020. https://stats.foldingathome.org/os ↩

  78. Folding@home (March 25, 2020). "Thanks to our AMAZING community, we've crossed the exaFLOP barrier! That's over a 1,000,000,000,000,000,000 operations per second, making us ~10x faster than the IBM Summit!pic.twitter.com/mPMnb4xdH3". @foldingathome. Retrieved April 4, 2020. https://twitter.com/foldingathome/status/1242918035788365830 ↩

  79. "Folding@Home Crushes Exascale Barrier, Now Faster Than Dozens of Supercomputers - ExtremeTech". extremetech.com. Retrieved April 4, 2020. https://www.extremetech.com/computing/308332-foldinghome-crushes-exascale-barrier-now-faster-than-dozens-of-supercomputers ↩

  80. "Folding@Home exceeds 1.5 ExaFLOPS in the battle against Covid-19". TechSpot. March 26, 2020. Retrieved April 4, 2020. https://www.techspot.com/news/84561-foldinghome-exceeds-15-exaflops-battle-against-covid-19.html ↩

  81. "Sony Computer Entertainment's Support for Folding@home Project on PlayStation™3 Receives This Year's "Good Design Gold Award"" (Press release). Sony Computer Entertainment Inc. November 6, 2008. Archived from the original on January 31, 2009. Retrieved December 11, 2008. https://web.archive.org/web/20090131082202/http://www.scei.co.jp/corporate/release/081106de.html ↩

  82. "BOINC Computing Power". BOINC. Retrieved December 28, 2020. http://boinc.berkeley.edu/computing.php ↩

  83. "SETI@Home Credit overview". BOINC. Retrieved June 15, 2018. http://boincstats.com/en/stats/0/project/detail ↩

  84. "Einstein@Home Credit overview". BOINC. Retrieved June 15, 2018. http://boincstats.com/en/stats/5/project/detail ↩

  85. "MilkyWay@Home Credit overview". BOINC. Retrieved June 15, 2018. http://boincstats.com/en/stats/61/project/detail ↩

  86. "Internet PrimeNet Server Distributed Computing Technology for the Great Internet Mersenne Prime Search". GIMPS. Retrieved June 15, 2018. http://www.mersenne.org/primenet ↩

  87. 1634–1699: McCusker, J. J. (1997). How Much Is That in Real Money? A Historical Price Index for Use as a Deflator of Money Values in the Economy of the United States: Addenda et Corrigenda (PDF). American Antiquarian Society. 1700–1799: McCusker, J. J. (1992). How Much Is That in Real Money? A Historical Price Index for Use as a Deflator of Money Values in the Economy of the United States (PDF). American Antiquarian Society. 1800–present: Federal Reserve Bank of Minneapolis. "Consumer Price Index (estimate) 1800–". Retrieved February 29, 2024. /wiki/John_J._McCusker ↩

  88. "The IBM 7030 (STRETCH)". Norman Hardy. Retrieved February 24, 2017. http://computer-history.info/Page4.dir/pages/IBM.7030.Stretch.dir/ ↩

  89. "Loki and Hyglac". Loki-www.lanl.gov. July 13, 1997. Archived from the original on July 21, 2011. Retrieved February 9, 2012. https://web.archive.org/web/20110721043504/http://loki-www.lanl.gov/papers/sc97/ ↩

  90. "Kentucky Linux Athlon Testbed 2 (KLAT2)". The Aggregate. Retrieved February 9, 2012. http://aggregate.org/KLAT2/ ↩

  91. "Haveland-Robinson Associates - Home Page". Haveland-Robinson Associates. August 23, 2003. Retrieved November 14, 2024. https://www.haveland.com/index.htm?povbench/index.php ↩

  92. "Microwulf: A Personal, Portable Beowulf Cluster". Archived from the original on September 12, 2007. Retrieved February 9, 2012. https://web.archive.org/web/20070912061302/http://www.calvin.edu/~adams/research/microwulf/ ↩

  93. Adam Stevenson, Yann Le Du, and Mariem El Afrit. "High-performance computing on gamer PCs." Ars Technica. March 31, 2011. https://arstechnica.com/science/news/2011/03/high-performance-computing-on-gamer-pcs-part-1-hardware.ars ↩

  94. Tom Logan (January 9, 2012). "HD7970 Quadfire Eyefinity Review". OC3D.net. http://www.overclock3d.net/reviews/gpu_displays/hd7970_quadfire_eyefinity_review/12 ↩

  95. "Sony Sparks Price War With PS4 Priced at $399." CNBC. June 11, 2013. https://www.cnbc.com/id/100805004 ↩

  96. "FreezePage". Archived from the original on November 16, 2013. Retrieved May 9, 2020. http://www.freezepage.com/1384601420XCIGYKCBKJ?url=http://pcpartpicker.com/p/22JOc ↩

  97. "FreezePage". Archived from the original on December 19, 2013. Retrieved May 9, 2020. http://www.freezepage.com/1387480124PSLSILVCMJ?url=http://pcpartpicker.com/p/2mQxd ↩

  98. "FreezePage". Archived from the original on January 10, 2015. Retrieved May 9, 2020. http://www.freezepage.com/1420850340WGSMHXRBLE?url=http://pcpartpicker.com/p/8z3cVn ↩

  99. "Radeon R9 295X2 8 GB Review: Project Hydra Gets Liquid Cooling". April 8, 2014. http://www.tomshardware.com/reviews/radeon-r9-295x2-review-benchmark-performance,3799.html ↩

  100. Perez, Carol E. (July 13, 2017). "Building a 50 Teraflops AMD Vega Deep Learning Box for Under $3K". Intuition Machine. Retrieved July 26, 2017. https://medium.com/intuitionmachine/building-a-50-teraflops-amd-vega-deep-learning-box-for-under-3k-ebdd60d4a93c ↩

  101. "lowest_$/fp16 - mattebaughman's Saved Part List - Celeron G3930 2.9GHz Dual-Core, Radeon RX VEGA 64 8GB (3-Way CrossFire), XON-350_BK ATX Mid Tower". pcpartpicker.com. Retrieved September 13, 2017. https://pcpartpicker.com/user/mattebaughman/saved/8DQZ8d ↩

  102. "System Builder". pcpartpicker.com. Retrieved December 7, 2020. https://pcpartpicker.com/list/9bPn8J ↩

  103. "AMD Playstation 5 GPU Specs". techpowerup.com. Retrieved May 12, 2021. https://www.techpowerup.com/gpu-specs/playstation-5-gpu.c3480 ↩

  104. "Xbox Series X | Xbox". xbox.com. Retrieved September 21, 2021. https://www.xbox.com/en-US/consoles/xbox-series-x?xr=shellnav#specs ↩

  105. "Nvidia Announces RTX 4090 Coming October 12, RTX 4080 Later". tomshardware.com. September 20, 2022. Retrieved September 20, 2022. https://www.tomshardware.com/news/nvidia-geforce-rtx-4090-rtx-4080-price-release-date-specs-revealed ↩

  106. "AMD Radeon RX 7600 Review: Incremental Upgrades". tomshardware.com. May 24, 2023. Retrieved May 24, 2023. https://www.tomshardware.com/reviews/amd-radeon-rx-7600-review ↩