30
$\begingroup$

I am planning to purchase a new computer especially to use for Mathematica programming purposes. Currently, I have MMA v.11. Could someone with Mathematica v.12 run the following benchmarking and provide a benchmarking report?

Needs["Benchmarking`"]
BenchmarkReport[]

The benchmarking reports in the repository are not up to date.

Thanks.

EDIT

From the answers given to my question, I understood that my question was not well-formulated. I like to have

"WolframMark System Comparison" and "WolframMark Detailed Timings"

Thanks for your answers.

EDIT 1 I noticed that BenchmarkReport[...] presents the relative performance of the tested Operating Systems in relation to a fixed and old set of OSs. This is apparent from the list of OSs reported below. I think MMA needs to update its inventory of OSs under Benchmark. Moderator(s) of this forum may take note of this observation to initiate a new, updated list of OSs.

Improve this question
$\endgroup$
3
  • 1
    $\begingroup$ See this MSE answer for the ingestion of the benchmark results answers posted to this discussion $\endgroup$
    – Anton Antonov
    Commented Nov 26, 2020 at 18:25
  • 4
    $\begingroup$ Please, if you upvoted (or inclined to do so) this question then (consider and) post benchmarks. And if you do post your benchmark results, please post WL code output from Benchmark[] not just screenshots. $\endgroup$
    – Anton Antonov
    Commented Nov 26, 2020 at 19:16
  • $\begingroup$ That function hadn’t been updated in a long time $\endgroup$
    – user5601
    Commented Dec 31, 2020 at 1:12

34 Answers 34

Reset to default
1
2
6
$\begingroup$

enter image description here16-inch MacBook Pro (2.3 Ghz Intel i9)

enter image description here

Improve this answer
$\endgroup$
2
  • 1
    $\begingroup$ Can you also report the result of: Needs["Benchmarking`"] and BenchmarkReport[] $\endgroup$
    – Tugrul Temel
    Commented Nov 18, 2020 at 22:17
  • 1
    $\begingroup$ Interesting, I have the same machine, but mine achieves 3.90... $\endgroup$
    – Meclassic
    Commented Jan 22, 2021 at 2:17
9
$\begingroup$

A custom machine I built in the summer of 2020. With a "BenchmarkResult" -> 5.037, it seems I did a good job.

enter image description here

{"MachineName" -> "amos", "System" -> "Linux x86 (64-bit)", 
 "BenchmarkName" -> "WolframMark", "FullVersionNumber" -> 
  "12.1.1", "Date" -> "November 27, 2020", 
 "BenchmarkResult" -> 5.037, "TotalTime" -> 2.748, 
 "Results" -> {{"Data Fitting", 0.224}, {"Digits of Pi", 0.204}, 
   {"Discrete Fourier Transform", 0.257}, 
   {"Eigenvalues of a Matrix", 0.322}, {"Elementary Functions", 
    0.106}, {"Gamma Function", 0.272}, 
   {"Large Integer Multiplication", 0.263}, 
   {"Matrix Arithmetic", 0.068}, {"Matrix Multiplication", 
    0.051}, {"Matrix Transpose", 0.192}, 
   {"Numerical Integration", 0.373}, {"Polynomial Expansion", 
    0.057}, {"Random Number Sort", 0.059}, 
   {"Singular Value Decomposition", 0.18}, 
   {"Solving a Linear System", 0.12}}}

Machine Details

  • Mainboard: Gigabyte X299X DESIGNARE 10G
  • CPU: Intel(R) Core(TM) i9-10920X CPU @ 3.50GHz
  • RAM: 64GB DDR4 2133 MHz
  • Graphics: GeForce RTX 2080 Ti
  • 2x 2TB m.2 Gigabyte, 1x 1TB Samsung SSD 850, 1x 6TB WDC WD60EFAX-68S
Improve this answer
$\endgroup$
4
  • $\begingroup$ Doesn't that RTX 2080 Ti alone cost more than most desktops? $\endgroup$
    – bobthechemist
    Commented Dec 7, 2020 at 20:52
  • 3
    $\begingroup$ @bobthechemist Well, it's the one hobby I have. Also, I'm doing a lot of work from home and if I spend 16h in front of my PC, I want to enjoy it. $\endgroup$
    – halirutan
    Commented Dec 8, 2020 at 22:13
  • $\begingroup$ @halirutan my laptop, which is a year old now, has a very similar configuration. I have an i9 10980 CPU, an Nvidia GeForce RTX 2070 GPU, 64 GB of 3200 MHz RAM, and a 1 TB SSD. But my result is not close to yours. Are you using Clear Linux, which has all kinds of Intel optimisations built into it? $\endgroup$
    – Shredderroy
    Commented Nov 1, 2021 at 15:38
  • $\begingroup$ @Shredderroy Nope, standard Ubuntu 20.04. I guess the differences will be hidden in the details. For one, I have an "X" behind the CPU name and a "Ti" in the GPU :) But I'm not sure this is that important. But laptops often have the energy settings tuned down a lot. Maybe it's connected to this and you need to turn on performance mode? $\endgroup$
    – halirutan
    Commented Nov 13, 2021 at 2:56
8
$\begingroup$

I am running an Asus laptop in dual boot mode between Windows 10 Pro and Linux Mint 20.1. I am consistently getting much different results between the two when running the Benchmark in Mathematica 12.2.

Specs:

  • Intel i7-8550U @ 1.80Ghz (4 cores, 8 threads)
  • 16GB RAM
  • NVIDIA GeForce GTX1050
  • 256GB SATA M.2 SSD
  • 2TB SATA mechanical HD @ 5400 RPM

In Windows, the OS and Mathematica both boot from the SSD while in Linux, the OS and Mathematica are both running off a partition on the mechanical hard drive. I would expect to see a performance boost in Windows just because of the storage differences, but the exact opposite has been true. I am also seeing a lot more variability in Windows versus Linux.

Here is one of my better Windows runs:

 {"MachineName" -> "kickert-asus", 
 "System" -> "Microsoft Windows (64-bit)", 
 "BenchmarkName" -> "WolframMark", "FullVersionNumber" -> 
  "12.2.0", "Date" -> "January 11, 2021", 
 "BenchmarkResult" -> 2.653, "TotalTime" -> 5.217, 
 "Results" -> {{"Data Fitting", 0.395}, {"Digits of Pi", 0.281}, 
   {"Discrete Fourier Transform", 0.436}, 
   {"Eigenvalues of a Matrix", 0.37}, {"Elementary Functions", 
    0.595}, {"Gamma Function", 0.327}, 
   {"Large Integer Multiplication", 0.345}, 
   {"Matrix Arithmetic", 0.364}, {"Matrix Multiplication", 
    0.292}, {"Matrix Transpose", 0.44}, 
   {"Numerical Integration", 0.497}, {"Polynomial Expansion", 
    0.067}, {"Random Number Sort", 0.19}, 
   {"Singular Value Decomposition", 0.3}, 
   {"Solving a Linear System", 0.318}}}

And then one from Linux:

{"MachineName" -> "bk-mint", "System" -> "Linux x86 (64-bit)",
 "BenchmarkName" -> "WolframMark", "FullVersionNumber" ->
  "12.2.0", "Date" -> "January 11, 2021",
 "BenchmarkResult" -> 3.637, "TotalTime" -> 3.806,
 "Results" -> {{"Data Fitting", 0.247}, {"Digits of Pi", 0.235},
   {"Discrete Fourier Transform", 0.387},
   {"Eigenvalues of a Matrix", 0.319}, {"Elementary Functions",
    0.241}, {"Gamma Function", 0.329},
   {"Large Integer Multiplication", 0.304},
   {"Matrix Arithmetic", 0.135}, {"Matrix Multiplication",
    0.216}, {"Matrix Transpose", 0.319},
   {"Numerical Integration", 0.385}, {"Polynomial Expansion",
    0.064}, {"Random Number Sort", 0.143},
   {"Singular Value Decomposition", 0.22},
   {"Solving a Linear System", 0.262}}}

All runs were done in fresh kernels with the computer as close to ambient temperature as possible to ensure thermal throttling wasn't an issue.

As I mentioned, in Windows, I was getting quite a range of outcomes so I tried running 10 back to back runs with this code:

Table[Benchmark[][[1, 6, 2]], 10]

Here were my Windows results looking only at overall results:

{2.514, 2.508, 2.475, 2.449, 2.039, 1.848, 1.854, 1.77, 1.766, 2.017}

And for Linux:

{3.637, 3.656, 3.685, 3.66, 3.677, 3.655, 3.568, 3.486, 3.488, 3.583}

I am curious if anyone else is running dual boot, or has also experienced significant differences on the same hardware, but in different OS.

EDIT to add new benchmark

Thought it would be fun to run the benchmark on my Raspberry Pi 400 (Quad-core ARM processor overclocked to 2.2Ghz with 4GB of RAM) since Mathematica comes pre-installed on it.

Definitely not a powerhouse even with the overclock. Here are my results:

"MachineName" -> "raspberrypi"
"System" -> "Linux ARM (32-bit)"
"BenchmarkName" -> "WolframMark"
"FullVersionNumber" -> "12.1.1"
"Date" -> "February 25, 2021"
"BenchmarkResult" -> 0.255
"TotalTime" -> 54.201
"Results" -> {{"Data Fitting", 2.651}, {"Digits of Pi", 1.129}, {"Discrete Fourier Transform", 8.236}, {"Eigenvalues of a Matrix", 2.667}, {"Elementary Functions", 4.464}, {"Gamma Function", 1.531}, {"Large Integer Multiplication", 1.734}, {"Matrix Arithmetic", 1.378}, {"Matrix Multiplication", 7.831}, {"Matrix Transpose", 5.465}, {"Numerical Integration", 1.765}, {"Polynomial Expansion", 0.261}, {"Random Number Sort", 0.853}, {"Singular Value Decomposition", 7.15}, {"Solving a Linear System", 7.086}}

EDIT 2 New laptop, so new benchmark to post.

Specs

  • Windows 11 Home x64
  • AMD Ryzen 7 4800H @ 2.90 Ghz (Boost to 4.20 Ghz)
  • 32GB RAM
  • NVIDIA GeForce RTX 3060 Max-P
  • NVMe SSD

Results:

{"MachineName" -> "bk-ryzen", 
 "System" -> "Microsoft Windows (64-bit)", 
 "BenchmarkName" -> "WolframMark", "FullVersionNumber" -> 
  "12.3.1", "Date" -> "November 1, 2021", 
 "BenchmarkResult" -> 2.841, "TotalTime" -> 4.872, 
 "Results" -> {{"Data Fitting", 0.322}, {"Digits of Pi", 0.206}, 
   {"Discrete Fourier Transform", 0.318}, 
   {"Eigenvalues of a Matrix", 0.409}, {"Elementary Functions", 
    0.59}, {"Gamma Function", 0.256}, 
   {"Large Integer Multiplication", 0.257}, 
   {"Matrix Arithmetic", 0.267}, {"Matrix Multiplication", 
    0.499}, {"Matrix Transpose", 0.399}, 
   {"Numerical Integration", 0.447}, {"Polynomial Expansion", 
    0.043}, {"Random Number Sort", 0.112}, 
   {"Singular Value Decomposition", 0.341}, 
   {"Solving a Linear System", 0.406}}}
Improve this answer
$\endgroup$
7
$\begingroup$

Eluktronics Thinn-15 laptop: AMD Ryzen 4800H 8-core (2.9-4.2 Ghz), 32 GB DDR4.

I've applied the fix for MKL on AMD processors discussed here which led to a 30% speed boost.

{"MachineName" -> "desktop-o4n5ks2", "System" -> "Microsoft Windows (64-bit)", "BenchmarkName" -> "WolframMark", 
 "FullVersionNumber" -> "12.1.1", "Date" -> "December 4, 2020", "BenchmarkResult" -> 3.399, "TotalTime" -> 4.072, 
 "Results" -> {{"Data Fitting", 0.252}, {"Digits of Pi", 0.212}, {"Discrete Fourier Transform", 0.337}, 
   {"Eigenvalues of a Matrix", 0.323}, {"Elementary Functions", 0.444}, {"Gamma Function", 0.28}, 
   {"Large Integer Multiplication", 0.317}, {"Matrix Arithmetic", 0.26}, {"Matrix Multiplication", 0.178}, 
   {"Matrix Transpose", 0.407}, {"Numerical Integration", 0.422}, {"Polynomial Expansion", 0.043}, 
   {"Random Number Sort", 0.112}, {"Singular Value Decomposition", 0.196}, {"Solving a Linear System", 0.289}}}
Improve this answer
$\endgroup$
4
  • 1
    $\begingroup$ Thank you for mentioning the MKL fix, never heard about it. Maybe we should reach Wolfram officials for this fix to be implemented in newer Wolfram versions, because it is so significant. $\endgroup$
    – Alexander Nikolaenko
    Commented Dec 5, 2020 at 12:02
  • 1
    $\begingroup$ Yep, it makes a huge difference. The thread that is linked to in the link also mentions how to make the change system wide (so you don't have to launch Mathematica using the .bat file). Something to keep an eye on is that the fix no longer works starting in the 2020 version of MKL (fortunately Mathematica ships with a year-old version!) $\endgroup$
    – ala10
    Commented Dec 5, 2020 at 13:50
  • $\begingroup$ @ala10 i tried using this technique with my 3800x with powershell and wolfram script..unfortunately it had no difference, did you create the bash script or run on powershell? $\endgroup$
    – DrMrstheMonarch
    Commented Dec 12, 2020 at 17:36
  • $\begingroup$ I actually couldn't get the .bat file to work and ended up just changing the path variable via the environment settings as shown in link. $\endgroup$
    – ala10
    Commented Dec 12, 2020 at 18:17
7
$\begingroup$

Updated

Maybe you need this command.

Needs["Benchmarking`"]
BenchmarkReport[]

I use Gentoo calculate Linux recently, it is faster then previous operation system.

enter image description here

Original

CPU: Intel i5-1035G4 (8) @ 3.700GHz

GPU: Intel Iris Plus Graphics G4

Memory: 2369MiB / 15773MiB (15%)

OS: ArcoLinux

DE: Plasma 5.20.3

{"MachineName" -> "cvgmt-950qcg", 
 "System" -> "Linux x86 (64-bit)", "BenchmarkName" -> 
  "WolframMark", "FullVersionNumber" -> "12.1.1", 
 "Date" -> "November 18, 2020", "BenchmarkResult" -> 3.22, 
 "TotalTime" -> 4.299, "Results" -> {{"Data Fitting", 0.22}, 
   {"Digits of Pi", 0.312}, {"Discrete Fourier Transform", 
    0.357}, {"Eigenvalues of a Matrix", 0.303}, 
   {"Elementary Functions", 0.185}, {"Gamma Function", 0.46}, 
   {"Large Integer Multiplication", 0.371}, 
   {"Matrix Arithmetic", 0.12}, {"Matrix Multiplication", 
    0.278}, {"Matrix Transpose", 0.324}, 
   {"Numerical Integration", 0.449}, {"Polynomial Expansion", 
    0.059}, {"Random Number Sort", 0.181}, 
   {"Singular Value Decomposition", 0.354}, 
   {"Solving a Linear System", 0.326}}}
Improve this answer
$\endgroup$
1
  • 2
    $\begingroup$ I think the list of systems compared is very very limited given the fact that there are advanced processors. My MMA v.11 also generates the same list of systems. Is there any way to expand the list of systems to a wider set? $\endgroup$
    – Tugrul Temel
    Commented Nov 18, 2020 at 0:59
6
$\begingroup$

ROG laptop, 24 GB (8 GB at 2666 MHz, 16 GB at 3200 MHz both DDR5), GTX 1050 ti running at 3504 MHz i7 7700 HQ cpu @ 2.80 GHz, GTX 1050 ti 4 GB GDDR5 running at 3504 MHz

{"MachineName" -> "4-node homogeneous cluster", 
 "System" -> "Windows-x86-64", "BenchmarkName" -> 
 "WolframMark", "FullVersionNumber" -> "12.1.0", 
 "Date" -> "December 4, 2020", "BenchmarkResult" -> 4.462, 
 "TotalTime" -> 37.228}

Good call on the fresh kernel!

{"MachineName" -> "4-node homogeneous cluster", 
 "System" -> "Windows-x86-64", "BenchmarkName" -> 
  "WolframMark", "FullVersionNumber" -> "12.1.0", 
 "Date" -> "December 6, 2020", "BenchmarkResult" -> 4.105, 
 "TotalTime" -> 40.462}

There is no other output unless MMA opened a window I can't see. Benchmark report didn't give me the summary data everyone else got. It's a gaming laptop, so may have 4 kernels on startup.

    {{"Data Fitting", 0.4112875`}, {"Digits of Pi", 
   0.2719581`}, {"Discrete Fourier Transform", 
   0.4819707`}, {"Eigenvalues of a Matrix", 
   0.4298385`}, {"Elementary Functions", 
   0.6460083`}, {"Gamma Function", 
   0.3626365`}, {"Large Integer Multiplication", 
   0.4136961`}, {"Matrix Arithmetic", 
   0.3955658`}, {"Matrix Multiplication", 
   0.3505343`}, {"Matrix Transpose", 
   0.4625563`}, {"Numerical Integration", 
   0.5356864`}, {"Polynomial Expansion", 
   0.0668919`}, {"Random Number Sort", 
   0.2122121`}, {"Singular Value Decomposition", 
   0.353618`}, {"Solving a Linear System", 0.3778531`}}}

enter image description here

Improve this answer
$\endgroup$
5
  • $\begingroup$ Please, post the full output of Benchmark[]. $\endgroup$
    – Anton Antonov
    Commented Dec 5, 2020 at 4:25
  • 1
    $\begingroup$ The "4-node homogeneous cluster" makes me suspect you had four sub-kernels running before you ran the benchmark. I had the same problem at first. This seems to throw off the results - try running it again on a fresh kernel. $\endgroup$
    – ala10
    Commented Dec 5, 2020 at 4:37
  • $\begingroup$ Again, please post the full output of Benchmark[]. $\endgroup$
    – Anton Antonov
    Commented Dec 7, 2020 at 13:16
  • 1
    $\begingroup$ It does seem like there is a LaunchKernels[] hiding somewhere. If I run Benchmark[] on a fresh kernel I get {"MachineName" -> "desktop-o4n5ks2", ... "BenchmarkResult" -> 3.327, "TotalTime" -> 4.161,...} and the timings of the individual tests. Whereas if I run LaunchKernels[] beforehand I get {"MachineName" -> "8-node homogeneous cluster",... "BenchmarkResult" -> 7.857, "TotalTime" -> 42.281} and no detailed timings. Note the change in "MachineName" and that the test now takes 42s to run rather than 4s (yours also took 40s+). $\endgroup$
    – ala10
    Commented Dec 7, 2020 at 21:42
  • $\begingroup$ Thanks ala10, that may answer a few questions. I got ZERO detailed timing until I ran each test individually. There may be a launch kernels command upon startup somewhere, but I've never used it consciously. $\endgroup$
    – zeattledave
    Commented Dec 8, 2020 at 23:05
6
$\begingroup$ 
{"MachineName" -> "carls-computer", "System" -> "Linux x86 (64-bit)", "BenchmarkName" -> "WolframMark", 
 "FullVersionNumber" -> "12.2.0", "Date" -> "April 12, 2021", 
 "BenchmarkResult" -> 5.45, "TotalTime" -> 2.54, 
 "Results" -> {{"Data Fitting", 0.168}, {"Digits of Pi", 0.18}, {"Discrete Fourier Transform", 0.286}, 
   {"Eigenvalues of a Matrix", 0.272}, {"Elementary Functions", 0.091}, {"Gamma Function", 0.234}, 
   {"Large Integer Multiplication", 0.233}, {"Matrix Arithmetic", 0.035}, {"Matrix Multiplication", 0.067}, 
   {"Matrix Transpose", 0.22}, {"Numerical Integration", 0.33}, {"Polynomial Expansion", 0.051}, 
   {"Random Number Sort", 0.049}, {"Singular Value Decomposition", 0.155}, {"Solving a Linear System", 0.169}}}

Using the AMD MKL fix outlined in this post magically brought me from 4.2 or so to 5.34.

I custom built this computer for Mathematica (and also, lockdown), the outline is:

Motherboard: ASUS TUF Gaming B550

CPU: AMD 3900 (non-X)

RAM: 96GB, (2x16GB 2400Mhz, 2x32 3200Mhz)

GPU: GeForce GTX 2060 Super

Storage: 1TB Sabrent M.2, (1x8TB, 1x1TB) spinning disk

OS: Pop!_OS 20.10 (Linux 5.11)

Improve this answer
$\endgroup$
6
  • $\begingroup$ The post you linked had said that “this setting no longer has any effect as of MKL 2020 update 1”. Does it work again? :) $\endgroup$
    – SnzFor16Min
    Commented Jan 31, 2021 at 17:55
  • $\begingroup$ It certainly worked for me, using 12.2! $\endgroup$
    – Carl Lange
    Commented Jan 31, 2021 at 18:30
  • 2
    $\begingroup$ Each Mathematica update seems to use a version of MKL that's about a year old. Worth keeping this in mind - I guess at some point this fix might not work... $\endgroup$
    – ala10
    Commented Feb 26, 2021 at 12:50
  • $\begingroup$ What speed is your RAM set to run at in your BIOS? Running 2400 at 3200 is a pretty big jump. Is everything actually running at the ddr4 default of 2133 with no docp? $\endgroup$
    – Derek H
    Commented Jul 27, 2021 at 16:40
  • $\begingroup$ Yeah, I experimented a lot with finding the right overclock for the slower ram. It seems the 2400Mhz ram I have ("gaming" ram, for what it's worth) can run without stability issues around 3000Mhz. I made it up to 3200Mhz and got a WolframMark of 5.828, but my computer crashed about once a day. $\endgroup$
    – Carl Lange
    Commented Jul 27, 2021 at 20:54
6
$\begingroup$

Late 2013 Macbook Pro 2.4ghz i5, 16gb 2400mhz ram, Intel Iris 1536mb ram.

{"System"-> "Mac OS X x86 (64-bit)", 
"BenchmarkName"-> "WolframMark", 
"FullVersionNumber"-> "12.0.0", 
"Date"-> "November 25, 2020", 
"BenchmarkResult"-> 1.613, 
"TotalTime"-> 8.579,
"Results" ->{
{"Data Fitting", 0.478}, 
{"Digits of Pi", 0.34}, 
{"Discrete Fourier Transform", 0.464}, 
{"Eigenvalues of a Matrix", 0.528}, 
{"Elementary Functions", 0.696}, 
{"Gamma Function", 0.469}, 
{"Large Integer Multiplication", 0.455}, 
{"Matrix Arithmetic", 0.456}, 
{"Matrix Multiplication", 0.5}, 
{"Matrix Transpose", 0.85}, 
{"Numerical Integration", 0.639}, 
{"Polynomial Expansion", 0.128}, 
{"Random Number Sort", 1.156}, 
{"Singular Value Decomposition", 0.746}, 
{"Solving a Linear System", 0.674}}}

My Desktop, AMD 3800x, 64gb 3400mhz ram, rtx 2070s

{"MachineName" -> "veronica", 
"System" -> "Microsoft Windows (64-bit)",
"BenchmarkName" -> "WolframMark",
"FullVersionNumber" -> "12.1.1", 
"Date" -> "December 12, 2020",
"BenchmarkResult" -> 3.637,
"TotalTime" -> 3.806,
"Results" -> {{"Data Fitting", 0.263}, 
{"Digits of Pi", 0.222},
{"Discrete Fourier Transform", 0.382},
{"Eigenvalues of a Matrix", 0.285},
{"Elementary Functions", 0.422},
{"Gamma Function", 0.284},
{"Large Integer Multiplication", 0.299}, 
{"Matrix Arithmetic", 0.24}, 
{"Matrix Multiplication", 0.151},
{"Matrix Transpose", 0.338}, 
{"Numerical Integration", 0.398}, 
{"Polynomial Expansion", 0.042},
{"Random Number Sort", 0.109}, 
{"Singular Value Decomposition", 0.178},
{"Solving a Linear System", 0.193}}}

Macbook Pro Late 2020 Arm M1 Through Rosetta 2, 16GB DD4 Ram The result is lower than i expected...though I assume if I had a native Arm mathematica the score would be probably closer to my AMD desktop.

{"MachineName" -> "laederlappen", 
"System" -> "Mac OS X x86 (64-bit)", 
"BenchmarkName" -> "WolframMark", 
"FullVersionNumber" -> "12.0.0", 
"Date" -> "February 26, 2021", 
"BenchmarkResult" -> 2.724, 
"TotalTime" -> 5.081, 
"Results" -> {
{"Data Fitting", 0.29}, 
{"Digits of Pi", 0.284}, 
{"Discrete Fourier Transform", 0.159}, 
{"Eigenvalues of a Matrix", 0.508}, 
{"Elementary Functions", 0.283}, 
{"Gamma Function", 0.406}, 
{"Large Integer Multiplication", 0.418}, 
{"Matrix Arithmetic", 0.153}, 
{"Matrix Multiplication", 0.365}, 
{"Matrix Transpose", 0.358}, 
{"Numerical Integration", 0.371}, 
{"Polynomial Expansion", 0.076}, 
{"Random Number Sort", 0.662}, 
{"Singular Value Decomposition", 0.367}, 
{"Solving a Linear System", 0.381}}}

My results for my M1 macbook with native support via mathematica 12.3.1

{"MachineName" -> "laederlappen", 
"System" -> "Mac OS X ARM (64-bit)", 
"BenchmarkName" -> 
"WolframMark", 
"FullVersionNumber" -> "12.3.1", 
"Date" -> "July 9, 2021", 
"BenchmarkResult" -> 3.147, 
"TotalTime" -> 4.398, 
"Results" -> {{"Data Fitting", 0.191}, 
{"Digits of Pi", 0.171}, 
{"Discrete Fourier Transform", 0.307}, 
{"Eigenvalues of a Matrix", 0.453}, 
{"Elementary Functions", 0.606}, 
{"Gamma Function", 0.221}, 
{"Large Integer Multiplication", 0.187}, 
{"Matrix Arithmetic", 0.145}, 
{"Matrix Multiplication", 0.302}, 
{"Matrix Transpose", 0.181}, 
{"Numerical Integration", 0.322}, 
{"Polynomial Expansion", 0.048}, 
{"Random Number Sort", 0.399}, 
{"Singular Value Decomposition", 0.545},{"Solving a Linear System", 0.32}}}
Improve this answer
$\endgroup$
3
  • $\begingroup$ Have you tried the fix for AMD processors outlined in this post? mathematica.stackexchange.com/questions/221767/… $\endgroup$
    – ala10
    Commented Feb 26, 2021 at 12:52
  • $\begingroup$ @ala10 i did infact, without the fix my amd score was much lower. $\endgroup$
    – DrMrstheMonarch
    Commented Feb 26, 2021 at 12:53
  • 1
    $\begingroup$ I wonder if there is some way of getting in touch with the Mathematica folks about this. MATLAB has included the fix in the version of MKL that they bundle - maybe Mathematica could do the same... $\endgroup$
    – ala10
    Commented Feb 26, 2021 at 17:01
5
$\begingroup$

Here are my results on an Intel Core i5-8265U @ 1.6GHz with 16GB of RAM:

{"MachineName" -> "REDACTED", "System" -> "Microsoft Windows (64-bit)", 
"BenchmarkName" -> "WolframMark", "FullVersionNumber" -> "12.0.0", 
"Date" -> "November 17, 2020", "BenchmarkResult" -> 1.269, "TotalTime" -> 10.91, 
"Results" -> {{"Data Fitting", 0.493}, {"Digits of Pi", 0.348}, 
  {"Discrete Fourier Transform", 0.48}, {"Eigenvalues of a Matrix", 0.471}, 
  {"Elementary Functions", 0.709}, {"Gamma Function", 0.382}, 
  {"Large Integer Multiplication", 0.345}, {"Matrix Arithmetic", 0.443}, 
  {"Matrix Multiplication", 0.473}, {"Matrix Transpose", 1.416}, 
  {"Numerical Integration", 1.185}, {"Polynomial Expansion", 0.17}, 
  {"Random Number Sort", 2.129}, {"Singular Value Decomposition", 0.659}, 
  {"Solving a Linear System", 1.207}}}
Improve this answer
$\endgroup$
5
$\begingroup$

Intel Core i9-9900K 8c @ 5.0GHz / 64GB RAM / Quadro P4000

{"MachineName" -> "m1", "System" -> "Linux x86 (64-bit)", 
 "BenchmarkName" -> "WolframMark", "FullVersionNumber" -> 
  "12.1.1", "Date" -> "November 26, 2020", 
 "BenchmarkResult" -> 5.863, "TotalTime" -> 2.361, 
 "Results" -> {{"Data Fitting", 0.146}, {"Digits of Pi", 0.172}, 
   {"Discrete Fourier Transform", 0.27}, 
   {"Eigenvalues of a Matrix", 0.224}, {"Elementary Functions", 
    0.158}, {"Gamma Function", 0.239}, 
   {"Large Integer Multiplication", 0.238}, 
   {"Matrix Arithmetic", 0.06}, {"Matrix Multiplication", 
    0.068}, {"Matrix Transpose", 0.174}, 
   {"Numerical Integration", 0.266}, {"Polynomial Expansion", 
    0.035}, {"Random Number Sort", 0.059}, 
   {"Singular Value Decomposition", 0.123}, 
   {"Solving a Linear System", 0.129}}}
Improve this answer
$\endgroup$
1
  • $\begingroup$ Can you also report: Needs["Benchmarking"]` and BenchmarkReport[]. $\endgroup$
    – Tugrul Temel
    Commented Apr 2, 2021 at 18:53
5
$\begingroup$

Retina 5K 27-inch iMac, 3.6GHz 8-Core Intel Core i9, 64GB 2556 MHz DDR4 RAM, macOS Catalina 10.15.7 :

{"MachineName" -> "blackstone", 
 "System" -> "Mac OS X x86 (64-bit)", 
 "BenchmarkName" -> "WolframMark", 
 "FullVersionNumber" -> "12.1.1", 
 "Date" -> "November 27, 2020", 
 "BenchmarkResult" -> 4.85, 
 "TotalTime" -> 2.854, 
 "Results" -> {{"Data Fitting", 0.191}, 
   {"Digits of Pi", 0.187}, 
   {"Discrete Fourier Transform", 0.203}, 
   {"Eigenvalues of a Matrix", 0.234}, 
   {"Elementary Functions", 0.168}, 
   {"Gamma Function", 0.255}, 
   {"Large Integer Multiplication", 0.258}, 
   {"Matrix Arithmetic", 0.108}, 
   {"Matrix Multiplication", 0.097}, 
   {"Matrix Transpose", 0.161}, 
   {"Numerical Integration", 0.315}, 
   {"Polynomial Expansion", 0.042}, 
   {"Random Number Sort", 0.358}, 
   {"Singular Value Decomposition", 0.14}, 
   {"Solving a Linear System", 0.137}}}
Improve this answer
$\endgroup$
5
$\begingroup$

Intel Core i7-6820HQ @ 2.7 GHz with 24 GB (Lenovo ThinkPad P50):

Benchmark[] /. Rule["MachineName", _String ] -> Nothing /. 
      Rule -> Sequence /. List -> Sequence /. InputForm -> List /. 
   "Results" -> Nothing // OperatorApplied[Partition][2] // TableForm

\begin{array}{ll} \text{System} & \text{Microsoft Windows (64-bit)} \\ \text{BenchmarkName} & \text{WolframMark} \\ \text{FullVersionNumber} & \text{12.1.1} \\ \text{Date} & \text{November 18, 2020} \\ \text{BenchmarkResult} & 1.848 \\ \text{TotalTime} & 7.492 \\ \text{Data Fitting} & 0.55 \\ \text{Digits of Pi} & 0.417 \\ \text{Discrete Fourier Transform} & 0.78 \\ \text{Eigenvalues of a Matrix} & 0.485 \\ \text{Elementary Functions} & 0.77 \\ \text{Gamma Function} & 0.531 \\ \text{Large Integer Multiplication} & 0.612 \\ \text{Matrix Arithmetic} & 0.531 \\ \text{Matrix Multiplication} & 0.367 \\ \text{Matrix Transpose} & 0.637 \\ \text{Numerical Integration} & 0.658 \\ \text{Polynomial Expansion} & 0.083 \\ \text{Random Number Sort} & 0.246 \\ \text{Singular Value Decomposition} & 0.391 \\ \text{Solving a Linear System} & 0.434 \\ \end{array}

Update

Here are the Results from BenchmarkReport:

WolframMarkResults

DetailedTimings

... and this is for Anton

{"MachineName" -> "HappyLappy", 
 "System" -> "Microsoft Windows (64-bit)", 
 "BenchmarkName" -> "WolframMark", "FullVersionNumber" -> 
  "12.1.1", "Date" -> "November 28, 2020", 
 "BenchmarkResult" -> 1.98, "TotalTime" -> 6.992, 
 "Results" -> {{"Data Fitting", 0.482}, 
   {"Digits of Pi", 0.358}, {"Discrete Fourier Transform", 
    0.77}, {"Eigenvalues of a Matrix", 0.458}, 
   {"Elementary Functions", 0.766}, {"Gamma Function", 0.46}, 
   {"Large Integer Multiplication", 0.49}, 
   {"Matrix Arithmetic", 0.506}, {"Matrix Multiplication", 
    0.357}, {"Matrix Transpose", 0.627}, 
   {"Numerical Integration", 0.631}, {"Polynomial Expansion", 
    0.093}, {"Random Number Sort", 0.222}, 
   {"Singular Value Decomposition", 0.366}, 
   {"Solving a Linear System", 0.406}}}
Improve this answer
$\endgroup$
2
  • 1
    $\begingroup$ Can you also run: Needs["Benchmarking`"] BenchmarkReport[] $\endgroup$
    – Tugrul Temel
    Commented Nov 18, 2020 at 22:18
  • 1
    $\begingroup$ @TugrulTemel Just added the BenchmarkReport. $\endgroup$
    – gwr
    Commented Nov 28, 2020 at 18:08
5
$\begingroup$

MacBook Pro (15-inch, 2018), Processor 2.9 GHz Intel Core i9, Memory 32 GB 2400 MHz DDR4, Graphics Radeon Pro 560X 4 GB; Intel UHD Graphics 630 1536 MB

{"MachineName" -> "macbook-pro",
 "System" -> "Mac OS X x86 (64-bit)",
 "BenchmarkName" -> "WolframMark",
 "FullVersionNumber" -> "12.1.1", 
 "Date" -> "December 4, 2020",
 "BenchmarkResult" -> 3.262,
 "TotalTime" -> 4.244, 
 "Results" -> {
   {"Data Fitting", 0.261},
   {"Digits of Pi", 0.234},
   {"Discrete Fourier Transform", 0.32},
   {"Eigenvalues of a Matrix", 0.308}, 
   {"Elementary Functions", 0.229},
   {"Gamma Function", 0.325},
   {"Large Integer Multiplication", 0.298},
   {"Matrix Arithmetic", 0.274}, 
   {"Matrix Multiplication", 0.14},
   {"Matrix Transpose", 0.351},
   {"Numerical Integration", 0.43}, 
   {"Polynomial Expansion", 0.057}, 
   {"Random Number Sort", 0.553},
   {"Singular Value Decomposition", 0.21},
   {"Solving a Linear System", 0.254}}}
Improve this answer
$\endgroup$
5
$\begingroup$

Mathematica 12.1 and 12.2 were benchmarked, the winner is random but two tests stand out as having a distinct trend, test-1 and test-11.

HP ENVY Phoenix 850se Win 10 Desktop PC
Product number: M0K57AV#ABA
4th Generation Intel(R) Core(TM) i7-5820K processor hexa-core [3.3GHz, 15MB Shared Cache]
32GB DDR4-2133 DIMM (4x8GB) RAM
NVIDIA GTX 745 4GB DDR3 FH GFX
Operating System:   Windows 10 Home, 64-bit
DirectX version:    12.0 
GPU processor:      GeForce GTX 745
Driver version:     456.71
Driver Type:        DCH
Direct3D API version:   12
Direct3D feature level: 11_0
CUDA Cores:     384 
Core clock:     1032 MHz 
Memory data rate:   1.80 Gbps
Memory interface:   128-bit 
Memory bandwidth:   28.80 GB/s
Total available graphics memory:    20428 MB
Dedicated video memory: 4096 MB DDR3

12.2 vs 12.1 (12.2 wins this round) Head to head 12.2 on top

Mathematica 12.1

{"MachineName" -> "desktop-n3opac6", 
 "System" -> "Microsoft Windows (64-bit)", 
 "BenchmarkName" -> "WolframMark", "FullVersionNumber" -> "12.1.0", 
 "Date" -> "December 23, 2020", "BenchmarkResult" -> 2.337, 
 "TotalTime" -> 5.924, "Results" -> {{"Data Fitting", 0.409}, 
   {"Digits of Pi", 0.308}, {"Discrete Fourier Transform", 0.578}, 
   {"Eigenvalues of a Matrix", 0.487}, {"Elementary Functions", 0.555}, 
   {"Gamma Function", 0.442}, {"Large Integer Multiplication", 0.527}, 
   {"Matrix Arithmetic", 0.352}, {"Matrix Multiplication", 0.253}, 
   {"Matrix Transpose", 0.429}, {"Numerical Integration", 0.677}, 
   {"Polynomial Expansion", 0.062}, {"Random Number Sort", 0.159}, 
   {"Singular Value Decomposition", 0.39}, {"Solving a Linear System", 
    0.296}}}

Mathematica 12.2

{"MachineName" -> "desktop-n3opac6", 
 "System" -> "Microsoft Windows (64-bit)", 
 "BenchmarkName" -> "WolframMark", "FullVersionNumber" -> "12.2.0", 
 "Date" -> "December 23, 2020", "BenchmarkResult" -> 2.358, 
 "TotalTime" -> 5.87, "Results" -> {{"Data Fitting", 0.446}, 
   {"Digits of Pi", 0.312}, {"Discrete Fourier Transform", 0.566}, 
   {"Eigenvalues of a Matrix", 0.479}, {"Elementary Functions", 0.548}, 
   {"Gamma Function", 0.43}, {"Large Integer Multiplication", 0.438}, 
   {"Matrix Arithmetic", 0.343}, {"Matrix Multiplication", 0.241}, 
   {"Matrix Transpose", 0.423}, {"Numerical Integration", 0.723}, 
   {"Polynomial Expansion", 0.063}, {"Random Number Sort", 0.17}, 
   {"Singular Value Decomposition", 0.399}, {"Solving a Linear System", 
    0.289}}}
Improve this answer
$\endgroup$
5
$\begingroup$

Asus tufA15: Ryzen 4800H, 32gb at 3200mhz, gtx1650ti. Mathematica 12.2 and ubuntu-budgie-20.10-desktop-amd64. I used this command: export MKL_DEBUG_CPU_TYPE=5.

This is my result:

enter image description here

Improve this answer
$\endgroup$
5
$\begingroup$

iMac (Mid 2020) 27-inch, 3.6GHz 10-Core Intel i9, 128GB RAM, Radeon 5700, macOS Big Sur 11.1 with MMA 12.2:
the result of Benchmark[]

{"System" -> "Mac OS X x86 (64-bit)", 
 "BenchmarkName" -> "WolframMark", 
 "FullVersionNumber" -> "12.2.0", 
 "Date" -> "January 22, 2021", 
 "BenchmarkResult" -> 4.776, 
 "TotalTime" -> 2.898, 
 "Results" -> {{"Data Fitting", 0.19}, {"Digits of Pi", 0.217}, 
   {"Discrete Fourier Transform", 0.159}, {"Eigenvalues of a Matrix", 0.256}, 
   {"Elementary Functions", 0.156}, {"Gamma Function", 0.314}, 
   {"Large Integer Multiplication", 0.302}, {"Matrix Arithmetic", 0.099}, 
   {"Matrix Multiplication", 0.074}, {"Matrix Transpose", 0.149}, 
   {"Numerical Integration", 0.328}, {"Polynomial Expansion", 0.044}, 
   {"Random Number Sort", 0.353}, {"Singular Value Decomposition", 0.141}, 
   {"Solving a Linear System", 0.116}}}
Improve this answer
$\endgroup$
5
$\begingroup$

With macOS 11.0.1 (Big Sur) on a MacBook Pro (13-inch, 2020, 2.3 GHz Quad-Core Intel Core i7, 32 GB, Intel Iris Plus Graphics 1536 MB)

Needs["Benchmarking`"]

Benchmark[]

{"MachineName" -> "macbook-pro", "System" -> "Mac OS X x86 (64-bit)", 
 "BenchmarkName" -> "WolframMark", "FullVersionNumber" -> "12.1.1", 
 "Date" -> "November 17, 2020", "BenchmarkResult" -> 2.963, 
 "TotalTime" -> 4.672, "Results" -> 
  {{"Data Fitting", 0.22}, 
   {"Digits of Pi", 0.234}, 
   {"Discrete Fourier Transform", 0.252}, 
   {"Eigenvalues of a Matrix", 0.264}, 
   {"Elementary Functions", 0.141}, 
   {"Gamma Function", 0.328}, 
   {"Large Integer Multiplication", 0.824}, 
   {"Matrix Arithmetic", 0.247}, 
   {"Matrix Multiplication", 0.253}, 
   {"Matrix Transpose", 0.282}, 
   {"Numerical Integration", 0.642}, 
   {"Polynomial Expansion", 0.081}, 
   {"Random Number Sort", 0.497}, 
   {"Singular Value Decomposition", 0.192}, 
   {"Solving a Linear System", 0.215}}}

EDIT: Update with macOS 11.2 .3 (Big Sur) on a MacBook Pro (13 - inch, 2020, 2.3 GHz Quad - Core Intel Core i7, 32 GB, Intel Iris Plus Graphics 1536 MB)

$Version

(* "12.2.0 for Mac OS X x86 (64-bit) (December 12, 2020)" *)

Needs["Benchmarking`"]

Benchmark[]

(* {"MachineName" -> 
  "macbook-pro", "System" -> "Mac OS X x86 (64-bit)", 
 "BenchmarkName" -> "WolframMark", 
 "FullVersionNumber" -> "12.2.0", "Date" -> "April 12, 2021", 
 "BenchmarkResult" -> 3.621, 
 "TotalTime" -> 3.823, 
 "Results" -> 
  {{"Data Fitting", 0.221}, 
   {"Digits of Pi", 0.26}, 
   {"Discrete Fourier Transform", 0.226}, 
   {"Eigenvalues of a Matrix", 0.278}, 
   {"Elementary Functions", 0.14}, 
   {"Gamma Function", 0.368}, 
   {"Large Integer Multiplication", 0.346}, 
   {"Matrix Arithmetic", 0.178}, 
   {"Matrix Multiplication", 0.18}, 
   {"Matrix Transpose", 0.242}, 
   {"Numerical Integration", 0.437}, 
   {"Polynomial Expansion", 0.059}, 
   {"Random Number Sort", 0.481}, 
    {"Singular Value Decomposition", 0.195}, 
   {"Solving a Linear System", 0.212}}}
Improve this answer
$\endgroup$
5
$\begingroup$

The Results of my Notebook 10 Core Core I9, 128 GB RAM, 2*2 TB NVME, Nvidia 2080:

WolframMark Results

Detailed Timings

Here is the corresponding code:

{ "FullVersionNumber"->"12.2.0", "BenchmarkResult"->3.591, "TotalTime"->3.855, "Results" -> {{"Data Fitting", 0.29}, {"Digits of Pi", 0.249}, {"Discrete Fourier Transform", 0.353}, {"Eigenvalues of a Matrix", 0.294}, {"Elementary Functions", 0.37}, {"Gamma Function", 0.346}, {"Large Integer Multiplication", 0.339}, {"Matrix Arithmetic", 0.198}, {"Matrix Multiplication", 0.128}, {"Matrix Transpose", .304}, {"Numerical Integration", 0.474}, {"Polynomial Expansion", 0.044}, {"Random Number Sort", 0.098}, {"Singular Value Decomposition", 0.187}, {"Solving a Linear System", 0.181}}}
Improve this answer
$\endgroup$
2
  • $\begingroup$ Please post the results of the function Benchmark[]. $\endgroup$
    – Anton Antonov
    Commented Jan 20, 2021 at 12:58
  • $\begingroup$ { "FullVersionNumber"->"12.2.0", "BenchmarkResult"->3.591, "TotalTime"->3.855, "Results" -> {{"Data Fitting", 0.29}, {"Digits of Pi", 0.249}, {"Discrete Fourier Transform", 0.353}, {"Eigenvalues of a Matrix", 0.294}, {"Elementary Functions", 0.37}, {"Gamma Function", 0.346}, {"Large Integer Multiplication", 0.339}, {"Matrix Arithmetic", 0.198}, {"Matrix Multiplication", 0.128}, {"Matrix Transpose", .304}, {"Numerical Integration", 0.474}, {"Polynomial Expansion", 0.044}, {"Random Number Sort", 0.098}, {"Singular Value Decomposition", 0.187}, {"Solving a Linear System", 0.181}}} $\endgroup$
    – Andre Koppel
    Commented Apr 3, 2021 at 15:35
5
$\begingroup$

Apple MacBook Pro 2021 14" M1 Max 64GB

MM 12.3.1

enter image description here

Improve this answer
$\endgroup$
1
  • 3
    $\begingroup$ Something seems odd here. User @morbo reports BenchmarkResult" -> 3.147 with a MacBook Air with M1 with native support via mathematica 12.3.1. You report a lower result with the newly released MacBook Pro 2021 M1 Max. That does not make sense to me, so I am either missing something (such as the number of cores), or apples aint apples. $\endgroup$
    – wolfies
    Commented Nov 1, 2021 at 14:53
5
$\begingroup$

Intel Core i7-7700k at stock speeds (4.2 GHz with turbo up to 4.5 GHz).

{"MachineName" -> "water", "System" -> "Mac OS X x86 (64-bit)", 
 "BenchmarkName" -> "WolframMark", "FullVersionNumber" -> "12.3.0", 
 "Date" -> "June 22, 2021", "BenchmarkResult" -> 4.149, "TotalTime" -> 3.336, 
 "Results" -> {{"Data Fitting", 0.236}, {"Digits of Pi", 0.204}, 
   {"Discrete Fourier Transform", 0.204}, {"Eigenvalues of a Matrix", 0.244}, 
   {"Elementary Functions", 0.17}, {"Gamma Function", 0.274}, 
   {"Large Integer Multiplication", 0.268}, {"Matrix Arithmetic", 0.184}, 
   {"Matrix Multiplication", 0.155}, {"Matrix Transpose", 0.203}, 
   {"Numerical Integration", 0.346}, {"Polynomial Expansion", 0.053}, 
   {"Random Number Sort", 0.433}, {"Singular Value Decomposition", 0.174}, 
   {"Solving a Linear System", 0.188}}}

MacBook Pro 16" - 2019 - Intel Core i9-9880H - 2.3 to 4.8 Ghz - 8 core - 16 GiB RAM

{"MachineName" -> "test", "System" -> "Mac OS X x86 (64-bit)", 
 "BenchmarkName" -> "WolframMark", "FullVersionNumber" -> "12.2.0", 
 "Date" -> "June 10, 2022", "BenchmarkResult" -> 3.577, "TotalTime" -> 3.87, 
 "Results" -> {{"Data Fitting", 0.233}, {"Digits of Pi", 0.233}, 
   {"Discrete Fourier Transform", 0.303}, {"Eigenvalues of a Matrix", 0.301}, 
   {"Elementary Functions", 0.303}, {"Gamma Function", 0.314}, 
   {"Large Integer Multiplication", 0.288}, {"Matrix Arithmetic", 0.105}, 
   {"Matrix Multiplication", 0.129}, {"Matrix Transpose", 0.355}, 
   {"Numerical Integration", 0.412}, {"Polynomial Expansion", 0.063}, 
   {"Random Number Sort", 0.467}, {"Singular Value Decomposition", 0.184}, 
   {"Solving a Linear System", 0.18}}}

Same system as above (MacBook Pro 16" - with macOS Monterey (12.6) and Mathematica 12.3.1):


    {"MachineName" -> "test", "System" -> "Mac OS X x86 (64-bit)", 
 "BenchmarkName" -> "WolframMark", "FullVersionNumber" -> "12.3.1", 
 "Date" -> "October 17, 2022", "BenchmarkResult" -> 3.881, "TotalTime" -> 3.567, 
 "Results" -> {{"Data Fitting", 0.219}, {"Digits of Pi", 0.223}, 
   {"Discrete Fourier Transform", 0.278}, {"Eigenvalues of a Matrix", 0.292}, 
   {"Elementary Functions", 0.259}, {"Gamma Function", 0.296}, 
   {"Large Integer Multiplication", 0.266}, {"Matrix Arithmetic", 0.09}, 
   {"Matrix Multiplication", 0.12}, {"Matrix Transpose", 0.285}, 
   {"Numerical Integration", 0.394}, {"Polynomial Expansion", 0.06}, 
   {"Random Number Sort", 0.459}, {"Singular Value Decomposition", 0.17}, 
   {"Solving a Linear System", 0.156}}}
Improve this answer
$\endgroup$
4
$\begingroup$

MacBook Pro (15-inch, 2017), Processor 3.1 GHz Quad-Core Intel Core i7, Memory 16 GB 2133 MHz LPDDR3, Graphics Radeon Pro 560 4 GB; Intel HD Graphics 630 1536 M

{"MachineName" -> "macbook-pro", "System" -> "Mac OS X x86 (64-bit)", 
 "BenchmarkName" -> "WolframMark", "FullVersionNumber" -> "12.1.1", 
 "Date" -> "November 26, 2020", "BenchmarkResult" -> 2.937, "TotalTime" -> 4.713, 
 "Results" -> {{"Data Fitting", 0.28}, {"Digits of Pi", 0.282}, 
   {"Discrete Fourier Transform", 0.358}, {"Eigenvalues of a Matrix", 0.326}, 
   {"Elementary Functions", 0.355}, {"Gamma Function", 0.34}, 
   {"Large Integer Multiplication", 0.348}, {"Matrix Arithmetic", 0.205}, 
   {"Matrix Multiplication", 0.219}, {"Matrix Transpose", 0.421}, 
   {"Numerical Integration", 0.491}, {"Polynomial Expansion", 0.075}, 
   {"Random Number Sort", 0.47}, {"Singular Value Decomposition", 0.272}, 
   {"Solving a Linear System", 0.271}}}
Improve this answer
$\endgroup$
4
$\begingroup$

My machine specs seem identical to @rohit-namjoshi yet my result is different:

{{"System", "Mac OS X x86 (64-bit)"}, {"BenchmarkName", 
  "WolframMark"}, {"FullVersionNumber", "12.1.1"}, {"Date", 
  "December 7, 2020"}, {"BenchmarkResult", 2.827}, {"TotalTime", 
  4.897}, {"Data Fitting", 0.324}, {"Digits of Pi", 
  0.313}, {"Discrete Fourier Transform", 
  0.354}, {"Eigenvalues of a Matrix", 0.364}, {"Elementary Functions",
   0.232}, {"Gamma Function", 0.381}, {"Large Integer Multiplication",
   0.38}, {"Matrix Arithmetic", 0.304}, {"Matrix Multiplication", 
  0.216}, {"Matrix Transpose", 0.387}, {"Numerical Integration", 
  0.508}, {"Polynomial Expansion", 0.067}, {"Random Number Sort", 
  0.525}, {"Singular Value Decomposition", 
  0.253}, {"Solving a Linear System", 0.289}}

I will note that the results improved over the 5 times I ran it until it settled around this value. I just reproduced this by quitting and restarting.

The summary results for each run (starting from a fresh kernel) are as follows: {2.589,2.791,2.83,2.766}

Here is the report:

Benchmark Report

Improve this answer
$\endgroup$
1
  • $\begingroup$ Could you also report the following: BenchmarkReport[]. I notice that Mathematica inventory of different machines for which comparison is made is outdated. $\endgroup$
    – Tugrul Temel
    Commented Dec 7, 2020 at 21:52
4
$\begingroup$

Macbook Air 2020 M1 with 8 GB of memory and 256 GB of SSD on Mathematica version 12.3.1 for Mac OS X ARM (64-bit):

{"MachineName" -> "eire", "System" -> "Mac OS X ARM (64-bit)", 
 "BenchmarkName" -> "WolframMark", "FullVersionNumber" -> "12.3.1", "Date" -> "July 8, 2021", 
 "BenchmarkResult" -> 3.2, "TotalTime" -> 4.326, 
 "Results" -> {{"Data Fitting", 0.219}, {"Digits of Pi", 0.17}, 
   {"Discrete Fourier Transform", 0.321}, {"Eigenvalues of a Matrix", 0.416}, 
   {"Elementary Functions", 0.592}, {"Gamma Function", 0.218}, 
   {"Large Integer Multiplication", 0.181}, {"Matrix Arithmetic", 0.147}, 
   {"Matrix Multiplication", 0.285}, {"Matrix Transpose", 0.184}, 
   {"Numerical Integration", 0.326}, {"Polynomial Expansion", 0.048}, 
   {"Random Number Sort", 0.397}, {"Singular Value Decomposition", 0.504}, 
   {"Solving a Linear System", 0.318}}}
Improve this answer
$\endgroup$
3
  • $\begingroup$ Did you have to run this test several times, or was this the first go? $\endgroup$
    – DrMrstheMonarch
    Commented Jul 10, 2021 at 9:39
  • $\begingroup$ This was the first run, but if I repeat the test I get consistently similar results, all "BenchmarkResult" values are over 3.15 and under 3.25. $\endgroup$
    – Ruben Esquivel
    Commented Jul 14, 2021 at 17:32
  • $\begingroup$ I repeated the test 30 consecutive times and got an average of 3.13033. Probably because of thermal throttling, although the test only took around three minutes. $\endgroup$
    – Ruben Esquivel
    Commented Jul 14, 2021 at 18:14
3
$\begingroup$

In many cases the hardware is not of great importance. Here are my results.

{"MachineName" -> "desktop-32f0eld", "System" -> "Microsoft Windows (64-bit)", 
 "BenchmarkName" -> "WolframMark", 
 "FullVersionNumber" -> "12.1.1", 
 "Date" -> "November 26, 2020", 
 "BenchmarkResult" -> 0.43, 
 "TotalTime" -> 32.18, 
 "Results" ->
 {{"Data Fitting", 2.181}, 
 {"Digits of Pi", 1.008}, 
 {"Discrete Fourier Transform",2.294}, 
 {"Eigenvalues of a Matrix", 1.751},
 {"Elementary Functions",3.909},
 {"Gamma Function",0.885}, 
 {"Large Integer Multiplication",1.019},
 {"Matrix Arithmetic",2.187},
 {"Matrix Multiplication", 3.216}, 
 {"Matrix Transpose", 2.383}, 
 {"Numerical Integration", 2.176}, 
 {"Polynomial Expansion", 0.612}, 
 {"Random Number Sort", 0.802}, 
 {"Singular Value Decomposition",3.602}, 
 {"Solving a Linear System",4.155}}}
Improve this answer
$\endgroup$
3
$\begingroup$

Model Name: MacBook Pro Model Identifier: MacBookPro15,2 Processor Name: Quad-Core Intel Core i5 Processor Speed: 2.4 GHz Number of Processors: 1 Total Number of Cores: 4 L2 Cache (per Core): 256 KB L3 Cache: 6 MB Hyper-Threading Technology: Enabled Memory: 16 GB System Version: macOS 10.15.7 (19H15)

{"MachineName" -> "hubris", "System" -> "Mac OS X x86 (64-bit)", 
 "BenchmarkName" -> "WolframMark", "FullVersionNumber" -> "12.1.1", 
 "Date" -> "December 11, 2020", "BenchmarkResult" -> 2.979, "TotalTime" -> 4.647, 
 "Results" -> {{"Data Fitting", 0.319}, {"Digits of Pi", 0.252}, 
   {"Discrete Fourier Transform", 0.294}, {"Eigenvalues of a Matrix", 0.346}, 
   {"Elementary Functions", 0.372}, {"Gamma Function", 0.358}, 
   {"Large Integer Multiplication", 0.335}, {"Matrix Arithmetic", 0.194}, 
   {"Matrix Multiplication", 0.254}, {"Matrix Transpose", 0.251}, 
   {"Numerical Integration", 0.548}, {"Polynomial Expansion", 0.066}, 
   {"Random Number Sort", 0.488}, {"Singular Value Decomposition", 0.29}, 
   {"Solving a Linear System", 0.28}}}
Improve this answer
$\endgroup$
3
$\begingroup$

Mathematica 12.1 on a decade-old deskside PC with an i7-2600 3.4 GHz CPU, 8 GB of RAM, 120 GB of SSD storage, and running the MS Windows® 10 operating system: 1.75 enter image description here

Improve this answer
$\endgroup$
7
  • 1
    $\begingroup$ Please post the results of the function Benchmark[]. $\endgroup$
    – Anton Antonov
    Commented Dec 12, 2020 at 19:17
  • $\begingroup$ What specific information are you interested in? $\endgroup$
    – Hermitian
    Commented Dec 12, 2020 at 22:12
  • $\begingroup$ "What specific information are you interested in?" -- Can you produce an output similar to the ones here. $\endgroup$
    – Anton Antonov
    Commented Dec 12, 2020 at 22:32
  • $\begingroup$ Anton, I'm an old school numerical analyst who has benchmarked many different kinds of hardware over the years in assembler and languages from Algol to Zephyr. I'm curious how the full report will benefit you? Also, will the notebook output of BenchmarkReport [] suffice? $\endgroup$
    – Hermitian
    Commented Dec 12, 2020 at 23:10
  • 1
    $\begingroup$ Well, you answered the question about output format but skirted the main question. Thank you for the link to your thread. $\endgroup$
    – Hermitian
    Commented Dec 12, 2020 at 23:55
3
$\begingroup$

system

{"MachineName" -> "desktop-68sp4kg", "System" -> "Microsoft Windows (64-bit)", "BenchmarkName" -> "WolframMark", "FullVersionNumber" -> "12.2.0", "Date" -> "April 2, 2021", "BenchmarkResult" -> 2.299, "TotalTime" -> 6.02, 
 "Results" -> {{"Data Fitting", 0.501}, {"Digits of Pi", 0.298}, {"Discrete Fourier Transform", 0.502}, {"Eigenvalues of a Matrix", 0.404}, {"Elementary Functions", 0.669}, {"Gamma Function", 0.417}, {"Large Integer Multiplication", 0.388}, {"Matrix Arithmetic", 0.436}, 
   {"Matrix Multiplication", 0.295}, {"Matrix Transpose", 0.55}, {"Numerical Integration", 0.62}, {"Polynomial Expansion", 0.079}, {"Random Number Sort", 0.204}, {"Singular Value Decomposition", 0.322}, {"Solving a Linear System", 0.335}}}

description

[benchmark2

Improve this answer
$\endgroup$
3
  • 2
    $\begingroup$ Could you please also report Needs["Benchmarking"]` and BenchmarkReport[] $\endgroup$
    – Tugrul Temel
    Commented Apr 2, 2021 at 18:55
  • 2
    $\begingroup$ Added some more output, is this what you needed? $\endgroup$
    – Wicher
    Commented Apr 2, 2021 at 23:08
  • $\begingroup$ Yes, this is what requested...Thanks a lot. $\endgroup$
    – Tugrul Temel
    Commented Apr 3, 2021 at 15:46
3
$\begingroup$

Ryzen 7 5800x stock speed, 32 GB RAM 3466 MHz, Manjaro Linux Kernel 5.11.

I used this command on terminal: export MKL_DEBUG_CPU_TYPE=5 and then executed mathematica from the same terminal.

{"MachineName" -> "cosmivac", "System" -> "Linux x86 (64-bit)",
"BenchmarkName" -> "WolframMark","FullVersionNumber" -> "12.2.0", "Date" -> "May 11, 2021", 
"BenchmarkResult" -> 6.055, "TotalTime" -> 2.286,"Results" -> {{"Data Fitting", 0.148}, 
{"Digits of Pi", 0.181},{"Discrete Fourier Transform", 0.206},
{"Eigenvalues of a Matrix", 0.193}, {"Elementary Functions", 0.144}, 
{"Gamma Function", 0.252},{"Large Integer Multiplication", 0.252},
{"Matrix Arithmetic", 0.056}, {"Matrix Multiplication", 0.091},
{"Matrix Transpose", 0.209}, {"Numerical Integration", 0.273}, 
{"Polynomial Expansion", 0.034},{"Random Number Sort", 0.059}, 
{"Singular Value Decomposition", 0.095}, {"Solving a Linear System", 0.093}}}
Improve this answer
$\endgroup$
2
  • $\begingroup$ I believe this is the first 6 in this thread, congratulations :) $\endgroup$
    – Carl Lange
    Commented Jul 29, 2021 at 5:00
  • $\begingroup$ @CarlLange thank you!! Lets hope to see even a new record from other users. $\endgroup$
    – Technomancer
    Commented Aug 3, 2021 at 6:37
2
$\begingroup$

HB Envy Laptop 13-ba1xxx
11th Gen Intel(R) Core(TM) i7-1165G7 @ 2.80GHz 2.80 GHz
16.0 GB

enter image description here

enter image description here

{"MachineName" -> "laptop-ap0ji8r2", "System" -> "Microsoft Windows (64-bit)", "BenchmarkName" -> "WolframMark", "FullVersionNumber" -> "12.3.0", "Date" -> "October 27, 2021", 
 "BenchmarkResult" -> 3.113, "TotalTime" -> 4.446, "Results" -> {{"Data Fitting", 0.324}, {"Digits of Pi", 0.237}, {"Discrete Fourier Transform", 0.381}, 
   {"Eigenvalues of a Matrix", 0.273}, {"Elementary Functions", 0.488}, {"Gamma Function", 0.331}, {"Large Integer Multiplication", 0.325}, {"Matrix Arithmetic", 0.275}, 
   {"Matrix Multiplication", 0.252}, {"Matrix Transpose", 0.431}, {"Numerical Integration", 0.371}, {"Polynomial Expansion", 0.052}, {"Random Number Sort", 0.175}, 
   {"Singular Value Decomposition", 0.261}, {"Solving a Linear System", 0.27}}}
Improve this answer
$\endgroup$
3
  • $\begingroup$ Please post the output of Needs["Benchmarking`"];BenchmarkReport[]. $\endgroup$
    – Anton Antonov
    Commented Oct 27, 2021 at 9:18
  • 1
    $\begingroup$ I think you mean the output of Benchmark[] not BenchmarkReport[]?! $\endgroup$
    – MMA13
    Commented Oct 27, 2021 at 9:42
  • $\begingroup$ Correct. Thanks for providing the output of Benchmark[]. $\endgroup$
    – Anton Antonov
    Commented Oct 27, 2021 at 11:59
1
$\begingroup$

Amd 5900X, Wolfram Engine, WSL2 Ubuntu

Out[5]= === System Information ===

    Machine Name:               desktop-xxx
    System:                     Linux x86 (64-bit)
    Date:                       October 28, 2021
    Wolfram Language Version:   12.3.1
    Benchmark Result:           4.68
Improve this answer
$\endgroup$
1
2

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.