CPU Optimizations


Recommended Posts

From a few different systems got access to....

real 0m30.470s

user 0m30.406s

sys 0m0.024s

Intel? Xeon? CPU X3360 @ 2.83GHz (4 Cores)

8GB Memory

real 0m22.688s

user 0m22.677s

sys 0m0.000s

Intel? Core? i5-2320 CPU @ 3.00GHz (4 Cores)

16GB Memory

real 1m19.754s

user 1m19.653s

sys 0m0.004s

Intel? Atom? CPU D2550 @ 1.86GHz (2 Cores)

cache size : 512 KB

4GB Memory

What's the difference between Funtoo and Gentoo?

Quote from funtoo.org

Funtoo Linux features native UTF-8 support enabled by default, a git-based, distributed Portage Tree and funtoo overlay, an enhanced Portage with more compact mini-manifest tree, automated imports of new Gentoo changes every 12 hours, GPT/GUID boot support and streamlined boot configuration, enhanced network configuration, up-to-date stable and current Funtoostages, all built using Funtoo's Metro build tool. We also offer Ubuntu Server, Debian, RHEL and Fedora-based kernels.

IOW, Optimized "from scratch" gentoo, git portage, currrent is based on ~x86 and ~amd_64 things like that

Hi All,

I have been playing around with some Compiler Optimizations in the Linux Kernel. I want to know what your results are if you run this in a terminal.

Whats your Hardware and whats your kernel version?

time echo "scale=5000; a(1)*4" | bc -l[/CODE]

Care to elaborate on why? You're basically benchmarking bc and how good your compiler is. The kernel (or OS in general) is going to have little to no effect on the result.

[b]Hardware[/b]

  • Sun UltraSparc T1 (Niagara) CPU clocked at 1.0 GHz
  • 8 GB of RAM

The T1 is a very interesting CPU architecture (terrible single threaded performance, god awful floating point, but great integer throughput). How'd you get your hands on one?

Care to elaborate on why? You're basically benchmarking bc and how good your compiler is. The kernel (or OS in general) is going to have little to no effect on the result.

The T1 is a very interesting CPU architecture (terrible single threaded performance, god awful floating point, but great integer throughput). How'd you get your hands on one?

I disagree. I have already shown that compiling the latest 3.9 Kernels with CPU specific optimizations yeilds better results than the 3.8 Kernels. Also In the early part of this thread the two different Kernels were producing DIFFERENT number streams.

I disagree. I have already shown that compiling the latest 3.9 Kernels with CPU specific optimizations yeilds better results than the 3.8 Kernels. Also In the early part of this thread the two different Kernels were producing DIFFERENT number streams.

The problem with this conclusion is that your results come from many different systems each with a different configuration. They may have different kernels, but different hardware or execution environment may be the cause of the difference.

To actually compare these results you would need to run your tests on the same hardware with the same configuration (OS, connected peripherals, etc...) and only vary the kernel version.

Run repeats to get more reliable timings, with both cold and warm starts, and only then could you start to draw any conclusions. At the moment all you can really say is that computer's owned by different people produce different results when calculating Pi and take different lengths of times to do so.

Also what do you want to measure? If you are just measuring the performance of a single process to complete a result then your results could be skewed. For example, you may miss an overall decrease in system performance if say the different compile optimisations increase the code size and make the task scheduling code too large to fit in the cache. By running a single high load application you may not hit this issue often enough to observer performance degregation. But in, say a webserver, multiple high load processes may end up performing worse due to this "optimisation". So you will need to run different tests to see the impact of any optimisation.

Of course this all depends on the hardware you are running on too, so you will need to run a benchmark on the different hardware with the same configurations you tested the first bit of hardware on.

In short, benchmarking performance is difficult. But, specifying what you mean by performance (latency, average completion time, total completion time, lateness, maximum time taken) will definitely help with benchmarking.

Various tests used to benchmark the kernel:

http://kernel-perf.sourceforge.net/about_tests.php

http://lbs.sourceforge.net/

https://wiki.archlinux.org/index.php/Benchmarking

Linux Mint 14.1 live usb key

Intel? Core? i7-3770K CPU @ 3.50GHz, 4800 MHz

real 0m13.728s

user 0m13.713s

sys 0m0.000s

Same CPU (though running at 3465.49Mhz) and Linux...and running in VirtualBox

real 0m17.286s

user 0m17.125s

sys 0m0.140s

The T1 is a very interesting CPU architecture (terrible single threaded performance, god awful floating point, but great integer throughput). How'd you get your hands on one?

You can buy Sun Fire T2000's on ebay for $400-800. While their single threaded performance is truly awful (and apparently floating point as well), they run heavily multithreaded applications very well. I have been impressed with the Java and Qemu performance in particular. I can build i386, AMD64, and ARM packages faster in qemubuilder on that machine than natively on their respective architectures. (That is comparing the 1.0 GHz T1 to a 2.4 GHz Core 2 Quad for i386 and AMD64 builds. The ARM machine is slow enough that it's not really a fair comparison.)

This topic is now closed to further replies.
  • Recently Browsing   0 members

    • No registered users viewing this page.
  • Posts

    • Quantum Error Correction Validated in Nature: Microsoft and Quantinuum Log 800-Fold Improvement Two years after the original press-release announcement, independently peer-reviewed results published in Nature on June 10, 2026, have confirmed that Microsoft and Quantinuum achieved an 800-fold reduction in quantum error rates on real trapped-ion hardware — the largest gap between physical and logical error rates ever independently validated.    What Quantum Error Correction Actually Does — and Why Breaking Even Is Hard https://www.techtimes.com/articles/318329/20260613/quantum-error-correction-validated-nature-microsoft-quantinuum-log-800-fold-improvement.htm   Quantum Computing Wiring Bottleneck Cracked by HKU Silicon Carbide Chip at Qubit Temperature Engineers at the University of Hong Kong have built the first cryogenic control chip that operates at the same temperature as superconducting qubits — 10 millikelvin, or just one-hundredth of a degree above absolute zero — without generating the heat that has forced every competing approach to park its electronics hundreds of meters of cable away. https://www.techtimes.com/articles/318325/20260613/quantum-computing-wiring-bottleneck-cracked-hku-silicon-carbide-chip-qubit-temperature.htm  
    • RevPDF 4.5.0 by Razvan Serea RevPDF is a free, fully offline PDF editor for Windows, macOS, and Linux that lets you edit text and images directly inside PDF files — no internet connection, no account, and no cloud uploads required. Unlike bloated alternatives that demand subscriptions and constant connectivity, RevPDF fits in under 60MB on desktop while delivering a complete editing toolkit: annotate, redact, sign, compress, split, merge, convert, and reorganize pages, all processed locally on your device. Smart font matching ensures edited text blends seamlessly with the original, and multi-language support includes RTL scripts such as Arabic and Hebrew. Where most PDF editors force you to choose between features and simplicity, RevPDF manages both. You can build interactive forms from scratch with text fields, checkboxes, and dropdowns, permanently redact sensitive data before sharing, draw freehand on contracts and diagrams, and add custom watermarks — all without a single file leaving your machine. Edit Text and Images Directly Inside PDFs RevPDF supports true inline PDF editing — not just annotation layers on top of a document, but actual modification of existing text and images within the file. A smart font-matching engine identifies the font used in the original document and applies it automatically when you make edits, so changes blend naturally with the surrounding content. You can reposition elements, resize images, and update text across single pages or entire documents. RevPDF 4.5.0 release notes: This is one of the biggest updates to RevPDF yet. A lot of things people have been asking for are finally here. New Features Auto Redaction Permanently redact sensitive text and areas from your PDFs before sharing. Clean, irreversible, and fully offline. Comments, Links & Bookmarks Add comments for review, insert clickable links, and create bookmarks to jump around long documents without scrolling forever. Find & Replace Search across the whole document and replace text in one go. Long overdue. Split Pages Vertically or Horizontally Split any page down the middle, vertically or horizontally. Perfect for scanned books or double-page spreads. New Drawing Tools More tools for freehand drawing and markup, better for annotations, sketches, and detailed notes. Continuous Scrolling in Editor The editor now scrolls continuously through pages instead of jumping between them. Working through long documents is a lot smoother now. PDF Metadata Editor View and edit the metadata stored inside your PDFs, including title, author, subject, and keywords. Better Font Matching Text edits now blend in more naturally by doing a better job of matching the original font. Tabbed PDF Viewer Open multiple PDFs at once in tabs and switch between them without going back to the home screen. Add Links Insert hyperlinks anywhere in your PDF, to external URLs or to other pages within the document. Share & Print Shortcuts Share or print directly from the editing screen, home screen, and viewer. No extra steps. Minor Updates Paste images directly from clipboard into your PDF New image editing tools for more control over images inside documents Bug Fixes Fixed file saving issues on Windows and Linux Everything still works fully offline. No login, no cloud, no account. Your files stay on your device. Download: RevPDF 4.5.0 | 58.0 MB (Open Source) Links: RevPDF Home Page | Github | Screenshots 1 | 2 Get alerted to all of our Software updates on Twitter at @NeowinSoftware
    • Interesting. I'm not using a VPN with my phone. I tried though my home internet (Rogers) and my cellular internet (Telus) using their respective DNS servers and both trigger the dialog above.
    • Three days after Anthropic launched Claude Fable 5 as the most capable AI model it had ever released to the public, the United States government ordered it switched off — and now the company is refunding customers who paid to use a product that vanished almost overnight https://www.techtimes.com/articles/318342/20260613/us-government-pulls-anthropics-fable-5-offline-now-come-refunds-vanished-ai.htm  
    • Microsoft fired the team and replaced them with AI and this is what you get.
  • Recent Achievements

    • Week One Done
      agatameier earned a badge
      Week One Done
    • One Month Later
      agatameier earned a badge
      One Month Later
    • Week One Done
      ssd21345 earned a badge
      Week One Done
    • Contributor
      MarkHughes4096 went up a rank
      Contributor
    • Dedicated
      jordanspringer earned a badge
      Dedicated
  • Popular Contributors

    1. 1
      +primortal
      507
    2. 2
      +Edouard
      175
    3. 3
      PsYcHoKiLLa
      139
    4. 4
      ATLien_0
      90
    5. 5
      Steven P.
      76
  • Tell a friend

    Love Neowin? Tell a friend!