↓
 
  • Phoronix
  • gromacs
  • OpenFOAM

Performance analysis, tools and experiments

An eclectic collection

  • Home
  • Blog
  • Tools
    • wspy – workload spy
  • Workloads
    • Geekbench
    • gromacs
      • lysozyme tutorial
      • PRACE benchmark
    • OpenFOAM
    • Phoronix
      • aobench
      • apache
      • asmfish
      • blake2
      • blender
      • botan
      • build-gcc
      • build-linux-kernel
      • build-llvm
      • build-php
      • bullet
      • c-ray
      • cachebench
      • compilebench
      • compress-p7zip
      • compress-pbzip2
      • compress-zstd
      • ebizzy
      • encode-flac
      • encode-mp3
      • ffmpeg
      • ffte
      • fftw
      • fhourstones
      • fio
      • fs-mark
      • gimp
      • git
      • go-benchmark
      • graphics-magick
      • hackbench
      • himeno
      • hmmer
      • indigobench
      • java-gradle-perf
      • java-scimark2
      • luajit
      • m-queens
      • mafft
      • n-queens
      • nginx
      • numpy
      • octave-benchmark
      • openssl
      • osbench
        • osbench – create processes
        • osbench – create threads
        • osbench – memory
      • parboil
      • pgbench
      • phpbench
      • polybench-c
      • povray
      • primesieve
      • pybench
      • radiance
      • rbenchmark
      • redis
      • rodinia
      • scikit-learn
      • scimark2
      • sqlite
      • stockfish
      • stream
      • stress-ng
      • tensorflow
      • tinymembench
      • tjbench
      • tscp
      • ttsiod-renderer
      • vpxenc
      • x264
      • y-cruncher
  • Experiments
Home - Page 3 << 1 2 3 4 5 … 7 8 >>

Post navigation

← Older posts
Newer posts →

Phoronix article – OpenSuSE leap – 2018-05-30

Performance analysis, tools and experiments Posted on 2018-05-30 by mev2018-05-30

Phoronix posted an article comparing OpenSuSE leap 15, leap 42.3 and tumbleweed.

I don’t have these operating systems on my benchmark system, but make the following notes about what the benchmarks are measuring.
Continue reading →

Posted in analysis | Tagged phoronix benchmark article | Leave a reply

TODO list at end of May

Performance analysis, tools and experiments Posted on 2018-05-26 by mev2018-05-26

May coming to a close, useful to take stock of where analysis is at as well as next steps.

I was cycling a good portion of May. The other parts were most focused on adding benchmark analysis needed for some Phoronix benchmark reviews and also some incremental tool additions.

As May comes to a close, following are done

  1. First level analysis of ~60 workloads with web pages created for each
  2. Phoronix published 10 articles that included benchmark runs. I went through workloads for these and created a chart of the Phoronix article. Focus on CPU, skipping graphics and some areas like filesystem performance benchmarks.
  3. Added “topdown” tool to show first and second level metrics and then selected metrics that folded into the third level
  4. Updated wspy performance metrics

This leaves multiple areas for further emphasis over the next month:

  1. Add some more “real world” codes to analyze. Top candidates are gromacs or openfoam
  2. Keep up with incremental phoronix articles including new benchmarks
  3. Look at creating a “topdown” that gives some key metrics on AMD Ryzen
  4. wspy breadth
    1. complete memstats and netstats
    2. handle nmi timer
  5. Architecture: measurements on tx1?
  6. Cleanups: e.g. create updated Phoronix inventory list, add some “about this graph”, update tests done early when tools didn’t create as much information
Posted in tools | Tagged progress report | Leave a reply

topdown tool – adding support for level 3 backend, rusage

Performance analysis, tools and experiments Posted on 2018-05-25 by mev2018-05-25

I have updated the topdown wrapper script to add some additional cache statistics for level 3 backend related information. I have also added a -x option to display some rusage information.
Continue reading →

Posted in tools | Tagged metrics, top-down | Leave a reply

topdown tool – adding support for level 3 frontend

Performance analysis, tools and experiments Posted on 2018-05-24 by mev2018-05-24

The Intel topdown performance analysis method separates out frontend stalls (level 1) into latency (level 2) and bandwidth (level 2). A frontend latency stall is when 0 uops are issued at all because the frontend is waiting. A frontend bandwidth stall is when 1, 2 or 3 uops are issued.

I have updated the “topdown” wrapper script to provide additional level 3 details related to frontend stalls.
Continue reading →

Posted in tools | Tagged metrics, top-down | Leave a reply

Phoronix article – compilers on threadripper (2018-05-23)

Performance analysis, tools and experiments Posted on 2018-05-23 by mev2018-05-26

Phoronix posted an article comparing compilers on threadripper.

The comparison uses gcc7/gcc8/llvm5/llvm6/llvm7 and AMD AOCC. All benchmarks were compiled with -O3 -march=native.

Continue reading →

Posted in analysis | Tagged phoronix benchmark article | Leave a reply

Phoronix article – Spectre V4 performance (2018-05-22)

Performance analysis, tools and experiments Posted on 2018-05-23 by mev2018-05-26

Phoronix posted an article measuring Spectre V4 changes. These tests happen with kernel patches for the Spectre 3a (rogue system register read) and Spectre 4 (speculative store bypass) fixes are applied to the kernel. There is an AMD whitepaper describing the vulnerability and fix.

The primary places these might affect performance are in the kernel and hence several I/O related benchmarks are measured. The I/O writes and forking microtests show differences and more real-world apps do not.
Continue reading →

Posted in analysis | Tagged phoronix benchmark article, spectre | Leave a reply

Phoronix article – Dragonfly BSD (2018-05-21)

Performance analysis, tools and experiments Posted on 2018-05-21 by mev2018-05-26

Phoronix posted an article comparing performance for newest release of Dragonfly BSD. The comparison made is between the old release (5.2) and the new release under development (5.3).

Overall, performance looks improved from new to older release. Unclear how this compares against other operating systems.
Continue reading →

Posted in analysis | Tagged phoronix benchmark article | Leave a reply

topdown tool

Performance analysis, tools and experiments Posted on 2018-05-21 by mev2018-05-21

I have added a basic tool “topdown” that is a wrapper to collect topdown metrics.
Continue reading →

Posted in tools | Tagged metrics, top-down | Leave a reply

Phoronix article – AMD A0CC 1.2 (2018-05-20)

Performance analysis, tools and experiments Posted on 2018-05-20 by mev2018-05-26

Phoronix posted an article benchmarking the newest AMD AOCC compiler.

The article compares performance with gcc 7, gcc 8 and llvm 6. This article goes through some of the benchmarks to understand what is measured. Overall, not sure the benchmarks chosen are particularly noteworthy. Some very small (tscp), non-cpu (redis) and some subtests strange (scimark2) but overall at least a few to give a generic comparison without big things standing out in the results.
Continue reading →

Posted in analysis | Tagged phoronix benchmark article | Leave a reply

Phoronix article – windows subsystem for linux benchmarks (2018-05-18)

Performance analysis, tools and experiments Posted on 2018-05-18 by mev2018-05-26

Phoronix posted an article benchmarking the window subsystem for linux. The comparisons are between Ubuntu 18.04 running in WSL vs. Ubuntu 18.04 running directly on the processor and the older WSL using Ubuntu 16.04.
Continue reading →

Posted in analysis | Tagged phoronix benchmark article | Leave a reply

Post navigation

← Older posts
Newer posts →
©2025 - Performance analysis, tools and experiments - Weaver Xtreme Theme
↑