Category Archives: PHP Master

BAD Benchmark Results for PHP Master 2017-08-24

Results for project PHP master, build date 2017-08-24 19:23:31-07:00

  • commit: a02cbb9
  • previous commit: cf1d42e
  • revision date: 2017-08-24 23:41:40+02:00
  • environment: Haswell-EP
    • cpu: Intel(R) Xeon(R) CPU E5-2699 v3 @ 2.30GHz 2×18 cores, stepping 2, LLC 45 MB
    • mem: 128 GB
    • os: CentOS 7.1
    • kernel: Linux 3.10.0-229.4.2.el7.x86_64

Baseline results were generated using release php-7.0.0, with hash 60fffd2 from 2015-12-01 04:16:47+00:00

benchmark relative std_dev* change since last run change since baseline current rev run with PGO
😐 WordPress 4.2.2 cgi -T10000 0.26% -0.44% 3.96% 9.20%
😐 Drupal 7.36 cgi -T10000 0.21% -0.40% 3.28% 6.36%
😐 MediaWiki 1.23.9 cgi -T5000 0.13% -0.33% 4.12% 4.26%
😐 bench.php cgi -T100 0.06% -0.23% 45.32% -0.36%
😐 micro_bench.php cgi -T10 0.00% -0.89% 28.38% 3.79%
🙁 mandelbrot.php cgi -T100 0.01% -4.62% 42.75% 5.62%

* Relative Standard Deviation (Standard Deviation/Average)

Note: Benchmark results for WordPress, Drupal, MediaWiki are measured in fetches/second while all others are measured in seconds.
More details on measurements methodology at:
https://01.org/lp/documentation/php-environment-setup.

Subject Label Legend:
Attributes are determined based on the performance evolution of the workloads compared to the previous measurement iteration.
NEUTRAL: performance did not change by more than 1% for any workload
GOOD: performance improved by more than 1% for at least one workload and there is no regression greater than 1%
BAD: performance dropped by more than 1% for at least one workload and there is no improvement greater than 1%
UGLY: performance improved by more than 1% for at least one workload and also dropped by more than 1% for at least one workload

Our lab does a nightly source pull and build of the PHP project and measures performance changes against the previous stable version and the previous nightly measurement. This is provided as a service to the community so that quality issues with current hardware can be identified quickly.

Intel technologies’ features and benefits depend on system configuration and may require enabled hardware, software or service activation. Performance varies depending on system configuration.

GOOD Benchmark Results for PHP Master 2017-08-23

Results for project PHP master, build date 2017-08-23 19:23:20-07:00

  • commit: cf1d42e
  • previous commit: 3cb6407
  • revision date: 2017-08-24 02:31:52+02:00
  • environment: Haswell-EP
    • cpu: Intel(R) Xeon(R) CPU E5-2699 v3 @ 2.30GHz 2×18 cores, stepping 2, LLC 45 MB
    • mem: 128 GB
    • os: CentOS 7.1
    • kernel: Linux 3.10.0-229.4.2.el7.x86_64

Baseline results were generated using release php-7.0.0, with hash 60fffd2 from 2015-12-01 04:16:47+00:00

benchmark relative std_dev* change since last run change since baseline current rev run with PGO
😐 WordPress 4.2.2 cgi -T10000 0.24% 0.57% 4.42% 8.88%
😐 Drupal 7.36 cgi -T10000 0.17% -0.02% 3.70% 5.56%
😐 MediaWiki 1.23.9 cgi -T5000 0.15% 0.51% 4.47% 3.64%
😐 bench.php cgi -T100 0.01% 0.33% 45.45% -0.12%
😐 micro_bench.php cgi -T10 0.01% 0.78% 29.02% 2.55%
🙂 mandelbrot.php cgi -T100 0.01% 4.41% 45.28% 0.17%

* Relative Standard Deviation (Standard Deviation/Average)

Note: Benchmark results for WordPress, Drupal, MediaWiki are measured in fetches/second while all others are measured in seconds.
More details on measurements methodology at:
https://01.org/lp/documentation/php-environment-setup.

Subject Label Legend:
Attributes are determined based on the performance evolution of the workloads compared to the previous measurement iteration.
NEUTRAL: performance did not change by more than 1% for any workload
GOOD: performance improved by more than 1% for at least one workload and there is no regression greater than 1%
BAD: performance dropped by more than 1% for at least one workload and there is no improvement greater than 1%
UGLY: performance improved by more than 1% for at least one workload and also dropped by more than 1% for at least one workload

Our lab does a nightly source pull and build of the PHP project and measures performance changes against the previous stable version and the previous nightly measurement. This is provided as a service to the community so that quality issues with current hardware can be identified quickly.

Intel technologies’ features and benefits depend on system configuration and may require enabled hardware, software or service activation. Performance varies depending on system configuration.

BAD Benchmark Results for PHP Master 2017-08-22

Results for project PHP master, build date 2017-08-22 19:23:33-07:00

  • commit: 3cb6407
  • previous commit: 1287c20
  • revision date: 2017-08-22 16:55:03+03:00
  • environment: Haswell-EP
    • cpu: Intel(R) Xeon(R) CPU E5-2699 v3 @ 2.30GHz 2×18 cores, stepping 2, LLC 45 MB
    • mem: 128 GB
    • os: CentOS 7.1
    • kernel: Linux 3.10.0-229.4.2.el7.x86_64

Baseline results were generated using release php-7.0.0, with hash 60fffd2 from 2015-12-01 04:16:47+00:00

benchmark relative std_dev* change since last run change since baseline current rev run with PGO
😐 WordPress 4.2.2 cgi -T10000 0.13% -0.98% 3.83% 9.13%
😐 Drupal 7.36 cgi -T10000 0.19% -0.26% 3.72% 5.41%
😐 MediaWiki 1.23.9 cgi -T5000 0.08% -0.60% 3.93% 4.39%
😐 bench.php cgi -T100 0.05% -0.33% 45.27% -0.37%
😐 micro_bench.php cgi -T10 0.01% -0.78% 28.46% 3.28%
🙁 mandelbrot.php cgi -T100 0.01% -4.59% 42.75% 4.66%

* Relative Standard Deviation (Standard Deviation/Average)

Note: Benchmark results for WordPress, Drupal, MediaWiki are measured in fetches/second while all others are measured in seconds.
More details on measurements methodology at:
https://01.org/lp/documentation/php-environment-setup.

Subject Label Legend:
Attributes are determined based on the performance evolution of the workloads compared to the previous measurement iteration.
NEUTRAL: performance did not change by more than 1% for any workload
GOOD: performance improved by more than 1% for at least one workload and there is no regression greater than 1%
BAD: performance dropped by more than 1% for at least one workload and there is no improvement greater than 1%
UGLY: performance improved by more than 1% for at least one workload and also dropped by more than 1% for at least one workload

Our lab does a nightly source pull and build of the PHP project and measures performance changes against the previous stable version and the previous nightly measurement. This is provided as a service to the community so that quality issues with current hardware can be identified quickly.

Intel technologies’ features and benefits depend on system configuration and may require enabled hardware, software or service activation. Performance varies depending on system configuration.

NEUTRAL Benchmark Results for PHP Master 2017-08-21

Results for project PHP master, build date 2017-08-21 19:23:03-07:00

  • commit: 1287c20
  • previous commit: 80745e6
  • revision date: 2017-08-21 19:38:44+02:00
  • environment: Haswell-EP
    • cpu: Intel(R) Xeon(R) CPU E5-2699 v3 @ 2.30GHz 2×18 cores, stepping 2, LLC 45 MB
    • mem: 128 GB
    • os: CentOS 7.1
    • kernel: Linux 3.10.0-229.4.2.el7.x86_64

Baseline results were generated using release php-7.0.0, with hash 60fffd2 from 2015-12-01 04:16:47+00:00

benchmark relative std_dev* change since last run change since baseline current rev run with PGO
😐 WordPress 4.2.2 cgi -T10000 0.16% 0.46% 4.86% 8.41%
😐 Drupal 7.36 cgi -T10000 0.19% 0.58% 3.99% 5.96%
😐 MediaWiki 1.23.9 cgi -T5000 0.08% 0.30% 4.56% 3.97%
😐 bench.php cgi -T100 0.00% 0.19% 45.45% -0.12%
😐 micro_bench.php cgi -T10 0.00% -0.16% 29.02% 2.80%
😐 mandelbrot.php cgi -T100 0.02% 0.01% 45.27% 0.28%

* Relative Standard Deviation (Standard Deviation/Average)

Note: Benchmark results for WordPress, Drupal, MediaWiki are measured in fetches/second while all others are measured in seconds.
More details on measurements methodology at:
https://01.org/lp/documentation/php-environment-setup.

Subject Label Legend:
Attributes are determined based on the performance evolution of the workloads compared to the previous measurement iteration.
NEUTRAL: performance did not change by more than 1% for any workload
GOOD: performance improved by more than 1% for at least one workload and there is no regression greater than 1%
BAD: performance dropped by more than 1% for at least one workload and there is no improvement greater than 1%
UGLY: performance improved by more than 1% for at least one workload and also dropped by more than 1% for at least one workload

Our lab does a nightly source pull and build of the PHP project and measures performance changes against the previous stable version and the previous nightly measurement. This is provided as a service to the community so that quality issues with current hardware can be identified quickly.

Intel technologies’ features and benefits depend on system configuration and may require enabled hardware, software or service activation. Performance varies depending on system configuration.

NEUTRAL Benchmark Results for PHP Master 2017-08-20

Results for project PHP master, build date 2017-08-20 19:23:13-07:00

  • commit: 80745e6
  • previous commit: e147ef1
  • revision date: 2017-08-19 21:09:54+01:00
  • environment: Haswell-EP
    • cpu: Intel(R) Xeon(R) CPU E5-2699 v3 @ 2.30GHz 2×18 cores, stepping 2, LLC 45 MB
    • mem: 128 GB
    • os: CentOS 7.1
    • kernel: Linux 3.10.0-229.4.2.el7.x86_64

Baseline results were generated using release php-7.0.0, with hash 60fffd2 from 2015-12-01 04:16:47+00:00

benchmark relative std_dev* change since last run change since baseline current rev run with PGO
😐 WordPress 4.2.2 cgi -T10000 0.25% -0.06% 4.38% 8.72%
😐 Drupal 7.36 cgi -T10000 0.16% -0.31% 3.39% 6.35%
😐 MediaWiki 1.23.9 cgi -T5000 0.08% 0.27% 4.25% 4.44%
😐 bench.php cgi -T100 0.02% 0.01% 45.34% -0.26%
😐 micro_bench.php cgi -T10 0.02% -0.02% 29.13% 2.63%
😐 mandelbrot.php cgi -T100 0.01% -0.08% 45.26% 0.26%

* Relative Standard Deviation (Standard Deviation/Average)

Note: Benchmark results for WordPress, Drupal, MediaWiki are measured in fetches/second while all others are measured in seconds.
More details on measurements methodology at:
https://01.org/lp/documentation/php-environment-setup.

Subject Label Legend:
Attributes are determined based on the performance evolution of the workloads compared to the previous measurement iteration.
NEUTRAL: performance did not change by more than 1% for any workload
GOOD: performance improved by more than 1% for at least one workload and there is no regression greater than 1%
BAD: performance dropped by more than 1% for at least one workload and there is no improvement greater than 1%
UGLY: performance improved by more than 1% for at least one workload and also dropped by more than 1% for at least one workload

Our lab does a nightly source pull and build of the PHP project and measures performance changes against the previous stable version and the previous nightly measurement. This is provided as a service to the community so that quality issues with current hardware can be identified quickly.

Intel technologies’ features and benefits depend on system configuration and may require enabled hardware, software or service activation. Performance varies depending on system configuration.

NEUTRAL Benchmark Results for PHP Master 2017-08-17

Results for project PHP master, build date 2017-08-17 19:23:07-07:00

  • commit: e147ef1
  • previous commit: 21cd57e
  • revision date: 2017-08-17 22:15:09+02:00
  • environment: Haswell-EP
    • cpu: Intel(R) Xeon(R) CPU E5-2699 v3 @ 2.30GHz 2×18 cores, stepping 2, LLC 45 MB
    • mem: 128 GB
    • os: CentOS 7.1
    • kernel: Linux 3.10.0-229.4.2.el7.x86_64

Baseline results were generated using release php-7.0.0, with hash 60fffd2 from 2015-12-01 04:16:47+00:00

benchmark relative std_dev* change since last run change since baseline current rev run with PGO
😐 WordPress 4.2.2 cgi -T10000 0.23% -0.03% 4.44% 8.66%
😐 Drupal 7.36 cgi -T10000 0.21% 0.21% 3.71% 6.28%
😐 MediaWiki 1.23.9 cgi -T5000 0.07% -0.03% 3.96% 3.87%
😐 bench.php cgi -T100 0.01% 0.01% 45.34% -0.48%
😐 micro_bench.php cgi -T10 0.01% -0.03% 29.14% 2.26%
😐 mandelbrot.php cgi -T100 0.01% 0.01% 45.30% 0.61%

* Relative Standard Deviation (Standard Deviation/Average)

Note: Benchmark results for WordPress, Drupal, MediaWiki are measured in fetches/second while all others are measured in seconds.
More details on measurements methodology at:
https://01.org/lp/documentation/php-environment-setup.

Subject Label Legend:
Attributes are determined based on the performance evolution of the workloads compared to the previous measurement iteration.
NEUTRAL: performance did not change by more than 1% for any workload
GOOD: performance improved by more than 1% for at least one workload and there is no regression greater than 1%
BAD: performance dropped by more than 1% for at least one workload and there is no improvement greater than 1%
UGLY: performance improved by more than 1% for at least one workload and also dropped by more than 1% for at least one workload

Our lab does a nightly source pull and build of the PHP project and measures performance changes against the previous stable version and the previous nightly measurement. This is provided as a service to the community so that quality issues with current hardware can be identified quickly.

Intel technologies’ features and benefits depend on system configuration and may require enabled hardware, software or service activation. Performance varies depending on system configuration.

NEUTRAL Benchmark Results for PHP Master 2017-08-16

Results for project PHP master, build date 2017-08-16 19:23:04-07:00

  • commit: 21cd57e
  • previous commit: 869fcce
  • revision date: 2017-08-16 17:05:47+02:00
  • environment: Haswell-EP
    • cpu: Intel(R) Xeon(R) CPU E5-2699 v3 @ 2.30GHz 2×18 cores, stepping 2, LLC 45 MB
    • mem: 128 GB
    • os: CentOS 7.1
    • kernel: Linux 3.10.0-229.4.2.el7.x86_64

Baseline results were generated using release php-7.0.0, with hash 60fffd2 from 2015-12-01 04:16:47+00:00

benchmark relative std_dev* change since last run change since baseline current rev run with PGO
😐 WordPress 4.2.2 cgi -T10000 0.21% 0.16% 4.47% 8.65%
😐 Drupal 7.36 cgi -T10000 0.18% -0.28% 3.49% 6.22%
😐 MediaWiki 1.23.9 cgi -T5000 0.11% -0.12% 4.00% 4.18%
😐 bench.php cgi -T100 0.01% -0.23% 45.34% 0.15%
😐 micro_bench.php cgi -T10 0.00% 0.20% 29.16% 2.45%
😐 mandelbrot.php cgi -T100 0.02% 0.03% 45.30% 1.26%

* Relative Standard Deviation (Standard Deviation/Average)

Note: Benchmark results for WordPress, Drupal, MediaWiki are measured in fetches/second while all others are measured in seconds.
More details on measurements methodology at:
https://01.org/lp/documentation/php-environment-setup.

Subject Label Legend:
Attributes are determined based on the performance evolution of the workloads compared to the previous measurement iteration.
NEUTRAL: performance did not change by more than 1% for any workload
GOOD: performance improved by more than 1% for at least one workload and there is no regression greater than 1%
BAD: performance dropped by more than 1% for at least one workload and there is no improvement greater than 1%
UGLY: performance improved by more than 1% for at least one workload and also dropped by more than 1% for at least one workload

Our lab does a nightly source pull and build of the PHP project and measures performance changes against the previous stable version and the previous nightly measurement. This is provided as a service to the community so that quality issues with current hardware can be identified quickly.

Intel technologies’ features and benefits depend on system configuration and may require enabled hardware, software or service activation. Performance varies depending on system configuration.

NEUTRAL Benchmark Results for PHP Master 2017-08-15

Results for project PHP master, build date 2017-08-15 19:23:01-07:00

  • commit: 869fcce
  • previous commit: b8f20d7
  • revision date: 2017-08-15 20:24:50+01:00
  • environment: Haswell-EP
    • cpu: Intel(R) Xeon(R) CPU E5-2699 v3 @ 2.30GHz 2×18 cores, stepping 2, LLC 45 MB
    • mem: 128 GB
    • os: CentOS 7.1
    • kernel: Linux 3.10.0-229.4.2.el7.x86_64

Baseline results were generated using release php-7.0.0, with hash 60fffd2 from 2015-12-01 04:16:47+00:00

benchmark relative std_dev* change since last run change since baseline current rev run with PGO
😐 WordPress 4.2.2 cgi -T10000 0.22% -0.35% 4.30% 8.89%
😐 Drupal 7.36 cgi -T10000 0.16% 0.48% 3.79% 6.09%
😐 MediaWiki 1.23.9 cgi -T5000 0.13% 0.36% 4.12% 4.56%
😐 bench.php cgi -T100 0.01% -0.59% 45.46% -0.76%
😐 micro_bench.php cgi -T10 0.01% -0.00% 29.02% 2.60%
😐 mandelbrot.php cgi -T100 0.01% 0.11% 45.29% 0.38%

* Relative Standard Deviation (Standard Deviation/Average)

Note: Benchmark results for WordPress, Drupal, MediaWiki are measured in fetches/second while all others are measured in seconds.
More details on measurements methodology at:
https://01.org/lp/documentation/php-environment-setup.

Subject Label Legend:
Attributes are determined based on the performance evolution of the workloads compared to the previous measurement iteration.
NEUTRAL: performance did not change by more than 1% for any workload
GOOD: performance improved by more than 1% for at least one workload and there is no regression greater than 1%
BAD: performance dropped by more than 1% for at least one workload and there is no improvement greater than 1%
UGLY: performance improved by more than 1% for at least one workload and also dropped by more than 1% for at least one workload

Our lab does a nightly source pull and build of the PHP project and measures performance changes against the previous stable version and the previous nightly measurement. This is provided as a service to the community so that quality issues with current hardware can be identified quickly.

Intel technologies’ features and benefits depend on system configuration and may require enabled hardware, software or service activation. Performance varies depending on system configuration.

GOOD Benchmark Results for PHP Master 2017-08-14

Results for project PHP master, build date 2017-08-14 19:23:08-07:00

  • commit: b8f20d7
  • previous commit: beb9295
  • revision date: 2017-08-14 21:23:05-04:00
  • environment: Haswell-EP
    • cpu: Intel(R) Xeon(R) CPU E5-2699 v3 @ 2.30GHz 2×18 cores, stepping 2, LLC 45 MB
    • mem: 128 GB
    • os: CentOS 7.1
    • kernel: Linux 3.10.0-229.4.2.el7.x86_64

Baseline results were generated using release php-7.0.0, with hash 60fffd2 from 2015-12-01 04:16:47+00:00

benchmark relative std_dev* change since last run change since baseline current rev run with PGO
😐 WordPress 4.2.2 cgi -T10000 0.23% -0.43% 4.67% 8.21%
😐 Drupal 7.36 cgi -T10000 0.19% -0.20% 3.29% 5.78%
😐 MediaWiki 1.23.9 cgi -T5000 0.08% -0.42% 3.74% 3.73%
😐 bench.php cgi -T100 0.01% 0.80% 45.78% -0.34%
🙂 micro_bench.php cgi -T10 0.02% 4.69% 29.02% 1.77%
🙂 mandelbrot.php cgi -T100 0.02% 2.67% 45.23% -1.57%

* Relative Standard Deviation (Standard Deviation/Average)

Note: Benchmark results for WordPress, Drupal, MediaWiki are measured in fetches/second while all others are measured in seconds.
More details on measurements methodology at:
https://01.org/lp/documentation/php-environment-setup.

Subject Label Legend:
Attributes are determined based on the performance evolution of the workloads compared to the previous measurement iteration.
NEUTRAL: performance did not change by more than 1% for any workload
GOOD: performance improved by more than 1% for at least one workload and there is no regression greater than 1%
BAD: performance dropped by more than 1% for at least one workload and there is no improvement greater than 1%
UGLY: performance improved by more than 1% for at least one workload and also dropped by more than 1% for at least one workload

Our lab does a nightly source pull and build of the PHP project and measures performance changes against the previous stable version and the previous nightly measurement. This is provided as a service to the community so that quality issues with current hardware can be identified quickly.

Intel technologies’ features and benefits depend on system configuration and may require enabled hardware, software or service activation. Performance varies depending on system configuration.

NEUTRAL Benchmark Results for PHP Master 2017-08-13

Results for project PHP master, build date 2017-08-13 19:23:06-07:00

  • commit: beb9295
  • previous commit: 9ae9533
  • revision date: 2017-08-14 00:53:33+02:00
  • environment: Haswell-EP
    • cpu: Intel(R) Xeon(R) CPU E5-2699 v3 @ 2.30GHz 2×18 cores, stepping 2, LLC 45 MB
    • mem: 128 GB
    • os: CentOS 7.1
    • kernel: Linux 3.10.0-229.4.2.el7.x86_64

Baseline results were generated using release php-7.0.0, with hash 60fffd2 from 2015-12-01 04:16:47+00:00

benchmark relative std_dev* change since last run change since baseline current rev run with PGO
😐 WordPress 4.2.2 cgi -T10000 0.23% 0.64% 5.12% 8.16%
😐 Drupal 7.36 cgi -T10000 0.17% 0.34% 3.50% 5.99%
😐 MediaWiki 1.23.9 cgi -T5000 0.17% 0.52% 4.19% 3.75%
😐 bench.php cgi -T100 0.01% 0.04% 45.34% 1.33%
😐 micro_bench.php cgi -T10 0.02% -0.26% 25.53% 6.55%
😐 mandelbrot.php cgi -T100 0.18% 0.13% 43.72% 1.83%

* Relative Standard Deviation (Standard Deviation/Average)

Note: Benchmark results for WordPress, Drupal, MediaWiki are measured in fetches/second while all others are measured in seconds.
More details on measurements methodology at:
https://01.org/lp/documentation/php-environment-setup.

Subject Label Legend:
Attributes are determined based on the performance evolution of the workloads compared to the previous measurement iteration.
NEUTRAL: performance did not change by more than 1% for any workload
GOOD: performance improved by more than 1% for at least one workload and there is no regression greater than 1%
BAD: performance dropped by more than 1% for at least one workload and there is no improvement greater than 1%
UGLY: performance improved by more than 1% for at least one workload and also dropped by more than 1% for at least one workload

Our lab does a nightly source pull and build of the PHP project and measures performance changes against the previous stable version and the previous nightly measurement. This is provided as a service to the community so that quality issues with current hardware can be identified quickly.

Intel technologies’ features and benefits depend on system configuration and may require enabled hardware, software or service activation. Performance varies depending on system configuration.