Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Mention that ThreadsX.jl API is deterministic #102

Merged
merged 1 commit into from
Mar 29, 2020
Merged

Mention that ThreadsX.jl API is deterministic #102

merged 1 commit into from
Mar 29, 2020

Conversation

tkf
Copy link
Owner

@tkf tkf commented Mar 29, 2020

No description provided.

@codecov-io
Copy link

codecov-io commented Mar 29, 2020 •
edited
Loading

Codecov Report

Merging #102 into master will not change coverage by %.
The diff coverage is n/a.

Impacted file tree graph

@@           Coverage Diff           @@
##           master     #102   +/-   ##
=======================================
  Coverage   84.48%   84.48%           
=======================================
  Files           9        9           
  Lines         406      406           
=======================================
  Hits          343      343           
  Misses         63       63

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update 3438e87...d8437c9. Read the comment docs.

@github-actions
Copy link
Contributor

Benchmark result

Judge result

Benchmark Report for /home/runner/work/ThreadsX.jl/ThreadsX.jl

Job Properties

  • Time of benchmarks:
    • Target: 29 Mar 2020 - 07:21
    • Baseline: 29 Mar 2020 - 07:27
  • Package commits:
    • Target: fb03c0
    • Baseline: 3438e8
  • Julia commits:
    • Target: b8e9a9
    • Baseline: b8e9a9
  • Julia command flags:
    • Target: None
    • Baseline: None
  • Environment variables:
    • Target: OMP_NUM_THREADS => 1 JULIA_NUM_THREADS => 2
    • Baseline: OMP_NUM_THREADS => 1 JULIA_NUM_THREADS => 2

Results

A ratio greater than 1.0 denotes a possible regression (marked with ❌), while a ratio less
than 1.0 denotes a possible improvement (marked with ✅). Only significant results - results
that indicate possible regressions or improvements - are shown below (thus, an empty table means that all
benchmark results remained invariant between builds).

ID time ratio memory ratio
["findfirst", "0%", "base"] 1.15 (5%) ❌ 1.00 (1%)
["findfirst", "0%", "tx"] 1.05 (5%) ❌ 1.00 (1%)
["findfirst", "0%", "tx-noterm"] 1.09 (5%) ❌ 1.00 (1%)
["findfirst", "10%", "base"] 1.49 (5%) ❌ 1.00 (1%)
["findfirst", "20%", "base"] 1.41 (5%) ❌ 1.00 (1%)
["findfirst", "20%", "tx"] 0.90 (5%) ✅ 1.00 (1%)
["findfirst", "20%", "tx-noterm"] 1.13 (5%) ❌ 1.78 (1%) ❌
["findfirst", "30%", "base"] 1.58 (5%) ❌ 1.00 (1%)
["findfirst", "40%", "base"] 1.73 (5%) ❌ 1.00 (1%)
["findfirst", "40%", "tx-noterm"] 0.80 (5%) ✅ 1.00 (1%)
["findfirst", "50%", "base"] 1.67 (5%) ❌ 1.00 (1%)
["findfirst", "50%", "tx"] 1.09 (5%) ❌ 1.00 (1%)
["foreach_seq", "base", "Transpose"] 1.09 (5%) ❌ 1.00 (1%)
["foreach_seq", "tx", "Transpose"] 1.10 (5%) ❌ 1.00 (1%)
["foreach_seq", "tx", "Vector"] 1.13 (5%) ❌ 1.00 (1%)
["foreach_seq_double", "cartesian", "man"] 0.83 (5%) ✅ 1.00 (1%)
["foreach_seq_double", "cartesian", "tx", ":simd => :ivdep"] 1.18 (5%) ❌ 1.00 (1%)
["foreach_seq_double", "cartesian", "tx", ":simd => true"] 1.31 (5%) ❌ 1.00 (1%)
["foreach_seq_double", "linear", "man"] 1.14 (5%) ❌ 1.00 (1%)
["foreach_seq_double", "linear", "tx", ":simd => :ivdep"] 43800.81 (5%) ❌ 1.00 (1%)
["foreach_seq_double", "linear", "tx", ":simd => false"] 47220.42 (5%) ❌ 1.00 (1%)
["foreach_seq_double", "linear", "tx", ":simd => true"] 49440.49 (5%) ❌ 1.00 (1%)
["foreach_seq_sum_many", ":nvecs => 8", "man"] 1.32 (5%) ❌ 1.00 (1%)
["foreach_seq_sum_many", ":nvecs => 8", "tx", ":simd => :ivdep"] 1.14 (5%) ❌ 1.00 (1%)
["foreach_seq_sum_many", ":nvecs => 8", "tx", ":simd => false"] 0.89 (5%) ✅ 1.00 (1%)
["foreach_seq_sum_many", ":nvecs => 8", "tx", ":simd => true"] 0.89 (5%) ✅ 1.00 (1%)
["sort", "F64 (narrow)", "ThreadsX.MergeSort"] 1.06 (5%) ❌ 1.00 (1%)
["sort", "F64 (narrow)", "ThreadsX.StableQuickSort"] 1.16 (5%) ❌ 1.00 (1%)
["sort", "F64 (wide)", "ThreadsX.MergeSort"] 0.90 (5%) ✅ 1.00 (1%)
["sort", "I64 (narrow)", "ThreadsX.StableQuickSort"] 1.07 (5%) ❌ 1.00 (1%)
["sort", "I64 (wide)", "ThreadsX.QuickSort"] 0.90 (5%) ✅ 1.00 (1%)
["sort", "reversed", "Base"] 0.84 (5%) ✅ 1.00 (1%)
["sort", "reversed", "ThreadsX.QuickSort"] 0.91 (5%) ✅ 1.00 (1%)
["sort", "sorted", "Base"] 1.19 (5%) ❌ 1.00 (1%)
["sort", "sorted", "ThreadsX.StableQuickSort"] 0.80 (5%) ✅ 1.00 (1%)
["unique", "rand(1:10, 1000000)", "tx"] 1.09 (5%) ❌ 1.00 (1%)

Benchmark Group List

Here's a list of all the benchmark groups executed by this job:

  • ["findfirst", "0%"]
  • ["findfirst", "10%"]
  • ["findfirst", "20%"]
  • ["findfirst", "30%"]
  • ["findfirst", "40%"]
  • ["findfirst", "50%"]
  • ["foreach", "base"]
  • ["foreach", "broadcast"]
  • ["foreach", "tx"]
  • ["foreach_seq", "base"]
  • ["foreach_seq", "tx"]
  • ["foreach_seq_double", "cartesian"]
  • ["foreach_seq_double", "cartesian", "tx"]
  • ["foreach_seq_double", "linear"]
  • ["foreach_seq_double", "linear", "tx"]
  • ["foreach_seq_sum_many", ":nvecs => 8"]
  • ["foreach_seq_sum_many", ":nvecs => 8", "tx"]
  • ["sort", "F64 (narrow)"]
  • ["sort", "F64 (wide)"]
  • ["sort", "I64 (narrow)"]
  • ["sort", "I64 (wide)"]
  • ["sort", "reversed"]
  • ["sort", "sorted"]
  • ["unique", "rand(1:10, 1000000)"]
  • ["unique", "rand(1:1000, 1000000)"]

Julia versioninfo

Target

Julia Version 1.4.0
Commit b8e9a9ecc6 (2020-03-21 16:36 UTC)
Platform Info:
  OS: Linux (x86_64-pc-linux-gnu)
      Ubuntu 18.04.4 LTS
  uname: Linux 5.0.0-1032-azure #34-Ubuntu SMP Mon Feb 10 19:37:25 UTC 2020 x86_64 x86_64
  CPU: Intel(R) Xeon(R) Platinum 8171M CPU @ 2.60GHz: 
              speed         user         nice          sys         idle          irq
       #1  2095 MHz      51702 s          0 s       2879 s      36122 s          0 s
       #2  2095 MHz      59338 s          0 s       2338 s      28522 s          0 s
       
  Memory: 6.782737731933594 GB (2772.13671875 MB free)
  Uptime: 922.0 sec
  Load Avg:  1.240234375  1.30712890625  0.89306640625
  WORD_SIZE: 64
  LIBM: libopenlibm
  LLVM: libLLVM-8.0.1 (ORCJIT, skylake)

Baseline

Julia Version 1.4.0
Commit b8e9a9ecc6 (2020-03-21 16:36 UTC)
Platform Info:
  OS: Linux (x86_64-pc-linux-gnu)
      Ubuntu 18.04.4 LTS
  uname: Linux 5.0.0-1032-azure #34-Ubuntu SMP Mon Feb 10 19:37:25 UTC 2020 x86_64 x86_64
  CPU: Intel(R) Xeon(R) Platinum 8171M CPU @ 2.60GHz: 
              speed         user         nice          sys         idle          irq
       #1  2095 MHz      77452 s          0 s       3458 s      47082 s          0 s
       #2  2095 MHz      82997 s          0 s       3160 s      41329 s          0 s
       
  Memory: 6.782737731933594 GB (2951.4921875 MB free)
  Uptime: 1297.0 sec
  Load Avg:  1.33642578125  1.36962890625  1.06591796875
  WORD_SIZE: 64
  LIBM: libopenlibm
  LLVM: libLLVM-8.0.1 (ORCJIT, skylake)

Target result

Benchmark Report for /home/runner/work/ThreadsX.jl/ThreadsX.jl

Job Properties

  • Time of benchmark: 29 Mar 2020 - 7:21
  • Package commit: fb03c0
  • Julia commit: b8e9a9
  • Julia command flags: None
  • Environment variables: OMP_NUM_THREADS => 1 JULIA_NUM_THREADS => 2

Results

Below is a table of this job's results, obtained by running the benchmarks.
The values listed in the ID column have the structure [parent_group, child_group, ..., key], and can be used to
index into the BaseBenchmarks suite to retrieve the corresponding benchmarks.
The percentages accompanying time and memory values in the below table are noise tolerances. The "true"
time/memory value for a given benchmark is expected to fall within this percentage of the reported value.
An empty cell means that the value was zero.

ID time GC time memory allocations
["findfirst", "0%", "base"] 3.000 ns (5%)
["findfirst", "0%", "tx"] 26.400 μs (5%) 11.95 KiB (1%) 218
["findfirst", "0%", "tx-noterm"] 22.500 μs (5%) 11.97 KiB (1%) 218
["findfirst", "0%", "tx-seq"] 186.030 ns (5%) 544 bytes (1%) 14
["findfirst", "10%", "base"] 87.601 μs (5%)
["findfirst", "10%", "tx"] 86.301 μs (5%) 14.36 KiB (1%) 266
["findfirst", "10%", "tx-noterm"] 276.904 μs (5%) 37.50 KiB (1%) 687
["findfirst", "10%", "tx-seq"] 87.801 μs (5%) 560 bytes (1%) 15
["findfirst", "20%", "base"] 194.003 μs (5%)
["findfirst", "20%", "tx"] 163.903 μs (5%) 21.33 KiB (1%) 393
["findfirst", "20%", "tx-noterm"] 309.005 μs (5%) 42.13 KiB (1%) 771
["findfirst", "20%", "tx-seq"] 176.203 μs (5%) 560 bytes (1%) 15
["findfirst", "30%", "base"] 281.305 μs (5%)
["findfirst", "30%", "tx"] 236.304 μs (5%) 28.27 KiB (1%) 520
["findfirst", "30%", "tx-noterm"] 312.705 μs (5%) 28.30 KiB (1%) 521
["findfirst", "30%", "tx-seq"] 263.805 μs (5%) 560 bytes (1%) 15
["findfirst", "40%", "base"] 407.007 μs (5%)
["findfirst", "40%", "tx"] 312.906 μs (5%) 35.28 KiB (1%) 649
["findfirst", "40%", "tx-noterm"] 315.505 μs (5%) 35.31 KiB (1%) 650
["findfirst", "40%", "tx-seq"] 351.306 μs (5%) 560 bytes (1%) 15
["findfirst", "50%", "base"] 491.709 μs (5%)
["findfirst", "50%", "tx"] 373.906 μs (5%) 37.67 KiB (1%) 696
["findfirst", "50%", "tx-noterm"] 471.809 μs (5%) 40.05 KiB (1%) 743
["findfirst", "50%", "tx-seq"] 438.807 μs (5%) 560 bytes (1%) 15
["foreach", "base", "A .= B .+ B'"] 321.851 ms (5%) 26.682 ms 305.18 MiB (1%) 16000002
["foreach", "base", "A .= B .+ C"] 245.765 ms (5%) 27.282 ms 305.18 MiB (1%) 16000001
["foreach", "broadcast", "A .= B .+ B'"] 9.092 ms (5%)
["foreach", "broadcast", "A .= B .+ C"] 6.994 ms (5%)
["foreach", "tx", "A .= B .+ B'"] 4.482 ms (5%) 25.94 KiB (1%) 360
["foreach", "tx", "A .= B .+ C"] 3.516 ms (5%) 12.75 KiB (1%) 124
["foreach_seq", "base", "Matrix"] 626.607 μs (5%)
["foreach_seq", "base", "Transpose"] 2.151 ms (5%)
["foreach_seq", "base", "Vector"] 626.207 μs (5%)
["foreach_seq", "tx", "Matrix"] 630.208 μs (5%)
["foreach_seq", "tx", "Transpose"] 1.125 ms (5%) 16 bytes (1%) 1
["foreach_seq", "tx", "Vector"] 707.608 μs (5%)
["foreach_seq_double", "cartesian", "man"] 17.601 μs (5%)
["foreach_seq_double", "cartesian", "tx", ":simd => :ivdep"] 21.400 μs (5%)
["foreach_seq_double", "cartesian", "tx", ":simd => false"] 23.300 μs (5%)
["foreach_seq_double", "cartesian", "tx", ":simd => true"] 23.400 μs (5%)
["foreach_seq_double", "linear", "man"] 49.949 ns (5%)
["foreach_seq_double", "linear", "tx", ":simd => :ivdep"] 43.801 ns (5%)
["foreach_seq_double", "linear", "tx", ":simd => false"] 47.220 ns (5%)
["foreach_seq_double", "linear", "tx", ":simd => true"] 49.440 ns (5%)
["foreach_seq_sum_many", ":nvecs => 8", "man"] 1.190 μs (5%)
["foreach_seq_sum_many", ":nvecs => 8", "tx", ":simd => :ivdep"] 910.000 ns (5%)
["foreach_seq_sum_many", ":nvecs => 8", "tx", ":simd => false"] 2.311 μs (5%)
["foreach_seq_sum_many", ":nvecs => 8", "tx", ":simd => true"] 2.311 μs (5%)
["sort", "F64 (narrow)", "Base"] 2.192 ms (5%)
["sort", "F64 (narrow)", "ThreadsX.MergeSort"] 3.003 ms (5%) 1.19 MiB (1%) 535
["sort", "F64 (narrow)", "ThreadsX.QuickSort"] 543.307 μs (5%) 965.13 KiB (1%) 1227
["sort", "F64 (narrow)", "ThreadsX.StableQuickSort"] 643.508 μs (5%) 1.02 MiB (1%) 1246
["sort", "F64 (wide)", "Base"] 7.253 ms (5%)
["sort", "F64 (wide)", "ThreadsX.MergeSort"] 5.348 ms (5%) 1.19 MiB (1%) 564
["sort", "F64 (wide)", "ThreadsX.QuickSort"] 3.932 ms (5%) 1.01 MiB (1%) 2148
["sort", "F64 (wide)", "ThreadsX.StableQuickSort"] 4.745 ms (5%) 1.39 MiB (1%) 2195
["sort", "I64 (narrow)", "Base"] 116.802 μs (5%) 160 bytes (1%) 1
["sort", "I64 (narrow)", "ThreadsX.MergeSort"] 109.701 μs (5%) 864 bytes (1%) 17
["sort", "I64 (narrow)", "ThreadsX.QuickSort"] 110.801 μs (5%) 864 bytes (1%) 17
["sort", "I64 (narrow)", "ThreadsX.StableQuickSort"] 114.002 μs (5%) 864 bytes (1%) 17
["sort", "I64 (wide)", "Base"] 6.605 ms (5%)
["sort", "I64 (wide)", "ThreadsX.MergeSort"] 4.857 ms (5%) 1.19 MiB (1%) 553
["sort", "I64 (wide)", "ThreadsX.QuickSort"] 3.426 ms (5%) 1.01 MiB (1%) 2232
["sort", "I64 (wide)", "ThreadsX.StableQuickSort"] 4.411 ms (5%) 1.40 MiB (1%) 2272
["sort", "reversed", "Base"] 795.411 μs (5%)
["sort", "reversed", "ThreadsX.MergeSort"] 1.149 ms (5%) 1.18 MiB (1%) 434
["sort", "reversed", "ThreadsX.QuickSort"] 912.212 μs (5%) 998.75 KiB (1%) 1871
["sort", "reversed", "ThreadsX.StableQuickSort"] 1.449 ms (5%) 1.36 MiB (1%) 1903
["sort", "sorted", "Base"] 904.911 μs (5%)
["sort", "sorted", "ThreadsX.MergeSort"] 898.311 μs (5%) 1.18 MiB (1%) 431
["sort", "sorted", "ThreadsX.QuickSort"] 897.711 μs (5%) 998.77 KiB (1%) 1872
["sort", "sorted", "ThreadsX.StableQuickSort"] 937.812 μs (5%) 1.36 MiB (1%) 1902
["unique", "rand(1:10, 1000000)", "base"] 10.584 ms (5%) 832 bytes (1%) 8
["unique", "rand(1:10, 1000000)", "tx"] 5.663 ms (5%) 50.98 KiB (1%) 882
["unique", "rand(1:1000, 1000000)", "base"] 10.021 ms (5%) 65.95 KiB (1%) 27
["unique", "rand(1:1000, 1000000)", "tx"] 5.756 ms (5%) 1.07 MiB (1%) 1186

Benchmark Group List

Here's a list of all the benchmark groups executed by this job:

  • ["findfirst", "0%"]
  • ["findfirst", "10%"]
  • ["findfirst", "20%"]
  • ["findfirst", "30%"]
  • ["findfirst", "40%"]
  • ["findfirst", "50%"]
  • ["foreach", "base"]
  • ["foreach", "broadcast"]
  • ["foreach", "tx"]
  • ["foreach_seq", "base"]
  • ["foreach_seq", "tx"]
  • ["foreach_seq_double", "cartesian"]
  • ["foreach_seq_double", "cartesian", "tx"]
  • ["foreach_seq_double", "linear"]
  • ["foreach_seq_double", "linear", "tx"]
  • ["foreach_seq_sum_many", ":nvecs => 8"]
  • ["foreach_seq_sum_many", ":nvecs => 8", "tx"]
  • ["sort", "F64 (narrow)"]
  • ["sort", "F64 (wide)"]
  • ["sort", "I64 (narrow)"]
  • ["sort", "I64 (wide)"]
  • ["sort", "reversed"]
  • ["sort", "sorted"]
  • ["unique", "rand(1:10, 1000000)"]
  • ["unique", "rand(1:1000, 1000000)"]

Julia versioninfo

Julia Version 1.4.0
Commit b8e9a9ecc6 (2020-03-21 16:36 UTC)
Platform Info:
  OS: Linux (x86_64-pc-linux-gnu)
      Ubuntu 18.04.4 LTS
  uname: Linux 5.0.0-1032-azure #34-Ubuntu SMP Mon Feb 10 19:37:25 UTC 2020 x86_64 x86_64
  CPU: Intel(R) Xeon(R) Platinum 8171M CPU @ 2.60GHz: 
              speed         user         nice          sys         idle          irq
       #1  2095 MHz      51702 s          0 s       2879 s      36122 s          0 s
       #2  2095 MHz      59338 s          0 s       2338 s      28522 s          0 s
       
  Memory: 6.782737731933594 GB (2772.13671875 MB free)
  Uptime: 922.0 sec
  Load Avg:  1.240234375  1.30712890625  0.89306640625
  WORD_SIZE: 64
  LIBM: libopenlibm
  LLVM: libLLVM-8.0.1 (ORCJIT, skylake)

Baseline result

Benchmark Report for /home/runner/work/ThreadsX.jl/ThreadsX.jl

Job Properties

  • Time of benchmark: 29 Mar 2020 - 7:27
  • Package commit: 3438e8
  • Julia commit: b8e9a9
  • Julia command flags: None
  • Environment variables: OMP_NUM_THREADS => 1 JULIA_NUM_THREADS => 2

Results

Below is a table of this job's results, obtained by running the benchmarks.
The values listed in the ID column have the structure [parent_group, child_group, ..., key], and can be used to
index into the BaseBenchmarks suite to retrieve the corresponding benchmarks.
The percentages accompanying time and memory values in the below table are noise tolerances. The "true"
time/memory value for a given benchmark is expected to fall within this percentage of the reported value.
An empty cell means that the value was zero.

ID time GC time memory allocations
["findfirst", "0%", "base"] 2.600 ns (5%)
["findfirst", "0%", "tx"] 25.100 μs (5%) 11.95 KiB (1%) 218
["findfirst", "0%", "tx-noterm"] 20.701 μs (5%) 11.97 KiB (1%) 218
["findfirst", "0%", "tx-seq"] 183.564 ns (5%) 544 bytes (1%) 14
["findfirst", "10%", "base"] 58.601 μs (5%)
["findfirst", "10%", "tx"] 84.502 μs (5%) 14.36 KiB (1%) 266
["findfirst", "10%", "tx-noterm"] 279.007 μs (5%) 37.44 KiB (1%) 685
["findfirst", "10%", "tx-seq"] 88.002 μs (5%) 560 bytes (1%) 15
["findfirst", "20%", "base"] 137.304 μs (5%)
["findfirst", "20%", "tx"] 182.005 μs (5%) 21.33 KiB (1%) 393
["findfirst", "20%", "tx-noterm"] 273.007 μs (5%) 23.67 KiB (1%) 437
["findfirst", "20%", "tx-seq"] 175.904 μs (5%) 560 bytes (1%) 15
["findfirst", "30%", "base"] 177.702 μs (5%)
["findfirst", "30%", "tx"] 231.503 μs (5%) 28.27 KiB (1%) 520
["findfirst", "30%", "tx-noterm"] 319.603 μs (5%) 28.30 KiB (1%) 521
["findfirst", "30%", "tx-seq"] 263.603 μs (5%) 560 bytes (1%) 15
["findfirst", "40%", "base"] 235.706 μs (5%)
["findfirst", "40%", "tx"] 307.908 μs (5%) 35.30 KiB (1%) 650
["findfirst", "40%", "tx-noterm"] 395.611 μs (5%) 35.31 KiB (1%) 650
["findfirst", "40%", "tx-seq"] 351.110 μs (5%) 560 bytes (1%) 15
["findfirst", "50%", "base"] 294.809 μs (5%)
["findfirst", "50%", "tx"] 342.710 μs (5%) 37.67 KiB (1%) 696
["findfirst", "50%", "tx-noterm"] 484.414 μs (5%) 40.03 KiB (1%) 742
["findfirst", "50%", "tx-seq"] 439.013 μs (5%) 560 bytes (1%) 15
["foreach", "base", "A .= B .+ B'"] 329.453 ms (5%) 35.870 ms 305.18 MiB (1%) 16000002
["foreach", "base", "A .= B .+ C"] 257.438 ms (5%) 34.975 ms 305.18 MiB (1%) 16000001
["foreach", "broadcast", "A .= B .+ B'"] 8.705 ms (5%)
["foreach", "broadcast", "A .= B .+ C"] 6.926 ms (5%)
["foreach", "tx", "A .= B .+ B'"] 4.446 ms (5%) 25.94 KiB (1%) 360
["foreach", "tx", "A .= B .+ C"] 3.488 ms (5%) 12.77 KiB (1%) 125
["foreach_seq", "base", "Matrix"] 626.712 μs (5%)
["foreach_seq", "base", "Transpose"] 1.971 ms (5%)
["foreach_seq", "base", "Vector"] 626.411 μs (5%)
["foreach_seq", "tx", "Matrix"] 629.312 μs (5%)
["foreach_seq", "tx", "Transpose"] 1.027 ms (5%) 16 bytes (1%) 1
["foreach_seq", "tx", "Vector"] 626.011 μs (5%)
["foreach_seq_double", "cartesian", "man"] 21.300 μs (5%)
["foreach_seq_double", "cartesian", "tx", ":simd => :ivdep"] 18.100 μs (5%)
["foreach_seq_double", "cartesian", "tx", ":simd => false"] 23.200 μs (5%)
["foreach_seq_double", "cartesian", "tx", ":simd => true"] 17.800 μs (5%)
["foreach_seq_double", "linear", "man"] 43.770 ns (5%)
["foreach_seq_double", "linear", "tx", ":simd => :ivdep"] 0.001 ns (5%)
["foreach_seq_double", "linear", "tx", ":simd => false"] 0.001 ns (5%)
["foreach_seq_double", "linear", "tx", ":simd => true"] 0.001 ns (5%)
["foreach_seq_sum_many", ":nvecs => 8", "man"] 900.000 ns (5%)
["foreach_seq_sum_many", ":nvecs => 8", "tx", ":simd => :ivdep"] 800.000 ns (5%)
["foreach_seq_sum_many", ":nvecs => 8", "tx", ":simd => false"] 2.600 μs (5%)
["foreach_seq_sum_many", ":nvecs => 8", "tx", ":simd => true"] 2.600 μs (5%)
["sort", "F64 (narrow)", "Base"] 2.276 ms (5%)
["sort", "F64 (narrow)", "ThreadsX.MergeSort"] 2.842 ms (5%) 1.19 MiB (1%) 534
["sort", "F64 (narrow)", "ThreadsX.QuickSort"] 555.212 μs (5%) 965.14 KiB (1%) 1228
["sort", "F64 (narrow)", "ThreadsX.StableQuickSort"] 556.912 μs (5%) 1.02 MiB (1%) 1245
["sort", "F64 (wide)", "Base"] 7.121 ms (5%)
["sort", "F64 (wide)", "ThreadsX.MergeSort"] 5.973 ms (5%) 1.19 MiB (1%) 563
["sort", "F64 (wide)", "ThreadsX.QuickSort"] 3.846 ms (5%) 1.01 MiB (1%) 2148
["sort", "F64 (wide)", "ThreadsX.StableQuickSort"] 4.845 ms (5%) 1.39 MiB (1%) 2197
["sort", "I64 (narrow)", "Base"] 120.603 μs (5%) 160 bytes (1%) 1
["sort", "I64 (narrow)", "ThreadsX.MergeSort"] 111.702 μs (5%) 864 bytes (1%) 17
["sort", "I64 (narrow)", "ThreadsX.QuickSort"] 109.602 μs (5%) 864 bytes (1%) 17
["sort", "I64 (narrow)", "ThreadsX.StableQuickSort"] 106.502 μs (5%) 864 bytes (1%) 17
["sort", "I64 (wide)", "Base"] 6.939 ms (5%)
["sort", "I64 (wide)", "ThreadsX.MergeSort"] 4.767 ms (5%) 1.19 MiB (1%) 553
["sort", "I64 (wide)", "ThreadsX.QuickSort"] 3.814 ms (5%) 1.01 MiB (1%) 2234
["sort", "I64 (wide)", "ThreadsX.StableQuickSort"] 4.241 ms (5%) 1.40 MiB (1%) 2271
["sort", "reversed", "Base"] 947.220 μs (5%)
["sort", "reversed", "ThreadsX.MergeSort"] 1.145 ms (5%) 1.18 MiB (1%) 434
["sort", "reversed", "ThreadsX.QuickSort"] 1.004 ms (5%) 998.75 KiB (1%) 1871
["sort", "reversed", "ThreadsX.StableQuickSort"] 1.429 ms (5%) 1.36 MiB (1%) 1902
["sort", "sorted", "Base"] 758.816 μs (5%)
["sort", "sorted", "ThreadsX.MergeSort"] 935.618 μs (5%) 1.18 MiB (1%) 432
["sort", "sorted", "ThreadsX.QuickSort"] 933.319 μs (5%) 998.73 KiB (1%) 1870
["sort", "sorted", "ThreadsX.StableQuickSort"] 1.169 ms (5%) 1.36 MiB (1%) 1904
["unique", "rand(1:10, 1000000)", "base"] 10.659 ms (5%) 832 bytes (1%) 8
["unique", "rand(1:10, 1000000)", "tx"] 5.208 ms (5%) 50.98 KiB (1%) 882
["unique", "rand(1:1000, 1000000)", "base"] 9.897 ms (5%) 65.95 KiB (1%) 27
["unique", "rand(1:1000, 1000000)", "tx"] 5.613 ms (5%) 1.07 MiB (1%) 1186

Benchmark Group List

Here's a list of all the benchmark groups executed by this job:

  • ["findfirst", "0%"]
  • ["findfirst", "10%"]
  • ["findfirst", "20%"]
  • ["findfirst", "30%"]
  • ["findfirst", "40%"]
  • ["findfirst", "50%"]
  • ["foreach", "base"]
  • ["foreach", "broadcast"]
  • ["foreach", "tx"]
  • ["foreach_seq", "base"]
  • ["foreach_seq", "tx"]
  • ["foreach_seq_double", "cartesian"]
  • ["foreach_seq_double", "cartesian", "tx"]
  • ["foreach_seq_double", "linear"]
  • ["foreach_seq_double", "linear", "tx"]
  • ["foreach_seq_sum_many", ":nvecs => 8"]
  • ["foreach_seq_sum_many", ":nvecs => 8", "tx"]
  • ["sort", "F64 (narrow)"]
  • ["sort", "F64 (wide)"]
  • ["sort", "I64 (narrow)"]
  • ["sort", "I64 (wide)"]
  • ["sort", "reversed"]
  • ["sort", "sorted"]
  • ["unique", "rand(1:10, 1000000)"]
  • ["unique", "rand(1:1000, 1000000)"]

Julia versioninfo

Julia Version 1.4.0
Commit b8e9a9ecc6 (2020-03-21 16:36 UTC)
Platform Info:
  OS: Linux (x86_64-pc-linux-gnu)
      Ubuntu 18.04.4 LTS
  uname: Linux 5.0.0-1032-azure #34-Ubuntu SMP Mon Feb 10 19:37:25 UTC 2020 x86_64 x86_64
  CPU: Intel(R) Xeon(R) Platinum 8171M CPU @ 2.60GHz: 
              speed         user         nice          sys         idle          irq
       #1  2095 MHz      77452 s          0 s       3458 s      47082 s          0 s
       #2  2095 MHz      82997 s          0 s       3160 s      41329 s          0 s
       
  Memory: 6.782737731933594 GB (2951.4921875 MB free)
  Uptime: 1297.0 sec
  Load Avg:  1.33642578125  1.36962890625  1.06591796875
  WORD_SIZE: 64
  LIBM: libopenlibm
  LLVM: libLLVM-8.0.1 (ORCJIT, skylake)

Runtime information

Runtime Info
BLAS #threads 2
BLAS.vendor() openblas64
Sys.CPU_THREADS 2

lscpu output:

Architecture:        x86_64
CPU op-mode(s):      32-bit, 64-bit
Byte Order:          Little Endian
CPU(s):              2
On-line CPU(s) list: 0,1
Thread(s) per core:  1
Core(s) per socket:  2
Socket(s):           1
NUMA node(s):        1
Vendor ID:           GenuineIntel
CPU family:          6
Model:               85
Model name:          Intel(R) Xeon(R) Platinum 8171M CPU @ 2.60GHz
Stepping:            4
CPU MHz:             2095.097
BogoMIPS:            4190.19
Hypervisor vendor:   Microsoft
Virtualization type: full
L1d cache:           32K
L1i cache:           32K
L2 cache:            1024K
L3 cache:            36608K
NUMA node0 CPU(s):   0,1
Flags:               fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss ht syscall nx pdpe1gb rdtscp lm constant_tsc rep_good nopl xtopology cpuid pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch invpcid_single pti fsgsbase bmi1 hle avx2 smep bmi2 erms invpcid rtm mpx avx512f avx512dq rdseed adx smap clflushopt avx512cd avx512bw avx512vl xsaveopt xsavec xsaves
Cpu Property Value
Brand Intel(R) Xeon(R) Platinum 8171M CPU @ 2.60GHz
Vendor :Intel
Architecture :Skylake
Model Family: 0x06, Model: 0x55, Stepping: 0x04, Type: 0x00
Cores 2 physical cores, 2 logical cores (on executing CPU)
No Hyperthreading detected
Clock Frequencies Not supported by CPU
Data Cache Level 1:3 : (32, 1024, 36608) kbytes
64 byte cache line size
Address Size 48 bits virtual, 44 bits physical
SIMD 512 bit = 64 byte max. SIMD vector size
Time Stamp Counter TSC is accessible via rdtsc
TSC increased at every clock cycle (non-invariant TSC)
Perf. Monitoring Performance Monitoring Counters (PMC) are not supported
Hypervisor Yes, Microsoft

@github-actions
Copy link
Contributor

Benchmark result

Judge result

Benchmark Report for /home/runner/work/ThreadsX.jl/ThreadsX.jl

Job Properties

  • Time of benchmarks:
    • Target: 29 Mar 2020 - 07:23
    • Baseline: 29 Mar 2020 - 07:29
  • Package commits:
    • Target: f193dc
    • Baseline: 3438e8
  • Julia commits:
    • Target: b8e9a9
    • Baseline: b8e9a9
  • Julia command flags:
    • Target: None
    • Baseline: None
  • Environment variables:
    • Target: OMP_NUM_THREADS => 1 JULIA_NUM_THREADS => 2
    • Baseline: OMP_NUM_THREADS => 1 JULIA_NUM_THREADS => 2

Results

A ratio greater than 1.0 denotes a possible regression (marked with ❌), while a ratio less
than 1.0 denotes a possible improvement (marked with ✅). Only significant results - results
that indicate possible regressions or improvements - are shown below (thus, an empty table means that all
benchmark results remained invariant between builds).

ID time ratio memory ratio
["findfirst", "0%", "tx-noterm"] 0.88 (5%) ✅ 1.00 (1%)
["findfirst", "10%", "tx-noterm"] 0.99 (5%) 1.15 (1%) ❌
["findfirst", "20%", "tx-noterm"] 0.99 (5%) 1.19 (1%) ❌
["findfirst", "30%", "tx-noterm"] 1.15 (5%) ❌ 1.00 (1%)
["findfirst", "40%", "tx-noterm"] 1.12 (5%) ❌ 1.00 (1%)
["findfirst", "50%", "tx-noterm"] 0.97 (5%) 1.12 (1%) ❌
["foreach_seq_sum_many", ":nvecs => 8", "man"] 1.33 (5%) ❌ 1.00 (1%)
["foreach_seq_sum_many", ":nvecs => 8", "tx", ":simd => :ivdep"] 1.33 (5%) ❌ 1.00 (1%)

Benchmark Group List

Here's a list of all the benchmark groups executed by this job:

  • ["findfirst", "0%"]
  • ["findfirst", "10%"]
  • ["findfirst", "20%"]
  • ["findfirst", "30%"]
  • ["findfirst", "40%"]
  • ["findfirst", "50%"]
  • ["foreach", "base"]
  • ["foreach", "broadcast"]
  • ["foreach", "tx"]
  • ["foreach_seq", "base"]
  • ["foreach_seq", "tx"]
  • ["foreach_seq_double", "cartesian"]
  • ["foreach_seq_double", "cartesian", "tx"]
  • ["foreach_seq_double", "linear"]
  • ["foreach_seq_double", "linear", "tx"]
  • ["foreach_seq_sum_many", ":nvecs => 8"]
  • ["foreach_seq_sum_many", ":nvecs => 8", "tx"]
  • ["sort", "F64 (narrow)"]
  • ["sort", "F64 (wide)"]
  • ["sort", "I64 (narrow)"]
  • ["sort", "I64 (wide)"]
  • ["sort", "reversed"]
  • ["sort", "sorted"]
  • ["unique", "rand(1:10, 1000000)"]
  • ["unique", "rand(1:1000, 1000000)"]

Julia versioninfo

Target

Julia Version 1.4.0
Commit b8e9a9ecc6 (2020-03-21 16:36 UTC)
Platform Info:
  OS: Linux (x86_64-pc-linux-gnu)
      Ubuntu 18.04.4 LTS
  uname: Linux 5.0.0-1032-azure #34-Ubuntu SMP Mon Feb 10 19:37:25 UTC 2020 x86_64 x86_64
  CPU: Intel(R) Xeon(R) CPU E5-2673 v4 @ 2.30GHz: 
              speed         user         nice          sys         idle          irq
       #1  2294 MHz      47533 s          0 s       2460 s      35140 s          0 s
       #2  2294 MHz      55809 s          0 s       2625 s      26770 s          0 s
       
  Memory: 6.782737731933594 GB (2678.2265625 MB free)
  Uptime: 867.0 sec
  Load Avg:  1.291015625  1.34033203125  0.8857421875
  WORD_SIZE: 64
  LIBM: libopenlibm
  LLVM: libLLVM-8.0.1 (ORCJIT, broadwell)

Baseline

Julia Version 1.4.0
Commit b8e9a9ecc6 (2020-03-21 16:36 UTC)
Platform Info:
  OS: Linux (x86_64-pc-linux-gnu)
      Ubuntu 18.04.4 LTS
  uname: Linux 5.0.0-1032-azure #34-Ubuntu SMP Mon Feb 10 19:37:25 UTC 2020 x86_64 x86_64
  CPU: Intel(R) Xeon(R) CPU E5-2673 v4 @ 2.30GHz: 
              speed         user         nice          sys         idle          irq
       #1  2294 MHz      64991 s          0 s       2982 s      49923 s          0 s
       #2  2294 MHz      82060 s          0 s       3543 s      32317 s          0 s
       
  Memory: 6.782737731933594 GB (2980.921875 MB free)
  Uptime: 1196.0 sec
  Load Avg:  1.26708984375  1.36279296875  1.04052734375
  WORD_SIZE: 64
  LIBM: libopenlibm
  LLVM: libLLVM-8.0.1 (ORCJIT, broadwell)

Target result

Benchmark Report for /home/runner/work/ThreadsX.jl/ThreadsX.jl

Job Properties

  • Time of benchmark: 29 Mar 2020 - 7:23
  • Package commit: f193dc
  • Julia commit: b8e9a9
  • Julia command flags: None
  • Environment variables: OMP_NUM_THREADS => 1 JULIA_NUM_THREADS => 2

Results

Below is a table of this job's results, obtained by running the benchmarks.
The values listed in the ID column have the structure [parent_group, child_group, ..., key], and can be used to
index into the BaseBenchmarks suite to retrieve the corresponding benchmarks.
The percentages accompanying time and memory values in the below table are noise tolerances. The "true"
time/memory value for a given benchmark is expected to fall within this percentage of the reported value.
An empty cell means that the value was zero.

ID time GC time memory allocations
["findfirst", "0%", "base"] 2.800 ns (5%)
["findfirst", "0%", "tx"] 21.900 μs (5%) 11.97 KiB (1%) 219
["findfirst", "0%", "tx-noterm"] 18.600 μs (5%) 11.97 KiB (1%) 218
["findfirst", "0%", "tx-seq"] 199.226 ns (5%) 544 bytes (1%) 14
["findfirst", "10%", "base"] 59.000 μs (5%)
["findfirst", "10%", "tx"] 65.900 μs (5%) 14.36 KiB (1%) 266
["findfirst", "10%", "tx-noterm"] 170.500 μs (5%) 35.20 KiB (1%) 646
["findfirst", "10%", "tx-seq"] 59.600 μs (5%) 560 bytes (1%) 15
["findfirst", "20%", "base"] 117.400 μs (5%)
["findfirst", "20%", "tx"] 117.800 μs (5%) 21.34 KiB (1%) 394
["findfirst", "20%", "tx-noterm"] 171.401 μs (5%) 28.28 KiB (1%) 520
["findfirst", "20%", "tx-seq"] 117.900 μs (5%) 560 bytes (1%) 15
["findfirst", "30%", "base"] 175.800 μs (5%)
["findfirst", "30%", "tx"] 158.400 μs (5%) 28.27 KiB (1%) 520
["findfirst", "30%", "tx-noterm"] 188.000 μs (5%) 28.30 KiB (1%) 521
["findfirst", "30%", "tx-seq"] 176.400 μs (5%) 560 bytes (1%) 15
["findfirst", "40%", "base"] 234.200 μs (5%)
["findfirst", "40%", "tx"] 227.400 μs (5%) 35.31 KiB (1%) 651
["findfirst", "40%", "tx-noterm"] 229.401 μs (5%) 35.33 KiB (1%) 651
["findfirst", "40%", "tx-seq"] 234.800 μs (5%) 560 bytes (1%) 15
["findfirst", "50%", "base"] 292.701 μs (5%)
["findfirst", "50%", "tx"] 256.501 μs (5%) 37.72 KiB (1%) 699
["findfirst", "50%", "tx-noterm"] 275.301 μs (5%) 44.63 KiB (1%) 825
["findfirst", "50%", "tx-seq"] 293.001 μs (5%) 560 bytes (1%) 15
["foreach", "base", "A .= B .+ B'"] 352.600 ms (5%) 23.098 ms 305.18 MiB (1%) 16000002
["foreach", "base", "A .= B .+ C"] 195.082 ms (5%) 23.111 ms 305.18 MiB (1%) 16000001
["foreach", "broadcast", "A .= B .+ B'"] 14.043 ms (5%)
["foreach", "broadcast", "A .= B .+ C"] 8.817 ms (5%)
["foreach", "tx", "A .= B .+ B'"] 6.915 ms (5%) 25.94 KiB (1%) 360
["foreach", "tx", "A .= B .+ C"] 4.676 ms (5%) 12.75 KiB (1%) 124
["foreach_seq", "base", "Matrix"] 560.400 μs (5%)
["foreach_seq", "base", "Transpose"] 1.860 ms (5%)
["foreach_seq", "base", "Vector"] 560.600 μs (5%)
["foreach_seq", "tx", "Matrix"] 564.001 μs (5%)
["foreach_seq", "tx", "Transpose"] 879.201 μs (5%) 16 bytes (1%) 1
["foreach_seq", "tx", "Vector"] 560.600 μs (5%)
["foreach_seq_double", "cartesian", "man"] 20.200 μs (5%)
["foreach_seq_double", "cartesian", "tx", ":simd => :ivdep"] 20.300 μs (5%)
["foreach_seq_double", "cartesian", "tx", ":simd => false"] 19.500 μs (5%)
["foreach_seq_double", "cartesian", "tx", ":simd => true"] 19.600 μs (5%)
["foreach_seq_double", "linear", "man"] 101.699 ns (5%)
["foreach_seq_double", "linear", "tx", ":simd => :ivdep"] 103.834 ns (5%)
["foreach_seq_double", "linear", "tx", ":simd => false"] 103.814 ns (5%)
["foreach_seq_double", "linear", "tx", ":simd => true"] 101.907 ns (5%)
["foreach_seq_sum_many", ":nvecs => 8", "man"] 2.122 μs (5%)
["foreach_seq_sum_many", ":nvecs => 8", "tx", ":simd => :ivdep"] 2.130 μs (5%)
["foreach_seq_sum_many", ":nvecs => 8", "tx", ":simd => false"] 2.589 μs (5%)
["foreach_seq_sum_many", ":nvecs => 8", "tx", ":simd => true"] 2.589 μs (5%)
["sort", "F64 (narrow)", "Base"] 1.980 ms (5%)
["sort", "F64 (narrow)", "ThreadsX.MergeSort"] 2.283 ms (5%) 1.19 MiB (1%) 536
["sort", "F64 (narrow)", "ThreadsX.QuickSort"] 1.377 ms (5%) 965.09 KiB (1%) 1225
["sort", "F64 (narrow)", "ThreadsX.StableQuickSort"] 1.390 ms (5%) 1.02 MiB (1%) 1246
["sort", "F64 (wide)", "Base"] 4.918 ms (5%)
["sort", "F64 (wide)", "ThreadsX.MergeSort"] 4.110 ms (5%) 1.19 MiB (1%) 564
["sort", "F64 (wide)", "ThreadsX.QuickSort"] 4.127 ms (5%) 1.01 MiB (1%) 2146
["sort", "F64 (wide)", "ThreadsX.StableQuickSort"] 4.614 ms (5%) 1.39 MiB (1%) 2192
["sort", "I64 (narrow)", "Base"] 128.800 μs (5%) 160 bytes (1%) 1
["sort", "I64 (narrow)", "ThreadsX.MergeSort"] 132.500 μs (5%) 864 bytes (1%) 17
["sort", "I64 (narrow)", "ThreadsX.QuickSort"] 132.600 μs (5%) 864 bytes (1%) 17
["sort", "I64 (narrow)", "ThreadsX.StableQuickSort"] 132.500 μs (5%) 864 bytes (1%) 17
["sort", "I64 (wide)", "Base"] 4.927 ms (5%)
["sort", "I64 (wide)", "ThreadsX.MergeSort"] 3.556 ms (5%) 1.19 MiB (1%) 553
["sort", "I64 (wide)", "ThreadsX.QuickSort"] 3.455 ms (5%) 1.01 MiB (1%) 2236
["sort", "I64 (wide)", "ThreadsX.StableQuickSort"] 3.989 ms (5%) 1.40 MiB (1%) 2271
["sort", "reversed", "Base"] 644.901 μs (5%)
["sort", "reversed", "ThreadsX.MergeSort"] 1.083 ms (5%) 1.18 MiB (1%) 435
["sort", "reversed", "ThreadsX.QuickSort"] 964.602 μs (5%) 998.77 KiB (1%) 1872
["sort", "reversed", "ThreadsX.StableQuickSort"] 1.341 ms (5%) 1.36 MiB (1%) 1904
["sort", "sorted", "Base"] 607.701 μs (5%)
["sort", "sorted", "ThreadsX.MergeSort"] 799.401 μs (5%) 1.18 MiB (1%) 431
["sort", "sorted", "ThreadsX.QuickSort"] 999.101 μs (5%) 998.77 KiB (1%) 1872
["sort", "sorted", "ThreadsX.StableQuickSort"] 1.109 ms (5%) 1.36 MiB (1%) 1904
["unique", "rand(1:10, 1000000)", "base"] 7.856 ms (5%) 832 bytes (1%) 8
["unique", "rand(1:10, 1000000)", "tx"] 4.020 ms (5%) 50.98 KiB (1%) 882
["unique", "rand(1:1000, 1000000)", "base"] 7.207 ms (5%) 65.95 KiB (1%) 27
["unique", "rand(1:1000, 1000000)", "tx"] 4.293 ms (5%) 1.07 MiB (1%) 1186

Benchmark Group List

Here's a list of all the benchmark groups executed by this job:

  • ["findfirst", "0%"]
  • ["findfirst", "10%"]
  • ["findfirst", "20%"]
  • ["findfirst", "30%"]
  • ["findfirst", "40%"]
  • ["findfirst", "50%"]
  • ["foreach", "base"]
  • ["foreach", "broadcast"]
  • ["foreach", "tx"]
  • ["foreach_seq", "base"]
  • ["foreach_seq", "tx"]
  • ["foreach_seq_double", "cartesian"]
  • ["foreach_seq_double", "cartesian", "tx"]
  • ["foreach_seq_double", "linear"]
  • ["foreach_seq_double", "linear", "tx"]
  • ["foreach_seq_sum_many", ":nvecs => 8"]
  • ["foreach_seq_sum_many", ":nvecs => 8", "tx"]
  • ["sort", "F64 (narrow)"]
  • ["sort", "F64 (wide)"]
  • ["sort", "I64 (narrow)"]
  • ["sort", "I64 (wide)"]
  • ["sort", "reversed"]
  • ["sort", "sorted"]
  • ["unique", "rand(1:10, 1000000)"]
  • ["unique", "rand(1:1000, 1000000)"]

Julia versioninfo

Julia Version 1.4.0
Commit b8e9a9ecc6 (2020-03-21 16:36 UTC)
Platform Info:
  OS: Linux (x86_64-pc-linux-gnu)
      Ubuntu 18.04.4 LTS
  uname: Linux 5.0.0-1032-azure #34-Ubuntu SMP Mon Feb 10 19:37:25 UTC 2020 x86_64 x86_64
  CPU: Intel(R) Xeon(R) CPU E5-2673 v4 @ 2.30GHz: 
              speed         user         nice          sys         idle          irq
       #1  2294 MHz      47533 s          0 s       2460 s      35140 s          0 s
       #2  2294 MHz      55809 s          0 s       2625 s      26770 s          0 s
       
  Memory: 6.782737731933594 GB (2678.2265625 MB free)
  Uptime: 867.0 sec
  Load Avg:  1.291015625  1.34033203125  0.8857421875
  WORD_SIZE: 64
  LIBM: libopenlibm
  LLVM: libLLVM-8.0.1 (ORCJIT, broadwell)

Baseline result

Benchmark Report for /home/runner/work/ThreadsX.jl/ThreadsX.jl

Job Properties

  • Time of benchmark: 29 Mar 2020 - 7:29
  • Package commit: 3438e8
  • Julia commit: b8e9a9
  • Julia command flags: None
  • Environment variables: OMP_NUM_THREADS => 1 JULIA_NUM_THREADS => 2

Results

Below is a table of this job's results, obtained by running the benchmarks.
The values listed in the ID column have the structure [parent_group, child_group, ..., key], and can be used to
index into the BaseBenchmarks suite to retrieve the corresponding benchmarks.
The percentages accompanying time and memory values in the below table are noise tolerances. The "true"
time/memory value for a given benchmark is expected to fall within this percentage of the reported value.
An empty cell means that the value was zero.

ID time GC time memory allocations
["findfirst", "0%", "base"] 2.800 ns (5%)
["findfirst", "0%", "tx"] 22.800 μs (5%) 11.95 KiB (1%) 218
["findfirst", "0%", "tx-noterm"] 21.200 μs (5%) 11.97 KiB (1%) 218
["findfirst", "0%", "tx-seq"] 194.892 ns (5%) 544 bytes (1%) 14
["findfirst", "10%", "base"] 59.200 μs (5%)
["findfirst", "10%", "tx"] 66.100 μs (5%) 14.36 KiB (1%) 266
["findfirst", "10%", "tx-noterm"] 171.500 μs (5%) 30.59 KiB (1%) 562
["findfirst", "10%", "tx-seq"] 59.200 μs (5%) 560 bytes (1%) 15
["findfirst", "20%", "base"] 117.500 μs (5%)
["findfirst", "20%", "tx"] 121.600 μs (5%) 21.34 KiB (1%) 394
["findfirst", "20%", "tx-noterm"] 173.300 μs (5%) 23.67 KiB (1%) 438
["findfirst", "20%", "tx-seq"] 118.000 μs (5%) 560 bytes (1%) 15
["findfirst", "30%", "base"] 175.500 μs (5%)
["findfirst", "30%", "tx"] 161.100 μs (5%) 28.27 KiB (1%) 520
["findfirst", "30%", "tx-noterm"] 164.000 μs (5%) 28.28 KiB (1%) 520
["findfirst", "30%", "tx-seq"] 175.900 μs (5%) 560 bytes (1%) 15
["findfirst", "40%", "base"] 234.700 μs (5%)
["findfirst", "40%", "tx"] 226.300 μs (5%) 35.31 KiB (1%) 651
["findfirst", "40%", "tx-noterm"] 205.700 μs (5%) 35.31 KiB (1%) 650
["findfirst", "40%", "tx-seq"] 234.400 μs (5%) 560 bytes (1%) 15
["findfirst", "50%", "base"] 292.601 μs (5%)
["findfirst", "50%", "tx"] 257.300 μs (5%) 37.70 KiB (1%) 698
["findfirst", "50%", "tx-noterm"] 282.800 μs (5%) 39.98 KiB (1%) 739
["findfirst", "50%", "tx-seq"] 293.100 μs (5%) 560 bytes (1%) 15
["foreach", "base", "A .= B .+ B'"] 342.890 ms (5%) 27.990 ms 305.18 MiB (1%) 16000002
["foreach", "base", "A .= B .+ C"] 200.186 ms (5%) 18.746 ms 305.18 MiB (1%) 16000001
["foreach", "broadcast", "A .= B .+ B'"] 14.217 ms (5%)
["foreach", "broadcast", "A .= B .+ C"] 8.753 ms (5%)
["foreach", "tx", "A .= B .+ B'"] 7.047 ms (5%) 25.94 KiB (1%) 360
["foreach", "tx", "A .= B .+ C"] 4.642 ms (5%) 12.73 KiB (1%) 123
["foreach_seq", "base", "Matrix"] 560.502 μs (5%)
["foreach_seq", "base", "Transpose"] 1.850 ms (5%)
["foreach_seq", "base", "Vector"] 560.801 μs (5%)
["foreach_seq", "tx", "Matrix"] 563.401 μs (5%)
["foreach_seq", "tx", "Transpose"] 876.702 μs (5%) 16 bytes (1%) 1
["foreach_seq", "tx", "Vector"] 560.501 μs (5%)
["foreach_seq_double", "cartesian", "man"] 20.201 μs (5%)
["foreach_seq_double", "cartesian", "tx", ":simd => :ivdep"] 20.400 μs (5%)
["foreach_seq_double", "cartesian", "tx", ":simd => false"] 20.100 μs (5%)
["foreach_seq_double", "cartesian", "tx", ":simd => true"] 20.100 μs (5%)
["foreach_seq_double", "linear", "man"] 101.592 ns (5%)
["foreach_seq_double", "linear", "tx", ":simd => :ivdep"] 100.000 ns (5%)
["foreach_seq_double", "linear", "tx", ":simd => false"] 100.000 ns (5%)
["foreach_seq_double", "linear", "tx", ":simd => true"] 100.000 ns (5%)
["foreach_seq_sum_many", ":nvecs => 8", "man"] 1.600 μs (5%)
["foreach_seq_sum_many", ":nvecs => 8", "tx", ":simd => :ivdep"] 1.600 μs (5%)
["foreach_seq_sum_many", ":nvecs => 8", "tx", ":simd => false"] 2.500 μs (5%)
["foreach_seq_sum_many", ":nvecs => 8", "tx", ":simd => true"] 2.500 μs (5%)
["sort", "F64 (narrow)", "Base"] 2.066 ms (5%)
["sort", "F64 (narrow)", "ThreadsX.MergeSort"] 2.265 ms (5%) 1.19 MiB (1%) 535
["sort", "F64 (narrow)", "ThreadsX.QuickSort"] 1.361 ms (5%) 965.09 KiB (1%) 1225
["sort", "F64 (narrow)", "ThreadsX.StableQuickSort"] 1.388 ms (5%) 1.02 MiB (1%) 1245
["sort", "F64 (wide)", "Base"] 4.961 ms (5%)
["sort", "F64 (wide)", "ThreadsX.MergeSort"] 4.104 ms (5%) 1.19 MiB (1%) 564
["sort", "F64 (wide)", "ThreadsX.QuickSort"] 4.143 ms (5%) 1.01 MiB (1%) 2145
["sort", "F64 (wide)", "ThreadsX.StableQuickSort"] 4.654 ms (5%) 1.39 MiB (1%) 2195
["sort", "I64 (narrow)", "Base"] 128.801 μs (5%) 160 bytes (1%) 1
["sort", "I64 (narrow)", "ThreadsX.MergeSort"] 132.401 μs (5%) 864 bytes (1%) 17
["sort", "I64 (narrow)", "ThreadsX.QuickSort"] 132.400 μs (5%) 864 bytes (1%) 17
["sort", "I64 (narrow)", "ThreadsX.StableQuickSort"] 132.400 μs (5%) 864 bytes (1%) 17
["sort", "I64 (wide)", "Base"] 4.922 ms (5%)
["sort", "I64 (wide)", "ThreadsX.MergeSort"] 3.572 ms (5%) 1.19 MiB (1%) 554
["sort", "I64 (wide)", "ThreadsX.QuickSort"] 3.442 ms (5%) 1.01 MiB (1%) 2236
["sort", "I64 (wide)", "ThreadsX.StableQuickSort"] 4.018 ms (5%) 1.40 MiB (1%) 2272
["sort", "reversed", "Base"] 644.502 μs (5%)
["sort", "reversed", "ThreadsX.MergeSort"] 1.060 ms (5%) 1.18 MiB (1%) 436
["sort", "reversed", "ThreadsX.QuickSort"] 986.803 μs (5%) 998.75 KiB (1%) 1871
["sort", "reversed", "ThreadsX.StableQuickSort"] 1.356 ms (5%) 1.36 MiB (1%) 1904
["sort", "sorted", "Base"] 606.302 μs (5%)
["sort", "sorted", "ThreadsX.MergeSort"] 799.302 μs (5%) 1.18 MiB (1%) 431
["sort", "sorted", "ThreadsX.QuickSort"] 1.004 ms (5%) 998.75 KiB (1%) 1871
["sort", "sorted", "ThreadsX.StableQuickSort"] 1.122 ms (5%) 1.36 MiB (1%) 1904
["unique", "rand(1:10, 1000000)", "base"] 7.796 ms (5%) 832 bytes (1%) 8
["unique", "rand(1:10, 1000000)", "tx"] 4.088 ms (5%) 50.97 KiB (1%) 881
["unique", "rand(1:1000, 1000000)", "base"] 7.197 ms (5%) 65.95 KiB (1%) 27
["unique", "rand(1:1000, 1000000)", "tx"] 4.346 ms (5%) 1.07 MiB (1%) 1186

Benchmark Group List

Here's a list of all the benchmark groups executed by this job:

  • ["findfirst", "0%"]
  • ["findfirst", "10%"]
  • ["findfirst", "20%"]
  • ["findfirst", "30%"]
  • ["findfirst", "40%"]
  • ["findfirst", "50%"]
  • ["foreach", "base"]
  • ["foreach", "broadcast"]
  • ["foreach", "tx"]
  • ["foreach_seq", "base"]
  • ["foreach_seq", "tx"]
  • ["foreach_seq_double", "cartesian"]
  • ["foreach_seq_double", "cartesian", "tx"]
  • ["foreach_seq_double", "linear"]
  • ["foreach_seq_double", "linear", "tx"]
  • ["foreach_seq_sum_many", ":nvecs => 8"]
  • ["foreach_seq_sum_many", ":nvecs => 8", "tx"]
  • ["sort", "F64 (narrow)"]
  • ["sort", "F64 (wide)"]
  • ["sort", "I64 (narrow)"]
  • ["sort", "I64 (wide)"]
  • ["sort", "reversed"]
  • ["sort", "sorted"]
  • ["unique", "rand(1:10, 1000000)"]
  • ["unique", "rand(1:1000, 1000000)"]

Julia versioninfo

Julia Version 1.4.0
Commit b8e9a9ecc6 (2020-03-21 16:36 UTC)
Platform Info:
  OS: Linux (x86_64-pc-linux-gnu)
      Ubuntu 18.04.4 LTS
  uname: Linux 5.0.0-1032-azure #34-Ubuntu SMP Mon Feb 10 19:37:25 UTC 2020 x86_64 x86_64
  CPU: Intel(R) Xeon(R) CPU E5-2673 v4 @ 2.30GHz: 
              speed         user         nice          sys         idle          irq
       #1  2294 MHz      64991 s          0 s       2982 s      49923 s          0 s
       #2  2294 MHz      82060 s          0 s       3543 s      32317 s          0 s
       
  Memory: 6.782737731933594 GB (2980.921875 MB free)
  Uptime: 1196.0 sec
  Load Avg:  1.26708984375  1.36279296875  1.04052734375
  WORD_SIZE: 64
  LIBM: libopenlibm
  LLVM: libLLVM-8.0.1 (ORCJIT, broadwell)

Runtime information

Runtime Info
BLAS #threads 2
BLAS.vendor() openblas64
Sys.CPU_THREADS 2

lscpu output:

Architecture:        x86_64
CPU op-mode(s):      32-bit, 64-bit
Byte Order:          Little Endian
CPU(s):              2
On-line CPU(s) list: 0,1
Thread(s) per core:  1
Core(s) per socket:  2
Socket(s):           1
NUMA node(s):        1
Vendor ID:           GenuineIntel
CPU family:          6
Model:               79
Model name:          Intel(R) Xeon(R) CPU E5-2673 v4 @ 2.30GHz
Stepping:            1
CPU MHz:             2294.687
BogoMIPS:            4589.37
Hypervisor vendor:   Microsoft
Virtualization type: full
L1d cache:           32K
L1i cache:           32K
L2 cache:            256K
L3 cache:            51200K
NUMA node0 CPU(s):   0,1
Flags:               fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss ht syscall nx pdpe1gb rdtscp lm constant_tsc rep_good nopl xtopology cpuid pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch invpcid_single pti fsgsbase bmi1 hle avx2 smep bmi2 erms invpcid rtm rdseed adx smap xsaveopt md_clear
Cpu Property Value
Brand Intel(R) Xeon(R) CPU E5-2673 v4 @ 2.30GHz
Vendor :Intel
Architecture :Broadwell
Model Family: 0x06, Model: 0x4f, Stepping: 0x01, Type: 0x00
Cores 2 physical cores, 2 logical cores (on executing CPU)
No Hyperthreading detected
Clock Frequencies Not supported by CPU
Data Cache Level 1:3 : (32, 256, 51200) kbytes
64 byte cache line size
Address Size 48 bits virtual, 44 bits physical
SIMD 256 bit = 32 byte max. SIMD vector size
Time Stamp Counter TSC is accessible via rdtsc
TSC increased at every clock cycle (non-invariant TSC)
Perf. Monitoring Performance Monitoring Counters (PMC) are not supported
Hypervisor Yes, Microsoft

@mergify mergify bot merged commit b69c3f3 into master Mar 29, 2020
@mergify mergify bot deleted the docs branch March 29, 2020 07:30
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@mergify mergify[bot] mergify[bot] approved these changes

Assignees
No one assigned
Labels
ready-to-merge:squash
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@tkf @codecov-io