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

issue 492: Create distribution that returns <: Real #494

Closed
wants to merge 7 commits into from
Closed

issue 492: Create distribution that returns <: Real #494

wants to merge 7 commits into from

Conversation

SamuelBrand1
Copy link
Collaborator

@SamuelBrand1 SamuelBrand1 commented Oct 10, 2024 •
edited
Loading

This draft PR introduces RealUnivariateDistribution with an eltype method

Base.eltype(::Type{<:Sampleable{F,RealValued}}) where {F} = Real

This means that rand is no longer hard encoded to expect either Float64 or Int values.

Flagging for @seabbs. I want to see the CI and benchmarks before possible merge.

NB: This branch is not using the change in CI from #491 ... which was accidental but actually might be a good test case.

@SamuelBrand1 SamuelBrand1 linked an issue Oct 10, 2024 that may be closed by this pull request
Change SafePoisson and SafeNegativeBinomial to return value from rand calls #492
Open
@github-actions GitHub Actions
Copy link
Contributor

Try this Pull Request!

Open Julia and type:

import Pkg
Pkg.activate(temp=true)
Pkg.add(url="https://github.com/CDCgov/Rt-without-renewal", rev="492-rand-ret-type", subdir="EpiAware")
using EpiAware

@github-actions GitHub Actions
Copy link
Contributor

Benchmark result

Judge result

Benchmark Report for /home/runner/work/Rt-without-renewal/Rt-without-renewal

Job Properties

  • Time of benchmarks:
    • Target: 10 Oct 2024 - 15:37
    • Baseline: 10 Oct 2024 - 16:02
  • Package commits:
    • Target: 022db3
    • Baseline: 46b751
  • Julia commits:
    • Target: 501a4f
    • Baseline: 501a4f
  • Julia command flags:
    • Target: None
    • Baseline: None
  • Environment variables:
    • Target: None
    • Baseline: None

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
["EpiInfModels", "DirectInfections", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 1.06 (5%) ❌ 1.00 (1%)
["EpiInfModels", "DirectInfections", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 0.95 (5%) ✅ 1.00 (1%)
["EpiInfModels", "ExpGrowthRate", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "linked"] 1.07 (5%) ❌ 1.00 (1%)
["EpiInfModels", "ExpGrowthRate", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 1.07 (5%) ❌ 1.00 (1%)
["EpiLatentModels", "AR", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 0.95 (5%) ✅ 1.00 (1%)
["EpiLatentModels", "ConcatLatentModels", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 0.94 (5%) ✅ 1.00 (1%)
["EpiLatentModels", "PrefixLatentModel", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 0.93 (5%) ✅ 1.00 (1%)
["EpiLatentModels", "PrefixLatentModel", "gradient", "ADTypes.AutoReverseDiff()", "standard"] 0.94 (5%) ✅ 1.00 (1%)
["EpiLatentModels", "RandomWalk", "evaluation", "standard"] 1.05 (5%) ❌ 1.00 (1%)
["EpiLatentModels", "RandomWalk", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 0.95 (5%) ✅ 1.00 (1%)
["EpiLatentModels", "RandomWalk", "gradient", "ADTypes.AutoReverseDiff()", "standard"] 0.94 (5%) ✅ 1.00 (1%)
["EpiLatentModels", "RecordExpectedLatent", "evaluation", "standard"] 1.09 (5%) ❌ 1.00 (1%)
["EpiLatentModels", "RecordExpectedLatent", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 1.05 (5%) ❌ 1.00 (1%)
["EpiLatentModels", "RecordExpectedLatent", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 0.93 (5%) ✅ 1.00 (1%)
["EpiLatentModels", "TransformLatentModel", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "linked"] 1.15 (5%) ❌ 1.00 (1%)
["EpiLatentModels", "TransformLatentModel", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 1.12 (5%) ❌ 1.00 (1%)
["EpiLatentModels", "broadcast_dayofweek", "gradient", "ADTypes.AutoReverseDiff()", "standard"] 0.95 (5%) ✅ 1.00 (1%)
["EpiLatentModels", "broadcast_weekly", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 0.90 (5%) ✅ 1.00 (1%)
["EpiLatentModels", "broadcast_weekly", "gradient", "ADTypes.AutoReverseDiff()", "standard"] 0.95 (5%) ✅ 1.00 (1%)
["EpiObsModels", "LatentDelay", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "linked"] 0.95 (5%) ✅ 1.00 (1%)
["EpiObsModels", "LatentDelay", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 0.94 (5%) ✅ 1.00 (1%)
["EpiObsModels", "observation_error", "missing obs", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "linked"] 1.24 (5%) ❌ 1.00 (1%)
["EpiObsModels", "observation_error", "missing obs", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 1.25 (5%) ❌ 1.00 (1%)
["EpiObsModels", "observation_error", "no missing obs", "evaluation", "linked"] 1.09 (5%) ❌ 1.00 (1%)
["EpiObsModels", "observation_error", "no missing obs", "evaluation", "standard"] 1.09 (5%) ❌ 1.00 (1%)
["EpiObsModels", "observation_error", "no missing obs", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "linked"] 1.25 (5%) ❌ 1.00 (1%)
["EpiObsModels", "observation_error", "no missing obs", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 1.26 (5%) ❌ 1.00 (1%)
["EpiObsModels", "observation_error", "partially missing obs", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "linked"] 1.23 (5%) ❌ 1.00 (1%)
["EpiObsModels", "observation_error", "partially missing obs", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 1.22 (5%) ❌ 1.00 (1%)

Benchmark Group List

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

  • ["EpiAwareUtils"]
  • ["EpiInfModels", "DirectInfections", "evaluation"]
  • ["EpiInfModels", "DirectInfections", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiInfModels", "DirectInfections", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiInfModels", "DirectInfections", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiInfModels", "ExpGrowthRate", "evaluation"]
  • ["EpiInfModels", "ExpGrowthRate", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiInfModels", "ExpGrowthRate", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiInfModels", "ExpGrowthRate", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiLatentModels", "AR", "evaluation"]
  • ["EpiLatentModels", "AR", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiLatentModels", "AR", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiLatentModels", "AR", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiLatentModels", "BroadcastLatentModel", "evaluation"]
  • ["EpiLatentModels", "BroadcastLatentModel", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiLatentModels", "BroadcastLatentModel", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiLatentModels", "BroadcastLatentModel", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiLatentModels", "CombineLatentModels", "evaluation"]
  • ["EpiLatentModels", "CombineLatentModels", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiLatentModels", "CombineLatentModels", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiLatentModels", "CombineLatentModels", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiLatentModels", "ConcatLatentModels", "evaluation"]
  • ["EpiLatentModels", "ConcatLatentModels", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiLatentModels", "ConcatLatentModels", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiLatentModels", "ConcatLatentModels", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiLatentModels", "DiffLatentModel", "evaluation"]
  • ["EpiLatentModels", "DiffLatentModel", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiLatentModels", "DiffLatentModel", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiLatentModels", "DiffLatentModel", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiLatentModels", "HierarchicalNormal", "evaluation"]
  • ["EpiLatentModels", "HierarchicalNormal", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiLatentModels", "HierarchicalNormal", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiLatentModels", "HierarchicalNormal", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiLatentModels", "Intercept", "evaluation"]
  • ["EpiLatentModels", "Intercept", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiLatentModels", "Intercept", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiLatentModels", "Intercept", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiLatentModels", "PrefixLatentModel", "evaluation"]
  • ["EpiLatentModels", "PrefixLatentModel", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiLatentModels", "PrefixLatentModel", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiLatentModels", "PrefixLatentModel", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiLatentModels", "RandomWalk", "evaluation"]
  • ["EpiLatentModels", "RandomWalk", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiLatentModels", "RandomWalk", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiLatentModels", "RandomWalk", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiLatentModels", "RecordExpectedLatent", "evaluation"]
  • ["EpiLatentModels", "RecordExpectedLatent", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiLatentModels", "RecordExpectedLatent", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiLatentModels", "RecordExpectedLatent", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiLatentModels", "TransformLatentModel", "evaluation"]
  • ["EpiLatentModels", "TransformLatentModel", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiLatentModels", "TransformLatentModel", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiLatentModels", "TransformLatentModel", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiLatentModels", "broadcast_dayofweek", "evaluation"]
  • ["EpiLatentModels", "broadcast_dayofweek", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiLatentModels", "broadcast_dayofweek", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiLatentModels", "broadcast_dayofweek", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiLatentModels", "broadcast_weekly", "evaluation"]
  • ["EpiLatentModels", "broadcast_weekly", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiLatentModels", "broadcast_weekly", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiLatentModels", "broadcast_weekly", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiObsModels", "Ascertainment", "evaluation"]
  • ["EpiObsModels", "Ascertainment", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiObsModels", "Ascertainment", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiObsModels", "Ascertainment", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiObsModels", "LatentDelay", "evaluation"]
  • ["EpiObsModels", "LatentDelay", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiObsModels", "LatentDelay", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiObsModels", "LatentDelay", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiObsModels", "NegativeBinomialError", "evaluation"]
  • ["EpiObsModels", "NegativeBinomialError", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiObsModels", "NegativeBinomialError", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiObsModels", "NegativeBinomialError", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiObsModels", "PoissonError", "evaluation"]
  • ["EpiObsModels", "PoissonError", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiObsModels", "PoissonError", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiObsModels", "PoissonError", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiObsModels", "PrefixObservationModel", "evaluation"]
  • ["EpiObsModels", "PrefixObservationModel", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiObsModels", "PrefixObservationModel", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiObsModels", "PrefixObservationModel", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiObsModels", "StackObservationModels", "evaluation"]
  • ["EpiObsModels", "StackObservationModels", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiObsModels", "StackObservationModels", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiObsModels", "StackObservationModels", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiObsModels", "ascertainment_dayofweek", "evaluation"]
  • ["EpiObsModels", "ascertainment_dayofweek", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiObsModels", "ascertainment_dayofweek", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiObsModels", "ascertainment_dayofweek", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiObsModels", "observation_error", "missing obs", "evaluation"]
  • ["EpiObsModels", "observation_error", "missing obs", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiObsModels", "observation_error", "missing obs", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiObsModels", "observation_error", "missing obs", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiObsModels", "observation_error", "no missing obs", "evaluation"]
  • ["EpiObsModels", "observation_error", "no missing obs", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiObsModels", "observation_error", "no missing obs", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiObsModels", "observation_error", "no missing obs", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiObsModels", "observation_error", "partially missing obs", "evaluation"]
  • ["EpiObsModels", "observation_error", "partially missing obs", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiObsModels", "observation_error", "partially missing obs", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiObsModels", "observation_error", "partially missing obs", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]

Julia versioninfo

Target

Julia Version 1.11.0
Commit 501a4f25c2b (2024-10-07 11:40 UTC)
Build Info:
  Official https://julialang.org/ release
Platform Info:
  OS: Linux (x86_64-linux-gnu)
      Ubuntu 22.04.5 LTS
  uname: Linux 6.5.0-1025-azure #26~22.04.1-Ubuntu SMP Thu Jul 11 22:33:04 UTC 2024 x86_64 x86_64
  CPU: AMD EPYC 7763 64-Core Processor: 
              speed         user         nice          sys         idle          irq
       #1     0 MHz       6348 s          0 s        531 s      14860 s          0 s
       #2     0 MHz       6163 s          0 s        425 s      15151 s          0 s
       #3     0 MHz       5617 s          0 s        483 s      15636 s          0 s
       #4     0 MHz       5355 s          0 s        456 s      15919 s          0 s
  Memory: 15.606491088867188 GB (13215.2734375 MB free)
  Uptime: 2180.25 sec
  Load Avg:  1.0  1.01  1.01
  WORD_SIZE: 64
  LLVM: libLLVM-16.0.6 (ORCJIT, znver3)
Threads: 1 default, 0 interactive, 1 GC (on 4 virtual cores)

Baseline

Julia Version 1.11.0
Commit 501a4f25c2b (2024-10-07 11:40 UTC)
Build Info:
  Official https://julialang.org/ release
Platform Info:
  OS: Linux (x86_64-linux-gnu)
      Ubuntu 22.04.5 LTS
  uname: Linux 6.5.0-1025-azure #26~22.04.1-Ubuntu SMP Thu Jul 11 22:33:04 UTC 2024 x86_64 x86_64
  CPU: AMD EPYC 7763 64-Core Processor: 
              speed         user         nice          sys         idle          irq
       #1     0 MHz      10405 s          0 s        885 s      25616 s          0 s
       #2     0 MHz       9604 s          0 s        698 s      26601 s          0 s
       #3     0 MHz       8523 s          0 s        718 s      27661 s          0 s
       #4     0 MHz       9453 s          0 s        803 s      26644 s          0 s
  Memory: 15.606491088867188 GB (13007.9375 MB free)
  Uptime: 3699.53 sec
  Load Avg:  1.05  1.03  1.0
  WORD_SIZE: 64
  LLVM: libLLVM-16.0.6 (ORCJIT, znver3)
Threads: 1 default, 0 interactive, 1 GC (on 4 virtual cores)

Target result

Benchmark Report for /home/runner/work/Rt-without-renewal/Rt-without-renewal

Job Properties

  • Time of benchmark: 10 Oct 2024 - 15:37
  • Package commit: 022db3
  • Julia commit: 501a4f
  • Julia command flags: None
  • Environment variables: None

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
["EpiAwareUtils", "censored_pmf"] 2.087 μs (5%) 416 bytes (1%) 10
["EpiInfModels", "DirectInfections", "evaluation", "linked"] 288.646 ns (5%) 464 bytes (1%) 10
["EpiInfModels", "DirectInfections", "evaluation", "standard"] 282.309 ns (5%) 464 bytes (1%) 10
["EpiInfModels", "DirectInfections", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "linked"] 438.457 ns (5%) 816 bytes (1%) 18
["EpiInfModels", "DirectInfections", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 435.894 ns (5%) 816 bytes (1%) 18
["EpiInfModels", "DirectInfections", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 10.059 μs (5%) 5.55 KiB (1%) 125
["EpiInfModels", "DirectInfections", "gradient", "ADTypes.AutoReverseDiff()", "standard"] 10.069 μs (5%) 5.55 KiB (1%) 125
["EpiInfModels", "DirectInfections", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "linked"] 486.224 ns (5%) 256 bytes (1%) 7
["EpiInfModels", "DirectInfections", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 482.922 ns (5%) 256 bytes (1%) 7
["EpiInfModels", "ExpGrowthRate", "evaluation", "linked"] 184.457 ns (5%) 288 bytes (1%) 8
["EpiInfModels", "ExpGrowthRate", "evaluation", "standard"] 176.416 ns (5%) 288 bytes (1%) 8
["EpiInfModels", "ExpGrowthRate", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "linked"] 293.585 ns (5%) 544 bytes (1%) 15
["EpiInfModels", "ExpGrowthRate", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 286.520 ns (5%) 544 bytes (1%) 15
["EpiInfModels", "ExpGrowthRate", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 10.119 μs (5%) 5.53 KiB (1%) 124
["EpiInfModels", "ExpGrowthRate", "gradient", "ADTypes.AutoReverseDiff()", "standard"] 10.049 μs (5%) 5.53 KiB (1%) 124
["EpiInfModels", "ExpGrowthRate", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "linked"] 517.531 ns (5%) 256 bytes (1%) 7
["EpiInfModels", "ExpGrowthRate", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 513.192 ns (5%) 256 bytes (1%) 7
["EpiLatentModels", "AR", "evaluation", "linked"] 4.796 μs (5%) 4.19 KiB (1%) 91
["EpiLatentModels", "AR", "evaluation", "standard"] 4.461 μs (5%) 3.20 KiB (1%) 84
["EpiLatentModels", "AR", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "linked"] 6.147 μs (5%) 12.20 KiB (1%) 108
["EpiLatentModels", "AR", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 5.719 μs (5%) 10.64 KiB (1%) 97
["EpiLatentModels", "AR", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 125.285 μs (5%) 54.77 KiB (1%) 1247
["EpiLatentModels", "AR", "gradient", "ADTypes.AutoReverseDiff()", "standard"] 82.885 μs (5%) 40.47 KiB (1%) 917
["EpiLatentModels", "AR", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "linked"] 16.922 μs (5%) 8.33 KiB (1%) 257
["EpiLatentModels", "AR", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 15.669 μs (5%) 7.20 KiB (1%) 221
["EpiLatentModels", "BroadcastLatentModel", "evaluation", "linked"] 934.846 ns (5%) 2.75 KiB (1%) 34
["EpiLatentModels", "BroadcastLatentModel", "evaluation", "standard"] 723.694 ns (5%) 1.88 KiB (1%) 30
["EpiLatentModels", "BroadcastLatentModel", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "linked"] 1.260 μs (5%) 4.83 KiB (1%) 45
["EpiLatentModels", "BroadcastLatentModel", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 1.097 μs (5%) 3.95 KiB (1%) 41
["EpiLatentModels", "BroadcastLatentModel", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 47.018 μs (5%) 23.62 KiB (1%) 461
["EpiLatentModels", "BroadcastLatentModel", "gradient", "ADTypes.AutoReverseDiff()", "standard"] 30.477 μs (5%) 16.55 KiB (1%) 353
["EpiLatentModels", "BroadcastLatentModel", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "linked"] 2.885 μs (5%) 1.02 KiB (1%) 32
["EpiLatentModels", "BroadcastLatentModel", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 2.674 μs (5%) 1.02 KiB (1%) 32
["EpiLatentModels", "CombineLatentModels", "evaluation", "linked"] 22.162 μs (5%) 45.67 KiB (1%) 383
["EpiLatentModels", "CombineLatentModels", "evaluation", "standard"] 19.005 μs (5%) 31.16 KiB (1%) 339
["EpiLatentModels", "CombineLatentModels", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "linked"] 48.401 μs (5%) 105.72 KiB (1%) 805
["EpiLatentModels", "CombineLatentModels", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 41.468 μs (5%) 75.84 KiB (1%) 709
["EpiLatentModels", "CombineLatentModels", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 159.348 μs (5%) 100.33 KiB (1%) 1607
["EpiLatentModels", "CombineLatentModels", "gradient", "ADTypes.AutoReverseDiff()", "standard"] 112.551 μs (5%) 72.50 KiB (1%) 1240
["EpiLatentModels", "CombineLatentModels", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "linked"] 17.523 μs (5%) 8.44 KiB (1%) 258
["EpiLatentModels", "CombineLatentModels", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 16.190 μs (5%) 7.31 KiB (1%) 222
["EpiLatentModels", "ConcatLatentModels", "evaluation", "linked"] 42.630 μs (5%) 37.27 KiB (1%) 496
["EpiLatentModels", "ConcatLatentModels", "evaluation", "standard"] 40.255 μs (5%) 28.83 KiB (1%) 466
["EpiLatentModels", "ConcatLatentModels", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "linked"] 44.112 μs (5%) 40.86 KiB (1%) 511
["EpiLatentModels", "ConcatLatentModels", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 41.548 μs (5%) 32.42 KiB (1%) 481
["EpiLatentModels", "ConcatLatentModels", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 116.979 μs (5%) 62.78 KiB (1%) 1021
["EpiLatentModels", "ConcatLatentModels", "gradient", "ADTypes.AutoReverseDiff()", "standard"] 96.521 μs (5%) 49.59 KiB (1%) 888
["EpiLatentModels", "ConcatLatentModels", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "linked"] 5.059 μs (5%) 2.20 KiB (1%) 60
["EpiLatentModels", "ConcatLatentModels", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 4.845 μs (5%) 2.20 KiB (1%) 60
["EpiLatentModels", "DiffLatentModel", "evaluation", "linked"] 8.005 μs (5%) 5.55 KiB (1%) 102
["EpiLatentModels", "DiffLatentModel", "evaluation", "standard"] 7.561 μs (5%) 3.86 KiB (1%) 96
["EpiLatentModels", "DiffLatentModel", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "linked"] 9.067 μs (5%) 13.92 KiB (1%) 115
["EpiLatentModels", "DiffLatentModel", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 8.556 μs (5%) 12.23 KiB (1%) 109
["EpiLatentModels", "DiffLatentModel", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 86.091 μs (5%) 39.72 KiB (1%) 833
["EpiLatentModels", "DiffLatentModel", "gradient", "ADTypes.AutoReverseDiff()", "standard"] 67.756 μs (5%) 33.28 KiB (1%) 724
["EpiLatentModels", "DiffLatentModel", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "linked"] 6.494 μs (5%) 2.27 KiB (1%) 59
["EpiLatentModels", "DiffLatentModel", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 6.296 μs (5%) 2.27 KiB (1%) 59
["EpiLatentModels", "HierarchicalNormal", "evaluation", "linked"] 392.025 ns (5%) 1.03 KiB (1%) 14
["EpiLatentModels", "HierarchicalNormal", "evaluation", "standard"] 303.098 ns (5%) 896 bytes (1%) 13
["EpiLatentModels", "HierarchicalNormal", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "linked"] 991.800 ns (5%) 5.12 KiB (1%) 23
["EpiLatentModels", "HierarchicalNormal", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 884.500 ns (5%) 4.97 KiB (1%) 22
["EpiLatentModels", "HierarchicalNormal", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 43.702 μs (5%) 19.03 KiB (1%) 381
["EpiLatentModels", "HierarchicalNormal", "gradient", "ADTypes.AutoReverseDiff()", "standard"] 27.561 μs (5%) 14.17 KiB (1%) 278
["EpiLatentModels", "HierarchicalNormal", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "linked"] 1.088 μs (5%) 608 bytes (1%) 9
["EpiLatentModels", "HierarchicalNormal", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 913.892 ns (5%) 608 bytes (1%) 9
["EpiLatentModels", "Intercept", "evaluation", "linked"] 223.074 ns (5%) 400 bytes (1%) 10
["EpiLatentModels", "Intercept", "evaluation", "standard"] 212.379 ns (5%) 400 bytes (1%) 10
["EpiLatentModels", "Intercept", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "linked"] 306.452 ns (5%) 704 bytes (1%) 17
["EpiLatentModels", "Intercept", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 295.576 ns (5%) 704 bytes (1%) 17
["EpiLatentModels", "Intercept", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 5.333 μs (5%) 3.62 KiB (1%) 87
["EpiLatentModels", "Intercept", "gradient", "ADTypes.AutoReverseDiff()", "standard"] 5.293 μs (5%) 3.62 KiB (1%) 87
["EpiLatentModels", "Intercept", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "linked"] 402.905 ns (5%) 208 bytes (1%) 4
["EpiLatentModels", "Intercept", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 408.920 ns (5%) 208 bytes (1%) 4
["EpiLatentModels", "PrefixLatentModel", "evaluation", "linked"] 1.837 μs (5%) 3.56 KiB (1%) 40
["EpiLatentModels", "PrefixLatentModel", "evaluation", "standard"] 1.634 μs (5%) 3.09 KiB (1%) 37
["EpiLatentModels", "PrefixLatentModel", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "linked"] 2.550 μs (5%) 7.66 KiB (1%) 49
["EpiLatentModels", "PrefixLatentModel", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 2.318 μs (5%) 7.19 KiB (1%) 46
["EpiLatentModels", "PrefixLatentModel", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 46.397 μs (5%) 21.42 KiB (1%) 406
["EpiLatentModels", "PrefixLatentModel", "gradient", "ADTypes.AutoReverseDiff()", "standard"] 29.956 μs (5%) 16.25 KiB (1%) 301
["EpiLatentModels", "PrefixLatentModel", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "linked"] 1.083 μs (5%) 608 bytes (1%) 9
["EpiLatentModels", "PrefixLatentModel", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 915.028 ns (5%) 608 bytes (1%) 9
["EpiLatentModels", "RandomWalk", "evaluation", "linked"] 603.850 ns (5%) 1.72 KiB (1%) 21
["EpiLatentModels", "RandomWalk", "evaluation", "standard"] 461.773 ns (5%) 1.28 KiB (1%) 19
["EpiLatentModels", "RandomWalk", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "linked"] 1.473 μs (5%) 8.11 KiB (1%) 32
["EpiLatentModels", "RandomWalk", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 1.267 μs (5%) 7.67 KiB (1%) 30
["EpiLatentModels", "RandomWalk", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 51.807 μs (5%) 25.52 KiB (1%) 504
["EpiLatentModels", "RandomWalk", "gradient", "ADTypes.AutoReverseDiff()", "standard"] 35.427 μs (5%) 20.33 KiB (1%) 399
["EpiLatentModels", "RandomWalk", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "linked"] 3.466 μs (5%) 1.33 KiB (1%) 32
["EpiLatentModels", "RandomWalk", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 3.279 μs (5%) 1.33 KiB (1%) 32
["EpiLatentModels", "RecordExpectedLatent", "evaluation", "linked"] 575.193 ns (5%) 1.25 KiB (1%) 20
["EpiLatentModels", "RecordExpectedLatent", "evaluation", "standard"] 448.761 ns (5%) 960 bytes (1%) 18
["EpiLatentModels", "RecordExpectedLatent", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "linked"] 700.965 ns (5%) 1.78 KiB (1%) 29
["EpiLatentModels", "RecordExpectedLatent", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 579.220 ns (5%) 1.47 KiB (1%) 27
["EpiLatentModels", "RecordExpectedLatent", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 43.051 μs (5%) 18.31 KiB (1%) 387
["EpiLatentModels", "RecordExpectedLatent", "gradient", "ADTypes.AutoReverseDiff()", "standard"] 27.121 μs (5%) 13.30 KiB (1%) 283
["EpiLatentModels", "RecordExpectedLatent", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "linked"] 1.022 μs (5%) 352 bytes (1%) 9
["EpiLatentModels", "RecordExpectedLatent", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 834.429 ns (5%) 352 bytes (1%) 9
["EpiLatentModels", "TransformLatentModel", "evaluation", "linked"] 269.628 ns (5%) 448 bytes (1%) 12
["EpiLatentModels", "TransformLatentModel", "evaluation", "standard"] 259.946 ns (5%) 448 bytes (1%) 12
["EpiLatentModels", "TransformLatentModel", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "linked"] 402.171 ns (5%) 768 bytes (1%) 19
["EpiLatentModels", "TransformLatentModel", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 381.866 ns (5%) 768 bytes (1%) 19
["EpiLatentModels", "TransformLatentModel", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 5.597 μs (5%) 3.93 KiB (1%) 95
["EpiLatentModels", "TransformLatentModel", "gradient", "ADTypes.AutoReverseDiff()", "standard"] 5.532 μs (5%) 3.93 KiB (1%) 95
["EpiLatentModels", "TransformLatentModel", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "linked"] 489.790 ns (5%) 160 bytes (1%) 4
["EpiLatentModels", "TransformLatentModel", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 487.323 ns (5%) 160 bytes (1%) 4
["EpiLatentModels", "broadcast_dayofweek", "evaluation", "linked"] 1.203 μs (5%) 3.73 KiB (1%) 43
["EpiLatentModels", "broadcast_dayofweek", "evaluation", "standard"] 886.182 ns (5%) 2.42 KiB (1%) 37
["EpiLatentModels", "broadcast_dayofweek", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "linked"] 2.138 μs (5%) 9.80 KiB (1%) 54
["EpiLatentModels", "broadcast_dayofweek", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 1.817 μs (5%) 8.48 KiB (1%) 48
["EpiLatentModels", "broadcast_dayofweek", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 68.248 μs (5%) 34.69 KiB (1%) 702
["EpiLatentModels", "broadcast_dayofweek", "gradient", "ADTypes.AutoReverseDiff()", "standard"] 50.836 μs (5%) 28.62 KiB (1%) 593
["EpiLatentModels", "broadcast_dayofweek", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "linked"] 4.826 μs (5%) 1.23 KiB (1%) 32
["EpiLatentModels", "broadcast_dayofweek", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 4.776 μs (5%) 1.23 KiB (1%) 32
["EpiLatentModels", "broadcast_weekly", "evaluation", "linked"] 8.342 μs (5%) 5.78 KiB (1%) 113
["EpiLatentModels", "broadcast_weekly", "evaluation", "standard"] 7.812 μs (5%) 3.95 KiB (1%) 103
["EpiLatentModels", "broadcast_weekly", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "linked"] 8.806 μs (5%) 8.98 KiB (1%) 130
["EpiLatentModels", "broadcast_weekly", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 8.292 μs (5%) 6.83 KiB (1%) 116
["EpiLatentModels", "broadcast_weekly", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 99.917 μs (5%) 42.25 KiB (1%) 861
["EpiLatentModels", "broadcast_weekly", "gradient", "ADTypes.AutoReverseDiff()", "standard"] 64.501 μs (5%) 29.61 KiB (1%) 608
["EpiLatentModels", "broadcast_weekly", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "linked"] 5.233 μs (5%) 1.83 KiB (1%) 57
["EpiLatentModels", "broadcast_weekly", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 4.571 μs (5%) 1.70 KiB (1%) 53
["EpiObsModels", "Ascertainment", "evaluation", "linked"] 3.335 μs (5%) 3.61 KiB (1%) 64
["EpiObsModels", "Ascertainment", "evaluation", "standard"] 3.245 μs (5%) 3.61 KiB (1%) 64
["EpiObsModels", "Ascertainment", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "linked"] 4.088 μs (5%) 3.95 KiB (1%) 73
["EpiObsModels", "Ascertainment", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 4.009 μs (5%) 3.95 KiB (1%) 73
["EpiObsModels", "Ascertainment", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 75.762 μs (5%) 38.80 KiB (1%) 919
["EpiObsModels", "Ascertainment", "gradient", "ADTypes.AutoReverseDiff()", "standard"] 60.153 μs (5%) 34.05 KiB (1%) 816
["EpiObsModels", "Ascertainment", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "linked"] 5.722 μs (5%) 96 bytes (1%) 3
["EpiObsModels", "Ascertainment", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 5.554 μs (5%) 96 bytes (1%) 3
["EpiObsModels", "LatentDelay", "evaluation", "linked"] 14.537 μs (5%) 22.08 KiB (1%) 412
["EpiObsModels", "LatentDelay", "evaluation", "standard"] 14.617 μs (5%) 22.08 KiB (1%) 412
["EpiObsModels", "LatentDelay", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "linked"] 18.143 μs (5%) 22.30 KiB (1%) 419
["EpiObsModels", "LatentDelay", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 17.784 μs (5%) 22.30 KiB (1%) 419
["EpiObsModels", "LatentDelay", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 530.554 μs (5%) 293.05 KiB (1%) 7011
["EpiObsModels", "LatentDelay", "gradient", "ADTypes.AutoReverseDiff()", "standard"] 506.738 μs (5%) 288.30 KiB (1%) 6908
["EpiObsModels", "LatentDelay", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "linked"] 50.715 μs (5%) 96 bytes (1%) 3
["EpiObsModels", "LatentDelay", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 50.274 μs (5%) 96 bytes (1%) 3
["EpiObsModels", "NegativeBinomialError", "evaluation", "linked"] 1.139 μs (5%) 400 bytes (1%) 10
["EpiObsModels", "NegativeBinomialError", "evaluation", "standard"] 1.089 μs (5%) 400 bytes (1%) 10
["EpiObsModels", "NegativeBinomialError", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "linked"] 1.667 μs (5%) 624 bytes (1%) 17
["EpiObsModels", "NegativeBinomialError", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 1.602 μs (5%) 624 bytes (1%) 17
["EpiObsModels", "NegativeBinomialError", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 71.003 μs (5%) 35.95 KiB (1%) 903
["EpiObsModels", "NegativeBinomialError", "gradient", "ADTypes.AutoReverseDiff()", "standard"] 56.245 μs (5%) 31.20 KiB (1%) 800
["EpiObsModels", "NegativeBinomialError", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "linked"] 5.777 μs (5%) 96 bytes (1%) 3
["EpiObsModels", "NegativeBinomialError", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 5.479 μs (5%) 96 bytes (1%) 3
["EpiObsModels", "PoissonError", "evaluation", "linked"] 1.409 μs (5%) 1.83 KiB (1%) 30
["EpiObsModels", "PoissonError", "evaluation", "standard"] 1.065 μs (5%) 1.47 KiB (1%) 26
["EpiObsModels", "PoissonError", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "linked"] 3.272 μs (5%) 7.78 KiB (1%) 43
["EpiObsModels", "PoissonError", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 2.530 μs (5%) 4.70 KiB (1%) 35
["EpiObsModels", "PoissonError", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 164.578 μs (5%) 86.44 KiB (1%) 1870
["EpiObsModels", "PoissonError", "gradient", "ADTypes.AutoReverseDiff()", "standard"] 45.876 μs (5%) 29.38 KiB (1%) 727
["EpiObsModels", "PoissonError", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "linked"] 6.077 μs (5%) 176 bytes (1%) 3
["EpiObsModels", "PoissonError", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 4.075 μs (5%) 176 bytes (1%) 3
["EpiObsModels", "PrefixObservationModel", "evaluation", "linked"] 1.692 μs (5%) 1.56 KiB (1%) 34
["EpiObsModels", "PrefixObservationModel", "evaluation", "standard"] 1.614 μs (5%) 1.56 KiB (1%) 34
["EpiObsModels", "PrefixObservationModel", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "linked"] 1.873 μs (5%) 1.78 KiB (1%) 41
["EpiObsModels", "PrefixObservationModel", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 1.804 μs (5%) 1.78 KiB (1%) 41
["EpiObsModels", "PrefixObservationModel", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 26.549 μs (5%) 12.59 KiB (1%) 290
["EpiObsModels", "PrefixObservationModel", "gradient", "ADTypes.AutoReverseDiff()", "standard"] 12.954 μs (5%) 7.84 KiB (1%) 187
["EpiObsModels", "PrefixObservationModel", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "linked"] 1.123 μs (5%) 96 bytes (1%) 3
["EpiObsModels", "PrefixObservationModel", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 974.643 ns (5%) 96 bytes (1%) 3
["EpiObsModels", "StackObservationModels", "evaluation", "linked"] 7.051 μs (5%) 5.81 KiB (1%) 117
["EpiObsModels", "StackObservationModels", "evaluation", "standard"] 7.003 μs (5%) 5.81 KiB (1%) 117
["EpiObsModels", "StackObservationModels", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "linked"] 7.812 μs (5%) 6.16 KiB (1%) 126
["EpiObsModels", "StackObservationModels", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 7.720 μs (5%) 6.16 KiB (1%) 126
["EpiObsModels", "StackObservationModels", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 92.414 μs (5%) 49.09 KiB (1%) 1044
["EpiObsModels", "StackObservationModels", "gradient", "ADTypes.AutoReverseDiff()", "standard"] 73.037 μs (5%) 44.34 KiB (1%) 941
["EpiObsModels", "StackObservationModels", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "linked"] 6.164 μs (5%) 96 bytes (1%) 3
["EpiObsModels", "StackObservationModels", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 6.017 μs (5%) 96 bytes (1%) 3
["EpiObsModels", "ascertainment_dayofweek", "evaluation", "linked"] 4.068 μs (5%) 9.12 KiB (1%) 101
["EpiObsModels", "ascertainment_dayofweek", "evaluation", "standard"] 3.572 μs (5%) 7.88 KiB (1%) 93
["EpiObsModels", "ascertainment_dayofweek", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "linked"] 5.841 μs (5%) 16.25 KiB (1%) 112
["EpiObsModels", "ascertainment_dayofweek", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 5.415 μs (5%) 15.00 KiB (1%) 104
["EpiObsModels", "ascertainment_dayofweek", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 104.696 μs (5%) 59.86 KiB (1%) 1165
["EpiObsModels", "ascertainment_dayofweek", "gradient", "ADTypes.AutoReverseDiff()", "standard"] 88.546 μs (5%) 53.91 KiB (1%) 1055
["EpiObsModels", "ascertainment_dayofweek", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "linked"] 5.440 μs (5%) 496 bytes (1%) 9
["EpiObsModels", "ascertainment_dayofweek", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 5.298 μs (5%) 496 bytes (1%) 9
["EpiObsModels", "observation_error", "missing obs", "evaluation", "linked"] 1.465 μs (5%) 3.05 KiB (1%) 38
["EpiObsModels", "observation_error", "missing obs", "evaluation", "standard"] 924.088 ns (5%) 1.48 KiB (1%) 28
["EpiObsModels", "observation_error", "missing obs", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "linked"] 1.814 μs (5%) 4.11 KiB (1%) 48
["EpiObsModels", "observation_error", "missing obs", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 1.259 μs (5%) 2.55 KiB (1%) 38
["EpiObsModels", "observation_error", "missing obs", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 38.933 μs (5%) 24.38 KiB (1%) 498
["EpiObsModels", "observation_error", "missing obs", "gradient", "ADTypes.AutoReverseDiff()", "standard"] 21.781 μs (5%) 17.39 KiB (1%) 366
["EpiObsModels", "observation_error", "missing obs", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "linked"] 2.735 μs (5%) 144 bytes (1%) 3
["EpiObsModels", "observation_error", "missing obs", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 2.502 μs (5%) 144 bytes (1%) 3
["EpiObsModels", "observation_error", "no missing obs", "evaluation", "linked"] 469.573 ns (5%) 352 bytes (1%) 10
["EpiObsModels", "observation_error", "no missing obs", "evaluation", "standard"] 405.831 ns (5%) 352 bytes (1%) 10
["EpiObsModels", "observation_error", "no missing obs", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "linked"] 572.543 ns (5%) 576 bytes (1%) 17
["EpiObsModels", "observation_error", "no missing obs", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 508.933 ns (5%) 576 bytes (1%) 17
["EpiObsModels", "observation_error", "no missing obs", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 31.469 μs (5%) 18.34 KiB (1%) 418
["EpiObsModels", "observation_error", "no missing obs", "gradient", "ADTypes.AutoReverseDiff()", "standard"] 16.872 μs (5%) 12.92 KiB (1%) 296
["EpiObsModels", "observation_error", "no missing obs", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "linked"] 2.372 μs (5%) 96 bytes (1%) 3
["EpiObsModels", "observation_error", "no missing obs", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 2.038 μs (5%) 96 bytes (1%) 3
["EpiObsModels", "observation_error", "partially missing obs", "evaluation", "linked"] 29.035 μs (5%) 3.02 KiB (1%) 64
["EpiObsModels", "observation_error", "partially missing obs", "evaluation", "standard"] 28.854 μs (5%) 2.70 KiB (1%) 62
["EpiObsModels", "observation_error", "partially missing obs", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "linked"] 19.216 μs (5%) 2.73 KiB (1%) 51
["EpiObsModels", "observation_error", "partially missing obs", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 19.035 μs (5%) 2.42 KiB (1%) 49
["EpiObsModels", "observation_error", "partially missing obs", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 60.163 μs (5%) 24.08 KiB (1%) 525
["EpiObsModels", "observation_error", "partially missing obs", "gradient", "ADTypes.AutoReverseDiff()", "standard"] 40.605 μs (5%) 18.34 KiB (1%) 401
["EpiObsModels", "observation_error", "partially missing obs", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "linked"] 2.743 μs (5%) 112 bytes (1%) 3
["EpiObsModels", "observation_error", "partially missing obs", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 2.458 μs (5%) 112 bytes (1%) 3

Benchmark Group List

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

  • ["EpiAwareUtils"]
  • ["EpiInfModels", "DirectInfections", "evaluation"]
  • ["EpiInfModels", "DirectInfections", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiInfModels", "DirectInfections", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiInfModels", "DirectInfections", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiInfModels", "ExpGrowthRate", "evaluation"]
  • ["EpiInfModels", "ExpGrowthRate", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiInfModels", "ExpGrowthRate", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiInfModels", "ExpGrowthRate", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiLatentModels", "AR", "evaluation"]
  • ["EpiLatentModels", "AR", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiLatentModels", "AR", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiLatentModels", "AR", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiLatentModels", "BroadcastLatentModel", "evaluation"]
  • ["EpiLatentModels", "BroadcastLatentModel", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiLatentModels", "BroadcastLatentModel", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiLatentModels", "BroadcastLatentModel", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiLatentModels", "CombineLatentModels", "evaluation"]
  • ["EpiLatentModels", "CombineLatentModels", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiLatentModels", "CombineLatentModels", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiLatentModels", "CombineLatentModels", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiLatentModels", "ConcatLatentModels", "evaluation"]
  • ["EpiLatentModels", "ConcatLatentModels", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiLatentModels", "ConcatLatentModels", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiLatentModels", "ConcatLatentModels", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiLatentModels", "DiffLatentModel", "evaluation"]
  • ["EpiLatentModels", "DiffLatentModel", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiLatentModels", "DiffLatentModel", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiLatentModels", "DiffLatentModel", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiLatentModels", "HierarchicalNormal", "evaluation"]
  • ["EpiLatentModels", "HierarchicalNormal", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiLatentModels", "HierarchicalNormal", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiLatentModels", "HierarchicalNormal", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiLatentModels", "Intercept", "evaluation"]
  • ["EpiLatentModels", "Intercept", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiLatentModels", "Intercept", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiLatentModels", "Intercept", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiLatentModels", "PrefixLatentModel", "evaluation"]
  • ["EpiLatentModels", "PrefixLatentModel", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiLatentModels", "PrefixLatentModel", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiLatentModels", "PrefixLatentModel", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiLatentModels", "RandomWalk", "evaluation"]
  • ["EpiLatentModels", "RandomWalk", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiLatentModels", "RandomWalk", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiLatentModels", "RandomWalk", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiLatentModels", "RecordExpectedLatent", "evaluation"]
  • ["EpiLatentModels", "RecordExpectedLatent", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiLatentModels", "RecordExpectedLatent", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiLatentModels", "RecordExpectedLatent", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiLatentModels", "TransformLatentModel", "evaluation"]
  • ["EpiLatentModels", "TransformLatentModel", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiLatentModels", "TransformLatentModel", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiLatentModels", "TransformLatentModel", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiLatentModels", "broadcast_dayofweek", "evaluation"]
  • ["EpiLatentModels", "broadcast_dayofweek", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiLatentModels", "broadcast_dayofweek", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiLatentModels", "broadcast_dayofweek", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiLatentModels", "broadcast_weekly", "evaluation"]
  • ["EpiLatentModels", "broadcast_weekly", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiLatentModels", "broadcast_weekly", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiLatentModels", "broadcast_weekly", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiObsModels", "Ascertainment", "evaluation"]
  • ["EpiObsModels", "Ascertainment", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiObsModels", "Ascertainment", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiObsModels", "Ascertainment", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiObsModels", "LatentDelay", "evaluation"]
  • ["EpiObsModels", "LatentDelay", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiObsModels", "LatentDelay", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiObsModels", "LatentDelay", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiObsModels", "NegativeBinomialError", "evaluation"]
  • ["EpiObsModels", "NegativeBinomialError", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiObsModels", "NegativeBinomialError", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiObsModels", "NegativeBinomialError", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiObsModels", "PoissonError", "evaluation"]
  • ["EpiObsModels", "PoissonError", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiObsModels", "PoissonError", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiObsModels", "PoissonError", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiObsModels", "PrefixObservationModel", "evaluation"]
  • ["EpiObsModels", "PrefixObservationModel", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiObsModels", "PrefixObservationModel", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiObsModels", "PrefixObservationModel", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiObsModels", "StackObservationModels", "evaluation"]
  • ["EpiObsModels", "StackObservationModels", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiObsModels", "StackObservationModels", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiObsModels", "StackObservationModels", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiObsModels", "ascertainment_dayofweek", "evaluation"]
  • ["EpiObsModels", "ascertainment_dayofweek", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiObsModels", "ascertainment_dayofweek", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiObsModels", "ascertainment_dayofweek", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiObsModels", "observation_error", "missing obs", "evaluation"]
  • ["EpiObsModels", "observation_error", "missing obs", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiObsModels", "observation_error", "missing obs", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiObsModels", "observation_error", "missing obs", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiObsModels", "observation_error", "no missing obs", "evaluation"]
  • ["EpiObsModels", "observation_error", "no missing obs", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiObsModels", "observation_error", "no missing obs", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiObsModels", "observation_error", "no missing obs", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiObsModels", "observation_error", "partially missing obs", "evaluation"]
  • ["EpiObsModels", "observation_error", "partially missing obs", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiObsModels", "observation_error", "partially missing obs", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiObsModels", "observation_error", "partially missing obs", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]

Julia versioninfo

Julia Version 1.11.0
Commit 501a4f25c2b (2024-10-07 11:40 UTC)
Build Info:
  Official https://julialang.org/ release
Platform Info:
  OS: Linux (x86_64-linux-gnu)
      Ubuntu 22.04.5 LTS
  uname: Linux 6.5.0-1025-azure #26~22.04.1-Ubuntu SMP Thu Jul 11 22:33:04 UTC 2024 x86_64 x86_64
  CPU: AMD EPYC 7763 64-Core Processor: 
              speed         user         nice          sys         idle          irq
       #1     0 MHz       6348 s          0 s        531 s      14860 s          0 s
       #2     0 MHz       6163 s          0 s        425 s      15151 s          0 s
       #3     0 MHz       5617 s          0 s        483 s      15636 s          0 s
       #4     0 MHz       5355 s          0 s        456 s      15919 s          0 s
  Memory: 15.606491088867188 GB (13215.2734375 MB free)
  Uptime: 2180.25 sec
  Load Avg:  1.0  1.01  1.01
  WORD_SIZE: 64
  LLVM: libLLVM-16.0.6 (ORCJIT, znver3)
Threads: 1 default, 0 interactive, 1 GC (on 4 virtual cores)

Baseline result

Benchmark Report for /home/runner/work/Rt-without-renewal/Rt-without-renewal

Job Properties

  • Time of benchmark: 10 Oct 2024 - 16:2
  • Package commit: 46b751
  • Julia commit: 501a4f
  • Julia command flags: None
  • Environment variables: None

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
["EpiAwareUtils", "censored_pmf"] 2.091 μs (5%) 416 bytes (1%) 10
["EpiInfModels", "DirectInfections", "evaluation", "linked"] 301.701 ns (5%) 464 bytes (1%) 10
["EpiInfModels", "DirectInfections", "evaluation", "standard"] 283.902 ns (5%) 464 bytes (1%) 10
["EpiInfModels", "DirectInfections", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "linked"] 421.241 ns (5%) 816 bytes (1%) 18
["EpiInfModels", "DirectInfections", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 412.332 ns (5%) 816 bytes (1%) 18
["EpiInfModels", "DirectInfections", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 10.399 μs (5%) 5.55 KiB (1%) 125
["EpiInfModels", "DirectInfections", "gradient", "ADTypes.AutoReverseDiff()", "standard"] 10.380 μs (5%) 5.55 KiB (1%) 125
["EpiInfModels", "DirectInfections", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "linked"] 506.751 ns (5%) 256 bytes (1%) 7
["EpiInfModels", "DirectInfections", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 508.812 ns (5%) 256 bytes (1%) 7
["EpiInfModels", "ExpGrowthRate", "evaluation", "linked"] 187.703 ns (5%) 288 bytes (1%) 8
["EpiInfModels", "ExpGrowthRate", "evaluation", "standard"] 179.468 ns (5%) 288 bytes (1%) 8
["EpiInfModels", "ExpGrowthRate", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "linked"] 275.433 ns (5%) 544 bytes (1%) 15
["EpiInfModels", "ExpGrowthRate", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 266.848 ns (5%) 544 bytes (1%) 15
["EpiInfModels", "ExpGrowthRate", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 10.209 μs (5%) 5.53 KiB (1%) 124
["EpiInfModels", "ExpGrowthRate", "gradient", "ADTypes.AutoReverseDiff()", "standard"] 10.109 μs (5%) 5.53 KiB (1%) 124
["EpiInfModels", "ExpGrowthRate", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "linked"] 512.365 ns (5%) 256 bytes (1%) 7
["EpiInfModels", "ExpGrowthRate", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 505.244 ns (5%) 256 bytes (1%) 7
["EpiLatentModels", "AR", "evaluation", "linked"] 4.896 μs (5%) 4.19 KiB (1%) 91
["EpiLatentModels", "AR", "evaluation", "standard"] 4.518 μs (5%) 3.20 KiB (1%) 84
["EpiLatentModels", "AR", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "linked"] 6.160 μs (5%) 12.20 KiB (1%) 108
["EpiLatentModels", "AR", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 5.659 μs (5%) 10.64 KiB (1%) 97
["EpiLatentModels", "AR", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 132.499 μs (5%) 54.77 KiB (1%) 1247
["EpiLatentModels", "AR", "gradient", "ADTypes.AutoReverseDiff()", "standard"] 86.763 μs (5%) 40.47 KiB (1%) 917
["EpiLatentModels", "AR", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "linked"] 16.982 μs (5%) 8.33 KiB (1%) 257
["EpiLatentModels", "AR", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 15.739 μs (5%) 7.20 KiB (1%) 221
["EpiLatentModels", "BroadcastLatentModel", "evaluation", "linked"] 934.038 ns (5%) 2.75 KiB (1%) 34
["EpiLatentModels", "BroadcastLatentModel", "evaluation", "standard"] 695.240 ns (5%) 1.88 KiB (1%) 30
["EpiLatentModels", "BroadcastLatentModel", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "linked"] 1.317 μs (5%) 4.83 KiB (1%) 45
["EpiLatentModels", "BroadcastLatentModel", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 1.054 μs (5%) 3.95 KiB (1%) 41
["EpiLatentModels", "BroadcastLatentModel", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 49.262 μs (5%) 23.62 KiB (1%) 461
["EpiLatentModels", "BroadcastLatentModel", "gradient", "ADTypes.AutoReverseDiff()", "standard"] 31.529 μs (5%) 16.55 KiB (1%) 353
["EpiLatentModels", "BroadcastLatentModel", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "linked"] 2.879 μs (5%) 1.02 KiB (1%) 32
["EpiLatentModels", "BroadcastLatentModel", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 2.664 μs (5%) 1.02 KiB (1%) 32
["EpiLatentModels", "CombineLatentModels", "evaluation", "linked"] 21.721 μs (5%) 45.67 KiB (1%) 383
["EpiLatentModels", "CombineLatentModels", "evaluation", "standard"] 18.785 μs (5%) 31.16 KiB (1%) 339
["EpiLatentModels", "CombineLatentModels", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "linked"] 48.561 μs (5%) 105.72 KiB (1%) 805
["EpiLatentModels", "CombineLatentModels", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 40.776 μs (5%) 75.84 KiB (1%) 709
["EpiLatentModels", "CombineLatentModels", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 164.769 μs (5%) 100.33 KiB (1%) 1607
["EpiLatentModels", "CombineLatentModels", "gradient", "ADTypes.AutoReverseDiff()", "standard"] 114.955 μs (5%) 72.50 KiB (1%) 1240
["EpiLatentModels", "CombineLatentModels", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "linked"] 17.533 μs (5%) 8.44 KiB (1%) 258
["EpiLatentModels", "CombineLatentModels", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 16.190 μs (5%) 7.31 KiB (1%) 222
["EpiLatentModels", "ConcatLatentModels", "evaluation", "linked"] 42.720 μs (5%) 37.27 KiB (1%) 496
["EpiLatentModels", "ConcatLatentModels", "evaluation", "standard"] 40.296 μs (5%) 28.83 KiB (1%) 466
["EpiLatentModels", "ConcatLatentModels", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "linked"] 44.303 μs (5%) 40.86 KiB (1%) 511
["EpiLatentModels", "ConcatLatentModels", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 41.819 μs (5%) 32.42 KiB (1%) 481
["EpiLatentModels", "ConcatLatentModels", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 124.082 μs (5%) 62.78 KiB (1%) 1021
["EpiLatentModels", "ConcatLatentModels", "gradient", "ADTypes.AutoReverseDiff()", "standard"] 100.609 μs (5%) 49.59 KiB (1%) 888
["EpiLatentModels", "ConcatLatentModels", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "linked"] 5.044 μs (5%) 2.20 KiB (1%) 60
["EpiLatentModels", "ConcatLatentModels", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 4.846 μs (5%) 2.20 KiB (1%) 60
["EpiLatentModels", "DiffLatentModel", "evaluation", "linked"] 8.008 μs (5%) 5.55 KiB (1%) 102
["EpiLatentModels", "DiffLatentModel", "evaluation", "standard"] 7.622 μs (5%) 3.86 KiB (1%) 96
["EpiLatentModels", "DiffLatentModel", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "linked"] 9.217 μs (5%) 13.92 KiB (1%) 115
["EpiLatentModels", "DiffLatentModel", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 8.727 μs (5%) 12.23 KiB (1%) 109
["EpiLatentModels", "DiffLatentModel", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 90.429 μs (5%) 39.72 KiB (1%) 833
["EpiLatentModels", "DiffLatentModel", "gradient", "ADTypes.AutoReverseDiff()", "standard"] 71.174 μs (5%) 33.28 KiB (1%) 724
["EpiLatentModels", "DiffLatentModel", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "linked"] 6.520 μs (5%) 2.27 KiB (1%) 59
["EpiLatentModels", "DiffLatentModel", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 6.376 μs (5%) 2.27 KiB (1%) 59
["EpiLatentModels", "HierarchicalNormal", "evaluation", "linked"] 394.920 ns (5%) 1.03 KiB (1%) 14
["EpiLatentModels", "HierarchicalNormal", "evaluation", "standard"] 300.237 ns (5%) 896 bytes (1%) 13
["EpiLatentModels", "HierarchicalNormal", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "linked"] 1.044 μs (5%) 5.12 KiB (1%) 23
["EpiLatentModels", "HierarchicalNormal", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 883.111 ns (5%) 4.97 KiB (1%) 22
["EpiLatentModels", "HierarchicalNormal", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 45.606 μs (5%) 19.03 KiB (1%) 381
["EpiLatentModels", "HierarchicalNormal", "gradient", "ADTypes.AutoReverseDiff()", "standard"] 28.623 μs (5%) 14.17 KiB (1%) 278
["EpiLatentModels", "HierarchicalNormal", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "linked"] 1.097 μs (5%) 608 bytes (1%) 9
["EpiLatentModels", "HierarchicalNormal", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 923.714 ns (5%) 608 bytes (1%) 9
["EpiLatentModels", "Intercept", "evaluation", "linked"] 222.676 ns (5%) 400 bytes (1%) 10
["EpiLatentModels", "Intercept", "evaluation", "standard"] 210.209 ns (5%) 400 bytes (1%) 10
["EpiLatentModels", "Intercept", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "linked"] 307.119 ns (5%) 704 bytes (1%) 17
["EpiLatentModels", "Intercept", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 304.317 ns (5%) 704 bytes (1%) 17
["EpiLatentModels", "Intercept", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 5.427 μs (5%) 3.62 KiB (1%) 87
["EpiLatentModels", "Intercept", "gradient", "ADTypes.AutoReverseDiff()", "standard"] 5.490 μs (5%) 3.62 KiB (1%) 87
["EpiLatentModels", "Intercept", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "linked"] 396.866 ns (5%) 208 bytes (1%) 4
["EpiLatentModels", "Intercept", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 395.915 ns (5%) 208 bytes (1%) 4
["EpiLatentModels", "PrefixLatentModel", "evaluation", "linked"] 1.817 μs (5%) 3.56 KiB (1%) 40
["EpiLatentModels", "PrefixLatentModel", "evaluation", "standard"] 1.631 μs (5%) 3.09 KiB (1%) 37
["EpiLatentModels", "PrefixLatentModel", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "linked"] 2.580 μs (5%) 7.66 KiB (1%) 49
["EpiLatentModels", "PrefixLatentModel", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 2.341 μs (5%) 7.19 KiB (1%) 46
["EpiLatentModels", "PrefixLatentModel", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 49.763 μs (5%) 21.42 KiB (1%) 406
["EpiLatentModels", "PrefixLatentModel", "gradient", "ADTypes.AutoReverseDiff()", "standard"] 31.849 μs (5%) 16.25 KiB (1%) 301
["EpiLatentModels", "PrefixLatentModel", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "linked"] 1.089 μs (5%) 608 bytes (1%) 9
["EpiLatentModels", "PrefixLatentModel", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 908.049 ns (5%) 608 bytes (1%) 9
["EpiLatentModels", "RandomWalk", "evaluation", "linked"] 609.592 ns (5%) 1.72 KiB (1%) 21
["EpiLatentModels", "RandomWalk", "evaluation", "standard"] 439.611 ns (5%) 1.28 KiB (1%) 19
["EpiLatentModels", "RandomWalk", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "linked"] 1.464 μs (5%) 8.11 KiB (1%) 32
["EpiLatentModels", "RandomWalk", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 1.339 μs (5%) 7.67 KiB (1%) 30
["EpiLatentModels", "RandomWalk", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 53.790 μs (5%) 25.52 KiB (1%) 504
["EpiLatentModels", "RandomWalk", "gradient", "ADTypes.AutoReverseDiff()", "standard"] 37.491 μs (5%) 20.33 KiB (1%) 399
["EpiLatentModels", "RandomWalk", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "linked"] 3.523 μs (5%) 1.33 KiB (1%) 32
["EpiLatentModels", "RandomWalk", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 3.296 μs (5%) 1.33 KiB (1%) 32
["EpiLatentModels", "RecordExpectedLatent", "evaluation", "linked"] 550.390 ns (5%) 1.25 KiB (1%) 20
["EpiLatentModels", "RecordExpectedLatent", "evaluation", "standard"] 410.568 ns (5%) 960 bytes (1%) 18
["EpiLatentModels", "RecordExpectedLatent", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "linked"] 720.296 ns (5%) 1.78 KiB (1%) 29
["EpiLatentModels", "RecordExpectedLatent", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 551.140 ns (5%) 1.47 KiB (1%) 27
["EpiLatentModels", "RecordExpectedLatent", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 46.417 μs (5%) 18.31 KiB (1%) 387
["EpiLatentModels", "RecordExpectedLatent", "gradient", "ADTypes.AutoReverseDiff()", "standard"] 28.473 μs (5%) 13.30 KiB (1%) 283
["EpiLatentModels", "RecordExpectedLatent", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "linked"] 1.013 μs (5%) 352 bytes (1%) 9
["EpiLatentModels", "RecordExpectedLatent", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 838.459 ns (5%) 352 bytes (1%) 9
["EpiLatentModels", "TransformLatentModel", "evaluation", "linked"] 276.036 ns (5%) 448 bytes (1%) 12
["EpiLatentModels", "TransformLatentModel", "evaluation", "standard"] 266.794 ns (5%) 448 bytes (1%) 12
["EpiLatentModels", "TransformLatentModel", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "linked"] 349.699 ns (5%) 768 bytes (1%) 19
["EpiLatentModels", "TransformLatentModel", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 339.648 ns (5%) 768 bytes (1%) 19
["EpiLatentModels", "TransformLatentModel", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 5.649 μs (5%) 3.93 KiB (1%) 95
["EpiLatentModels", "TransformLatentModel", "gradient", "ADTypes.AutoReverseDiff()", "standard"] 5.717 μs (5%) 3.93 KiB (1%) 95
["EpiLatentModels", "TransformLatentModel", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "linked"] 488.349 ns (5%) 160 bytes (1%) 4
["EpiLatentModels", "TransformLatentModel", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 490.608 ns (5%) 160 bytes (1%) 4
["EpiLatentModels", "broadcast_dayofweek", "evaluation", "linked"] 1.240 μs (5%) 3.73 KiB (1%) 43
["EpiLatentModels", "broadcast_dayofweek", "evaluation", "standard"] 915.067 ns (5%) 2.42 KiB (1%) 37
["EpiLatentModels", "broadcast_dayofweek", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "linked"] 2.158 μs (5%) 9.80 KiB (1%) 54
["EpiLatentModels", "broadcast_dayofweek", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 1.766 μs (5%) 8.48 KiB (1%) 48
["EpiLatentModels", "broadcast_dayofweek", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 71.424 μs (5%) 34.69 KiB (1%) 702
["EpiLatentModels", "broadcast_dayofweek", "gradient", "ADTypes.AutoReverseDiff()", "standard"] 53.760 μs (5%) 28.62 KiB (1%) 593
["EpiLatentModels", "broadcast_dayofweek", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "linked"] 4.862 μs (5%) 1.23 KiB (1%) 32
["EpiLatentModels", "broadcast_dayofweek", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 4.715 μs (5%) 1.23 KiB (1%) 32
["EpiLatentModels", "broadcast_weekly", "evaluation", "linked"] 8.469 μs (5%) 5.78 KiB (1%) 113
["EpiLatentModels", "broadcast_weekly", "evaluation", "standard"] 7.812 μs (5%) 3.95 KiB (1%) 103
["EpiLatentModels", "broadcast_weekly", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "linked"] 8.847 μs (5%) 8.98 KiB (1%) 130
["EpiLatentModels", "broadcast_weekly", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 8.436 μs (5%) 6.83 KiB (1%) 116
["EpiLatentModels", "broadcast_weekly", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 111.048 μs (5%) 42.25 KiB (1%) 861
["EpiLatentModels", "broadcast_weekly", "gradient", "ADTypes.AutoReverseDiff()", "standard"] 67.977 μs (5%) 29.61 KiB (1%) 608
["EpiLatentModels", "broadcast_weekly", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "linked"] 5.139 μs (5%) 1.83 KiB (1%) 57
["EpiLatentModels", "broadcast_weekly", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 4.564 μs (5%) 1.70 KiB (1%) 53
["EpiObsModels", "Ascertainment", "evaluation", "linked"] 3.281 μs (5%) 3.61 KiB (1%) 64
["EpiObsModels", "Ascertainment", "evaluation", "standard"] 3.186 μs (5%) 3.61 KiB (1%) 64
["EpiObsModels", "Ascertainment", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "linked"] 3.965 μs (5%) 3.95 KiB (1%) 73
["EpiObsModels", "Ascertainment", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 3.943 μs (5%) 3.95 KiB (1%) 73
["EpiObsModels", "Ascertainment", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 77.004 μs (5%) 38.80 KiB (1%) 919
["EpiObsModels", "Ascertainment", "gradient", "ADTypes.AutoReverseDiff()", "standard"] 61.395 μs (5%) 34.05 KiB (1%) 816
["EpiObsModels", "Ascertainment", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "linked"] 5.587 μs (5%) 96 bytes (1%) 3
["EpiObsModels", "Ascertainment", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 5.492 μs (5%) 96 bytes (1%) 3
["EpiObsModels", "LatentDelay", "evaluation", "linked"] 14.066 μs (5%) 22.08 KiB (1%) 412
["EpiObsModels", "LatentDelay", "evaluation", "standard"] 14.056 μs (5%) 22.08 KiB (1%) 412
["EpiObsModels", "LatentDelay", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "linked"] 18.806 μs (5%) 22.30 KiB (1%) 419
["EpiObsModels", "LatentDelay", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 17.864 μs (5%) 22.30 KiB (1%) 419
["EpiObsModels", "LatentDelay", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 538.067 μs (5%) 293.05 KiB (1%) 7011
["EpiObsModels", "LatentDelay", "gradient", "ADTypes.AutoReverseDiff()", "standard"] 516.627 μs (5%) 288.30 KiB (1%) 6908
["EpiObsModels", "LatentDelay", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "linked"] 53.410 μs (5%) 96 bytes (1%) 3
["EpiObsModels", "LatentDelay", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 53.530 μs (5%) 96 bytes (1%) 3
["EpiObsModels", "NegativeBinomialError", "evaluation", "linked"] 1.130 μs (5%) 400 bytes (1%) 10
["EpiObsModels", "NegativeBinomialError", "evaluation", "standard"] 1.087 μs (5%) 400 bytes (1%) 10
["EpiObsModels", "NegativeBinomialError", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "linked"] 1.634 μs (5%) 624 bytes (1%) 17
["EpiObsModels", "NegativeBinomialError", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 1.570 μs (5%) 624 bytes (1%) 17
["EpiObsModels", "NegativeBinomialError", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 72.726 μs (5%) 35.95 KiB (1%) 903
["EpiObsModels", "NegativeBinomialError", "gradient", "ADTypes.AutoReverseDiff()", "standard"] 57.126 μs (5%) 31.20 KiB (1%) 800
["EpiObsModels", "NegativeBinomialError", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "linked"] 5.649 μs (5%) 96 bytes (1%) 3
["EpiObsModels", "NegativeBinomialError", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 5.527 μs (5%) 96 bytes (1%) 3
["EpiObsModels", "PoissonError", "evaluation", "linked"] 1.419 μs (5%) 1.83 KiB (1%) 30
["EpiObsModels", "PoissonError", "evaluation", "standard"] 1.098 μs (5%) 1.47 KiB (1%) 26
["EpiObsModels", "PoissonError", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "linked"] 3.151 μs (5%) 7.78 KiB (1%) 43
["EpiObsModels", "PoissonError", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 2.500 μs (5%) 4.70 KiB (1%) 35
["EpiObsModels", "PoissonError", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 167.895 μs (5%) 86.44 KiB (1%) 1870
["EpiObsModels", "PoissonError", "gradient", "ADTypes.AutoReverseDiff()", "standard"] 46.146 μs (5%) 29.38 KiB (1%) 727
["EpiObsModels", "PoissonError", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "linked"] 6.089 μs (5%) 176 bytes (1%) 3
["EpiObsModels", "PoissonError", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 4.139 μs (5%) 176 bytes (1%) 3
["EpiObsModels", "PrefixObservationModel", "evaluation", "linked"] 1.694 μs (5%) 1.56 KiB (1%) 34
["EpiObsModels", "PrefixObservationModel", "evaluation", "standard"] 1.626 μs (5%) 1.56 KiB (1%) 34
["EpiObsModels", "PrefixObservationModel", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "linked"] 1.828 μs (5%) 1.78 KiB (1%) 41
["EpiObsModels", "PrefixObservationModel", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 1.746 μs (5%) 1.78 KiB (1%) 41
["EpiObsModels", "PrefixObservationModel", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 27.912 μs (5%) 12.59 KiB (1%) 290
["EpiObsModels", "PrefixObservationModel", "gradient", "ADTypes.AutoReverseDiff()", "standard"] 13.265 μs (5%) 7.84 KiB (1%) 187
["EpiObsModels", "PrefixObservationModel", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "linked"] 1.108 μs (5%) 96 bytes (1%) 3
["EpiObsModels", "PrefixObservationModel", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 956.000 ns (5%) 96 bytes (1%) 3
["EpiObsModels", "StackObservationModels", "evaluation", "linked"] 6.799 μs (5%) 5.81 KiB (1%) 117
["EpiObsModels", "StackObservationModels", "evaluation", "standard"] 6.682 μs (5%) 5.81 KiB (1%) 117
["EpiObsModels", "StackObservationModels", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "linked"] 7.544 μs (5%) 6.16 KiB (1%) 126
["EpiObsModels", "StackObservationModels", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 7.447 μs (5%) 6.16 KiB (1%) 126
["EpiObsModels", "StackObservationModels", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 91.481 μs (5%) 49.09 KiB (1%) 1044
["EpiObsModels", "StackObservationModels", "gradient", "ADTypes.AutoReverseDiff()", "standard"] 72.777 μs (5%) 44.34 KiB (1%) 941
["EpiObsModels", "StackObservationModels", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "linked"] 6.135 μs (5%) 96 bytes (1%) 3
["EpiObsModels", "StackObservationModels", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 5.933 μs (5%) 96 bytes (1%) 3
["EpiObsModels", "ascertainment_dayofweek", "evaluation", "linked"] 4.125 μs (5%) 9.12 KiB (1%) 101
["EpiObsModels", "ascertainment_dayofweek", "evaluation", "standard"] 3.671 μs (5%) 7.88 KiB (1%) 93
["EpiObsModels", "ascertainment_dayofweek", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "linked"] 5.983 μs (5%) 16.25 KiB (1%) 112
["EpiObsModels", "ascertainment_dayofweek", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 5.425 μs (5%) 15.00 KiB (1%) 104
["EpiObsModels", "ascertainment_dayofweek", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 110.156 μs (5%) 59.86 KiB (1%) 1165
["EpiObsModels", "ascertainment_dayofweek", "gradient", "ADTypes.AutoReverseDiff()", "standard"] 89.827 μs (5%) 53.91 KiB (1%) 1055
["EpiObsModels", "ascertainment_dayofweek", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "linked"] 5.388 μs (5%) 496 bytes (1%) 9
["EpiObsModels", "ascertainment_dayofweek", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 5.238 μs (5%) 496 bytes (1%) 9
["EpiObsModels", "observation_error", "missing obs", "evaluation", "linked"] 1.455 μs (5%) 3.05 KiB (1%) 38
["EpiObsModels", "observation_error", "missing obs", "evaluation", "standard"] 894.122 ns (5%) 1.48 KiB (1%) 28
["EpiObsModels", "observation_error", "missing obs", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "linked"] 1.784 μs (5%) 4.11 KiB (1%) 48
["EpiObsModels", "observation_error", "missing obs", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 1.223 μs (5%) 2.55 KiB (1%) 38
["EpiObsModels", "observation_error", "missing obs", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 38.953 μs (5%) 24.38 KiB (1%) 498
["EpiObsModels", "observation_error", "missing obs", "gradient", "ADTypes.AutoReverseDiff()", "standard"] 22.262 μs (5%) 17.39 KiB (1%) 366
["EpiObsModels", "observation_error", "missing obs", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "linked"] 2.209 μs (5%) 144 bytes (1%) 3
["EpiObsModels", "observation_error", "missing obs", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 1.999 μs (5%) 144 bytes (1%) 3
["EpiObsModels", "observation_error", "no missing obs", "evaluation", "linked"] 430.407 ns (5%) 352 bytes (1%) 10
["EpiObsModels", "observation_error", "no missing obs", "evaluation", "standard"] 371.131 ns (5%) 352 bytes (1%) 10
["EpiObsModels", "observation_error", "no missing obs", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "linked"] 551.299 ns (5%) 576 bytes (1%) 17
["EpiObsModels", "observation_error", "no missing obs", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 485.369 ns (5%) 576 bytes (1%) 17
["EpiObsModels", "observation_error", "no missing obs", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 31.970 μs (5%) 18.34 KiB (1%) 418
["EpiObsModels", "observation_error", "no missing obs", "gradient", "ADTypes.AutoReverseDiff()", "standard"] 16.932 μs (5%) 12.92 KiB (1%) 296
["EpiObsModels", "observation_error", "no missing obs", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "linked"] 1.897 μs (5%) 96 bytes (1%) 3
["EpiObsModels", "observation_error", "no missing obs", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 1.622 μs (5%) 96 bytes (1%) 3
["EpiObsModels", "observation_error", "partially missing obs", "evaluation", "linked"] 29.094 μs (5%) 3.02 KiB (1%) 64
["EpiObsModels", "observation_error", "partially missing obs", "evaluation", "standard"] 28.804 μs (5%) 2.70 KiB (1%) 62
["EpiObsModels", "observation_error", "partially missing obs", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "linked"] 19.256 μs (5%) 2.73 KiB (1%) 51
["EpiObsModels", "observation_error", "partially missing obs", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)", "standard"] 19.136 μs (5%) 2.42 KiB (1%) 49
["EpiObsModels", "observation_error", "partially missing obs", "gradient", "ADTypes.AutoReverseDiff()", "linked"] 60.693 μs (5%) 24.08 KiB (1%) 525
["EpiObsModels", "observation_error", "partially missing obs", "gradient", "ADTypes.AutoReverseDiff()", "standard"] 40.796 μs (5%) 18.34 KiB (1%) 401
["EpiObsModels", "observation_error", "partially missing obs", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "linked"] 2.222 μs (5%) 112 bytes (1%) 3
["EpiObsModels", "observation_error", "partially missing obs", "gradient", "ADTypes.AutoReverseDiff(compile=true)", "standard"] 2.009 μs (5%) 112 bytes (1%) 3

Benchmark Group List

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

  • ["EpiAwareUtils"]
  • ["EpiInfModels", "DirectInfections", "evaluation"]
  • ["EpiInfModels", "DirectInfections", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiInfModels", "DirectInfections", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiInfModels", "DirectInfections", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiInfModels", "ExpGrowthRate", "evaluation"]
  • ["EpiInfModels", "ExpGrowthRate", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiInfModels", "ExpGrowthRate", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiInfModels", "ExpGrowthRate", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiLatentModels", "AR", "evaluation"]
  • ["EpiLatentModels", "AR", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiLatentModels", "AR", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiLatentModels", "AR", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiLatentModels", "BroadcastLatentModel", "evaluation"]
  • ["EpiLatentModels", "BroadcastLatentModel", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiLatentModels", "BroadcastLatentModel", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiLatentModels", "BroadcastLatentModel", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiLatentModels", "CombineLatentModels", "evaluation"]
  • ["EpiLatentModels", "CombineLatentModels", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiLatentModels", "CombineLatentModels", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiLatentModels", "CombineLatentModels", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiLatentModels", "ConcatLatentModels", "evaluation"]
  • ["EpiLatentModels", "ConcatLatentModels", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiLatentModels", "ConcatLatentModels", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiLatentModels", "ConcatLatentModels", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiLatentModels", "DiffLatentModel", "evaluation"]
  • ["EpiLatentModels", "DiffLatentModel", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiLatentModels", "DiffLatentModel", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiLatentModels", "DiffLatentModel", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiLatentModels", "HierarchicalNormal", "evaluation"]
  • ["EpiLatentModels", "HierarchicalNormal", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiLatentModels", "HierarchicalNormal", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiLatentModels", "HierarchicalNormal", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiLatentModels", "Intercept", "evaluation"]
  • ["EpiLatentModels", "Intercept", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiLatentModels", "Intercept", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiLatentModels", "Intercept", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiLatentModels", "PrefixLatentModel", "evaluation"]
  • ["EpiLatentModels", "PrefixLatentModel", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiLatentModels", "PrefixLatentModel", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiLatentModels", "PrefixLatentModel", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiLatentModels", "RandomWalk", "evaluation"]
  • ["EpiLatentModels", "RandomWalk", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiLatentModels", "RandomWalk", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiLatentModels", "RandomWalk", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiLatentModels", "RecordExpectedLatent", "evaluation"]
  • ["EpiLatentModels", "RecordExpectedLatent", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiLatentModels", "RecordExpectedLatent", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiLatentModels", "RecordExpectedLatent", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiLatentModels", "TransformLatentModel", "evaluation"]
  • ["EpiLatentModels", "TransformLatentModel", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiLatentModels", "TransformLatentModel", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiLatentModels", "TransformLatentModel", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiLatentModels", "broadcast_dayofweek", "evaluation"]
  • ["EpiLatentModels", "broadcast_dayofweek", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiLatentModels", "broadcast_dayofweek", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiLatentModels", "broadcast_dayofweek", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiLatentModels", "broadcast_weekly", "evaluation"]
  • ["EpiLatentModels", "broadcast_weekly", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiLatentModels", "broadcast_weekly", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiLatentModels", "broadcast_weekly", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiObsModels", "Ascertainment", "evaluation"]
  • ["EpiObsModels", "Ascertainment", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiObsModels", "Ascertainment", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiObsModels", "Ascertainment", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiObsModels", "LatentDelay", "evaluation"]
  • ["EpiObsModels", "LatentDelay", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiObsModels", "LatentDelay", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiObsModels", "LatentDelay", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiObsModels", "NegativeBinomialError", "evaluation"]
  • ["EpiObsModels", "NegativeBinomialError", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiObsModels", "NegativeBinomialError", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiObsModels", "NegativeBinomialError", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiObsModels", "PoissonError", "evaluation"]
  • ["EpiObsModels", "PoissonError", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiObsModels", "PoissonError", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiObsModels", "PoissonError", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiObsModels", "PrefixObservationModel", "evaluation"]
  • ["EpiObsModels", "PrefixObservationModel", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiObsModels", "PrefixObservationModel", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiObsModels", "PrefixObservationModel", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiObsModels", "StackObservationModels", "evaluation"]
  • ["EpiObsModels", "StackObservationModels", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiObsModels", "StackObservationModels", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiObsModels", "StackObservationModels", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiObsModels", "ascertainment_dayofweek", "evaluation"]
  • ["EpiObsModels", "ascertainment_dayofweek", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiObsModels", "ascertainment_dayofweek", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiObsModels", "ascertainment_dayofweek", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiObsModels", "observation_error", "missing obs", "evaluation"]
  • ["EpiObsModels", "observation_error", "missing obs", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiObsModels", "observation_error", "missing obs", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiObsModels", "observation_error", "missing obs", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiObsModels", "observation_error", "no missing obs", "evaluation"]
  • ["EpiObsModels", "observation_error", "no missing obs", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiObsModels", "observation_error", "no missing obs", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiObsModels", "observation_error", "no missing obs", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]
  • ["EpiObsModels", "observation_error", "partially missing obs", "evaluation"]
  • ["EpiObsModels", "observation_error", "partially missing obs", "gradient", "ADTypes.AutoForwardDiff(chunksize=0)"]
  • ["EpiObsModels", "observation_error", "partially missing obs", "gradient", "ADTypes.AutoReverseDiff()"]
  • ["EpiObsModels", "observation_error", "partially missing obs", "gradient", "ADTypes.AutoReverseDiff(compile=true)"]

Julia versioninfo

Julia Version 1.11.0
Commit 501a4f25c2b (2024-10-07 11:40 UTC)
Build Info:
  Official https://julialang.org/ release
Platform Info:
  OS: Linux (x86_64-linux-gnu)
      Ubuntu 22.04.5 LTS
  uname: Linux 6.5.0-1025-azure #26~22.04.1-Ubuntu SMP Thu Jul 11 22:33:04 UTC 2024 x86_64 x86_64
  CPU: AMD EPYC 7763 64-Core Processor: 
              speed         user         nice          sys         idle          irq
       #1     0 MHz      10405 s          0 s        885 s      25616 s          0 s
       #2     0 MHz       9604 s          0 s        698 s      26601 s          0 s
       #3     0 MHz       8523 s          0 s        718 s      27661 s          0 s
       #4     0 MHz       9453 s          0 s        803 s      26644 s          0 s
  Memory: 15.606491088867188 GB (13007.9375 MB free)
  Uptime: 3699.53 sec
  Load Avg:  1.05  1.03  1.0
  WORD_SIZE: 64
  LLVM: libLLVM-16.0.6 (ORCJIT, znver3)
Threads: 1 default, 0 interactive, 1 GC (on 4 virtual cores)

Runtime information

Runtime Info
BLAS #threads 2
BLAS.vendor() lbt
Sys.CPU_THREADS 4

lscpu output:

Architecture:                       x86_64
CPU op-mode(s):                     32-bit, 64-bit
Address sizes:                      48 bits physical, 48 bits virtual
Byte Order:                         Little Endian
CPU(s):                             4
On-line CPU(s) list:                0-3
Vendor ID:                          AuthenticAMD
Model name:                         AMD EPYC 7763 64-Core Processor
CPU family:                         25
Model:                              1
Thread(s) per core:                 2
Core(s) per socket:                 2
Socket(s):                          1
Stepping:                           1
BogoMIPS:                           4890.87
Flags:                              fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl tsc_reliable nonstop_tsc cpuid extd_apicid aperfmperf pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy svm cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw topoext invpcid_single vmmcall fsgsbase bmi1 avx2 smep bmi2 erms invpcid rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves clzero xsaveerptr rdpru arat npt nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold v_vmsave_vmload umip vaes vpclmulqdq rdpid fsrm
Virtualization:                     AMD-V
Hypervisor vendor:                  Microsoft
Virtualization type:                full
L1d cache:                          64 KiB (2 instances)
L1i cache:                          64 KiB (2 instances)
L2 cache:                           1 MiB (2 instances)
L3 cache:                           32 MiB (1 instance)
NUMA node(s):                       1
NUMA node0 CPU(s):                  0-3
Vulnerability Gather data sampling: Not affected
Vulnerability Itlb multihit:        Not affected
Vulnerability L1tf:                 Not affected
Vulnerability Mds:                  Not affected
Vulnerability Meltdown:             Not affected
Vulnerability Mmio stale data:      Not affected
Vulnerability Retbleed:             Not affected
Vulnerability Spec rstack overflow: Vulnerable: Safe RET, no microcode
Vulnerability Spec store bypass:    Vulnerable
Vulnerability Spectre v1:           Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2:           Mitigation; Retpolines; STIBP disabled; RSB filling; PBRSB-eIBRS Not affected; BHI Not affected
Vulnerability Srbds:                Not affected
Vulnerability Tsx async abort:      Not affected
Cpu Property Value
Brand AMD EPYC 7763 64-Core Processor
Vendor :AMD
Architecture :Unknown
Model Family: 0xaf, Model: 0x01, Stepping: 0x01, Type: 0x00
Cores 16 physical cores, 16 logical cores (on executing CPU)
No Hyperthreading hardware capability detected
Clock Frequencies Not supported by CPU
Data Cache Level 1:3 : (32, 512, 32768) kbytes
64 byte cache line size
Address Size 48 bits virtual, 48 bits physical
SIMD 256 bit = 32 byte max. SIMD vector size
Time Stamp Counter TSC is accessible via rdtsc
TSC runs at constant rate (invariant from clock frequency)
Perf. Monitoring Performance Monitoring Counters (PMC) are not supported
Hypervisor Yes, Microsoft

@SamuelBrand1
Copy link
Collaborator Author

Note that the benchmarks for observations are worse.

This might suggest going for something a bit more specialised like Union{Int,BigInt}

@SamuelBrand1 SamuelBrand1 mentioned this pull request Oct 10, 2024
Merged
@SamuelBrand1
Copy link
Collaborator Author

Closing this as #497 looks much more promising.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

Change SafePoisson and SafeNegativeBinomial to return value from rand calls
1 participant
@SamuelBrand1