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

Add LoopVectorization.jl to tests and benchmarks to speed up Tullio #66

Merged
merged 2 commits into from
May 25, 2022
Merged

Add LoopVectorization.jl to tests and benchmarks to speed up Tullio #66

merged 2 commits into from
May 25, 2022

Conversation

adrhill
Copy link
Member

@adrhill adrhill commented May 24, 2022

No description provided.

@codecov-commenter
Copy link

codecov-commenter commented May 24, 2022 •
edited
Loading

Codecov Report

Merging #66 (79b7926) into master (af5a2d8) will not change coverage.
The diff coverage is n/a.

@@           Coverage Diff           @@
##           master      #66   +/-   ##
=======================================
  Coverage   96.76%   96.76%           
=======================================
  Files          11       11           
  Lines         309      309           
=======================================
  Hits          299      299           
  Misses         10       10

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 af5a2d8...79b7926. Read the comment docs.

@adrhill adrhill added the run benchmark Run benchmark CI action label May 25, 2022
@github-actions
Copy link

Benchmark result

Judge result

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

Job Properties

  • Time of benchmarks:
    • Target: 25 May 2022 - 14:25
    • Baseline: 25 May 2022 - 14:29
  • Package commits:
    • Target: a7ff7a
    • Baseline: af5a2d
  • Julia commits:
    • Target: bf5349
    • Baseline: bf5349
  • 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
["Layer", "Conv", "ZBoxRule"] 0.90 (5%) ✅ 1.00 (1%)
["Layer", "Dense", "GammaRule"] 0.91 (5%) ✅ 1.00 (1%)
["Layer", "Dense", "ZeroRule"] 1.10 (5%) ❌ 1.00 (1%)
["Layer", "MaxPool", "GammaRule"] 1.27 (5%) ❌ 1.00 (1%)
["Layer", "MaxPool", "ZBoxRule"] 1.17 (5%) ❌ 1.00 (1%)
["Layer", "MaxPool", "ZeroRule"] 1.05 (5%) ❌ 1.00 (1%)
["Layer", "WrappedDense", "EpsilonRule"] 0.95 (5%) ✅ 1.00 (1%)
["Layer", "WrappedDense", "ZBoxRule"] 1.08 (5%) ❌ 1.00 (1%)
["Layer", "WrappedDense", "ZeroRule"] 0.87 (5%) ✅ 1.00 (1%)
["VGG", "Gradient", "construct analyzer"] 0.81 (5%) ✅ 1.00 (1%)
["VGG", "InputTimesGradient", "analyze"] 0.06 (5%) ✅ 0.64 (1%) ✅
["VGG", "InputTimesGradient", "construct analyzer"] 1.32 (5%) ❌ 1.00 (1%)
["VGG", "IntegratedGradients", "construct analyzer"] 0.90 (5%) ✅ 1.00 (1%)
["VGG", "LRPCustom", "analyze"] 0.36 (5%) ✅ 0.89 (1%) ✅
["VGG", "LRPZero", "analyze"] 0.26 (5%) ✅ 0.78 (1%) ✅
["VGG", "LRPZero", "construct analyzer"] 1.15 (5%) ❌ 1.00 (1%)
["VGG", "SmoothGrad", "analyze"] 0.82 (5%) ✅ 0.95 (1%) ✅
["VGG", "SmoothGrad", "construct analyzer"] 0.92 (5%) ✅ 1.00 (1%)

Benchmark Group List

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

  • ["Layer", "Conv"]
  • ["Layer", "Dense"]
  • ["Layer", "MaxPool"]
  • ["Layer", "WrappedDense"]
  • ["VGG", "Gradient"]
  • ["VGG", "InputTimesGradient"]
  • ["VGG", "IntegratedGradients"]
  • ["VGG", "LRPCustom"]
  • ["VGG", "LRPZero"]
  • ["VGG", "SmoothGrad"]

Julia versioninfo

Target

Julia Version 1.7.2
Commit bf53498635 (2022-02-06 15:21 UTC)
Platform Info:
  OS: Linux (x86_64-pc-linux-gnu)
      Ubuntu 20.04.4 LTS
  uname: Linux 5.13.0-1023-azure #27~20.04.1-Ubuntu SMP Mon Apr 25 22:39:07 UTC 2022 x86_64 x86_64
  CPU: Intel(R) Xeon(R) Platinum 8171M CPU @ 2.60GHz: 
              speed         user         nice          sys         idle          irq
       #1  2095 MHz       6009 s          2 s        586 s       1404 s          0 s
       #2  2095 MHz       3843 s          1 s        534 s       3612 s          0 s
       
  Memory: 6.783603668212891 GB (1006.1796875 MB free)
  Uptime: 805.15 sec
  Load Avg:  1.15  1.31  0.93
  WORD_SIZE: 64
  LIBM: libopenlibm
  LLVM: libLLVM-12.0.1 (ORCJIT, skylake-avx512)

Baseline

Julia Version 1.7.2
Commit bf53498635 (2022-02-06 15:21 UTC)
Platform Info:
  OS: Linux (x86_64-pc-linux-gnu)
      Ubuntu 20.04.4 LTS
  uname: Linux 5.13.0-1023-azure #27~20.04.1-Ubuntu SMP Mon Apr 25 22:39:07 UTC 2022 x86_64 x86_64
  CPU: Intel(R) Xeon(R) Platinum 8171M CPU @ 2.60GHz: 
              speed         user         nice          sys         idle          irq
       #1  2095 MHz       8558 s          2 s        673 s       1453 s          0 s
       #2  2095 MHz       4171 s          1 s        638 s       5854 s          0 s
       
  Memory: 6.783603668212891 GB (1489.859375 MB free)
  Uptime: 1073.63 sec
  Load Avg:  1.14  1.22  1.0
  WORD_SIZE: 64
  LIBM: libopenlibm
  LLVM: libLLVM-12.0.1 (ORCJIT, skylake-avx512)

Target result

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

Job Properties

  • Time of benchmark: 25 May 2022 - 14:25
  • Package commit: a7ff7a
  • Julia commit: bf5349
  • 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
["Layer", "Conv", "EpsilonRule"] 651.354 μs (5%) 1.43 MiB (1%) 169
["Layer", "Conv", "GammaRule"] 667.856 μs (5%) 1.44 MiB (1%) 181
["Layer", "Conv", "ZBoxRule"] 2.117 ms (5%) 4.46 MiB (1%) 492
["Layer", "Conv", "ZeroRule"] 634.953 μs (5%) 1.43 MiB (1%) 169
["Layer", "Dense", "EpsilonRule"] 34.602 μs (5%) 1.45 KiB (1%) 3
["Layer", "Dense", "GammaRule"] 104.908 μs (5%) 588.98 KiB (1%) 12
["Layer", "Dense", "ZBoxRule"] 356.330 μs (5%) 1017.84 KiB (1%) 152
["Layer", "Dense", "ZeroRule"] 46.003 μs (5%) 1.45 KiB (1%) 3
["Layer", "MaxPool", "EpsilonRule"] 71.706 μs (5%) 86.69 KiB (1%) 61
["Layer", "MaxPool", "GammaRule"] 89.908 μs (5%) 86.69 KiB (1%) 61
["Layer", "MaxPool", "ZBoxRule"] 75.007 μs (5%) 85.97 KiB (1%) 61
["Layer", "MaxPool", "ZeroRule"] 71.506 μs (5%) 85.97 KiB (1%) 61
["Layer", "WrappedDense", "EpsilonRule"] 99.608 μs (5%) 206.62 KiB (1%) 57
["Layer", "WrappedDense", "GammaRule"] 174.914 μs (5%) 794.16 KiB (1%) 66
["Layer", "WrappedDense", "ZBoxRule"] 378.832 μs (5%) 1017.84 KiB (1%) 152
["Layer", "WrappedDense", "ZeroRule"] 91.307 μs (5%) 206.19 KiB (1%) 57
["VGG", "Gradient", "analyze"] 1.206 s (5%) 13.336 ms 1.10 GiB (1%) 2012
["VGG", "Gradient", "construct analyzer"] 15.602 μs (5%) 26.66 KiB (1%) 189
["VGG", "InputTimesGradient", "analyze"] 1.196 s (5%) 12.217 ms 1.10 GiB (1%) 2015
["VGG", "InputTimesGradient", "construct analyzer"] 17.402 μs (5%) 26.66 KiB (1%) 189
["VGG", "IntegratedGradients", "analyze"] 10.728 s (5%) 88.196 ms 10.34 GiB (1%) 16942
["VGG", "IntegratedGradients", "construct analyzer"] 15.101 μs (5%) 24.69 KiB (1%) 187
["VGG", "LRPCustom", "analyze"] 2.100 s (5%) 30.800 ms 2.47 GiB (1%) 2731
["VGG", "LRPCustom", "construct analyzer"] 21.402 μs (5%) 45.52 KiB (1%) 155
["VGG", "LRPZero", "analyze"] 1.153 s (5%) 11.212 ms 830.02 MiB (1%) 2285
["VGG", "LRPZero", "construct analyzer"] 15.002 μs (5%) 43.88 KiB (1%) 82
["VGG", "SmoothGrad", "analyze"] 10.699 s (5%) 87.605 ms 10.33 GiB (1%) 16852
["VGG", "SmoothGrad", "construct analyzer"] 14.402 μs (5%) 24.69 KiB (1%) 187

Benchmark Group List

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

  • ["Layer", "Conv"]
  • ["Layer", "Dense"]
  • ["Layer", "MaxPool"]
  • ["Layer", "WrappedDense"]
  • ["VGG", "Gradient"]
  • ["VGG", "InputTimesGradient"]
  • ["VGG", "IntegratedGradients"]
  • ["VGG", "LRPCustom"]
  • ["VGG", "LRPZero"]
  • ["VGG", "SmoothGrad"]

Julia versioninfo

Julia Version 1.7.2
Commit bf53498635 (2022-02-06 15:21 UTC)
Platform Info:
  OS: Linux (x86_64-pc-linux-gnu)
      Ubuntu 20.04.4 LTS
  uname: Linux 5.13.0-1023-azure #27~20.04.1-Ubuntu SMP Mon Apr 25 22:39:07 UTC 2022 x86_64 x86_64
  CPU: Intel(R) Xeon(R) Platinum 8171M CPU @ 2.60GHz: 
              speed         user         nice          sys         idle          irq
       #1  2095 MHz       6009 s          2 s        586 s       1404 s          0 s
       #2  2095 MHz       3843 s          1 s        534 s       3612 s          0 s
       
  Memory: 6.783603668212891 GB (1006.1796875 MB free)
  Uptime: 805.15 sec
  Load Avg:  1.15  1.31  0.93
  WORD_SIZE: 64
  LIBM: libopenlibm
  LLVM: libLLVM-12.0.1 (ORCJIT, skylake-avx512)

Baseline result

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

Job Properties

  • Time of benchmark: 25 May 2022 - 14:29
  • Package commit: af5a2d
  • Julia commit: bf5349
  • 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
["Layer", "Conv", "EpsilonRule"] 667.155 μs (5%) 1.43 MiB (1%) 169
["Layer", "Conv", "GammaRule"] 652.055 μs (5%) 1.44 MiB (1%) 181
["Layer", "Conv", "ZBoxRule"] 2.342 ms (5%) 4.46 MiB (1%) 492
["Layer", "Conv", "ZeroRule"] 665.255 μs (5%) 1.43 MiB (1%) 169
["Layer", "Dense", "EpsilonRule"] 34.503 μs (5%) 1.45 KiB (1%) 3
["Layer", "Dense", "GammaRule"] 115.510 μs (5%) 588.98 KiB (1%) 12
["Layer", "Dense", "ZBoxRule"] 367.330 μs (5%) 1017.84 KiB (1%) 152
["Layer", "Dense", "ZeroRule"] 42.004 μs (5%) 1.45 KiB (1%) 3
["Layer", "MaxPool", "EpsilonRule"] 75.206 μs (5%) 86.69 KiB (1%) 61
["Layer", "MaxPool", "GammaRule"] 71.006 μs (5%) 86.69 KiB (1%) 61
["Layer", "MaxPool", "ZBoxRule"] 64.306 μs (5%) 85.97 KiB (1%) 61
["Layer", "MaxPool", "ZeroRule"] 68.006 μs (5%) 85.97 KiB (1%) 61
["Layer", "WrappedDense", "EpsilonRule"] 105.008 μs (5%) 206.62 KiB (1%) 57
["Layer", "WrappedDense", "GammaRule"] 180.715 μs (5%) 794.16 KiB (1%) 66
["Layer", "WrappedDense", "ZBoxRule"] 351.630 μs (5%) 1017.84 KiB (1%) 152
["Layer", "WrappedDense", "ZeroRule"] 105.109 μs (5%) 206.19 KiB (1%) 57
["VGG", "Gradient", "analyze"] 1.224 s (5%) 13.113 ms 1.10 GiB (1%) 2012
["VGG", "Gradient", "construct analyzer"] 19.301 μs (5%) 26.66 KiB (1%) 189
["VGG", "InputTimesGradient", "analyze"] 20.901 s (5%) 213.696 ms 1.74 GiB (1%) 12102174
["VGG", "InputTimesGradient", "construct analyzer"] 13.201 μs (5%) 26.66 KiB (1%) 189
["VGG", "IntegratedGradients", "analyze"] 11.047 s (5%) 146.848 ms 10.34 GiB (1%) 16942
["VGG", "IntegratedGradients", "construct analyzer"] 16.801 μs (5%) 24.69 KiB (1%) 187
["VGG", "LRPCustom", "analyze"] 5.795 s (5%) 79.107 ms 2.77 GiB (1%) 6162301
["VGG", "LRPCustom", "construct analyzer"] 22.302 μs (5%) 45.52 KiB (1%) 155
["VGG", "LRPZero", "analyze"] 4.402 s (5%) 111.489 ms 1.04 GiB (1%) 4599412
["VGG", "LRPZero", "construct analyzer"] 13.001 μs (5%) 43.88 KiB (1%) 82
["VGG", "SmoothGrad", "analyze"] 13.122 s (5%) 226.229 ms 10.82 GiB (1%) 9309203
["VGG", "SmoothGrad", "construct analyzer"] 15.601 μs (5%) 24.69 KiB (1%) 187

Benchmark Group List

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

  • ["Layer", "Conv"]
  • ["Layer", "Dense"]
  • ["Layer", "MaxPool"]
  • ["Layer", "WrappedDense"]
  • ["VGG", "Gradient"]
  • ["VGG", "InputTimesGradient"]
  • ["VGG", "IntegratedGradients"]
  • ["VGG", "LRPCustom"]
  • ["VGG", "LRPZero"]
  • ["VGG", "SmoothGrad"]

Julia versioninfo

Julia Version 1.7.2
Commit bf53498635 (2022-02-06 15:21 UTC)
Platform Info:
  OS: Linux (x86_64-pc-linux-gnu)
      Ubuntu 20.04.4 LTS
  uname: Linux 5.13.0-1023-azure #27~20.04.1-Ubuntu SMP Mon Apr 25 22:39:07 UTC 2022 x86_64 x86_64
  CPU: Intel(R) Xeon(R) Platinum 8171M CPU @ 2.60GHz: 
              speed         user         nice          sys         idle          irq
       #1  2095 MHz       8558 s          2 s        673 s       1453 s          0 s
       #2  2095 MHz       4171 s          1 s        638 s       5854 s          0 s
       
  Memory: 6.783603668212891 GB (1489.859375 MB free)
  Uptime: 1073.63 sec
  Load Avg:  1.14  1.22  1.0
  WORD_SIZE: 64
  LIBM: libopenlibm
  LLVM: libLLVM-12.0.1 (ORCJIT, skylake-avx512)

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
Address sizes:                   46 bits physical, 48 bits virtual
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:                         2095.226
BogoMIPS:                        4190.45
Hypervisor vendor:               Microsoft
Virtualization type:             full
L1d cache:                       64 KiB
L1i cache:                       64 KiB
L2 cache:                        2 MiB
L3 cache:                        35.8 MiB
NUMA node0 CPU(s):               0,1
Vulnerability Itlb multihit:     KVM: Mitigation: VMX unsupported
Vulnerability L1tf:              Mitigation; PTE Inversion
Vulnerability Mds:               Mitigation; Clear CPU buffers; SMT Host state unknown
Vulnerability Meltdown:          Mitigation; PTI
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
Vulnerability Srbds:             Not affected
Vulnerability Tsx async abort:   Mitigation; Clear CPU buffers; SMT Host state unknown
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 md_clear
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 hardware capability 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, 46 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

@adrhill adrhill merged commit c6c8db9 into master May 25, 2022
@adrhill adrhill deleted the ah/lv-tests branch May 25, 2022 14:30
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
run benchmark Run benchmark CI action
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

None yet
2 participants
@adrhill @codecov-commenter