-
Notifications
You must be signed in to change notification settings - Fork 13
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Backend-specific utilities (derivative, multiderivative, gradient, ja…
…cobian) (#24) * Add special cases * More complex backends * Fix benchmarks * More benchmarks * Reactivate JET test * Remove weird build folder * Don't import dangerous stuff before JET test * Re-skip JET * Wrong JET test * Better docstrings, more exhaustive tests, benchmark with NN layer * Minor doc fixes
- Loading branch information
Showing
44 changed files
with
1,271 additions
and
544 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -6,6 +6,7 @@ | |
| /benchmark/*.json | ||
|
|
||
| /docs/build/ | ||
| /docs/src/index.md | ||
|
|
||
| /Manifest.toml | ||
| /docs/Manifest.toml | ||
|
|
||
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,63 +1,210 @@ | ||
| # Run benchmarks locally by calling: | ||
| # julia -e 'using BenchmarkCI; BenchmarkCI.judge(baseline="origin/main"); BenchmarkCI.displayjudgement()' | ||
|
|
||
| using Base: Fix2 | ||
| using BenchmarkTools | ||
| using DifferentiationInterface | ||
| using LinearAlgebra | ||
|
|
||
| using Diffractor: Diffractor | ||
| using Enzyme: Enzyme | ||
| using FiniteDiff: FiniteDiff | ||
| using ForwardDiff: ForwardDiff | ||
| using PolyesterForwardDiff: PolyesterForwardDiff | ||
| using ReverseDiff: ReverseDiff | ||
| using Zygote: Zygote | ||
|
|
||
| scalar_to_scalar(x::Real) = x | ||
| scalar_to_vector(x::Real, n) = collect((1:n) .* x) | ||
| vector_to_scalar(x::AbstractVector{<:Real}) = dot(1:length(x), x) | ||
| vector_to_vector(x::AbstractVector{<:Real}) = (1:length(x)) .* x | ||
| ## Settings | ||
|
|
||
| BenchmarkTools.DEFAULT_PARAMETERS.evals = 1 | ||
| BenchmarkTools.DEFAULT_PARAMETERS.samples = 100 | ||
| BenchmarkTools.DEFAULT_PARAMETERS.seconds = 1 | ||
|
|
||
| ## Functions | ||
|
|
||
| struct Layer{W<:Union{Number,AbstractArray},B<:Union{Number,AbstractArray},S<:Function} | ||
| w::W | ||
| b::B | ||
| σ::S | ||
| end | ||
|
|
||
| function (l::Layer{<:Number,<:Number})(x::Number)::Number | ||
| return l.σ(l.w * x + l.b) | ||
| end | ||
|
|
||
| function (l::Layer{<:AbstractVector,<:AbstractVector})(x::Number)::AbstractVector | ||
| return l.σ.(l.w .* x .+ l.b) | ||
| end | ||
|
|
||
| forward_backends = [EnzymeForwardBackend(), FiniteDiffBackend(), ForwardDiffBackend()] | ||
| function (l::Layer{<:AbstractVector,<:Number})(x::AbstractVector)::Number | ||
| return l.σ(dot(l.w, x) + l.b) | ||
| end | ||
|
|
||
| function (l::Layer{<:AbstractMatrix,<:AbstractVector})(x::AbstractVector)::AbstractVector | ||
| return l.σ.(l.w * x .+ l.b) | ||
| end | ||
|
|
||
| reverse_backends = [ | ||
| ChainRulesReverseBackend(Zygote.ZygoteRuleConfig()), | ||
| EnzymeReverseBackend(), | ||
| ReverseDiffBackend(), | ||
| ## Backends | ||
|
|
||
| forward_custom_backends = [ | ||
| EnzymeForwardBackend(; custom=true), | ||
| FiniteDiffBackend(; custom=true), | ||
| ForwardDiffBackend(; custom=true), | ||
| PolyesterForwardDiffBackend(4; custom=true), | ||
| ] | ||
|
|
||
| forward_fallback_backends = [ | ||
| EnzymeForwardBackend(; custom=false), | ||
| FiniteDiffBackend(; custom=false), | ||
| ForwardDiffBackend(; custom=false), | ||
| ] | ||
|
|
||
| n_values = [10] | ||
| reverse_custom_backends = [ | ||
| ZygoteBackend(; custom=true), | ||
| EnzymeReverseBackend(; custom=true), | ||
| ReverseDiffBackend(; custom=true), | ||
| ] | ||
|
|
||
| reverse_fallback_backends = [ | ||
| ZygoteBackend(; custom=false), | ||
| EnzymeReverseBackend(; custom=false), | ||
| ReverseDiffBackend(; custom=false), | ||
| ] | ||
|
|
||
| all_custom_backends = vcat(forward_custom_backends, reverse_custom_backends) | ||
| all_fallback_backends = vcat(forward_fallback_backends, reverse_fallback_backends) | ||
| all_backends = vcat(all_custom_backends, all_fallback_backends) | ||
|
|
||
| ## Suite | ||
|
|
||
| SUITE = BenchmarkGroup() | ||
|
|
||
| for n in n_values | ||
| for backend in forward_backends | ||
| SUITE["forward"]["scalar_to_scalar"][n][string(backend)] = @benchmarkable begin | ||
| value_and_pushforward!(dy, $backend, scalar_to_scalar, x, dx) | ||
| end setup = (x = 1.0; dx = 1.0; dy = 0.0) evals = 1 | ||
| if backend != EnzymeForwardBackend() # type instability? | ||
| SUITE["forward"]["scalar_to_vector"][n][string(backend)] = @benchmarkable begin | ||
| value_and_pushforward!(dy, $backend, Fix2(scalar_to_vector, $n), x, dx) | ||
| end setup = (x = 1.0; dx = 1.0; dy = zeros($n)) evals = 1 | ||
| ### Scalar to scalar | ||
|
|
||
| scalar_to_scalar = Layer(randn(), randn(), tanh) | ||
|
|
||
| for backend in all_backends | ||
| handles_types(backend, Number, Number) || continue | ||
| SUITE["value_and_derivative"][(1, 1)][string(backend)] = @benchmarkable begin | ||
| value_and_derivative($backend, $scalar_to_scalar, x) | ||
| end setup = (x = randn()) | ||
| end | ||
|
|
||
| for backend in all_fallback_backends | ||
| handles_types(backend, Number, Number) || continue | ||
| if autodiff_mode(backend) == :forward | ||
| SUITE["value_and_pushforward"][(1, 1)][string(backend)] = @benchmarkable begin | ||
| value_and_pushforward($backend, $scalar_to_scalar, x, dx) | ||
| end setup = (x = randn(); dx = randn()) | ||
| else | ||
| SUITE["value_and_pullback"][(1, 1)][string(backend)] = @benchmarkable begin | ||
| value_and_pullback($backend, $scalar_to_scalar, x, dy) | ||
| end setup = (x = randn(); dy = randn()) | ||
| end | ||
| end | ||
|
|
||
| ### Scalar to vector | ||
|
|
||
| for m in [10] | ||
| scalar_to_vector = Layer(randn(m), randn(m), tanh) | ||
|
|
||
| for backend in all_backends | ||
| handles_types(backend, Number, Vector) || continue | ||
| SUITE["value_and_multiderivative"][(1, m)][string(backend)] = @benchmarkable begin | ||
| value_and_multiderivative($backend, $scalar_to_vector, x) | ||
| end setup = (x = randn()) | ||
| SUITE["value_and_multiderivative!"][(1, m)][string(backend)] = @benchmarkable begin | ||
| value_and_multiderivative!(multider, $backend, $scalar_to_vector, x) | ||
| end setup = (x = randn(); multider = zeros($m)) | ||
| end | ||
|
|
||
| for backend in all_fallback_backends | ||
| handles_types(backend, Number, Vector) || continue | ||
| if autodiff_mode(backend) == :forward | ||
| SUITE["value_and_pushforward"][(1, m)][string(backend)] = @benchmarkable begin | ||
| value_and_pushforward($backend, $scalar_to_vector, x, dx) | ||
| end setup = (x = randn(); dx = randn()) | ||
| SUITE["value_and_pushforward!"][(1, m)][string(backend)] = @benchmarkable begin | ||
| value_and_pushforward!(dy, $backend, $scalar_to_vector, x, dx) | ||
| end setup = (x = randn(); dx = randn(); dy = zeros($m)) | ||
| else | ||
| SUITE["value_and_pullback"][(1, m)][string(backend)] = @benchmarkable begin | ||
| value_and_pullback($backend, $scalar_to_vector, x, dy) | ||
| end setup = (x = randn(); dy = ones($m)) | ||
| SUITE["value_and_pullback!"][(1, m)][string(backend)] = @benchmarkable begin | ||
| value_and_pullback!(dx, $backend, $scalar_to_vector, x, dy) | ||
| end setup = (x = randn(); dy = ones($m); dx = 0.0) | ||
| end | ||
| SUITE["forward"]["vector_to_vector"][n][string(backend)] = @benchmarkable begin | ||
| value_and_pushforward!(dy, $backend, vector_to_vector, x, dx) | ||
| end setup = (x = randn($n); dx = randn($n); dy = zeros($n)) evals = 1 | ||
| end | ||
| end | ||
|
|
||
| ### Vector to scalar | ||
|
|
||
| for n in [10] | ||
| vector_to_scalar = Layer(randn(n), randn(), tanh) | ||
|
|
||
| for backend in all_backends | ||
| handles_types(backend, Vector, Number) || continue | ||
| SUITE["value_and_gradient"][(n, 1)][string(backend)] = @benchmarkable begin | ||
| value_and_gradient($backend, $vector_to_scalar, x) | ||
| end setup = (x = randn($n)) | ||
| SUITE["value_and_gradient!"][(n, 1)][string(backend)] = @benchmarkable begin | ||
| value_and_gradient!(grad, $backend, $vector_to_scalar, x) | ||
| end setup = (x = randn($n); grad = zeros($n)) | ||
| end | ||
|
|
||
| for backend in reverse_backends | ||
| if backend != ReverseDiffBackend() | ||
| SUITE["reverse"]["scalar_to_scalar"][n][string(backend)] = @benchmarkable begin | ||
| value_and_pullback!(dx, $backend, scalar_to_scalar, x, dy) | ||
| end setup = (x = 1.0; dy = 1.0; dx = 0.0) evals = 1 | ||
| for backend in all_fallback_backends | ||
| handles_types(backend, Vector, Number) || continue | ||
| if autodiff_mode(backend) == :forward | ||
| SUITE["value_and_pushforward"][(n, 1)][string(backend)] = @benchmarkable begin | ||
| value_and_pushforward($backend, $vector_to_scalar, x, dx) | ||
| end setup = (x = randn($n); dx = randn($n)) | ||
| SUITE["value_and_pushforward!"][(n, 1)][string(backend)] = @benchmarkable begin | ||
| value_and_pushforward!(dy, $backend, $vector_to_scalar, x, dx) | ||
| end setup = (x = randn($n); dx = randn($n); dy = 0.0) | ||
| else | ||
| SUITE["value_and_pullback"][(n, 1)][string(backend)] = @benchmarkable begin | ||
| value_and_pullback($backend, $vector_to_scalar, x, dy) | ||
| end setup = (x = randn($n); dy = randn()) | ||
| SUITE["value_and_pullback!"][(n, 1)][string(backend)] = @benchmarkable begin | ||
| value_and_pullback!(dx, $backend, $vector_to_scalar, x, dy) | ||
| end setup = (x = randn($n); dy = randn(); dx = zeros($n)) | ||
| end | ||
| SUITE["reverse"]["vector_to_scalar"][n][string(backend)] = @benchmarkable begin | ||
| value_and_pullback!(dx, $backend, vector_to_scalar, x, dy) | ||
| end setup = (x = randn($n); dy = 1.0; dx = zeros($n)) evals = 1 | ||
| if backend != EnzymeReverseBackend() | ||
| SUITE["reverse"]["vector_to_vector"][n][string(backend)] = @benchmarkable begin | ||
| value_and_pullback!(dx, $backend, vector_to_vector, x, dy) | ||
| end setup = (x = randn($n); dy = randn($n); dx = zeros($n)) evals = 1 | ||
| end | ||
| end | ||
|
|
||
| ### Vector to vector | ||
|
|
||
| for (n, m) in [(10, 10)] | ||
| vector_to_vector = Layer(randn(m, n), randn(m), tanh) | ||
|
|
||
| for backend in all_backends | ||
| handles_types(backend, Vector, Vector) || continue | ||
| SUITE["value_and_jacobian"][(n, m)][string(backend)] = @benchmarkable begin | ||
| value_and_jacobian($backend, $vector_to_vector, x) | ||
| end setup = (x = randn($n)) | ||
| SUITE["value_and_jacobian!"][(n, m)][string(backend)] = @benchmarkable begin | ||
| value_and_jacobian!(jac, $backend, $vector_to_vector, x) | ||
| end setup = (x = randn($n); jac = zeros($m, $n)) | ||
| end | ||
|
|
||
| for backend in all_fallback_backends | ||
| handles_types(backend, Vector, Vector) || continue | ||
| if autodiff_mode(backend) == :forward | ||
| SUITE["value_and_pushforward"][(n, m)][string(backend)] = @benchmarkable begin | ||
| value_and_pushforward($backend, $vector_to_vector, x, dx) | ||
| end setup = (x = randn($n); dx = randn($n)) | ||
| SUITE["value_and_pushforward!"][(n, m)][string(backend)] = @benchmarkable begin | ||
| value_and_pushforward!(dy, $backend, $vector_to_vector, x, dx) | ||
| end setup = (x = randn($n); dx = randn($n); dy = zeros($m)) | ||
| else | ||
| SUITE["value_and_pullback"][(n, m)][string(backend)] = @benchmarkable begin | ||
| value_and_pullback($backend, $vector_to_vector, x, dy) | ||
| end setup = (x = randn($n); dy = randn($m)) | ||
| SUITE["value_and_pullback!"][(n, m)][string(backend)] = @benchmarkable begin | ||
| value_and_pullback!(dx, $backend, $vector_to_vector, x, dy) | ||
| end setup = (x = randn($n); dy = randn($m); dx = zeros($n)) | ||
| end | ||
| end | ||
| end | ||
|
|
||
| # Run benchmarks locally | ||
| # results = BenchmarkTools.run(SUITE; verbose=true) | ||
|
|
||
| # Compare commits locally | ||
| # using BenchmarkCI; BenchmarkCI.judge(baseline="origin/main"); BenchmarkCI.displayjudgement() |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.