implementation: finished pre-processing section; updated code
Some checks are pending
CI / Julia ${{ matrix.version }} - ${{ matrix.os }} - ${{ matrix.arch }} - ${{ github.event_name }} (x64, ubuntu-latest, 1.10) (push) Waiting to run
CI / Julia ${{ matrix.version }} - ${{ matrix.os }} - ${{ matrix.arch }} - ${{ github.event_name }} (x64, ubuntu-latest, 1.6) (push) Waiting to run
CI / Julia ${{ matrix.version }} - ${{ matrix.os }} - ${{ matrix.arch }} - ${{ github.event_name }} (x64, ubuntu-latest, pre) (push) Waiting to run

This commit is contained in:
2025-04-26 13:46:23 +02:00
parent ad2eab2e0a
commit e571fa5bd6
10 changed files with 238 additions and 46 deletions

View File

@ -73,16 +73,17 @@ end
# Add /usr/local/cuda/bin in .bashrc to PATH to access ncu and nsys (depending how well this works with my 1080 do it on my machine, otherwise re do the tests and perform them on FH PCs)
# University setup at 10.20.1.7 if needed
compareWithCPU = true
compareWithCPU = false
suite = BenchmarkGroup()
suite["CPU"] = BenchmarkGroup(["CPUInterpreter"])
suite["GPUI"] = BenchmarkGroup(["GPUInterpreter"])
suite["GPUT"] = BenchmarkGroup(["GPUTranspiler"])
varsets_small = 100
varsets_medium = 1000
varsets_large = 10000
# TODO: see CpuInterpreterTests.jl to see how all data is loaded and implement this here
varsets_small = 1000 # 1k should be absolute minimum
varsets_medium = 10000
varsets_large = 100000 # 100k should be absolute maximum (although not as strict as minimum)
if compareWithCPU
X_small = randn(Float32, varsets_small, 5)
@ -112,7 +113,7 @@ suite["GPUT"]["large varset"] = @benchmarkable evaluate_gpu(exprsGPU, X_large_GP
loadparams!(suite, BenchmarkTools.load("params.json")[1], :samples, :evals, :gctrial, :time_tolerance, :evals_set, :gcsample, :seconds, :overhead, :memory_tolerance)
results = run(suite, verbose=true, seconds=180)
results = run(suite, verbose=true, seconds=3600) # 1 hour because of CPU. lets see if more is needed
if compareWithCPU
medianCPU = median(results["CPU"])