Jukka Aho 2e48a356a3 bench: Add GPU benchmarks test script ...

Shell script for quick validation of GPU benchmarks without running
full suites (which can take minutes on large problem sizes).

Features:
- Julia installation check (version validation)
- GPU availability detection (nvidia-smi query)
- CUDA.jl functionality verification
- Quick state management test (10K elements, not 1M)
- Quick matrix-free test (1K DOFs, not 1M)
- Both CPU and GPU paths tested
- Error handling with informative messages

Runs small problem sizes to verify:
- Code compiles and loads correctly
- CUDA kernels launch without errors
- Basic functionality works before long benchmarks
- Development workflow (test before full run)

Executable: chmod +x benchmarks/test_gpu_benchmarks.sh (159 lines)

2025-11-12 00:19:50 +02:00

..

results

feat(benchmark): Validate O(n) vs O(1) struct scaling hypothesis

2025-11-09 21:00:51 +02:00

basis_function_access_patterns.jl

bench: Add basis function access pattern benchmark for Tet10

2025-11-12 00:09:42 +02:00

basis_function_access_tet10.jl

bench: Add Tet10 basis function access benchmark

2025-11-12 00:10:31 +02:00

deformation_gradient_analysis.jl

bench: Add deformation gradient performance analysis

2025-11-12 00:10:49 +02:00

element_immutability_benchmark.jl

docs(design): Add immutability design doc with comprehensive benchmark

2025-11-09 17:51:34 +02:00

field_storage_comparison.jl

perf(benchmarks): Add field storage performance comparison script

2025-11-09 11:07:53 +02:00

gpu_state_management_benchmark.jl

bench: Add GPU state management strategy comparison

2025-11-12 00:13:30 +02:00

integration_points_benchmark.jl

bench: Add integration point access pattern comparison

2025-11-12 00:16:50 +02:00

linear_elastic_analysis.jl

bench: Add comprehensive linear elastic material analysis

2025-11-12 00:17:08 +02:00

material_models_benchmark_results.txt

bench: Add material models benchmark execution results

2025-11-12 00:18:16 +02:00

material_models_benchmark.jl

bench: Add comprehensive material models performance comparison

2025-11-12 00:17:30 +02:00

matrix_free_gpu_benchmark.jl

bench: Add matrix-free Newton-Krylov GPU benchmark

2025-11-12 00:18:46 +02:00

multigpu_mpi_benchmark.jl

feat(gpu): Multi-GPU MPI benchmark with nodal assembly

2025-11-09 15:59:00 +02:00

multigpu_results_2025-11-09.md

feat(gpu): Multi-GPU MPI benchmark with nodal assembly

2025-11-09 15:59:00 +02:00

neo_hookean_analysis.jl

bench: Add Neo-Hookean hyperelastic material analysis

2025-11-12 00:19:10 +02:00

nodal_assembly_scalability.jl

perf(benchmark): Add CPU nodal assembly scalability benchmark

2025-11-09 16:04:39 +02:00

perfect_plasticity_analysis.jl

bench: Add perfect plasticity material performance analysis

2025-11-12 00:19:30 +02:00

README_GPU_BENCHMARKS.md

docs: Add GPU benchmark suite documentation

2025-11-12 00:09:18 +02:00

struct_size_scaling.jl

feat(benchmark): Validate O(n) vs O(1) struct scaling hypothesis

2025-11-09 21:00:51 +02:00

test_gpu_benchmarks.sh

bench: Add GPU benchmarks test script

2025-11-12 00:19:50 +02:00

tet10_derivatives_benchmark.jl

docs: Benchmark manual vs AD derivatives for Tet10

2025-11-09 03:41:47 +02:00

VALIDATION_RESULTS.md

docs(benchmarks): Add validation results for field storage design

2025-11-09 11:08:22 +02:00