diff --git a/READEME.md b/READEME.md new file mode 100644 index 0000000..b7aa55a --- /dev/null +++ b/READEME.md @@ -0,0 +1,11 @@ +# AgResearch Scientific Compute Platform Benchmark Suite + +This repository includes benchmarks that will be used to ensure the fit for purpose and to measure the performance of the Scientific Compute Platform in AgResearch. Benchmarks are classified into three categories: + +* Science - based on science applications that are frequently run or are expected to run on the platform. It benchmarks the platform's capability on supporting strategically important applications; + +* Workflow - based on science workflows that are frequently run or are expected to run on the platform. It benchmarks the platform's capability and also capacity on support strategically important workflows. A workflow is a series of runs of science applications; + +* Platform - well known HPC platform benchmarks which measure performance of the platform in an theoretical way. + +Each individual benchmark has its own README file which describes the purpose of the benchmark, how to run the benchmark and how to verify its output(s). diff --git a/platfrom/HPCG/HPCG.md b/platfrom/HPCG/HPCG.md new file mode 100644 index 0000000..e69de29 diff --git a/platfrom/HPC_Challenge/HPC_Challenge.md b/platfrom/HPC_Challenge/HPC_Challenge.md new file mode 100644 index 0000000..e69de29 diff --git a/platfrom/IOR/IOR.md b/platfrom/IOR/IOR.md new file mode 100644 index 0000000..e69de29 diff --git a/platfrom/IOZONE/IOZONE.md b/platfrom/IOZONE/IOZONE.md new file mode 100644 index 0000000..5daa9bc --- /dev/null +++ b/platfrom/IOZONE/IOZONE.md @@ -0,0 +1,30 @@ +# IOzone Filesystem Benchmark + +IOzone is a free filesystem benchmark tool. It generates and measure a +variety of file operations. + +## Purpose + +This benchmark is used to measure the performance of the platform's filesystem. +It measures the performance of the following operations: *Read, write, re-read, r +e-write, read backwards, read strided, fread, fwrite, random read, pread ,mmap, +aio_read, aio_write.* + +## Installation + +The benchmark (v3-471)can be downloaded from http://www.iozone.org/src/current/iozone3_471.tar + +Once the file is downloaded, navigate to the directory where the downloaded file is store and use the following instructions to build it: + +``` +tar xf iozone3_471.tar +cd iozone3_471/src +make +# make will display a list of supported platform. Pick the one that matches the platform. +make + +``` + +## Execution + +Instructions for executing this benchmark. to be completed. diff --git a/platfrom/MDTEST/MDTEST.md b/platfrom/MDTEST/MDTEST.md new file mode 100644 index 0000000..e69de29 diff --git a/science/TODO.md b/science/TODO.md new file mode 100644 index 0000000..17313df --- /dev/null +++ b/science/TODO.md @@ -0,0 +1 @@ +Create subdirectories for each science benchmark. diff --git a/template.md b/template.md new file mode 100644 index 0000000..cb8c323 --- /dev/null +++ b/template.md @@ -0,0 +1,21 @@ +# Name of the Benchmark + +## Purpose + +What's the purpose of this benchmark? What is it trying to measure? + +## Installation + +Instructions for obtaining and installing the benchmark. + +### Sample data [optional] + +Instructions for obtaining sample data required to run this benchmark. + +## Execution + +Instructions for executing this benchmark. + +### Output verification [optional] + +Instructions for verifying the output(s) generated by the benchmark meet expectation. diff --git a/workflow/TODO.md b/workflow/TODO.md new file mode 100644 index 0000000..9f3ef43 --- /dev/null +++ b/workflow/TODO.md @@ -0,0 +1 @@ +Create subdirectories for each workflow benchmark.