![]() ![]() sorting a set of records in multiple orders.deflate compression/decompression + base64 encoding/decoding.The algorithms are chosen to be independent, quick to execute, but complex enough to represent real-world code. It is basically a loop on multiple algorithms whose execution time has been balanced. The principle is very similar to SPECint or Coremark integer benchmarks. The default number of threads is the number of OS processors, and the default number of workers is 4 times the number of threads.īefore launching the tests, the program displays some information about the CPU extracted from /proc/cpuinfo and the NUMA topology of the system (if available). To build from source (for x86_64, from a x86_64 box):īy default, it runs for a bit more than 20 minutes (10 iterations of 60 seconds each for single and multiple threads). We suggest to use any Linux x86_64 box supporting the Go toolchain (no specific constraint here), and build the ARM binary using cross compilation. The idea is to use the same binaries on all the machines part of the benchmark to make sure the same exact code is run everywhere. It is recommended to build the binaries on a reference machine (eventually different from the machines to be compared by the benchmark). If this is not possible or acceptable, it is easy enough to build it, provided the correct version of the Go compiler is installed. The easiest way to run this tool is to directly download the binaries from github (see the releases). Depending on the hardware, hypervisor, and operating system configuration, it can correspond to a full CPU core, a vCPU, or just a hardware thread. a multi-threaded benchmark)Īn OS processor is defined as an entry in the /proc/cpuinfo file. an estimation of the throughput all the OS processors can sustain (i.e.an estimation of the throughput a single OS processor can sustain (i.e. ![]() It runs a number of throughput oriented tests to establish: It is delivered as static self-contained Go binaries for x86_64 and Aarch64 CPU architectures. It is used at Amadeus to qualify bare-metal and virtual boxes, and compare generations of machines or VMs. Cpubench1a - a CPU benchmark program PurposeĬpubench1a is a CPU benchmark whose purpose is to measure the global computing power of a Linux machine. ![]()
0 Comments
Leave a Reply. |