Introduction
UnixBench is an open source GPLv2 licensed tool that provides basic metrics on the performance of Unix-like systems.
By running UnixBench, you can get basic indicators about system performance, which can be used for comparison with other systems and can also be used as a reference for improving system performance. But UnixBench is not a comprehensive performance evaluation tool, it only provides some basic performance indicators. To fully evaluate system performance, other tools and tests need to be combined to obtain more comprehensive information.
test environment
| [Hardware parameters] |
|
| processor: |
SOPHON SG2042 x1 |
| Number of cores: | 64 cores |
| L1 Cache: |
I:64KB and D:64KB |
| L2 Cache: |
1MB/Cluster |
| L3 Cache: |
64MB System Cache |
| DRAM: |
Micron 2RX8 32G 3200 RDIMM 4slot |
| [Software Environment] | |
| linux version: | 22.1 |
| gcc version: |
12.2.0 |
| Unixbench version: |
5.1.3 |
Introduction to UnixBench test projects
Dhrystone (integer arithmetic test):
This benchmark is used to measure and compare computer performance. The test focuses on string handling, since it has no floating-point arithmetic. It is affected by factors such as hardware and software design, compiler and linker options, code optimization, cache memory, wait states, and integer data types.
Whetstone (floating point operation test):
Measures the speed and efficiency of floating point operations. The test contains several modules representing mixtures of operations commonly used in scientific applications. It uses many C functions, including floating point and integer math operations such as sin, cos, sqrt, exp, and log, array access, conditional branches, and procedure calls. This test measures both integer and floating point arithmetic.
Execl throughput:
This test measures the number of execl calls that can be performed per second. Execl is part of the exec family of functions, which replaces the current process image with a new one. It and many other similar commands are front-ends to the execve() function.
File Copy test :
This test measures the rate at which data is transferred from one file to another, using different buffer sizes. The file read, write, and copy tests capture the number of characters that can be written, read, and copied within a specified time (default is 10 seconds).
Pipe Throughput test :
Pipes are the simplest form of communication between processes. Pipe throughput is the number of times per second that a process can write 512 bytes to a pipe and read them back. Pipeline throughput testing has no real counterpart in real-world programming.
Pipe-based Context Switching (pipe-based context interaction) test :
This test measures the number of times two processes can exchange incrementing integers over a pipe. Pipeline based context switch tests are more like a real application. The test program spawns a child process that talks through a bidirectional pipe.
Process Creation (process creation) test :
This test measures the number of times a process can fork and reap a child process that exits immediately. Process creation refers to the actual creation of the process control block and memory allocation for the new process, so memory bandwidth is directly involved. Typically, this benchmark is used to compare implementations of various operating system process creation calls.
Shell Scripts test :
The Shell Script test measures the number of times per minute that a process can start and retract a set of one, two, four, and eight concurrent copies of a shell script that performs a series of transformations on a data file.
System Call Overhead (system call consumption) test :
Estimate the cost of entering and leaving the operating system kernel, that is, the overhead of executing system calls. It consists of a simple program repeatedly calling the getpid (returns the process ID of the calling process) system call. The time required to execute such calls is used to estimate the cost of entering and exiting the kernel.
Graphical Tests (graphics) test :
2D and 3D graphics tests are provided; currently, the 3D suite in particular is very limited and only contains the "ubgears" program. These tests are designed to provide an overview of the system's 2D and 3D graphics performance. Of course, reported performance depends not only on the hardware, but also on whether the system has the appropriate drivers.
test
Execute command test:
ubuntu@perfxlab:/public/benchmark/byte-unixbench_v5.1.3/UnixBench# ./Run64 core test results
in conclusion
Based on the provided UnixBench benchmark results, system performance testing was conducted on multi-core scenarios. In the multi-core test, all 64 CPU cores are used for parallel testing.
On the whole, the multi-core test clearly demonstrates the parallel computing advantages of the system, and the performance indicators have been greatly improved in all aspects. These test results help to evaluate the performance of the system under different loads, and provide a reference for optimizing system configuration and selecting appropriate hardware. It should be noted that different application scenarios may have different requirements for performance, so it is important to comprehensively consider the indicators of various aspects.
End of text
-
About HS-2
The HS-2 RISC-V universal motherboard is a standard mATX motherboard designed for developers jointly developed by Pengfeng Technology and its partners. It is pre-installed with a software package customized and developed by Pengfeng Technology for RISC-V high-performance servers. Including various standard benchmarks, GCC compilers supporting V extensions, computing libraries, middleware, and a variety of typical server applications.
The HS-2 RISC-V general-purpose motherboard is equipped with a domestic RISC-V 64-core processor (SG2042). SG2042 is the highest-performance RISC-V processor currently in mass production. It is mainly designed for the needs of high-performance computing and is suitable for large computing power application scenarios such as scientific computing, engineering computing, AI computing, and fusion computing.
-
About the RISC-V public test platform
RISC-V high-performance processor public test cloud platform · quick use guide, download link: https://www.kdocs.cn/l/cmnYcyFIlVRx
-
RISC-V public test cloud platform series of articles
-
RISC-V Public Test Platform Released Stream Bandwidth Complete Test
-
RISC-V public beta platform released·The first WEB Server "Hello RISC-V world!"
-
RISC-V public beta platform released·How to play k3s on SG2042
-
"RISC-V Growth Diary" blog released, the first blog running on RISC-V server?
-
RISC-V public beta platform released: How to play OpenMPI on SG2042
-
RISC-V public beta platform released: Compiling The Fedora Linux Kernel Natively on RISC-V
-
RISC-V public beta platform released·Unix Bench complete test (this article)