Tech riderRev. 22 Sept 2026
  1. 1Runs onLinux, Mac, Windows
  2. 2CostsNot stated by the maker
  3. 3Workload areasmemory bandwidth; vector-kernel computation rate; COPY; SCALE; ADD; TRIAD
  4. 4Operating systemsLinux; Windows; DOS; Power Mac
  5. 5Comparison databaseYes
  6. 6Result export formatscomma-delimited raw data files
  7. 7Custom test profilesYes
  8. 8CLI or automationYes
7 lines stated Written from the maker's own pages: cs.virginia.edu
The STREAM homepage

Overview

STREAM is ranked #14 of 65 in PC benchmark software on Specifiction. It runs on Linux, macOS, Windows.

Compared on PC benchmark software

Free plan
Yescs.virginia.edu
Workload areas
memory bandwidth; vector-kernel computation rate; COPY; SCALE; ADD; TRIADcs.virginia.edu
Operating systems
Linux; Windows; DOS; Power Maccs.virginia.edu
Comparison database
Yescs.virginia.edu
Result export formats
comma-delimited raw data filescs.virginia.edu
Custom test profiles
Yescs.virginia.edu
CLI or automation
Yescs.virginia.edu

Facts

Purpose
STREAM is a synthetic benchmark that measures sustainable memory bandwidth and computation rates for simple vector kernels.cs.virginia.edu · 5 Oct 2026
Intended use
It is designed to use datasets much larger than available cache, to make results more indicative of large vector style applications.cs.virginia.edu · 5 Oct 2026
Kernels
The benchmark repeats four kernels: Copy, Scale, Add, and Triad.cs.virginia.edu · 5 Oct 2026
Source languages
The maker recommends compiling the source code, which is available in C or Fortran.cs.virginia.edu · 5 Oct 2026
Parallel runs
The standard C and Fortran code includes OpenMP directives, and an MPI version is available for cluster runs.cs.virginia.edu · 5 Oct 2026
Published results
Results labeled as standard STREAM benchmark results must conform to the STREAM Run Rules; modified or nonconforming runs must be clearly labeled.cs.virginia.edu · 5 Oct 2026
Use and redistribution
The run rules permit use and redistribution, and permit modification for personal use including commercial use, subject to publication restrictions.cs.virginia.edu · 5 Oct 2026
Warranty
The run rules state that no warranty is expressed or implied.cs.virginia.edu · 5 Oct 2026
Results database
The site publishes benchmark results in tables covering bandwidth, machine balance, and equivalent MFLOPS.cs.virginia.edu · 5 Oct 2026
Standards
The standard results set uses C or Fortran versions with 64-bit data types on production hardware and excludes simulated results and significantly modified code.cs.virginia.edu · 5 Oct 2026
Tuned results
The tuned results set allows code modifications, including assembly language, while requiring 64-bit data types on production hardware.cs.virginia.edu · 5 Oct 2026
Windows and Linux binaries
The FAQ lists precompiled binaries for Windows and Linux but describes the available binaries as obsolete and recommends compiling the source.cs.virginia.edu · 5 Oct 2026
Maintainer
The FAQ identifies John McCalpin as STREAM's creator and maintainer.cs.virginia.edu · 5 Oct 2026
Project hosting
The site says STREAM is hosted at the University of Virginia in Charlottesville, Virginia.cs.virginia.edu · 5 Oct 2026
Workloads
The benchmark runs four kernels: Copy, Scale, Add, and Triad.cs.virginia.edu · 5 Oct 2026
Cache-sized data
STREAM is designed to use datasets much larger than available cache so results better reflect performance for large vector-style applications.cs.virginia.edu · 5 Oct 2026
Source code
The site recommends compiling the benchmark from its C or Fortran source code.cs.virginia.edu · 5 Oct 2026
Publishing results
Published results called “STREAM benchmark results” must conform to the run rules, and modified-code results must be clearly labelled.cs.virginia.edu · 5 Oct 2026
Project status
The site describes STREAM as an independent academic project hosted at the University of Virginia.cs.virginia.edu · 5 Oct 2026

Best STREAM alternatives

See all 20

Where it ranks on Specifiction

Is STREAM yours?

Claim it for free: prove the domain, then correct facts, plans and screenshots. An editor reviews every change.

Sources