The Embedded Microprocessor Benchmark Consortium (EEMBC) develops benchmarks to help system designers select the optimal processors and understand the performance and energy characteristics of their systems. EEMBC has benchmark suites targeting cloud and big data, mobile devices (for Android phones and tablets), networking, ultra-low power microcontrollers, the Internet of Things (IOT), digital media, Java, automotive, and other application areas. EEMBC also has benchmarks for general-purpose performance analysis including CoreMark, MultiBench (multicore), and FPMark (floating-point operations).

AutoBench

 

AutoBench is a suite of benchmarks that allow users to predict the performance of microprocessors and microcontrollers in automotive, industrial, and general-purpose applications. Its 16 benchmark kernels include the following:

Generic Workload Tests
These tests include bit manipulation, matrix mapping, a specific floating-point tester, a cache buster, pointer chasing, pulse-width modulation, multiplication, and shift operations (typical of encryption algorithms).

Basic Automotive Algorithms
These tests include controller area network (CAN), tooth-to-spark (locating the engine’s cog when the spark is ignited), angle-to-time conversion, road speed calculation, and table lookup and interpolation.

Signal Processing Algorithms
These tests include algorithms which are becoming increasingly important for sensors used in engine knock detection, vehicle stability control, and occupant safety systems. They include Fast Fourier Transforms (FFT and iFFT), a finite impulse response filter (FIR), an Inverse Discrete Cosine Transform (iDCT), and an Infinite Impulse Response (IIR) filter.

Forthcoming: AutoBench Version 2.0
The AutoBench Version 1.1 benchmarks are intended to be a CPU architecture test. EEMBC’s second generation of automotive benchmarks, AutoBench Version 2.0, will focus more on the system architecture and will include tests for analog-to-digital conversion, digital-to-analog conversion, serial interfaces, and other such peripherals.

AutoBench Benchmark Scores
Since the introduction of AutoBench Version 1.1, scores for approximately 60 processor/compiler combinations tested against this suite have been certified and published. View AutoBench benchmark scores


EEMBC benchmark characterization data allows designers to better understand how to interpret EEMBC benchmark scores relative to certain processor characteristics. The Kiviat graph above, visualizes multivariable data in a way that easily reveals program behavior, shows workload characteristics for the BaseFP benchmark within AutoBench 1.1.

Chairperson

  • Matt Montgomery, Volkswagen of America, Inc.

In Development

AMEBENCH

Automotive Microcontroller Efficiency

A collaborative project with the Volkswagen Group (and open to other automotive OEMs and Tier 1 suppliers) to establish a benchmark for microcontrollers aimed at making automotive end products more energy aware and more robust.

The new benchmark suite will include individual tests of the microcontroller to measure the power consumption of the CPU and peripherals under various loads, the amount of time it spends in low-power modes under various CPU/peripheral loads, and the time required to wake the MCU from its low-power states to resume processing.

Moreover, the working group will align this benchmark suite with the AUTOSAR development partnership, utilizing the Microcontroller Abstraction Layer (MCAL) to interface to the underlying microcontroller hardware.