AutoBench™ 2.0 - Performance Suite
for Multicore Automotive Processors
Find the strengths and weaknesses of multicore automotive processors and systems
- Analyze scalable multicore architectures, memory bottlenecks, thread scheduling support
- Measures the impact of scalability across both data processing and computationally intensive tasks
- Provides an analytical tool for optimizing programs for a specific processor
- Automotive-focused kernels combined in an extensive variety of workload combinations
AutoBench™ 2.0 is a suite of benchmarks that allows processor and system designers to analyze, test, and improve multicore automotive processors. It uses two forms of concurrency:
- Processing multiple data streams: uses common code running over multiple threads and demonstrating how well a processor scales over scalable data inputs.
- Multiple workload processing: shows the scalability of general-purpose processing, demonstrating concurrency over both code and data.
AutoBench 2.0 combines a wide variety of automotive workloads with the EEMBC Multi-Instance-Test Harness (MITH), compatible and portable with most any multicore processors and operating systems. MITH uses a thread-based API (POSIX-compliant) to establish a common programming model that communicates with the benchmark through an abstraction layer and provides a flexible interface to allow a wide variety of thread-enabled workloads to be tested.
The AutoBench 2.0 workloads can be individually parameterized to vary the amount of concurrency being implemented by the benchmark. By applying incrementally challenging and concurrent workloads, system designers can optimize programs for specific processors and systems, as well as assess the impact of memory bottlenecks, cache coherency, and thread scheduling support. The wide variety of workloads support judicious monitoring of parameters that highlight the strengths and weaknesses of multicore automotive processors and systems.
The EEMBC Technology Center offers porting, running, and analysis of AutoBench 2.0 results as one of its testing services.
“Putting multiple execution cores into a single processor does not by itself guarantee greater multiples of processing power. If the application code can't or won't scale with the number of cores, then putting more cores in the car increases cost and complexity without providing any benefit,” said Paul Teich, principal analyst at Tirias Research. “This is why AutoBench 2.0 is so important. It’s designed to show when performance scales across more cores—and when and why it doesn't.”