Benchmarks

Case Study: Benchmarks for Tools, Software Libraries, and More

System developers often rely on processor benchmarks to gauge system performance. However, the processor is just one of many components that determines overall performance. Fully understanding system performance requires careful analysis of many other elements, such as code-generation tools and third-party software libraries. Unfortunately, a host of factors can confound attempts to analyze these components. For example, it is difficult to prevent variations in programmer skill and style from Read more...

Jeff Bier’s Impulse Response—Multi-Core Math =

When does 1 GHz + 1 GHz  + 1 GHz  + 1 GHz not necessarily equal 4 GHz?  When you’re calculating the performance potential of a multi-core chip.  Freescale recently introduced a new DSP chip, the MSC8144, that contains four 1 GHz SC3400 processor cores. Freescale characterizes the new chip as being “performance-equivalent” to one 4 GHz core. But is it really?  As usual, the answer is, “It depends.”  It depends on what kind of application you’re running, how you map the application onto the Read more...

Case Study: Obtaining the Best Benchmark Results with the Least Engineering Effort

Benchmarks are used by processor vendors for a variety of purposes.  They are used internally for competitive analysis and new product development.  Externally they are used in presentations, articles, and marketing materials to credibly demonstrate the advantages of a processor.  In fact, sophisticated processor users increasing demand independently verified benchmark for use in their processor selection analyses.  Given the importance placed on benchmarks, processor vendors are well advised Read more...

Case Study: Custom Benchmarks

Even for established system designs that have had success using a particular processor, rapidly evolving application requirements and frequently changing processor offerings may necessitate a reevaluation of which processor best meets the product’s needs. The outcome of such a reevaluation can have profound and lasting effects on the future of the product; for example, whether it is competitive in terms of performance, energy efficiency, and cost. Unfortunately, system designers often have Read more...

BDTI Releases C55x+ Benchmark Results

Today BDTI released the first independent benchmark results for the Texas Instruments C55x+ processor core. As its name implies, the C55x+ is based on the C55x architecture. Unlike the C55x, which is available in a variety of chips, the C55x+ will be available only in custom chips for wireless handsets. The first of these products is expected to sample in the first quarter of 2007, with full production expected in 1Q08. BDTI found that the C55x+ will achieve a BDTIsimMark2000™ score of 3160 Read more...

Jeff Bier’s Impulse Response—Bamboozling with Benchmarks, Part 2

In the February 2006 column, I listed four of the Top Ten ways in which processor benchmark results are commonly misused. This month I’ll cover the remaining six. If you rely on benchmark results, you’ll want to watch out for these. Comparing projected benchmark results for a chip that doesn’t yet exist to results for a chip that does. Mixing projected and actual benchmark results isn’t necessarily bad (and can be quite informative) but there are a couple of ways in which it can be Read more...

Jeff Bier’s Impulse Response—Bamboozling with Benchmarks, Part 1

My colleagues and I at BDTI believe very strongly in benchmarks. We’ve been developing and implementing signal processing benchmarks for over a decade, and we know that good benchmarks play an essential role in evaluating processing engines. You can see, then, why we get bent out of shape when benchmarks are used misleadingly. This happens pretty regularly in vendor marketing materials, but we’ve also seen it in training classes and technical articles. Most people don’t set out to use Read more...

BDTI Releases MIPS24KEc Benchmark Scores

Today BDTI released the first independent benchmarks results for the MIPS24KEc licensable processor core. The MIPS24KEc is MIPS’ highest-performance 32-bit core, and it is the first core to incorporate the “DSP ASE” signal-processing instruction-set extensions. (For a discussion of these extensions, see the October 2004 edition of Inside DSP.) BDTI’s analysis shows that these extensions give the MIPS24KEc serious signal-processing capabilities: the MIPS24KEc achieves a BDTImark2000™ score of Read more...

Case Study: Video Benchmarking

Digital video has emerged as one of the hottest markets for DSPs and other types of processors. As a result, many processors now target digital video applications. However, not every processor is up to the challenge. Digital video applications have heavy computation and memory-bandwidth loads, so it’s critical to choose a processor that can handle those demands. For this reason, system and SoC designers who are evaluating processors for digital video applications are strongly motivated to Read more...

Case Study–Benchmarks for Tools, Software Libraries, and More

System developers often rely on processor benchmarks to gauge system performance. However, the processor is just one of many components that determines overall performance. Fully understanding system performance requires careful analysis of many other elements, such as code-generation tools and third-party software libraries. Unfortunately, a host of factors can confound attempts to analyze these components. For example, it is difficult to prevent variations in programmer skill and style from Read more...