blob: 14cf7c83e6ea95896baa44123e49097aecb91ebf [file] [log] [blame]
Notes about performance benchmarks
For each benchmark, here is a brief description and notes about its
strengths and weaknesses.
Artificial stress tests
bigcode1, bigcode2:
- Description: Executes a lot of (nonsensical) code.
- Strengths: Demonstrates the cost of translation which is a large part
of runtime, particularly on larger programs.
- Weaknesses: Highly artificial.
- Description: Does a lot of heap allocation and deallocation, and has a lot
of heap blocks live while doing so.
- Strengths: Stress test for an important sub-system; bug #105039 showed
that inefficiencies in heap allocation can make a big
difference to programs that allocate a lot.
- Weaknesses: Highly artificial -- allocation pattern is not real, and only
a few different size allocations are used.
- Description: Does a lot of stack allocation and deallocation.
- Strengths: Tests for a specific performance bug that existed in 3.1.0 and
all earlier versions.
- Weaknesses: Highly artificial.
Real programs
- Description: Burrows-Wheeler compression and decompression.
- Strengths: A real, widely used program, very similar to the 256.bzip2
SPEC2000 benchmark. Not dominated by any code, the hottest
55 blocks account for only 90% of execution. Has lots of
short blocks and stresses the memory system hard.
- Weaknesses: None, really, it's a good benchmark.
- Description: Does some ray-tracing.
- Strengths: Moderately realistic program.
- Weaknesses: Dominated by sin and cos, which are not widely used, and are
hardware-supported on x86 but not on other platforms such as
- Description: Does a Fast Fourier Transform (FFT).
- Strengths: Tests common FP ops (mostly adding and multiplying array
elements), FFT is a very important operation.
- Weaknesses: Dominated by the inner loop, which is quite long and flatters
Valgrind due to the small dispatcher overhead.
- Description: A very small and fast C compiler. A munged version of
Fabrice Bellard's TinyCC compiling itself multiple times.
- Strengths: A real program, lots of code (top 100 blocks only account for
47% of execution), involves large irregular data structures
(presumably, since it's a compiler). Does lots of
malloc/free calls and so changes that make a big improvement
to perf/heap typically cause a small improvement.
- Weaknesses None, really, it's a good benchmark.