summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorJohn MacFarlane <jgm@berkeley.edu>2015-06-03 10:23:35 +0200
committerJohn MacFarlane <jgm@berkeley.edu>2015-06-03 10:23:35 +0200
commitdc0e8aac6cd8b891e23a3bd29459eb63b07af3e7 (patch)
treef4d4a0476199414c59c748885b3732bf0d886909
parent9ff1cccc955f108ed76b0039e1ca1b61d44cad56 (diff)
Added note on 64-bit timings in benchmarks.md.
-rw-r--r--benchmarks.md7
1 files changed, 7 insertions, 0 deletions
diff --git a/benchmarks.md b/benchmarks.md
index 58b3de4..848c54a 100644
--- a/benchmarks.md
+++ b/benchmarks.md
@@ -31,3 +31,10 @@ with the benchmark input and the time to run it with no input.
not penalized by startup time.) A median of ten runs is taken. The
process is reniced to a high priority so that the system doesn't
interrupt runs.
+
+Note that these benchmarks were done on a 32-bit machine. On a 64-bit
+machines, sundown is significantly faster than cmark (0.146s vs 0.237s
+on Intel i5/OSX with Clang, 0.130s vs 0.191s on a 64-bit Debian VPS
+with GCC). I do not know why the performance difference shows up on
+the 64-bit architecture and not the 32-bit, but that is something that
+might be investigated.