Added benchmark for hoedown.

Note that hoedown doesn't show the 32/64 bit difference that
sundown does -- so it was probably a bug in sundown.  Removed
the comments from benchmarks.md about this.

2 files changed, 5 insertions, 12 deletions

diff --git a/README.md b/README.md
index 465efe0..ff0fa3f 100644
--- a/README.md
+++ b/README.md
@@ -22,8 +22,8 @@ Advantages of this library:
   C99 and have no external dependencies.  It has been tested with
   MSVC, gcc, tcc, and clang.
 
-- **Fast.** Performance is on par with the fastest existing
-  Markdown parser, [sundown]:  see the [benchmarks].
+- **Fast.** Performance is very good, on par with the fastest
+  Markdown processors:  see the [benchmarks].
 
 - **Accurate.** The library passes all CommonMark conformance tests.
 
diff --git a/benchmarks.md b/benchmarks.md
index 848c54a..e905119 100644
--- a/benchmarks.md
+++ b/benchmarks.md
@@ -14,9 +14,9 @@ Some benchmarks, run on an ancient Thinkpad running Intel Core 2 Duo at 2GHz.
 | marked            |    1.94    |
 | **commonmark.js** |    1.93    |
 | discount          |    1.86    |
-| sundown           |    0.33    |
-| **cmark**         |    0.33    |
-
+| **cmark**         |    0.35    |
+| sundown           |    0.34    |
+| hoedown           |    0.21    |
 
 To run these benchmarks, use `make bench PROG=/path/to/program`.
 
@@ -31,10 +31,3 @@ 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.