I had not anticipated this being really worthwhile, but it turns out

to have been so! Change MDx_HashFunction::hash to a new compress_n
which hashes an arbitrary number of blocks. I had a thought this might
reduce a bit of loop overhead but the results were far better than I
anticipated. Speedup across the board of about 2%, and very
noticable (+10%) increases for MD4 and Tiger (probably b/c both
of those have so few instructions in each iteration of the
compression function).

Before:
SHA-1:
  amd64: 211.9 MiB/s
  core: 210.0 MiB/s
  sse2: 295.2 MiB/s

MD4: 476.2 MiB/s
MD5: 355.2 MiB/s
SHA-256: 99.8 MiB/s
SHA-512: 151.4 MiB/s
RIPEMD-128: 326.9 MiB/s
RIPEMD-160: 225.1 MiB/s
Tiger: 214.8 MiB/s
Whirlpool: 38.4 MiB/s

After:
SHA-1:
  amd64: 215.6 MiB/s
  core: 213.8 MiB/s
  sse2: 299.9 MiB/s

MD4: 528.4 MiB/s
MD5: 368.8 MiB/s
SHA-256: 103.9 MiB/s
SHA-512: 156.8 MiB/s
RIPEMD-128: 334.8 MiB/s
RIPEMD-160: 229.7 MiB/s
Tiger: 240.7 MiB/s
Whirlpool: 38.6 MiB/s

1 files changed, 12 insertions, 8 deletions

diff --git a/src/hash/mdx_hash/mdx_hash.h b/src/hash/mdx_hash/mdx_hash.h
index b07a78de7..484774aea 100644
--- a/src/hash/mdx_hash/mdx_hash.h
+++ b/src/hash/mdx_hash/mdx_hash.h
@@ -1,7 +1,7 @@
-/*************************************************
-* MDx Hash Function Header File                  *
-* (C) 1999-2007 Jack Lloyd                       *
-*************************************************/
+/**
+* MDx Hash Function Header File
+* (C) 1999-2008 Jack Lloyd
+*/
 
 #ifndef BOTAN_MDX_BASE_H__
 #define BOTAN_MDX_BASE_H__
@@ -10,9 +10,9 @@
 
 namespace Botan {
 
-/*************************************************
-* MDx Hash Function Base Class                   *
-*************************************************/
+/**
+* MDx Hash Function Base Class
+*/
 class BOTAN_DLL MDx_HashFunction : public HashFunction
    {
    public:
@@ -27,7 +27,11 @@ class BOTAN_DLL MDx_HashFunction : public HashFunction
       void add_data(const byte[], u32bit);
       void final_result(byte output[]);
 
-      virtual void hash(const byte[]) = 0;
+      // these are mutually recurisve unless one is overridden
+      // (backwards compatability hack)
+      virtual void compress_n(const byte block[], u32bit block_n) = 0;
+      //virtual void hash(const byte[]);
+
       virtual void copy_out(byte[]) = 0;
       virtual void write_count(byte[]);