diff options
| author | lloyd <[email protected]> | 2008-11-23 02:03:16 +0000 |
|---|---|---|
| committer | lloyd <[email protected]> | 2008-11-23 02:03:16 +0000 |
| commit | f4ad8ecfa14b59dbf06a9595f8dacccb3b7f04e3 (patch) | |
| tree | 76077c951bb44373ad7c2ca632f2e24cf758e88f /src/hash/sha1_sse2 | |
| parent | 8ec4a1fe7e8af6f8223908cdf8fe7de39170fc2a (diff) | |
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
Diffstat (limited to 'src/hash/sha1_sse2')
| -rw-r--r-- | src/hash/sha1_sse2/sha1_sse2.cpp | 8 | ||||
| -rw-r--r-- | src/hash/sha1_sse2/sha1_sse2.h | 2 |
2 files changed, 7 insertions, 3 deletions
diff --git a/src/hash/sha1_sse2/sha1_sse2.cpp b/src/hash/sha1_sse2/sha1_sse2.cpp index 1d47cb1df..e2e0352fe 100644 --- a/src/hash/sha1_sse2/sha1_sse2.cpp +++ b/src/hash/sha1_sse2/sha1_sse2.cpp @@ -10,9 +10,13 @@ namespace Botan { /************************************************* * SHA-160 Compression Function * *************************************************/ -void SHA_160_SSE2::hash(const byte input[]) +void SHA_160_SSE2::compress_n(const byte input[], u32bit blocks) { - botan_sha1_sse2_compress(digest, reinterpret_cast<const u32bit*>(input)); + for(u32bit i = 0; i != blocks; ++i) + { + botan_sha1_sse2_compress(digest, reinterpret_cast<const u32bit*>(input)); + input += HASH_BLOCK_SIZE; + } } } diff --git a/src/hash/sha1_sse2/sha1_sse2.h b/src/hash/sha1_sse2/sha1_sse2.h index 4bd8c1baa..57348e461 100644 --- a/src/hash/sha1_sse2/sha1_sse2.h +++ b/src/hash/sha1_sse2/sha1_sse2.h @@ -19,7 +19,7 @@ class BOTAN_DLL SHA_160_SSE2 : public SHA_160 HashFunction* clone() const { return new SHA_160_SSE2; } SHA_160_SSE2() : SHA_160(0) {} // no W needed private: - void hash(const byte[]); + void compress_n(const byte[], u32bit blocks); }; extern "C" void botan_sha1_sse2_compress(u32bit[5], const u32bit*); |