From 55608e7dd1aa593944f967f2549564e4f42b654e Mon Sep 17 00:00:00 2001 From: lloyd Date: Thu, 31 May 2007 03:25:19 +0000 Subject: Write functions to handle loading and saving words a block at a time, taking into account endian differences. The current code does not take advantage of the knowledge of which endianness we are running on; an optimization suggested by Yves Jerschow is to use (unsafe) casts to speed up the load/store operations. This turns out to provide large performance increases (30% or more) in some cases. Even without the unsafe casts, this version seems to average a few percent faster, probably because the longer loading loops have been partially or fully unrolled. This also makes the code implementing low-level algorithms like ciphers and hashes a bit more succint. --- src/md4.cpp | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'src/md4.cpp') diff --git a/src/md4.cpp b/src/md4.cpp index a0a32b179..b4cc4ce17 100644 --- a/src/md4.cpp +++ b/src/md4.cpp @@ -45,7 +45,7 @@ inline void HH(u32bit& A, u32bit B, u32bit C, u32bit D, u32bit M, byte S) void MD4::hash(const byte input[]) { for(u32bit j = 0; j != 16; ++j) - M[j] = make_u32bit(input[4*j+3], input[4*j+2], input[4*j+1], input[4*j]); + M[j] = load_le(input, j); u32bit A = digest[0], B = digest[1], C = digest[2], D = digest[3]; @@ -78,8 +78,8 @@ void MD4::hash(const byte input[]) *************************************************/ void MD4::copy_out(byte output[]) { - for(u32bit j = 0; j != OUTPUT_LENGTH; ++j) - output[j] = get_byte(3 - (j % 4), digest[j/4]); + for(u32bit j = 0; j != OUTPUT_LENGTH; j += 4) + store_le(digest[j/4], output + j); } /************************************************* -- cgit v1.2.3