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.

1 files changed, 8 insertions, 24 deletions

diff --git a/src/des.cpp b/src/des.cpp
index 47bdb8f56..e8f173c5c 100644
--- a/src/des.cpp
+++ b/src/des.cpp
@@ -13,17 +13,13 @@ namespace Botan {
 *************************************************/
 void DES::enc(const byte in[], byte out[]) const
    {
-   u32bit L = make_u32bit(in[0], in[1], in[2], in[3]),
-          R = make_u32bit(in[4], in[5], in[6], in[7]);
+   u32bit L = load_be<u32bit>(in, 0), R = load_be<u32bit>(in, 1);
 
    IP(L, R);
    raw_encrypt(L, R);
    FP(L, R);
 
-   out[0] = get_byte(0, R); out[1] = get_byte(1, R);
-   out[2] = get_byte(2, R); out[3] = get_byte(3, R);
-   out[4] = get_byte(0, L); out[5] = get_byte(1, L);
-   out[6] = get_byte(2, L); out[7] = get_byte(3, L);
+   store_be(out, R, L);
    }
 
 /*************************************************
@@ -31,17 +27,13 @@ void DES::enc(const byte in[], byte out[]) const
 *************************************************/
 void DES::dec(const byte in[], byte out[]) const
    {
-   u32bit L = make_u32bit(in[0], in[1], in[2], in[3]),
-          R = make_u32bit(in[4], in[5], in[6], in[7]);
+   u32bit L = load_be<u32bit>(in, 0), R = load_be<u32bit>(in, 1);
 
    IP(L, R);
    raw_decrypt(L, R);
    FP(L, R);
 
-   out[0] = get_byte(0, R); out[1] = get_byte(1, R);
-   out[2] = get_byte(2, R); out[3] = get_byte(3, R);
-   out[4] = get_byte(0, L); out[5] = get_byte(1, L);
-   out[6] = get_byte(2, L); out[7] = get_byte(3, L);
+   store_be(out, R, L);
    }
 
 /*************************************************
@@ -193,8 +185,7 @@ void DES::key(const byte key[], u32bit)
 *************************************************/
 void TripleDES::enc(const byte in[], byte out[]) const
    {
-   u32bit L = make_u32bit(in[0], in[1], in[2], in[3]),
-          R = make_u32bit(in[4], in[5], in[6], in[7]);
+   u32bit L = load_be<u32bit>(in, 0), R = load_be<u32bit>(in, 1);
 
    DES::IP(L, R);
    des1.raw_encrypt(L, R);
@@ -202,10 +193,7 @@ void TripleDES::enc(const byte in[], byte out[]) const
    des3.raw_encrypt(L, R);
    DES::FP(L, R);
 
-   out[0] = get_byte(0, R); out[1] = get_byte(1, R);
-   out[2] = get_byte(2, R); out[3] = get_byte(3, R);
-   out[4] = get_byte(0, L); out[5] = get_byte(1, L);
-   out[6] = get_byte(2, L); out[7] = get_byte(3, L);
+   store_be(out, R, L);
    }
 
 /*************************************************
@@ -213,8 +201,7 @@ void TripleDES::enc(const byte in[], byte out[]) const
 *************************************************/
 void TripleDES::dec(const byte in[], byte out[]) const
    {
-   u32bit L = make_u32bit(in[0], in[1], in[2], in[3]),
-          R = make_u32bit(in[4], in[5], in[6], in[7]);
+   u32bit L = load_be<u32bit>(in, 0), R = load_be<u32bit>(in, 1);
 
    DES::IP(L, R);
    des3.raw_decrypt(L, R);
@@ -222,10 +209,7 @@ void TripleDES::dec(const byte in[], byte out[]) const
    des1.raw_decrypt(L, R);
    DES::FP(L, R);
 
-   out[0] = get_byte(0, R); out[1] = get_byte(1, R);
-   out[2] = get_byte(2, R); out[3] = get_byte(3, R);
-   out[4] = get_byte(0, L); out[5] = get_byte(1, L);
-   out[6] = get_byte(2, L); out[7] = get_byte(3, L);
+   store_be(out, R, L);
    }
 
 /*************************************************