Add a new looping load_be / load_le for loading large arrays at once, and

change some of the hash functions to use it as low hanging fruit.

Probably could use further optimization (just unrolls x4 currently), but
merely having it as syntax is good as it allows optimizing many functions
at once (eg using SSE2 to do 4-way byteswaps).

1 files changed, 2 insertions, 2 deletions

diff --git a/src/hash/skein/skein_512.cpp b/src/hash/skein/skein_512.cpp
index b24efd5f7..e1ca08c15 100644
--- a/src/hash/skein/skein_512.cpp
+++ b/src/hash/skein/skein_512.cpp
@@ -34,8 +34,8 @@ void ubi_512(u64bit H[9], u64bit T[], const byte msg[], u64bit msg_len)
       T[0] += to_proc;
 
       u64bit M[8] = { 0 };
-      for(u32bit j = 0; j != to_proc / 8; ++j)
-         M[j] = load_le<u64bit>(msg, j);
+
+      load_le(M, msg, to_proc / 8);
 
       if(to_proc % 8)
          {