[PATCH 1/1] Improved ripemd160 perfromance

Meta Schima metaschima at inbox.com
Fri Aug 22 00:34:58 CEST 2014


Hello, I am new to the mailing list. I have a patch here to improve ripemd160 performance by interleaving left and right lanes. On my system before:
Hash:
                |  nanosecs/byte   mebibytes/sec   cycles/byte
 RIPEMD160      |      3.31 ns/B     288.1 MiB/s         - c/B
after:
Hash:
                |  nanosecs/byte   mebibytes/sec   cycles/byte
 RIPEMD160      |      2.08 ns/B     458.3 MiB/s         - c/B

Note that I removed one temporary u32 variable, and this reduces the stack burn from 108 to 104, hope this is right.

~ Andrei

----
diff -ruNp libgcrypt-1.6.2/cipher/rmd160.c libgcrypt-1.6.3/cipher/rmd160.c
--- libgcrypt-1.6.2/cipher/rmd160.c	2014-08-21 07:50:39.000000000 -0500
+++ libgcrypt-1.6.3/cipher/rmd160.c	2014-08-21 17:15:13.678664524 -0500
@@ -178,8 +178,7 @@ static unsigned int
 transform ( void *ctx, const unsigned char *data )
 {
   RMD160_CONTEXT *hd = ctx;
-  register u32 a,b,c,d,e;
-  u32 aa,bb,cc,dd,ee,t;
+  register u32 al, ar, bl, br, cl, cr, dl, dr, el, er;
   u32 x[16];
   int i;
 
@@ -201,196 +200,186 @@ transform ( void *ctx, const unsigned ch
 #define F2(x,y,z)   ( ((x) | ~(y)) ^ (z) )
 #define F3(x,y,z)   ( ((x) & (z)) | ((y) & ~(z)) )
 #define F4(x,y,z)   ( (x) ^ ((y) | ~(z)) )
-#define R(a,b,c,d,e,f,k,r,s) do { t = a + f(b,c,d) + k + x[r]; \
-				  a = rol(t,s) + e;	       \
+#define R(a,b,c,d,e,f,k,r,s) do { a += f(b,c,d) + k + x[r]; \
+				  a = rol(a,s) + e;	       \
 				  c = rol(c,10);	       \
 				} while(0)
 
-  /* left lane */
-  a = hd->h0;
-  b = hd->h1;
-  c = hd->h2;
-  d = hd->h3;
-  e = hd->h4;
-  R( a, b, c, d, e, F0, K0,  0, 11 );
-  R( e, a, b, c, d, F0, K0,  1, 14 );
-  R( d, e, a, b, c, F0, K0,  2, 15 );
-  R( c, d, e, a, b, F0, K0,  3, 12 );
-  R( b, c, d, e, a, F0, K0,  4,  5 );
-  R( a, b, c, d, e, F0, K0,  5,  8 );
-  R( e, a, b, c, d, F0, K0,  6,  7 );
-  R( d, e, a, b, c, F0, K0,  7,  9 );
-  R( c, d, e, a, b, F0, K0,  8, 11 );
-  R( b, c, d, e, a, F0, K0,  9, 13 );
-  R( a, b, c, d, e, F0, K0, 10, 14 );
-  R( e, a, b, c, d, F0, K0, 11, 15 );
-  R( d, e, a, b, c, F0, K0, 12,  6 );
-  R( c, d, e, a, b, F0, K0, 13,  7 );
-  R( b, c, d, e, a, F0, K0, 14,  9 );
-  R( a, b, c, d, e, F0, K0, 15,  8 );
-  R( e, a, b, c, d, F1, K1,  7,  7 );
-  R( d, e, a, b, c, F1, K1,  4,  6 );
-  R( c, d, e, a, b, F1, K1, 13,  8 );
-  R( b, c, d, e, a, F1, K1,  1, 13 );
-  R( a, b, c, d, e, F1, K1, 10, 11 );
-  R( e, a, b, c, d, F1, K1,  6,  9 );
-  R( d, e, a, b, c, F1, K1, 15,  7 );
-  R( c, d, e, a, b, F1, K1,  3, 15 );
-  R( b, c, d, e, a, F1, K1, 12,  7 );
-  R( a, b, c, d, e, F1, K1,  0, 12 );
-  R( e, a, b, c, d, F1, K1,  9, 15 );
-  R( d, e, a, b, c, F1, K1,  5,  9 );
-  R( c, d, e, a, b, F1, K1,  2, 11 );
-  R( b, c, d, e, a, F1, K1, 14,  7 );
-  R( a, b, c, d, e, F1, K1, 11, 13 );
-  R( e, a, b, c, d, F1, K1,  8, 12 );
-  R( d, e, a, b, c, F2, K2,  3, 11 );
-  R( c, d, e, a, b, F2, K2, 10, 13 );
-  R( b, c, d, e, a, F2, K2, 14,  6 );
-  R( a, b, c, d, e, F2, K2,  4,  7 );
-  R( e, a, b, c, d, F2, K2,  9, 14 );
-  R( d, e, a, b, c, F2, K2, 15,  9 );
-  R( c, d, e, a, b, F2, K2,  8, 13 );
-  R( b, c, d, e, a, F2, K2,  1, 15 );
-  R( a, b, c, d, e, F2, K2,  2, 14 );
-  R( e, a, b, c, d, F2, K2,  7,  8 );
-  R( d, e, a, b, c, F2, K2,  0, 13 );
-  R( c, d, e, a, b, F2, K2,  6,  6 );
-  R( b, c, d, e, a, F2, K2, 13,  5 );
-  R( a, b, c, d, e, F2, K2, 11, 12 );
-  R( e, a, b, c, d, F2, K2,  5,  7 );
-  R( d, e, a, b, c, F2, K2, 12,  5 );
-  R( c, d, e, a, b, F3, K3,  1, 11 );
-  R( b, c, d, e, a, F3, K3,  9, 12 );
-  R( a, b, c, d, e, F3, K3, 11, 14 );
-  R( e, a, b, c, d, F3, K3, 10, 15 );
-  R( d, e, a, b, c, F3, K3,  0, 14 );
-  R( c, d, e, a, b, F3, K3,  8, 15 );
-  R( b, c, d, e, a, F3, K3, 12,  9 );
-  R( a, b, c, d, e, F3, K3,  4,  8 );
-  R( e, a, b, c, d, F3, K3, 13,  9 );
-  R( d, e, a, b, c, F3, K3,  3, 14 );
-  R( c, d, e, a, b, F3, K3,  7,  5 );
-  R( b, c, d, e, a, F3, K3, 15,  6 );
-  R( a, b, c, d, e, F3, K3, 14,  8 );
-  R( e, a, b, c, d, F3, K3,  5,  6 );
-  R( d, e, a, b, c, F3, K3,  6,  5 );
-  R( c, d, e, a, b, F3, K3,  2, 12 );
-  R( b, c, d, e, a, F4, K4,  4,  9 );
-  R( a, b, c, d, e, F4, K4,  0, 15 );
-  R( e, a, b, c, d, F4, K4,  5,  5 );
-  R( d, e, a, b, c, F4, K4,  9, 11 );
-  R( c, d, e, a, b, F4, K4,  7,  6 );
-  R( b, c, d, e, a, F4, K4, 12,  8 );
-  R( a, b, c, d, e, F4, K4,  2, 13 );
-  R( e, a, b, c, d, F4, K4, 10, 12 );
-  R( d, e, a, b, c, F4, K4, 14,  5 );
-  R( c, d, e, a, b, F4, K4,  1, 12 );
-  R( b, c, d, e, a, F4, K4,  3, 13 );
-  R( a, b, c, d, e, F4, K4,  8, 14 );
-  R( e, a, b, c, d, F4, K4, 11, 11 );
-  R( d, e, a, b, c, F4, K4,  6,  8 );
-  R( c, d, e, a, b, F4, K4, 15,  5 );
-  R( b, c, d, e, a, F4, K4, 13,  6 );
-
-  aa = a; bb = b; cc = c; dd = d; ee = e;
-
-  /* right lane */
-  a = hd->h0;
-  b = hd->h1;
-  c = hd->h2;
-  d = hd->h3;
-  e = hd->h4;
-  R( a, b, c, d, e, F4, KK0,	5,  8);
-  R( e, a, b, c, d, F4, KK0, 14,  9);
-  R( d, e, a, b, c, F4, KK0,	7,  9);
-  R( c, d, e, a, b, F4, KK0,	0, 11);
-  R( b, c, d, e, a, F4, KK0,	9, 13);
-  R( a, b, c, d, e, F4, KK0,	2, 15);
-  R( e, a, b, c, d, F4, KK0, 11, 15);
-  R( d, e, a, b, c, F4, KK0,	4,  5);
-  R( c, d, e, a, b, F4, KK0, 13,  7);
-  R( b, c, d, e, a, F4, KK0,	6,  7);
-  R( a, b, c, d, e, F4, KK0, 15,  8);
-  R( e, a, b, c, d, F4, KK0,	8, 11);
-  R( d, e, a, b, c, F4, KK0,	1, 14);
-  R( c, d, e, a, b, F4, KK0, 10, 14);
-  R( b, c, d, e, a, F4, KK0,	3, 12);
-  R( a, b, c, d, e, F4, KK0, 12,  6);
-  R( e, a, b, c, d, F3, KK1,	6,  9);
-  R( d, e, a, b, c, F3, KK1, 11, 13);
-  R( c, d, e, a, b, F3, KK1,	3, 15);
-  R( b, c, d, e, a, F3, KK1,	7,  7);
-  R( a, b, c, d, e, F3, KK1,	0, 12);
-  R( e, a, b, c, d, F3, KK1, 13,  8);
-  R( d, e, a, b, c, F3, KK1,	5,  9);
-  R( c, d, e, a, b, F3, KK1, 10, 11);
-  R( b, c, d, e, a, F3, KK1, 14,  7);
-  R( a, b, c, d, e, F3, KK1, 15,  7);
-  R( e, a, b, c, d, F3, KK1,	8, 12);
-  R( d, e, a, b, c, F3, KK1, 12,  7);
-  R( c, d, e, a, b, F3, KK1,	4,  6);
-  R( b, c, d, e, a, F3, KK1,	9, 15);
-  R( a, b, c, d, e, F3, KK1,	1, 13);
-  R( e, a, b, c, d, F3, KK1,	2, 11);
-  R( d, e, a, b, c, F2, KK2, 15,  9);
-  R( c, d, e, a, b, F2, KK2,	5,  7);
-  R( b, c, d, e, a, F2, KK2,	1, 15);
-  R( a, b, c, d, e, F2, KK2,	3, 11);
-  R( e, a, b, c, d, F2, KK2,	7,  8);
-  R( d, e, a, b, c, F2, KK2, 14,  6);
-  R( c, d, e, a, b, F2, KK2,	6,  6);
-  R( b, c, d, e, a, F2, KK2,	9, 14);
-  R( a, b, c, d, e, F2, KK2, 11, 12);
-  R( e, a, b, c, d, F2, KK2,	8, 13);
-  R( d, e, a, b, c, F2, KK2, 12,  5);
-  R( c, d, e, a, b, F2, KK2,	2, 14);
-  R( b, c, d, e, a, F2, KK2, 10, 13);
-  R( a, b, c, d, e, F2, KK2,	0, 13);
-  R( e, a, b, c, d, F2, KK2,	4,  7);
-  R( d, e, a, b, c, F2, KK2, 13,  5);
-  R( c, d, e, a, b, F1, KK3,	8, 15);
-  R( b, c, d, e, a, F1, KK3,	6,  5);
-  R( a, b, c, d, e, F1, KK3,	4,  8);
-  R( e, a, b, c, d, F1, KK3,	1, 11);
-  R( d, e, a, b, c, F1, KK3,	3, 14);
-  R( c, d, e, a, b, F1, KK3, 11, 14);
-  R( b, c, d, e, a, F1, KK3, 15,  6);
-  R( a, b, c, d, e, F1, KK3,	0, 14);
-  R( e, a, b, c, d, F1, KK3,	5,  6);
-  R( d, e, a, b, c, F1, KK3, 12,  9);
-  R( c, d, e, a, b, F1, KK3,	2, 12);
-  R( b, c, d, e, a, F1, KK3, 13,  9);
-  R( a, b, c, d, e, F1, KK3,	9, 12);
-  R( e, a, b, c, d, F1, KK3,	7,  5);
-  R( d, e, a, b, c, F1, KK3, 10, 15);
-  R( c, d, e, a, b, F1, KK3, 14,  8);
-  R( b, c, d, e, a, F0, KK4, 12,  8);
-  R( a, b, c, d, e, F0, KK4, 15,  5);
-  R( e, a, b, c, d, F0, KK4, 10, 12);
-  R( d, e, a, b, c, F0, KK4,	4,  9);
-  R( c, d, e, a, b, F0, KK4,	1, 12);
-  R( b, c, d, e, a, F0, KK4,	5,  5);
-  R( a, b, c, d, e, F0, KK4,	8, 14);
-  R( e, a, b, c, d, F0, KK4,	7,  6);
-  R( d, e, a, b, c, F0, KK4,	6,  8);
-  R( c, d, e, a, b, F0, KK4,	2, 13);
-  R( b, c, d, e, a, F0, KK4, 13,  6);
-  R( a, b, c, d, e, F0, KK4, 14,  5);
-  R( e, a, b, c, d, F0, KK4,	0, 15);
-  R( d, e, a, b, c, F0, KK4,	3, 13);
-  R( c, d, e, a, b, F0, KK4,	9, 11);
-  R( b, c, d, e, a, F0, KK4, 11, 11);
-
-
-  t	   = hd->h1 + d + cc;
-  hd->h1 = hd->h2 + e + dd;
-  hd->h2 = hd->h3 + a + ee;
-  hd->h3 = hd->h4 + b + aa;
-  hd->h4 = hd->h0 + c + bb;
-  hd->h0 = t;
+  /* left lane and right lanes interleaved */
+  al = ar = hd->h0;
+  bl = br = hd->h1;
+  cl = cr = hd->h2;
+  dl = dr = hd->h3;
+  el = er = hd->h4;
+  R( al, bl, cl, dl, el, F0, K0,  0, 11 );
+  R( ar, br, cr, dr, er, F4, KK0,	5,  8);
+  R( el, al, bl, cl, dl, F0, K0,  1, 14 );
+  R( er, ar, br, cr, dr, F4, KK0, 14,  9);
+  R( dl, el, al, bl, cl, F0, K0,  2, 15 );
+  R( dr, er, ar, br, cr, F4, KK0,	7,  9);
+  R( cl, dl, el, al, bl, F0, K0,  3, 12 );
+  R( cr, dr, er, ar, br, F4, KK0,	0, 11);
+  R( bl, cl, dl, el, al, F0, K0,  4,  5 );
+  R( br, cr, dr, er, ar, F4, KK0,	9, 13);
+  R( al, bl, cl, dl, el, F0, K0,  5,  8 );
+  R( ar, br, cr, dr, er, F4, KK0,	2, 15);
+  R( el, al, bl, cl, dl, F0, K0,  6,  7 );
+  R( er, ar, br, cr, dr, F4, KK0, 11, 15);
+  R( dl, el, al, bl, cl, F0, K0,  7,  9 );
+  R( dr, er, ar, br, cr, F4, KK0,	4,  5);
+  R( cl, dl, el, al, bl, F0, K0,  8, 11 );
+  R( cr, dr, er, ar, br, F4, KK0, 13,  7);
+  R( bl, cl, dl, el, al, F0, K0,  9, 13 );
+  R( br, cr, dr, er, ar, F4, KK0,	6,  7);
+  R( al, bl, cl, dl, el, F0, K0, 10, 14 );
+  R( ar, br, cr, dr, er, F4, KK0, 15,  8);
+  R( el, al, bl, cl, dl, F0, K0, 11, 15 );
+  R( er, ar, br, cr, dr, F4, KK0,	8, 11);
+  R( dl, el, al, bl, cl, F0, K0, 12,  6 );
+  R( dr, er, ar, br, cr, F4, KK0,	1, 14);
+  R( cl, dl, el, al, bl, F0, K0, 13,  7 );
+  R( cr, dr, er, ar, br, F4, KK0, 10, 14);
+  R( bl, cl, dl, el, al, F0, K0, 14,  9 );
+  R( br, cr, dr, er, ar, F4, KK0,	3, 12);
+  R( al, bl, cl, dl, el, F0, K0, 15,  8 );
+  R( ar, br, cr, dr, er, F4, KK0, 12,  6);
+  R( el, al, bl, cl, dl, F1, K1,  7,  7 );
+  R( er, ar, br, cr, dr, F3, KK1,	6,  9);
+  R( dl, el, al, bl, cl, F1, K1,  4,  6 );
+  R( dr, er, ar, br, cr, F3, KK1, 11, 13);
+  R( cl, dl, el, al, bl, F1, K1, 13,  8 );
+  R( cr, dr, er, ar, br, F3, KK1,	3, 15);
+  R( bl, cl, dl, el, al, F1, K1,  1, 13 );
+  R( br, cr, dr, er, ar, F3, KK1,	7,  7);
+  R( al, bl, cl, dl, el, F1, K1, 10, 11 );
+  R( ar, br, cr, dr, er, F3, KK1,	0, 12);
+  R( el, al, bl, cl, dl, F1, K1,  6,  9 );
+  R( er, ar, br, cr, dr, F3, KK1, 13,  8);
+  R( dl, el, al, bl, cl, F1, K1, 15,  7 );
+  R( dr, er, ar, br, cr, F3, KK1,	5,  9);
+  R( cl, dl, el, al, bl, F1, K1,  3, 15 );
+  R( cr, dr, er, ar, br, F3, KK1, 10, 11);
+  R( bl, cl, dl, el, al, F1, K1, 12,  7 );
+  R( br, cr, dr, er, ar, F3, KK1, 14,  7);
+  R( al, bl, cl, dl, el, F1, K1,  0, 12 );
+  R( ar, br, cr, dr, er, F3, KK1, 15,  7);
+  R( el, al, bl, cl, dl, F1, K1,  9, 15 );
+  R( er, ar, br, cr, dr, F3, KK1,	8, 12);
+  R( dl, el, al, bl, cl, F1, K1,  5,  9 );
+  R( dr, er, ar, br, cr, F3, KK1, 12,  7);
+  R( cl, dl, el, al, bl, F1, K1,  2, 11 );
+  R( cr, dr, er, ar, br, F3, KK1,	4,  6);
+  R( bl, cl, dl, el, al, F1, K1, 14,  7 );
+  R( br, cr, dr, er, ar, F3, KK1,	9, 15);
+  R( al, bl, cl, dl, el, F1, K1, 11, 13 );
+  R( ar, br, cr, dr, er, F3, KK1,	1, 13);
+  R( el, al, bl, cl, dl, F1, K1,  8, 12 );
+  R( er, ar, br, cr, dr, F3, KK1,	2, 11);
+  R( dl, el, al, bl, cl, F2, K2,  3, 11 );
+  R( dr, er, ar, br, cr, F2, KK2, 15,  9);
+  R( cl, dl, el, al, bl, F2, K2, 10, 13 );
+  R( cr, dr, er, ar, br, F2, KK2,	5,  7);
+  R( bl, cl, dl, el, al, F2, K2, 14,  6 );
+  R( br, cr, dr, er, ar, F2, KK2,	1, 15);
+  R( al, bl, cl, dl, el, F2, K2,  4,  7 );
+  R( ar, br, cr, dr, er, F2, KK2,	3, 11);
+  R( el, al, bl, cl, dl, F2, K2,  9, 14 );
+  R( er, ar, br, cr, dr, F2, KK2,	7,  8);
+  R( dl, el, al, bl, cl, F2, K2, 15,  9 );
+  R( dr, er, ar, br, cr, F2, KK2, 14,  6);
+  R( cl, dl, el, al, bl, F2, K2,  8, 13 );
+  R( cr, dr, er, ar, br, F2, KK2,	6,  6);
+  R( bl, cl, dl, el, al, F2, K2,  1, 15 );
+  R( br, cr, dr, er, ar, F2, KK2,	9, 14);
+  R( al, bl, cl, dl, el, F2, K2,  2, 14 );
+  R( ar, br, cr, dr, er, F2, KK2, 11, 12);
+  R( el, al, bl, cl, dl, F2, K2,  7,  8 );
+  R( er, ar, br, cr, dr, F2, KK2,	8, 13);
+  R( dl, el, al, bl, cl, F2, K2,  0, 13 );
+  R( dr, er, ar, br, cr, F2, KK2, 12,  5);
+  R( cl, dl, el, al, bl, F2, K2,  6,  6 );
+  R( cr, dr, er, ar, br, F2, KK2,	2, 14);
+  R( bl, cl, dl, el, al, F2, K2, 13,  5 );
+  R( br, cr, dr, er, ar, F2, KK2, 10, 13);
+  R( al, bl, cl, dl, el, F2, K2, 11, 12 );
+  R( ar, br, cr, dr, er, F2, KK2,	0, 13);
+  R( el, al, bl, cl, dl, F2, K2,  5,  7 );
+  R( er, ar, br, cr, dr, F2, KK2,	4,  7);
+  R( dl, el, al, bl, cl, F2, K2, 12,  5 );
+  R( dr, er, ar, br, cr, F2, KK2, 13,  5);
+  R( cl, dl, el, al, bl, F3, K3,  1, 11 );
+  R( cr, dr, er, ar, br, F1, KK3,	8, 15);
+  R( bl, cl, dl, el, al, F3, K3,  9, 12 );
+  R( br, cr, dr, er, ar, F1, KK3,	6,  5);
+  R( al, bl, cl, dl, el, F3, K3, 11, 14 );
+  R( ar, br, cr, dr, er, F1, KK3,	4,  8);
+  R( el, al, bl, cl, dl, F3, K3, 10, 15 );
+  R( er, ar, br, cr, dr, F1, KK3,	1, 11);
+  R( dl, el, al, bl, cl, F3, K3,  0, 14 );
+  R( dr, er, ar, br, cr, F1, KK3,	3, 14);
+  R( cl, dl, el, al, bl, F3, K3,  8, 15 );
+  R( cr, dr, er, ar, br, F1, KK3, 11, 14);
+  R( bl, cl, dl, el, al, F3, K3, 12,  9 );
+  R( br, cr, dr, er, ar, F1, KK3, 15,  6);
+  R( al, bl, cl, dl, el, F3, K3,  4,  8 );
+  R( ar, br, cr, dr, er, F1, KK3,	0, 14);
+  R( el, al, bl, cl, dl, F3, K3, 13,  9 );
+  R( er, ar, br, cr, dr, F1, KK3,	5,  6);
+  R( dl, el, al, bl, cl, F3, K3,  3, 14 );
+  R( dr, er, ar, br, cr, F1, KK3, 12,  9);
+  R( cl, dl, el, al, bl, F3, K3,  7,  5 );
+  R( cr, dr, er, ar, br, F1, KK3,	2, 12);
+  R( bl, cl, dl, el, al, F3, K3, 15,  6 );
+  R( br, cr, dr, er, ar, F1, KK3, 13,  9);
+  R( al, bl, cl, dl, el, F3, K3, 14,  8 );
+  R( ar, br, cr, dr, er, F1, KK3,	9, 12);
+  R( el, al, bl, cl, dl, F3, K3,  5,  6 );
+  R( er, ar, br, cr, dr, F1, KK3,	7,  5);
+  R( dl, el, al, bl, cl, F3, K3,  6,  5 );
+  R( dr, er, ar, br, cr, F1, KK3, 10, 15);
+  R( cl, dl, el, al, bl, F3, K3,  2, 12 );
+  R( cr, dr, er, ar, br, F1, KK3, 14,  8);
+  R( bl, cl, dl, el, al, F4, K4,  4,  9 );
+  R( br, cr, dr, er, ar, F0, KK4, 12,  8);
+  R( al, bl, cl, dl, el, F4, K4,  0, 15 );
+  R( ar, br, cr, dr, er, F0, KK4, 15,  5);
+  R( el, al, bl, cl, dl, F4, K4,  5,  5 );
+  R( er, ar, br, cr, dr, F0, KK4, 10, 12);
+  R( dl, el, al, bl, cl, F4, K4,  9, 11 );
+  R( dr, er, ar, br, cr, F0, KK4,	4,  9);
+  R( cl, dl, el, al, bl, F4, K4,  7,  6 );
+  R( cr, dr, er, ar, br, F0, KK4,	1, 12);
+  R( bl, cl, dl, el, al, F4, K4, 12,  8 );
+  R( br, cr, dr, er, ar, F0, KK4,	5,  5);
+  R( al, bl, cl, dl, el, F4, K4,  2, 13 );
+  R( ar, br, cr, dr, er, F0, KK4,	8, 14);
+  R( el, al, bl, cl, dl, F4, K4, 10, 12 );
+  R( er, ar, br, cr, dr, F0, KK4,	7,  6);
+  R( dl, el, al, bl, cl, F4, K4, 14,  5 );
+  R( dr, er, ar, br, cr, F0, KK4,	6,  8);
+  R( cl, dl, el, al, bl, F4, K4,  1, 12 );
+  R( cr, dr, er, ar, br, F0, KK4,	2, 13);
+  R( bl, cl, dl, el, al, F4, K4,  3, 13 );
+  R( br, cr, dr, er, ar, F0, KK4, 13,  6);
+  R( al, bl, cl, dl, el, F4, K4,  8, 14 );
+  R( ar, br, cr, dr, er, F0, KK4, 14,  5);
+  R( el, al, bl, cl, dl, F4, K4, 11, 11 );
+  R( er, ar, br, cr, dr, F0, KK4,	0, 15);
+  R( dl, el, al, bl, cl, F4, K4,  6,  8 );
+  R( dr, er, ar, br, cr, F0, KK4,	3, 13);
+  R( cl, dl, el, al, bl, F4, K4, 15,  5 );
+  R( cr, dr, er, ar, br, F0, KK4,	9, 11);
+  R( bl, cl, dl, el, al, F4, K4, 13,  6 );
+  R( br, cr, dr, er, ar, F0, KK4, 11, 11);
+
+  dr += cl + hd->h1;
+  hd->h1 = hd->h2 + dl + er;
+  hd->h2 = hd->h3 + el + ar;
+  hd->h3 = hd->h4 + al + br;
+  hd->h4 = hd->h0 + bl + cr;
+  hd->h0 = dr;
 
-  return /*burn_stack*/ 108+5*sizeof(void*);
+  return /*burn_stack*/ 104+5*sizeof(void*);
 }
 
 
----

____________________________________________________________
FREE ONLINE PHOTOSHARING - Share your photos online with your friends and family!
Visit http://www.inbox.com/photosharing to find out more!





More information about the Gcrypt-devel mailing list