thodg/cgminer

diff --git a/poclbm120222.cl b/poclbm120222.cl
index f006112..7a4439f 100644
--- a/poclbm120222.cl
+++ b/poclbm120222.cl
@@ -106,6 +106,7 @@ Vals[6]=Vals[2];
 Vals[6]+=g1;
 Vals[3]+=Ma2(g1,Vals[4],f1);
 Vals[2]+=(rotr(Vals[3],2)^rotr(Vals[3],13)^rotr(Vals[3],22));
+Vals[2]+=Ma2(f1,Vals[3],Vals[4]);
 
 Vals[1]=B1addK6;
 Vals[1]+=(rotr(Vals[6],6)^rotr(Vals[6],11)^rotr(Vals[6],25));
@@ -113,74 +114,86 @@ Vals[1]+=ch(Vals[6],Vals[7],Vals[0]);
 
 Vals[5]=Vals[1];
 Vals[5]+=f1;
-Vals[2]+=Ma2(f1,Vals[3],Vals[4]);
+
 Vals[1]+=(rotr(Vals[2],2)^rotr(Vals[2],13)^rotr(Vals[2],22));
+Vals[1]+=Ma(Vals[4],Vals[2],Vals[3]);
+
 Vals[0]+=(rotr(Vals[5],6)^rotr(Vals[5],11)^rotr(Vals[5],25));
 Vals[0]+=ch(Vals[5],Vals[6],Vals[7]);
 Vals[0]+=K[7];
-Vals[1]+=Ma(Vals[4],Vals[2],Vals[3]);
 Vals[4]+=Vals[0];
 Vals[0]+=(rotr(Vals[1],2)^rotr(Vals[1],13)^rotr(Vals[1],22));
 Vals[0]+=Ma(Vals[3],Vals[1],Vals[2]);
+
 Vals[7]+=(rotr(Vals[4],6)^rotr(Vals[4],11)^rotr(Vals[4],25));
 Vals[7]+=ch(Vals[4],Vals[5],Vals[6]);
 Vals[7]+=K[8];
 Vals[3]+=Vals[7];
 Vals[7]+=(rotr(Vals[0],2)^rotr(Vals[0],13)^rotr(Vals[0],22));
 Vals[7]+=Ma(Vals[2],Vals[0],Vals[1]);
+
 Vals[6]+=(rotr(Vals[3],6)^rotr(Vals[3],11)^rotr(Vals[3],25));
 Vals[6]+=ch(Vals[3],Vals[4],Vals[5]);
 Vals[6]+=K[9];
 Vals[2]+=Vals[6];
 Vals[6]+=(rotr(Vals[7],2)^rotr(Vals[7],13)^rotr(Vals[7],22));
 Vals[6]+=Ma(Vals[1],Vals[7],Vals[0]);
+
 Vals[5]+=(rotr(Vals[2],6)^rotr(Vals[2],11)^rotr(Vals[2],25));
 Vals[5]+=ch(Vals[2],Vals[3],Vals[4]);
 Vals[5]+=K[10];
 Vals[1]+=Vals[5];
 Vals[5]+=(rotr(Vals[6],2)^rotr(Vals[6],13)^rotr(Vals[6],22));
 Vals[5]+=Ma(Vals[0],Vals[6],Vals[7]);
+
 Vals[4]+=(rotr(Vals[1],6)^rotr(Vals[1],11)^rotr(Vals[1],25));
 Vals[4]+=ch(Vals[1],Vals[2],Vals[3]);
 Vals[4]+=K[11];
 Vals[0]+=Vals[4];
 Vals[4]+=(rotr(Vals[5],2)^rotr(Vals[5],13)^rotr(Vals[5],22));
 Vals[4]+=Ma(Vals[7],Vals[5],Vals[6]);
+
 Vals[3]+=(rotr(Vals[0],6)^rotr(Vals[0],11)^rotr(Vals[0],25));
 Vals[3]+=ch(Vals[0],Vals[1],Vals[2]);
 Vals[3]+=K[12];
 Vals[7]+=Vals[3];
 Vals[3]+=(rotr(Vals[4],2)^rotr(Vals[4],13)^rotr(Vals[4],22));
 Vals[3]+=Ma(Vals[6],Vals[4],Vals[5]);
+
 Vals[2]+=(rotr(Vals[7],6)^rotr(Vals[7],11)^rotr(Vals[7],25));
 Vals[2]+=ch(Vals[7],Vals[0],Vals[1]);
 Vals[2]+=K[13];
 Vals[6]+=Vals[2];
 Vals[2]+=(rotr(Vals[3],2)^rotr(Vals[3],13)^rotr(Vals[3],22));
 Vals[2]+=Ma(Vals[5],Vals[3],Vals[4]);
+
 Vals[1]+=(rotr(Vals[6],6)^rotr(Vals[6],11)^rotr(Vals[6],25));
 Vals[1]+=ch(Vals[6],Vals[7],Vals[0]);
 Vals[1]+=K[14];
 Vals[5]+=Vals[1];
 Vals[1]+=(rotr(Vals[2],2)^rotr(Vals[2],13)^rotr(Vals[2],22));
 Vals[1]+=Ma(Vals[4],Vals[2],Vals[3]);
+
 Vals[0]+=(rotr(Vals[5],6)^rotr(Vals[5],11)^rotr(Vals[5],25));
 Vals[0]+=ch(Vals[5],Vals[6],Vals[7]);
 Vals[0]+=0xC19BF3F4U;
 Vals[4]+=Vals[0];
 Vals[0]+=(rotr(Vals[1],2)^rotr(Vals[1],13)^rotr(Vals[1],22));
+Vals[0]+=Ma(Vals[3],Vals[1],Vals[2]);
+
 Vals[7]+=(rotr(Vals[4],6)^rotr(Vals[4],11)^rotr(Vals[4],25));
 Vals[7]+=ch(Vals[4],Vals[5],Vals[6]);
 Vals[7]+=W16addK16;
-Vals[0]+=Ma(Vals[3],Vals[1],Vals[2]);
 Vals[3]+=Vals[7];
 Vals[7]+=(rotr(Vals[0],2)^rotr(Vals[0],13)^rotr(Vals[0],22));
 Vals[7]+=Ma(Vals[2],Vals[0],Vals[1]);
+
 Vals[6]+=(rotr(Vals[3],6)^rotr(Vals[3],11)^rotr(Vals[3],25));
 Vals[6]+=ch(Vals[3],Vals[4],Vals[5]);
 Vals[6]+=W17addK17;
 Vals[2]+=Vals[6];
 Vals[6]+=(rotr(Vals[7],2)^rotr(Vals[7],13)^rotr(Vals[7],22));
+Vals[6]+=Ma(Vals[1],Vals[7],Vals[0]);
 
 W[2]=(rotr(nonce,7)^rotr(nonce,18)^(nonce>>3U));
 W[2]+=fw2;
@@ -188,7 +201,6 @@ Vals[5]+=W[2];
 Vals[5]+=(rotr(Vals[2],6)^rotr(Vals[2],11)^rotr(Vals[2],25));
 Vals[5]+=ch(Vals[2],Vals[3],Vals[4]);
 Vals[5]+=K[18];
-Vals[6]+=Ma(Vals[1],Vals[7],Vals[0]);
 Vals[1]+=Vals[5];
 Vals[5]+=(rotr(Vals[6],2)^rotr(Vals[6],13)^rotr(Vals[6],22));
 Vals[5]+=Ma(Vals[0],Vals[6],Vals[7]);
@@ -201,6 +213,7 @@ Vals[4]+=ch(Vals[1],Vals[2],Vals[3]);
 Vals[4]+=K[19];
 Vals[0]+=Vals[4];
 Vals[4]+=(rotr(Vals[5],2)^rotr(Vals[5],13)^rotr(Vals[5],22));
+Vals[4]+=Ma(Vals[7],Vals[5],Vals[6]);
 
 W[4]=(rotr(W[2],17)^rotr(W[2],19)^(W[2]>>10U));
 W[4]+=0x80000000U;
@@ -208,7 +221,6 @@ Vals[3]+=W[4];
 Vals[3]+=(rotr(Vals[0],6)^rotr(Vals[0],11)^rotr(Vals[0],25));
 Vals[3]+=ch(Vals[0],Vals[1],Vals[2]);
 Vals[3]+=K[20];
-Vals[4]+=Ma(Vals[7],Vals[5],Vals[6]);
 Vals[7]+=Vals[3];
 Vals[3]+=(rotr(Vals[4],2)^rotr(Vals[4],13)^rotr(Vals[4],22));
 Vals[3]+=Ma(Vals[6],Vals[4],Vals[5]);
@@ -220,6 +232,7 @@ Vals[2]+=ch(Vals[7],Vals[0],Vals[1]);
 Vals[2]+=K[21];
 Vals[6]+=Vals[2];
 Vals[2]+=(rotr(Vals[3],2)^rotr(Vals[3],13)^rotr(Vals[3],22));
+Vals[2]+=Ma(Vals[5],Vals[3],Vals[4]);
 
 W[6]=(rotr(W[4],17)^rotr(W[4],19)^(W[4]>>10U));
 W[6]+=0x00000280U;
@@ -227,7 +240,6 @@ Vals[1]+=W[6];
 Vals[1]+=(rotr(Vals[6],6)^rotr(Vals[6],11)^rotr(Vals[6],25));
 Vals[1]+=ch(Vals[6],Vals[7],Vals[0]);
 Vals[1]+=K[22];
-Vals[2]+=Ma(Vals[5],Vals[3],Vals[4]);
 Vals[5]+=Vals[1];
 Vals[1]+=(rotr(Vals[2],2)^rotr(Vals[2],13)^rotr(Vals[2],22));
 Vals[1]+=Ma(Vals[4],Vals[2],Vals[3]);
@@ -238,9 +250,9 @@ Vals[0]+=W[7];
 Vals[0]+=(rotr(Vals[5],6)^rotr(Vals[5],11)^rotr(Vals[5],25));
 Vals[0]+=ch(Vals[5],Vals[6],Vals[7]);
 Vals[0]+=K[23];
-
 Vals[4]+=Vals[0];
 Vals[0]+=(rotr(Vals[1],2)^rotr(Vals[1],13)^rotr(Vals[1],22));
+Vals[0]+=Ma(Vals[3],Vals[1],Vals[2]);
 
 W[8]=(rotr(W[6],17)^rotr(W[6],19)^(W[6]>>10U));
 W[8]+=fw1;
@@ -248,7 +260,6 @@ Vals[7]+=W[8];
 Vals[7]+=(rotr(Vals[4],6)^rotr(Vals[4],11)^rotr(Vals[4],25));
 Vals[7]+=ch(Vals[4],Vals[5],Vals[6]);
 Vals[7]+=K[24];
-Vals[0]+=Ma(Vals[3],Vals[1],Vals[2]);
 Vals[3]+=Vals[7];
 Vals[7]+=(rotr(Vals[0],2)^rotr(Vals[0],13)^rotr(Vals[0],22));
 Vals[7]+=Ma(Vals[2],Vals[0],Vals[1]);
@@ -259,9 +270,9 @@ Vals[6]+=W[9];
 Vals[6]+=(rotr(Vals[3],6)^rotr(Vals[3],11)^rotr(Vals[3],25));
 Vals[6]+=ch(Vals[3],Vals[4],Vals[5]);
 Vals[6]+=K[25];
-
 Vals[2]+=Vals[6];
 Vals[6]+=(rotr(Vals[7],2)^rotr(Vals[7],13)^rotr(Vals[7],22));
+Vals[6]+=Ma(Vals[1],Vals[7],Vals[0]);
 
 W[10]=W[3];
 W[10]+=(rotr(W[8],17)^rotr(W[8],19)^(W[8]>>10U));
@@ -269,7 +280,6 @@ Vals[5]+=W[10];
 Vals[5]+=(rotr(Vals[2],6)^rotr(Vals[2],11)^rotr(Vals[2],25));
 Vals[5]+=ch(Vals[2],Vals[3],Vals[4]);
 Vals[5]+=K[26];
-Vals[6]+=Ma(Vals[1],Vals[7],Vals[0]);
 Vals[1]+=Vals[5];
 Vals[5]+=(rotr(Vals[6],2)^rotr(Vals[6],13)^rotr(Vals[6],22));
 Vals[5]+=Ma(Vals[0],Vals[6],Vals[7]);
@@ -282,6 +292,7 @@ Vals[4]+=ch(Vals[1],Vals[2],Vals[3]);
 Vals[4]+=K[27];
 Vals[0]+=Vals[4];
 Vals[4]+=(rotr(Vals[5],2)^rotr(Vals[5],13)^rotr(Vals[5],22));
+Vals[4]+=Ma(Vals[7],Vals[5],Vals[6]);
 
 W[12]=W[5];
 W[12]+=(rotr(W[10],17)^rotr(W[10],19)^(W[10]>>10U));
@@ -289,7 +300,6 @@ Vals[3]+=W[12];
 Vals[3]+=(rotr(Vals[0],6)^rotr(Vals[0],11)^rotr(Vals[0],25));
 Vals[3]+=ch(Vals[0],Vals[1],Vals[2]);
 Vals[3]+=K[28];
-Vals[4]+=Ma(Vals[7],Vals[5],Vals[6]);
 Vals[7]+=Vals[3];
 Vals[3]+=(rotr(Vals[4],2)^rotr(Vals[4],13)^rotr(Vals[4],22));
 Vals[3]+=Ma(Vals[6],Vals[4],Vals[5]);
@@ -302,6 +312,7 @@ Vals[2]+=ch(Vals[7],Vals[0],Vals[1]);
 Vals[2]+=K[29];
 Vals[6]+=Vals[2];
 Vals[2]+=(rotr(Vals[3],2)^rotr(Vals[3],13)^rotr(Vals[3],22));
+Vals[2]+=Ma(Vals[5],Vals[3],Vals[4]);
 
 W[14]=0x00a00055U;
 W[14]+=W[7];
@@ -310,7 +321,6 @@ Vals[1]+=W[14];
 Vals[1]+=(rotr(Vals[6],6)^rotr(Vals[6],11)^rotr(Vals[6],25));
 Vals[1]+=ch(Vals[6],Vals[7],Vals[0]);
 Vals[1]+=K[30];
-Vals[2]+=Ma(Vals[5],Vals[3],Vals[4]);
 Vals[5]+=Vals[1];
 Vals[1]+=(rotr(Vals[2],2)^rotr(Vals[2],13)^rotr(Vals[2],22));
 Vals[1]+=Ma(Vals[4],Vals[2],Vals[3]);
@@ -324,6 +334,7 @@ Vals[0]+=ch(Vals[5],Vals[6],Vals[7]);
 Vals[0]+=K[31];
 Vals[4]+=Vals[0];
 Vals[0]+=(rotr(Vals[1],2)^rotr(Vals[1],13)^rotr(Vals[1],22));
+Vals[0]+=Ma(Vals[3],Vals[1],Vals[2]);
 
 W[0]=fw01r;
 W[0]+=W[9];
@@ -332,7 +343,6 @@ Vals[7]+=W[0];
 Vals[7]+=(rotr(Vals[4],6)^rotr(Vals[4],11)^rotr(Vals[4],25));
 Vals[7]+=ch(Vals[4],Vals[5],Vals[6]);
 Vals[7]+=K[32];
-Vals[0]+=Ma(Vals[3],Vals[1],Vals[2]);
 Vals[3]+=Vals[7];
 Vals[7]+=(rotr(Vals[0],2)^rotr(Vals[0],13)^rotr(Vals[0],22));
 Vals[7]+=Ma(Vals[2],Vals[0],Vals[1]);
@@ -347,303 +357,333 @@ Vals[6]+=ch(Vals[3],Vals[4],Vals[5]);
 Vals[6]+=K[33];
 Vals[2]+=Vals[6];
 Vals[6]+=(rotr(Vals[7],2)^rotr(Vals[7],13)^rotr(Vals[7],22));
+Vals[6]+=Ma(Vals[1],Vals[7],Vals[0]);
+
 W[2]+=(rotr(W[3],7)^rotr(W[3],18)^(W[3]>>3U));
 W[2]+=W[11];
+W[2]+=(rotr(W[0],17)^rotr(W[0],19)^(W[0]>>10U));
 Vals[5]+=(rotr(Vals[2],6)^rotr(Vals[2],11)^rotr(Vals[2],25));
 Vals[5]+=ch(Vals[2],Vals[3],Vals[4]);
-W[2]+=(rotr(W[0],17)^rotr(W[0],19)^(W[0]>>10U));
 Vals[5]+=K[34];
 Vals[5]+=W[2];
-Vals[6]+=Ma(Vals[1],Vals[7],Vals[0]);
 Vals[1]+=Vals[5];
 Vals[5]+=(rotr(Vals[6],2)^rotr(Vals[6],13)^rotr(Vals[6],22));
 Vals[5]+=Ma(Vals[0],Vals[6],Vals[7]);
+
 W[3]+=(rotr(W[4],7)^rotr(W[4],18)^(W[4]>>3U));
 W[3]+=W[12];
+W[3]+=(rotr(W[1],17)^rotr(W[1],19)^(W[1]>>10U));
 Vals[4]+=(rotr(Vals[1],6)^rotr(Vals[1],11)^rotr(Vals[1],25));
 Vals[4]+=ch(Vals[1],Vals[2],Vals[3]);
 Vals[4]+=K[35];
-W[3]+=(rotr(W[1],17)^rotr(W[1],19)^(W[1]>>10U));
 Vals[4]+=W[3];
 Vals[0]+=Vals[4];
 Vals[4]+=(rotr(Vals[5],2)^rotr(Vals[5],13)^rotr(Vals[5],22));
+Vals[4]+=Ma(Vals[7],Vals[5],Vals[6]);
+
 W[4]+=(rotr(W[5],7)^rotr(W[5],18)^(W[5]>>3U));
 W[4]+=W[13];
+W[4]+=(rotr(W[2],17)^rotr(W[2],19)^(W[2]>>10U));
 Vals[3]+=(rotr(Vals[0],6)^rotr(Vals[0],11)^rotr(Vals[0],25));
 Vals[3]+=ch(Vals[0],Vals[1],Vals[2]);
-W[4]+=(rotr(W[2],17)^rotr(W[2],19)^(W[2]>>10U));
 Vals[3]+=K[36];
 Vals[3]+=W[4];
-Vals[4]+=Ma(Vals[7],Vals[5],Vals[6]);
 Vals[7]+=Vals[3];
 Vals[3]+=(rotr(Vals[4],2)^rotr(Vals[4],13)^rotr(Vals[4],22));
 Vals[3]+=Ma(Vals[6],Vals[4],Vals[5]);
+
 W[5]+=(rotr(W[6],7)^rotr(W[6],18)^(W[6]>>3U));
 W[5]+=W[14];
+W[5]+=(rotr(W[3],17)^rotr(W[3],19)^(W[3]>>10U));
 Vals[2]+=(rotr(Vals[7],6)^rotr(Vals[7],11)^rotr(Vals[7],25));
 Vals[2]+=ch(Vals[7],Vals[0],Vals[1]);
 Vals[2]+=K[37];
-W[5]+=(rotr(W[3],17)^rotr(W[3],19)^(W[3]>>10U));
 Vals[2]+=W[5];
 Vals[6]+=Vals[2];
 Vals[2]+=(rotr(Vals[3],2)^rotr(Vals[3],13)^rotr(Vals[3],22));
+Vals[2]+=Ma(Vals[5],Vals[3],Vals[4]);
+
 W[6]+=(rotr(W[7],7)^rotr(W[7],18)^(W[7]>>3U));
 W[6]+=W[15];
+W[6]+=(rotr(W[4],17)^rotr(W[4],19)^(W[4]>>10U));
 Vals[1]+=(rotr(Vals[6],6)^rotr(Vals[6],11)^rotr(Vals[6],25));
 Vals[1]+=ch(Vals[6],Vals[7],Vals[0]);
-W[6]+=(rotr(W[4],17)^rotr(W[4],19)^(W[4]>>10U));
 Vals[1]+=K[38];
 Vals[1]+=W[6];
-Vals[2]+=Ma(Vals[5],Vals[3],Vals[4]);
 Vals[5]+=Vals[1];
 Vals[1]+=(rotr(Vals[2],2)^rotr(Vals[2],13)^rotr(Vals[2],22));
 Vals[1]+=Ma(Vals[4],Vals[2],Vals[3]);
+
 W[7]+=(rotr(W[8],7)^rotr(W[8],18)^(W[8]>>3U));
 W[7]+=W[0];
+W[7]+=(rotr(W[5],17)^rotr(W[5],19)^(W[5]>>10U));
 Vals[0]+=(rotr(Vals[5],6)^rotr(Vals[5],11)^rotr(Vals[5],25));
 Vals[0]+=ch(Vals[5],Vals[6],Vals[7]);
 Vals[0]+=K[39];
-W[7]+=(rotr(W[5],17)^rotr(W[5],19)^(W[5]>>10U));
 Vals[0]+=W[7];
 Vals[4]+=Vals[0];
 Vals[0]+=(rotr(Vals[1],2)^rotr(Vals[1],13)^rotr(Vals[1],22));
+Vals[0]+=Ma(Vals[3],Vals[1],Vals[2]);
+
 W[8]+=(rotr(W[9],7)^rotr(W[9],18)^(W[9]>>3U));
 W[8]+=W[1];
+W[8]+=(rotr(W[6],17)^rotr(W[6],19)^(W[6]>>10U));
 Vals[7]+=(rotr(Vals[4],6)^rotr(Vals[4],11)^rotr(Vals[4],25));
 Vals[7]+=ch(Vals[4],Vals[5],Vals[6]);
-W[8]+=(rotr(W[6],17)^rotr(W[6],19)^(W[6]>>10U));
 Vals[7]+=K[40];
 Vals[7]+=W[8];
-Vals[0]+=Ma(Vals[3],Vals[1],Vals[2]);
 Vals[3]+=Vals[7];
 Vals[7]+=(rotr(Vals[0],2)^rotr(Vals[0],13)^rotr(Vals[0],22));
 Vals[7]+=Ma(Vals[2],Vals[0],Vals[1]);
+
 W[9]+=(rotr(W[10],7)^rotr(W[10],18)^(W[10]>>3U));
 W[9]+=W[2];
+W[9]+=(rotr(W[7],17)^rotr(W[7],19)^(W[7]>>10U));
 Vals[6]+=(rotr(Vals[3],6)^rotr(Vals[3],11)^rotr(Vals[3],25));
 Vals[6]+=ch(Vals[3],Vals[4],Vals[5]);
 Vals[6]+=K[41];
-W[9]+=(rotr(W[7],17)^rotr(W[7],19)^(W[7]>>10U));
 Vals[6]+=W[9];
 Vals[2]+=Vals[6];
 Vals[6]+=(rotr(Vals[7],2)^rotr(Vals[7],13)^rotr(Vals[7],22));
+Vals[6]+=Ma(Vals[1],Vals[7],Vals[0]);
+
 W[10]+=(rotr(W[11],7)^rotr(W[11],18)^(W[11]>>3U));
 W[10]+=W[3];
+W[10]+=(rotr(W[8],17)^rotr(W[8],19)^(W[8]>>10U));
 Vals[5]+=(rotr(Vals[2],6)^rotr(Vals[2],11)^rotr(Vals[2],25));
 Vals[5]+=ch(Vals[2],Vals[3],Vals[4]);
-W[10]+=(rotr(W[8],17)^rotr(W[8],19)^(W[8]>>10U));
 Vals[5]+=K[42];
 Vals[5]+=W[10];
-Vals[6]+=Ma(Vals[1],Vals[7],Vals[0]);
 Vals[1]+=Vals[5];
 Vals[5]+=(rotr(Vals[6],2)^rotr(Vals[6],13)^rotr(Vals[6],22));
 Vals[5]+=Ma(Vals[0],Vals[6],Vals[7]);
+
 W[11]+=(rotr(W[12],7)^rotr(W[12],18)^(W[12]>>3U));
 W[11]+=W[4];
+W[11]+=(rotr(W[9],17)^rotr(W[9],19)^(W[9]>>10U));
 Vals[4]+=(rotr(Vals[1],6)^rotr(Vals[1],11)^rotr(Vals[1],25));
 Vals[4]+=ch(Vals[1],Vals[2],Vals[3]);
 Vals[4]+=K[43];
-W[11]+=(rotr(W[9],17)^rotr(W[9],19)^(W[9]>>10U));
 Vals[4]+=W[11];
 Vals[0]+=Vals[4];
 Vals[4]+=(rotr(Vals[5],2)^rotr(Vals[5],13)^rotr(Vals[5],22));
+Vals[4]+=Ma(Vals[7],Vals[5],Vals[6]);
+
 W[12]+=(rotr(W[13],7)^rotr(W[13],18)^(W[13]>>3U));
 W[12]+=W[5];
+W[12]+=(rotr(W[10],17)^rotr(W[10],19)^(W[10]>>10U));
 Vals[3]+=(rotr(Vals[0],6)^rotr(Vals[0],11)^rotr(Vals[0],25));
 Vals[3]+=ch(Vals[0],Vals[1],Vals[2]);
-W[12]+=(rotr(W[10],17)^rotr(W[10],19)^(W[10]>>10U));
 Vals[3]+=K[44];
 Vals[3]+=W[12];
-Vals[4]+=Ma(Vals[7],Vals[5],Vals[6]);
 Vals[7]+=Vals[3];
 Vals[3]+=(rotr(Vals[4],2)^rotr(Vals[4],13)^rotr(Vals[4],22));
 Vals[3]+=Ma(Vals[6],Vals[4],Vals[5]);
+
 W[13]+=(rotr(W[14],7)^rotr(W[14],18)^(W[14]>>3U));
 W[13]+=W[6];
+W[13]+=(rotr(W[11],17)^rotr(W[11],19)^(W[11]>>10U));
 Vals[2]+=(rotr(Vals[7],6)^rotr(Vals[7],11)^rotr(Vals[7],25));
 Vals[2]+=ch(Vals[7],Vals[0],Vals[1]);
 Vals[2]+=K[45];
-W[13]+=(rotr(W[11],17)^rotr(W[11],19)^(W[11]>>10U));
 Vals[2]+=W[13];
 Vals[6]+=Vals[2];
 Vals[2]+=(rotr(Vals[3],2)^rotr(Vals[3],13)^rotr(Vals[3],22));
+Vals[2]+=Ma(Vals[5],Vals[3],Vals[4]);
+
 W[14]+=(rotr(W[15],7)^rotr(W[15],18)^(W[15]>>3U));
 W[14]+=W[7];
+W[14]+=(rotr(W[12],17)^rotr(W[12],19)^(W[12]>>10U));
 Vals[1]+=(rotr(Vals[6],6)^rotr(Vals[6],11)^rotr(Vals[6],25));
 Vals[1]+=ch(Vals[6],Vals[7],Vals[0]);
-W[14]+=(rotr(W[12],17)^rotr(W[12],19)^(W[12]>>10U));
 Vals[1]+=K[46];
 Vals[1]+=W[14];
-Vals[2]+=Ma(Vals[5],Vals[3],Vals[4]);
 Vals[5]+=Vals[1];
 Vals[1]+=(rotr(Vals[2],2)^rotr(Vals[2],13)^rotr(Vals[2],22));
 Vals[1]+=Ma(Vals[4],Vals[2],Vals[3]);
+
 W[15]+=(rotr(W[0],7)^rotr(W[0],18)^(W[0]>>3U));
 W[15]+=W[8];
+W[15]+=(rotr(W[13],17)^rotr(W[13],19)^(W[13]>>10U));
 Vals[0]+=(rotr(Vals[5],6)^rotr(Vals[5],11)^rotr(Vals[5],25));
 Vals[0]+=ch(Vals[5],Vals[6],Vals[7]);
 Vals[0]+=K[47];
-W[15]+=(rotr(W[13],17)^rotr(W[13],19)^(W[13]>>10U));
 Vals[0]+=W[15];
 Vals[4]+=Vals[0];
 Vals[0]+=(rotr(Vals[1],2)^rotr(Vals[1],13)^rotr(Vals[1],22));
+Vals[0]+=Ma(Vals[3],Vals[1],Vals[2]);
+
 W[0]+=(rotr(W[1],7)^rotr(W[1],18)^(W[1]>>3U));
 W[0]+=W[9];
+W[0]+=(rotr(W[14],17)^rotr(W[14],19)^(W[14]>>10U));
 Vals[7]+=(rotr(Vals[4],6)^rotr(Vals[4],11)^rotr(Vals[4],25));
 Vals[7]+=ch(Vals[4],Vals[5],Vals[6]);
-W[0]+=(rotr(W[14],17)^rotr(W[14],19)^(W[14]>>10U));
 Vals[7]+=K[48];
 Vals[7]+=W[0];
-Vals[0]+=Ma(Vals[3],Vals[1],Vals[2]);
 Vals[3]+=Vals[7];
 Vals[7]+=(rotr(Vals[0],2)^rotr(Vals[0],13)^rotr(Vals[0],22));
 Vals[7]+=Ma(Vals[2],Vals[0],Vals[1]);
+
 W[1]+=(rotr(W[2],7)^rotr(W[2],18)^(W[2]>>3U));
 W[1]+=W[10];
+W[1]+=(rotr(W[15],17)^rotr(W[15],19)^(W[15]>>10U));
 Vals[6]+=(rotr(Vals[3],6)^rotr(Vals[3],11)^rotr(Vals[3],25));
 Vals[6]+=ch(Vals[3],Vals[4],Vals[5]);
 Vals[6]+=K[49];
-W[1]+=(rotr(W[15],17)^rotr(W[15],19)^(W[15]>>10U));
 Vals[6]+=W[1];
 Vals[2]+=Vals[6];
 Vals[6]+=(rotr(Vals[7],2)^rotr(Vals[7],13)^rotr(Vals[7],22));
+Vals[6]+=Ma(Vals[1],Vals[7],Vals[0]);
+
 W[2]+=(rotr(W[3],7)^rotr(W[3],18)^(W[3]>>3U));
 W[2]+=W[11];
+W[2]+=(rotr(W[0],17)^rotr(W[0],19)^(W[0]>>10U));
 Vals[5]+=(rotr(Vals[2],6)^rotr(Vals[2],11)^rotr(Vals[2],25));
 Vals[5]+=ch(Vals[2],Vals[3],Vals[4]);
-W[2]+=(rotr(W[0],17)^rotr(W[0],19)^(W[0]>>10U));
 Vals[5]+=K[50];
 Vals[5]+=W[2];
-Vals[6]+=Ma(Vals[1],Vals[7],Vals[0]);
 Vals[1]+=Vals[5];
 Vals[5]+=(rotr(Vals[6],2)^rotr(Vals[6],13)^rotr(Vals[6],22));
 Vals[5]+=Ma(Vals[0],Vals[6],Vals[7]);
+
 W[3]+=(rotr(W[4],7)^rotr(W[4],18)^(W[4]>>3U));
 W[3]+=W[12];
+W[3]+=(rotr(W[1],17)^rotr(W[1],19)^(W[1]>>10U));
 Vals[4]+=(rotr(Vals[1],6)^rotr(Vals[1],11)^rotr(Vals[1],25));
 Vals[4]+=ch(Vals[1],Vals[2],Vals[3]);
 Vals[4]+=K[51];
-W[3]+=(rotr(W[1],17)^rotr(W[1],19)^(W[1]>>10U));
 Vals[4]+=W[3];
 Vals[0]+=Vals[4];
 Vals[4]+=(rotr(Vals[5],2)^rotr(Vals[5],13)^rotr(Vals[5],22));
+Vals[4]+=Ma(Vals[7],Vals[5],Vals[6]);
+
 W[4]+=(rotr(W[5],7)^rotr(W[5],18)^(W[5]>>3U));
 W[4]+=W[13];
+W[4]+=(rotr(W[2],17)^rotr(W[2],19)^(W[2]>>10U));
 Vals[3]+=(rotr(Vals[0],6)^rotr(Vals[0],11)^rotr(Vals[0],25));
 Vals[3]+=ch(Vals[0],Vals[1],Vals[2]);
-W[4]+=(rotr(W[2],17)^rotr(W[2],19)^(W[2]>>10U));
 Vals[3]+=K[52];
 Vals[3]+=W[4];
-Vals[4]+=Ma(Vals[7],Vals[5],Vals[6]);
 Vals[7]+=Vals[3];
 Vals[3]+=(rotr(Vals[4],2)^rotr(Vals[4],13)^rotr(Vals[4],22));
 Vals[3]+=Ma(Vals[6],Vals[4],Vals[5]);
+
 W[5]+=(rotr(W[6],7)^rotr(W[6],18)^(W[6]>>3U));
 W[5]+=W[14];
+W[5]+=(rotr(W[3],17)^rotr(W[3],19)^(W[3]>>10U));
 Vals[2]+=(rotr(Vals[7],6)^rotr(Vals[7],11)^rotr(Vals[7],25));
 Vals[2]+=ch(Vals[7],Vals[0],Vals[1]);
 Vals[2]+=K[53];
-W[5]+=(rotr(W[3],17)^rotr(W[3],19)^(W[3]>>10U));
 Vals[2]+=W[5];
 Vals[6]+=Vals[2];
 Vals[2]+=(rotr(Vals[3],2)^rotr(Vals[3],13)^rotr(Vals[3],22));
+Vals[2]+=Ma(Vals[5],Vals[3],Vals[4]);
+
 W[6]+=(rotr(W[7],7)^rotr(W[7],18)^(W[7]>>3U));
 W[6]+=W[15];
+W[6]+=(rotr(W[4],17)^rotr(W[4],19)^(W[4]>>10U));
 Vals[1]+=(rotr(Vals[6],6)^rotr(Vals[6],11)^rotr(Vals[6],25));
 Vals[1]+=ch(Vals[6],Vals[7],Vals[0]);
-W[6]+=(rotr(W[4],17)^rotr(W[4],19)^(W[4]>>10U));
 Vals[1]+=K[54];
 Vals[1]+=W[6];
-Vals[2]+=Ma(Vals[5],Vals[3],Vals[4]);
 Vals[5]+=Vals[1];
 Vals[1]+=(rotr(Vals[2],2)^rotr(Vals[2],13)^rotr(Vals[2],22));
 Vals[1]+=Ma(Vals[4],Vals[2],Vals[3]);
+
 W[7]+=(rotr(W[8],7)^rotr(W[8],18)^(W[8]>>3U));
 W[7]+=W[0];
+W[7]+=(rotr(W[5],17)^rotr(W[5],19)^(W[5]>>10U));
 Vals[0]+=(rotr(Vals[5],6)^rotr(Vals[5],11)^rotr(Vals[5],25));
 Vals[0]+=ch(Vals[5],Vals[6],Vals[7]);
 Vals[0]+=K[55];
-W[7]+=(rotr(W[5],17)^rotr(W[5],19)^(W[5]>>10U));
 Vals[0]+=W[7];
 Vals[4]+=Vals[0];
 Vals[0]+=(rotr(Vals[1],2)^rotr(Vals[1],13)^rotr(Vals[1],22));
+Vals[0]+=Ma(Vals[3],Vals[1],Vals[2]);
+
 W[8]+=(rotr(W[9],7)^rotr(W[9],18)^(W[9]>>3U));
 W[8]+=W[1];
+W[8]+=(rotr(W[6],17)^rotr(W[6],19)^(W[6]>>10U));
 Vals[7]+=(rotr(Vals[4],6)^rotr(Vals[4],11)^rotr(Vals[4],25));
 Vals[7]+=ch(Vals[4],Vals[5],Vals[6]);
-W[8]+=(rotr(W[6],17)^rotr(W[6],19)^(W[6]>>10U));
 Vals[7]+=K[56];
 Vals[7]+=W[8];
-Vals[0]+=Ma(Vals[3],Vals[1],Vals[2]);
 Vals[3]+=Vals[7];
 Vals[7]+=(rotr(Vals[0],2)^rotr(Vals[0],13)^rotr(Vals[0],22));
 Vals[7]+=Ma(Vals[2],Vals[0],Vals[1]);
+
 W[9]+=(rotr(W[10],7)^rotr(W[10],18)^(W[10]>>3U));
 W[9]+=W[2];
+W[9]+=(rotr(W[7],17)^rotr(W[7],19)^(W[7]>>10U));
 Vals[6]+=(rotr(Vals[3],6)^rotr(Vals[3],11)^rotr(Vals[3],25));
 Vals[6]+=ch(Vals[3],Vals[4],Vals[5]);
 Vals[6]+=K[57];
-W[9]+=(rotr(W[7],17)^rotr(W[7],19)^(W[7]>>10U));
 Vals[6]+=W[9];
 Vals[2]+=Vals[6];
 Vals[6]+=(rotr(Vals[7],2)^rotr(Vals[7],13)^rotr(Vals[7],22));
+Vals[6]+=Ma(Vals[1],Vals[7],Vals[0]);
+
 W[10]+=(rotr(W[11],7)^rotr(W[11],18)^(W[11]>>3U));
 W[10]+=W[3];
+W[10]+=(rotr(W[8],17)^rotr(W[8],19)^(W[8]>>10U));
 Vals[5]+=(rotr(Vals[2],6)^rotr(Vals[2],11)^rotr(Vals[2],25));
 Vals[5]+=ch(Vals[2],Vals[3],Vals[4]);
-W[10]+=(rotr(W[8],17)^rotr(W[8],19)^(W[8]>>10U));
 Vals[5]+=K[58];
 Vals[5]+=W[10];
-Vals[6]+=Ma(Vals[1],Vals[7],Vals[0]);
 Vals[1]+=Vals[5];
 Vals[5]+=(rotr(Vals[6],2)^rotr(Vals[6],13)^rotr(Vals[6],22));
 Vals[5]+=Ma(Vals[0],Vals[6],Vals[7]);
+
 W[11]+=(rotr(W[12],7)^rotr(W[12],18)^(W[12]>>3U));
 W[11]+=W[4];
+W[11]+=(rotr(W[9],17)^rotr(W[9],19)^(W[9]>>10U));
 Vals[4]+=(rotr(Vals[1],6)^rotr(Vals[1],11)^rotr(Vals[1],25));
 Vals[4]+=ch(Vals[1],Vals[2],Vals[3]);
 Vals[4]+=K[59];
-W[11]+=(rotr(W[9],17)^rotr(W[9],19)^(W[9]>>10U));
 Vals[4]+=W[11];
 Vals[0]+=Vals[4];
 Vals[4]+=(rotr(Vals[5],2)^rotr(Vals[5],13)^rotr(Vals[5],22));
+Vals[4]+=Ma(Vals[7],Vals[5],Vals[6]);
+
 W[12]+=(rotr(W[13],7)^rotr(W[13],18)^(W[13]>>3U));
 W[12]+=W[5];
+W[12]+=(rotr(W[10],17)^rotr(W[10],19)^(W[10]>>10U));
 Vals[3]+=(rotr(Vals[0],6)^rotr(Vals[0],11)^rotr(Vals[0],25));
 Vals[3]+=ch(Vals[0],Vals[1],Vals[2]);
-W[12]+=(rotr(W[10],17)^rotr(W[10],19)^(W[10]>>10U));
 Vals[3]+=K[60];
 Vals[3]+=W[12];
-Vals[4]+=Ma(Vals[7],Vals[5],Vals[6]);
 Vals[7]+=Vals[3];
 Vals[3]+=(rotr(Vals[4],2)^rotr(Vals[4],13)^rotr(Vals[4],22));
 Vals[3]+=Ma(Vals[6],Vals[4],Vals[5]);
+
 W[13]+=(rotr(W[14],7)^rotr(W[14],18)^(W[14]>>3U));
 W[13]+=W[6];
+W[13]+=(rotr(W[11],17)^rotr(W[11],19)^(W[11]>>10U));
 Vals[2]+=(rotr(Vals[7],6)^rotr(Vals[7],11)^rotr(Vals[7],25));
 Vals[2]+=ch(Vals[7],Vals[0],Vals[1]);
 Vals[2]+=K[61];
-W[13]+=(rotr(W[11],17)^rotr(W[11],19)^(W[11]>>10U));
 Vals[2]+=W[13];
 Vals[6]+=Vals[2];
 Vals[2]+=(rotr(Vals[3],2)^rotr(Vals[3],13)^rotr(Vals[3],22));
+Vals[2]+=Ma(Vals[5],Vals[3],Vals[4]);
+
 W[14]+=(rotr(W[15],7)^rotr(W[15],18)^(W[15]>>3U));
 W[14]+=W[7];
+W[14]+=(rotr(W[12],17)^rotr(W[12],19)^(W[12]>>10U));
 Vals[1]+=(rotr(Vals[6],6)^rotr(Vals[6],11)^rotr(Vals[6],25));
 Vals[1]+=ch(Vals[6],Vals[7],Vals[0]);
-W[14]+=(rotr(W[12],17)^rotr(W[12],19)^(W[12]>>10U));
 Vals[1]+=K[62];
 Vals[1]+=W[14];
-Vals[2]+=Ma(Vals[5],Vals[3],Vals[4]);
 Vals[5]+=Vals[1];
 Vals[1]+=(rotr(Vals[2],2)^rotr(Vals[2],13)^rotr(Vals[2],22));
 Vals[1]+=Ma(Vals[4],Vals[2],Vals[3]);
+
 W[15]+=(rotr(W[0],7)^rotr(W[0],18)^(W[0]>>3U));
 W[15]+=W[8];
+W[15]+=(rotr(W[13],17)^rotr(W[13],19)^(W[13]>>10U));
 Vals[0]+=(rotr(Vals[5],6)^rotr(Vals[5],11)^rotr(Vals[5],25));
 Vals[0]+=ch(Vals[5],Vals[6],Vals[7]);
 Vals[0]+=K[63];
-W[15]+=(rotr(W[13],17)^rotr(W[13],19)^(W[13]>>10U));
 Vals[0]+=W[15];
 Vals[4]+=Vals[0];
 Vals[0]+=(rotr(Vals[1],2)^rotr(Vals[1],13)^rotr(Vals[1],22));