Version C des tests Cminor

git-svn-id: https://yquem.inria.fr/compcert/svn/compcert/trunk@40 fca1b0fc-160b-0410-b1d3-a4f43f01ea2e

1 files changed, 728 insertions, 0 deletions

diff --git a/test/c/aes.c b/test/c/aes.c
new file mode 100644
index 0000000..90abf57
--- /dev/null
+++ b/test/c/aes.c
@@ -0,0 +1,728 @@
+/**
+ * rijndael-alg-fst.c
+ *
+ * @version 3.0 (December 2000)
+ *
+ * Optimised ANSI C code for the Rijndael cipher (now AES)
+ *
+ * @author Vincent Rijmen <vincent.rijmen@esat.kuleuven.ac.be>
+ * @author Antoon Bosselaers <antoon.bosselaers@esat.kuleuven.ac.be>
+ * @author Paulo Barreto <paulo.barreto@terra.com.br>
+ *
+ * This code is hereby placed in the public domain.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE AUTHORS ''AS IS'' AND ANY EXPRESS
+ * OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHORS OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE
+ * OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE,
+ * EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+#include <assert.h>
+#include <stdlib.h>
+
+#define MAXKC	(256/32)
+#define MAXKB	(256/8)
+#define MAXNR	14
+
+typedef unsigned char	u8;	
+typedef unsigned short	u16;	
+typedef unsigned int	u32;
+
+#define ARCH_BIG_ENDIAN
+
+#ifdef ARCH_BIG_ENDIAN
+#define GETU32(pt) (*(u32 *)(pt))
+#define PUTU32(ct,st) (*(u32 *)(ct) = (st))
+#else
+#define GETU32(pt) (((u32)(pt)[0] << 24) ^ ((u32)(pt)[1] << 16) ^ ((u32)(pt)[2] <<  8) ^ ((u32)(pt)[3]))
+#define PUTU32(ct, st) { (ct)[0] = (u8)((st) >> 24); (ct)[1] = (u8)((st) >> 16); (ct)[2] = (u8)((st) >>  8); (ct)[3] = (u8)(st); }
+#endif
+
+extern u32 Te0[256], Te1[256], Te2[256], Te3[256], Te4[256];
+extern u32 Td0[256], Td1[256], Td2[256], Td3[256], Td4[256];
+extern u32 rcon[10];
+
+/**
+ * Expand the cipher key into the encryption key schedule.
+ *
+ * @return	the number of rounds for the given cipher key size.
+ */
+int rijndaelKeySetupEnc(u32 rk[/*4*(Nr + 1)*/], const u8 cipherKey[], int keyBits) {
+   	int i = 0;
+	u32 temp;
+
+	rk[0] = GETU32(cipherKey     );
+	rk[1] = GETU32(cipherKey +  4);
+	rk[2] = GETU32(cipherKey +  8);
+	rk[3] = GETU32(cipherKey + 12);
+	if (keyBits == 128) {
+		for (;;) {
+			temp  = rk[3];
+			rk[4] = rk[0] ^
+				(Te4[(temp >> 16) & 0xff] & 0xff000000) ^
+				(Te4[(temp >>  8) & 0xff] & 0x00ff0000) ^
+				(Te4[(temp      ) & 0xff] & 0x0000ff00) ^
+				(Te4[(temp >> 24)       ] & 0x000000ff) ^
+				rcon[i];
+			rk[5] = rk[1] ^ rk[4];
+			rk[6] = rk[2] ^ rk[5];
+			rk[7] = rk[3] ^ rk[6];
+			if (++i == 10) {
+				return 10;
+			}
+			rk += 4;
+		}
+	}
+	rk[4] = GETU32(cipherKey + 16);
+	rk[5] = GETU32(cipherKey + 20);
+	if (keyBits == 192) {
+		for (;;) {
+			temp = rk[ 5];
+			rk[ 6] = rk[ 0] ^
+				(Te4[(temp >> 16) & 0xff] & 0xff000000) ^
+				(Te4[(temp >>  8) & 0xff] & 0x00ff0000) ^
+				(Te4[(temp      ) & 0xff] & 0x0000ff00) ^
+				(Te4[(temp >> 24)       ] & 0x000000ff) ^
+				rcon[i];
+			rk[ 7] = rk[ 1] ^ rk[ 6];
+			rk[ 8] = rk[ 2] ^ rk[ 7];
+			rk[ 9] = rk[ 3] ^ rk[ 8];
+			if (++i == 8) {
+				return 12;
+			}
+			rk[10] = rk[ 4] ^ rk[ 9];
+			rk[11] = rk[ 5] ^ rk[10];
+			rk += 6;
+		}
+	}
+	rk[6] = GETU32(cipherKey + 24);
+	rk[7] = GETU32(cipherKey + 28);
+	if (keyBits == 256) {
+        for (;;) {
+        	temp = rk[ 7];
+        	rk[ 8] = rk[ 0] ^
+        		(Te4[(temp >> 16) & 0xff] & 0xff000000) ^
+        		(Te4[(temp >>  8) & 0xff] & 0x00ff0000) ^
+        		(Te4[(temp      ) & 0xff] & 0x0000ff00) ^
+        		(Te4[(temp >> 24)       ] & 0x000000ff) ^
+        		rcon[i];
+        	rk[ 9] = rk[ 1] ^ rk[ 8];
+        	rk[10] = rk[ 2] ^ rk[ 9];
+        	rk[11] = rk[ 3] ^ rk[10];
+			if (++i == 7) {
+				return 14;
+			}
+        	temp = rk[11];
+        	rk[12] = rk[ 4] ^
+        		(Te4[(temp >> 24)       ] & 0xff000000) ^
+        		(Te4[(temp >> 16) & 0xff] & 0x00ff0000) ^
+        		(Te4[(temp >>  8) & 0xff] & 0x0000ff00) ^
+        		(Te4[(temp      ) & 0xff] & 0x000000ff);
+        	rk[13] = rk[ 5] ^ rk[12];
+        	rk[14] = rk[ 6] ^ rk[13];
+        	rk[15] = rk[ 7] ^ rk[14];
+
+			rk += 8;
+        }
+	}
+	return 0;
+}
+
+/**
+ * Expand the cipher key into the decryption key schedule.
+ *
+ * @return	the number of rounds for the given cipher key size.
+ */
+int rijndaelKeySetupDec(u32 rk[/*4*(Nr + 1)*/], const u8 cipherKey[], int keyBits) {
+	int Nr, i, j;
+	u32 temp;
+
+	/* expand the cipher key: */
+	Nr = rijndaelKeySetupEnc(rk, cipherKey, keyBits);
+	/* invert the order of the round keys: */
+	for (i = 0, j = 4*Nr; i < j; i += 4, j -= 4) {
+		temp = rk[i    ]; rk[i    ] = rk[j    ]; rk[j    ] = temp;
+		temp = rk[i + 1]; rk[i + 1] = rk[j + 1]; rk[j + 1] = temp;
+		temp = rk[i + 2]; rk[i + 2] = rk[j + 2]; rk[j + 2] = temp;
+		temp = rk[i + 3]; rk[i + 3] = rk[j + 3]; rk[j + 3] = temp;
+	}
+	/* apply the inverse MixColumn transform to all round keys but the first and the last: */
+	for (i = 1; i < Nr; i++) {
+		rk += 4;
+		rk[0] =
+			Td0[Te4[(rk[0] >> 24)       ] & 0xff] ^
+			Td1[Te4[(rk[0] >> 16) & 0xff] & 0xff] ^
+			Td2[Te4[(rk[0] >>  8) & 0xff] & 0xff] ^
+			Td3[Te4[(rk[0]      ) & 0xff] & 0xff];
+		rk[1] =
+			Td0[Te4[(rk[1] >> 24)       ] & 0xff] ^
+			Td1[Te4[(rk[1] >> 16) & 0xff] & 0xff] ^
+			Td2[Te4[(rk[1] >>  8) & 0xff] & 0xff] ^
+			Td3[Te4[(rk[1]      ) & 0xff] & 0xff];
+		rk[2] =
+			Td0[Te4[(rk[2] >> 24)       ] & 0xff] ^
+			Td1[Te4[(rk[2] >> 16) & 0xff] & 0xff] ^
+			Td2[Te4[(rk[2] >>  8) & 0xff] & 0xff] ^
+			Td3[Te4[(rk[2]      ) & 0xff] & 0xff];
+		rk[3] =
+			Td0[Te4[(rk[3] >> 24)       ] & 0xff] ^
+			Td1[Te4[(rk[3] >> 16) & 0xff] & 0xff] ^
+			Td2[Te4[(rk[3] >>  8) & 0xff] & 0xff] ^
+			Td3[Te4[(rk[3]      ) & 0xff] & 0xff];
+	}
+	return Nr;
+}
+
+void rijndaelEncrypt(const u32 rk[/*4*(Nr + 1)*/], int Nr, const u8 pt[16], u8 ct[16]) {
+	u32 s0, s1, s2, s3, t0, t1, t2, t3;
+#ifndef FULL_UNROLL
+    int r;
+#endif /* ?FULL_UNROLL */
+
+    /*
+	 * map byte array block to cipher state
+	 * and add initial round key:
+	 */
+	s0 = GETU32(pt     ) ^ rk[0];
+	s1 = GETU32(pt +  4) ^ rk[1];
+	s2 = GETU32(pt +  8) ^ rk[2];
+	s3 = GETU32(pt + 12) ^ rk[3];
+#ifdef FULL_UNROLL
+    /* round 1: */
+   	t0 = Te0[s0 >> 24] ^ Te1[(s1 >> 16) & 0xff] ^ Te2[(s2 >>  8) & 0xff] ^ Te3[s3 & 0xff] ^ rk[ 4];
+   	t1 = Te0[s1 >> 24] ^ Te1[(s2 >> 16) & 0xff] ^ Te2[(s3 >>  8) & 0xff] ^ Te3[s0 & 0xff] ^ rk[ 5];
+   	t2 = Te0[s2 >> 24] ^ Te1[(s3 >> 16) & 0xff] ^ Te2[(s0 >>  8) & 0xff] ^ Te3[s1 & 0xff] ^ rk[ 6];
+   	t3 = Te0[s3 >> 24] ^ Te1[(s0 >> 16) & 0xff] ^ Te2[(s1 >>  8) & 0xff] ^ Te3[s2 & 0xff] ^ rk[ 7];
+   	/* round 2: */
+   	s0 = Te0[t0 >> 24] ^ Te1[(t1 >> 16) & 0xff] ^ Te2[(t2 >>  8) & 0xff] ^ Te3[t3 & 0xff] ^ rk[ 8];
+   	s1 = Te0[t1 >> 24] ^ Te1[(t2 >> 16) & 0xff] ^ Te2[(t3 >>  8) & 0xff] ^ Te3[t0 & 0xff] ^ rk[ 9];
+   	s2 = Te0[t2 >> 24] ^ Te1[(t3 >> 16) & 0xff] ^ Te2[(t0 >>  8) & 0xff] ^ Te3[t1 & 0xff] ^ rk[10];
+   	s3 = Te0[t3 >> 24] ^ Te1[(t0 >> 16) & 0xff] ^ Te2[(t1 >>  8) & 0xff] ^ Te3[t2 & 0xff] ^ rk[11];
+    /* round 3: */
+   	t0 = Te0[s0 >> 24] ^ Te1[(s1 >> 16) & 0xff] ^ Te2[(s2 >>  8) & 0xff] ^ Te3[s3 & 0xff] ^ rk[12];
+   	t1 = Te0[s1 >> 24] ^ Te1[(s2 >> 16) & 0xff] ^ Te2[(s3 >>  8) & 0xff] ^ Te3[s0 & 0xff] ^ rk[13];
+   	t2 = Te0[s2 >> 24] ^ Te1[(s3 >> 16) & 0xff] ^ Te2[(s0 >>  8) & 0xff] ^ Te3[s1 & 0xff] ^ rk[14];
+   	t3 = Te0[s3 >> 24] ^ Te1[(s0 >> 16) & 0xff] ^ Te2[(s1 >>  8) & 0xff] ^ Te3[s2 & 0xff] ^ rk[15];
+   	/* round 4: */
+   	s0 = Te0[t0 >> 24] ^ Te1[(t1 >> 16) & 0xff] ^ Te2[(t2 >>  8) & 0xff] ^ Te3[t3 & 0xff] ^ rk[16];
+   	s1 = Te0[t1 >> 24] ^ Te1[(t2 >> 16) & 0xff] ^ Te2[(t3 >>  8) & 0xff] ^ Te3[t0 & 0xff] ^ rk[17];
+   	s2 = Te0[t2 >> 24] ^ Te1[(t3 >> 16) & 0xff] ^ Te2[(t0 >>  8) & 0xff] ^ Te3[t1 & 0xff] ^ rk[18];
+   	s3 = Te0[t3 >> 24] ^ Te1[(t0 >> 16) & 0xff] ^ Te2[(t1 >>  8) & 0xff] ^ Te3[t2 & 0xff] ^ rk[19];
+    /* round 5: */
+   	t0 = Te0[s0 >> 24] ^ Te1[(s1 >> 16) & 0xff] ^ Te2[(s2 >>  8) & 0xff] ^ Te3[s3 & 0xff] ^ rk[20];
+   	t1 = Te0[s1 >> 24] ^ Te1[(s2 >> 16) & 0xff] ^ Te2[(s3 >>  8) & 0xff] ^ Te3[s0 & 0xff] ^ rk[21];
+   	t2 = Te0[s2 >> 24] ^ Te1[(s3 >> 16) & 0xff] ^ Te2[(s0 >>  8) & 0xff] ^ Te3[s1 & 0xff] ^ rk[22];
+   	t3 = Te0[s3 >> 24] ^ Te1[(s0 >> 16) & 0xff] ^ Te2[(s1 >>  8) & 0xff] ^ Te3[s2 & 0xff] ^ rk[23];
+   	/* round 6: */
+   	s0 = Te0[t0 >> 24] ^ Te1[(t1 >> 16) & 0xff] ^ Te2[(t2 >>  8) & 0xff] ^ Te3[t3 & 0xff] ^ rk[24];
+   	s1 = Te0[t1 >> 24] ^ Te1[(t2 >> 16) & 0xff] ^ Te2[(t3 >>  8) & 0xff] ^ Te3[t0 & 0xff] ^ rk[25];
+   	s2 = Te0[t2 >> 24] ^ Te1[(t3 >> 16) & 0xff] ^ Te2[(t0 >>  8) & 0xff] ^ Te3[t1 & 0xff] ^ rk[26];
+   	s3 = Te0[t3 >> 24] ^ Te1[(t0 >> 16) & 0xff] ^ Te2[(t1 >>  8) & 0xff] ^ Te3[t2 & 0xff] ^ rk[27];
+    /* round 7: */
+   	t0 = Te0[s0 >> 24] ^ Te1[(s1 >> 16) & 0xff] ^ Te2[(s2 >>  8) & 0xff] ^ Te3[s3 & 0xff] ^ rk[28];
+   	t1 = Te0[s1 >> 24] ^ Te1[(s2 >> 16) & 0xff] ^ Te2[(s3 >>  8) & 0xff] ^ Te3[s0 & 0xff] ^ rk[29];
+   	t2 = Te0[s2 >> 24] ^ Te1[(s3 >> 16) & 0xff] ^ Te2[(s0 >>  8) & 0xff] ^ Te3[s1 & 0xff] ^ rk[30];
+   	t3 = Te0[s3 >> 24] ^ Te1[(s0 >> 16) & 0xff] ^ Te2[(s1 >>  8) & 0xff] ^ Te3[s2 & 0xff] ^ rk[31];
+   	/* round 8: */
+   	s0 = Te0[t0 >> 24] ^ Te1[(t1 >> 16) & 0xff] ^ Te2[(t2 >>  8) & 0xff] ^ Te3[t3 & 0xff] ^ rk[32];
+   	s1 = Te0[t1 >> 24] ^ Te1[(t2 >> 16) & 0xff] ^ Te2[(t3 >>  8) & 0xff] ^ Te3[t0 & 0xff] ^ rk[33];
+   	s2 = Te0[t2 >> 24] ^ Te1[(t3 >> 16) & 0xff] ^ Te2[(t0 >>  8) & 0xff] ^ Te3[t1 & 0xff] ^ rk[34];
+   	s3 = Te0[t3 >> 24] ^ Te1[(t0 >> 16) & 0xff] ^ Te2[(t1 >>  8) & 0xff] ^ Te3[t2 & 0xff] ^ rk[35];
+    /* round 9: */
+   	t0 = Te0[s0 >> 24] ^ Te1[(s1 >> 16) & 0xff] ^ Te2[(s2 >>  8) & 0xff] ^ Te3[s3 & 0xff] ^ rk[36];
+   	t1 = Te0[s1 >> 24] ^ Te1[(s2 >> 16) & 0xff] ^ Te2[(s3 >>  8) & 0xff] ^ Te3[s0 & 0xff] ^ rk[37];
+   	t2 = Te0[s2 >> 24] ^ Te1[(s3 >> 16) & 0xff] ^ Te2[(s0 >>  8) & 0xff] ^ Te3[s1 & 0xff] ^ rk[38];
+   	t3 = Te0[s3 >> 24] ^ Te1[(s0 >> 16) & 0xff] ^ Te2[(s1 >>  8) & 0xff] ^ Te3[s2 & 0xff] ^ rk[39];
+    if (Nr > 10) {
+        /* round 10: */
+        s0 = Te0[t0 >> 24] ^ Te1[(t1 >> 16) & 0xff] ^ Te2[(t2 >>  8) & 0xff] ^ Te3[t3 & 0xff] ^ rk[40];
+        s1 = Te0[t1 >> 24] ^ Te1[(t2 >> 16) & 0xff] ^ Te2[(t3 >>  8) & 0xff] ^ Te3[t0 & 0xff] ^ rk[41];
+        s2 = Te0[t2 >> 24] ^ Te1[(t3 >> 16) & 0xff] ^ Te2[(t0 >>  8) & 0xff] ^ Te3[t1 & 0xff] ^ rk[42];
+        s3 = Te0[t3 >> 24] ^ Te1[(t0 >> 16) & 0xff] ^ Te2[(t1 >>  8) & 0xff] ^ Te3[t2 & 0xff] ^ rk[43];
+        /* round 11: */
+        t0 = Te0[s0 >> 24] ^ Te1[(s1 >> 16) & 0xff] ^ Te2[(s2 >>  8) & 0xff] ^ Te3[s3 & 0xff] ^ rk[44];
+        t1 = Te0[s1 >> 24] ^ Te1[(s2 >> 16) & 0xff] ^ Te2[(s3 >>  8) & 0xff] ^ Te3[s0 & 0xff] ^ rk[45];
+        t2 = Te0[s2 >> 24] ^ Te1[(s3 >> 16) & 0xff] ^ Te2[(s0 >>  8) & 0xff] ^ Te3[s1 & 0xff] ^ rk[46];
+        t3 = Te0[s3 >> 24] ^ Te1[(s0 >> 16) & 0xff] ^ Te2[(s1 >>  8) & 0xff] ^ Te3[s2 & 0xff] ^ rk[47];
+        if (Nr > 12) {
+            /* round 12: */
+            s0 = Te0[t0 >> 24] ^ Te1[(t1 >> 16) & 0xff] ^ Te2[(t2 >>  8) & 0xff] ^ Te3[t3 & 0xff] ^ rk[48];
+            s1 = Te0[t1 >> 24] ^ Te1[(t2 >> 16) & 0xff] ^ Te2[(t3 >>  8) & 0xff] ^ Te3[t0 & 0xff] ^ rk[49];
+            s2 = Te0[t2 >> 24] ^ Te1[(t3 >> 16) & 0xff] ^ Te2[(t0 >>  8) & 0xff] ^ Te3[t1 & 0xff] ^ rk[50];
+            s3 = Te0[t3 >> 24] ^ Te1[(t0 >> 16) & 0xff] ^ Te2[(t1 >>  8) & 0xff] ^ Te3[t2 & 0xff] ^ rk[51];
+            /* round 13: */
+            t0 = Te0[s0 >> 24] ^ Te1[(s1 >> 16) & 0xff] ^ Te2[(s2 >>  8) & 0xff] ^ Te3[s3 & 0xff] ^ rk[52];
+            t1 = Te0[s1 >> 24] ^ Te1[(s2 >> 16) & 0xff] ^ Te2[(s3 >>  8) & 0xff] ^ Te3[s0 & 0xff] ^ rk[53];
+            t2 = Te0[s2 >> 24] ^ Te1[(s3 >> 16) & 0xff] ^ Te2[(s0 >>  8) & 0xff] ^ Te3[s1 & 0xff] ^ rk[54];
+            t3 = Te0[s3 >> 24] ^ Te1[(s0 >> 16) & 0xff] ^ Te2[(s1 >>  8) & 0xff] ^ Te3[s2 & 0xff] ^ rk[55];
+        }
+    }
+    rk += Nr << 2;
+#else  /* !FULL_UNROLL */
+    /*
+	 * Nr - 1 full rounds:
+	 */
+    r = Nr >> 1;
+    for (;;) {
+        t0 =
+            Te0[(s0 >> 24)       ] ^
+            Te1[(s1 >> 16) & 0xff] ^
+            Te2[(s2 >>  8) & 0xff] ^
+            Te3[(s3      ) & 0xff] ^
+            rk[4];
+        t1 =
+            Te0[(s1 >> 24)       ] ^
+            Te1[(s2 >> 16) & 0xff] ^
+            Te2[(s3 >>  8) & 0xff] ^
+            Te3[(s0      ) & 0xff] ^
+            rk[5];
+        t2 =
+            Te0[(s2 >> 24)       ] ^
+            Te1[(s3 >> 16) & 0xff] ^
+            Te2[(s0 >>  8) & 0xff] ^
+            Te3[(s1      ) & 0xff] ^
+            rk[6];
+        t3 =
+            Te0[(s3 >> 24)       ] ^
+            Te1[(s0 >> 16) & 0xff] ^
+            Te2[(s1 >>  8) & 0xff] ^
+            Te3[(s2      ) & 0xff] ^
+            rk[7];
+
+        rk += 8;
+        if (--r == 0) {
+            break;
+        }
+
+        s0 =
+            Te0[(t0 >> 24)       ] ^
+            Te1[(t1 >> 16) & 0xff] ^
+            Te2[(t2 >>  8) & 0xff] ^
+            Te3[(t3      ) & 0xff] ^
+            rk[0];
+        s1 =
+            Te0[(t1 >> 24)       ] ^
+            Te1[(t2 >> 16) & 0xff] ^
+            Te2[(t3 >>  8) & 0xff] ^
+            Te3[(t0      ) & 0xff] ^
+            rk[1];
+        s2 =
+            Te0[(t2 >> 24)       ] ^
+            Te1[(t3 >> 16) & 0xff] ^
+            Te2[(t0 >>  8) & 0xff] ^
+            Te3[(t1      ) & 0xff] ^
+            rk[2];
+        s3 =
+            Te0[(t3 >> 24)       ] ^
+            Te1[(t0 >> 16) & 0xff] ^
+            Te2[(t1 >>  8) & 0xff] ^
+            Te3[(t2      ) & 0xff] ^
+            rk[3];
+    }
+#endif /* ?FULL_UNROLL */
+    /*
+	 * apply last round and
+	 * map cipher state to byte array block:
+	 */
+	s0 =
+		(Te4[(t0 >> 24)       ] & 0xff000000) ^
+		(Te4[(t1 >> 16) & 0xff] & 0x00ff0000) ^
+		(Te4[(t2 >>  8) & 0xff] & 0x0000ff00) ^
+		(Te4[(t3      ) & 0xff] & 0x000000ff) ^
+		rk[0];
+	PUTU32(ct     , s0);
+	s1 =
+		(Te4[(t1 >> 24)       ] & 0xff000000) ^
+		(Te4[(t2 >> 16) & 0xff] & 0x00ff0000) ^
+		(Te4[(t3 >>  8) & 0xff] & 0x0000ff00) ^
+		(Te4[(t0      ) & 0xff] & 0x000000ff) ^
+		rk[1];
+	PUTU32(ct +  4, s1);
+	s2 =
+		(Te4[(t2 >> 24)       ] & 0xff000000) ^
+		(Te4[(t3 >> 16) & 0xff] & 0x00ff0000) ^
+		(Te4[(t0 >>  8) & 0xff] & 0x0000ff00) ^
+		(Te4[(t1      ) & 0xff] & 0x000000ff) ^
+		rk[2];
+	PUTU32(ct +  8, s2);
+	s3 =
+		(Te4[(t3 >> 24)       ] & 0xff000000) ^
+		(Te4[(t0 >> 16) & 0xff] & 0x00ff0000) ^
+		(Te4[(t1 >>  8) & 0xff] & 0x0000ff00) ^
+		(Te4[(t2      ) & 0xff] & 0x000000ff) ^
+		rk[3];
+	PUTU32(ct + 12, s3);
+}
+
+void rijndaelDecrypt(const u32 rk[/*4*(Nr + 1)*/], int Nr, const u8 ct[16], u8 pt[16]) {
+	u32 s0, s1, s2, s3, t0, t1, t2, t3;
+#ifndef FULL_UNROLL
+    int r;
+#endif /* ?FULL_UNROLL */
+
+    /*
+	 * map byte array block to cipher state
+	 * and add initial round key:
+	 */
+    s0 = GETU32(ct     ) ^ rk[0];
+    s1 = GETU32(ct +  4) ^ rk[1];
+    s2 = GETU32(ct +  8) ^ rk[2];
+    s3 = GETU32(ct + 12) ^ rk[3];
+#ifdef FULL_UNROLL
+    /* round 1: */
+    t0 = Td0[s0 >> 24] ^ Td1[(s3 >> 16) & 0xff] ^ Td2[(s2 >>  8) & 0xff] ^ Td3[s1 & 0xff] ^ rk[ 4];
+    t1 = Td0[s1 >> 24] ^ Td1[(s0 >> 16) & 0xff] ^ Td2[(s3 >>  8) & 0xff] ^ Td3[s2 & 0xff] ^ rk[ 5];
+    t2 = Td0[s2 >> 24] ^ Td1[(s1 >> 16) & 0xff] ^ Td2[(s0 >>  8) & 0xff] ^ Td3[s3 & 0xff] ^ rk[ 6];
+    t3 = Td0[s3 >> 24] ^ Td1[(s2 >> 16) & 0xff] ^ Td2[(s1 >>  8) & 0xff] ^ Td3[s0 & 0xff] ^ rk[ 7];
+    /* round 2: */
+    s0 = Td0[t0 >> 24] ^ Td1[(t3 >> 16) & 0xff] ^ Td2[(t2 >>  8) & 0xff] ^ Td3[t1 & 0xff] ^ rk[ 8];
+    s1 = Td0[t1 >> 24] ^ Td1[(t0 >> 16) & 0xff] ^ Td2[(t3 >>  8) & 0xff] ^ Td3[t2 & 0xff] ^ rk[ 9];
+    s2 = Td0[t2 >> 24] ^ Td1[(t1 >> 16) & 0xff] ^ Td2[(t0 >>  8) & 0xff] ^ Td3[t3 & 0xff] ^ rk[10];
+    s3 = Td0[t3 >> 24] ^ Td1[(t2 >> 16) & 0xff] ^ Td2[(t1 >>  8) & 0xff] ^ Td3[t0 & 0xff] ^ rk[11];
+    /* round 3: */
+    t0 = Td0[s0 >> 24] ^ Td1[(s3 >> 16) & 0xff] ^ Td2[(s2 >>  8) & 0xff] ^ Td3[s1 & 0xff] ^ rk[12];
+    t1 = Td0[s1 >> 24] ^ Td1[(s0 >> 16) & 0xff] ^ Td2[(s3 >>  8) & 0xff] ^ Td3[s2 & 0xff] ^ rk[13];
+    t2 = Td0[s2 >> 24] ^ Td1[(s1 >> 16) & 0xff] ^ Td2[(s0 >>  8) & 0xff] ^ Td3[s3 & 0xff] ^ rk[14];
+    t3 = Td0[s3 >> 24] ^ Td1[(s2 >> 16) & 0xff] ^ Td2[(s1 >>  8) & 0xff] ^ Td3[s0 & 0xff] ^ rk[15];
+    /* round 4: */
+    s0 = Td0[t0 >> 24] ^ Td1[(t3 >> 16) & 0xff] ^ Td2[(t2 >>  8) & 0xff] ^ Td3[t1 & 0xff] ^ rk[16];
+    s1 = Td0[t1 >> 24] ^ Td1[(t0 >> 16) & 0xff] ^ Td2[(t3 >>  8) & 0xff] ^ Td3[t2 & 0xff] ^ rk[17];
+    s2 = Td0[t2 >> 24] ^ Td1[(t1 >> 16) & 0xff] ^ Td2[(t0 >>  8) & 0xff] ^ Td3[t3 & 0xff] ^ rk[18];
+    s3 = Td0[t3 >> 24] ^ Td1[(t2 >> 16) & 0xff] ^ Td2[(t1 >>  8) & 0xff] ^ Td3[t0 & 0xff] ^ rk[19];
+    /* round 5: */
+    t0 = Td0[s0 >> 24] ^ Td1[(s3 >> 16) & 0xff] ^ Td2[(s2 >>  8) & 0xff] ^ Td3[s1 & 0xff] ^ rk[20];
+    t1 = Td0[s1 >> 24] ^ Td1[(s0 >> 16) & 0xff] ^ Td2[(s3 >>  8) & 0xff] ^ Td3[s2 & 0xff] ^ rk[21];
+    t2 = Td0[s2 >> 24] ^ Td1[(s1 >> 16) & 0xff] ^ Td2[(s0 >>  8) & 0xff] ^ Td3[s3 & 0xff] ^ rk[22];
+    t3 = Td0[s3 >> 24] ^ Td1[(s2 >> 16) & 0xff] ^ Td2[(s1 >>  8) & 0xff] ^ Td3[s0 & 0xff] ^ rk[23];
+    /* round 6: */
+    s0 = Td0[t0 >> 24] ^ Td1[(t3 >> 16) & 0xff] ^ Td2[(t2 >>  8) & 0xff] ^ Td3[t1 & 0xff] ^ rk[24];
+    s1 = Td0[t1 >> 24] ^ Td1[(t0 >> 16) & 0xff] ^ Td2[(t3 >>  8) & 0xff] ^ Td3[t2 & 0xff] ^ rk[25];
+    s2 = Td0[t2 >> 24] ^ Td1[(t1 >> 16) & 0xff] ^ Td2[(t0 >>  8) & 0xff] ^ Td3[t3 & 0xff] ^ rk[26];
+    s3 = Td0[t3 >> 24] ^ Td1[(t2 >> 16) & 0xff] ^ Td2[(t1 >>  8) & 0xff] ^ Td3[t0 & 0xff] ^ rk[27];
+    /* round 7: */
+    t0 = Td0[s0 >> 24] ^ Td1[(s3 >> 16) & 0xff] ^ Td2[(s2 >>  8) & 0xff] ^ Td3[s1 & 0xff] ^ rk[28];
+    t1 = Td0[s1 >> 24] ^ Td1[(s0 >> 16) & 0xff] ^ Td2[(s3 >>  8) & 0xff] ^ Td3[s2 & 0xff] ^ rk[29];
+    t2 = Td0[s2 >> 24] ^ Td1[(s1 >> 16) & 0xff] ^ Td2[(s0 >>  8) & 0xff] ^ Td3[s3 & 0xff] ^ rk[30];
+    t3 = Td0[s3 >> 24] ^ Td1[(s2 >> 16) & 0xff] ^ Td2[(s1 >>  8) & 0xff] ^ Td3[s0 & 0xff] ^ rk[31];
+    /* round 8: */
+    s0 = Td0[t0 >> 24] ^ Td1[(t3 >> 16) & 0xff] ^ Td2[(t2 >>  8) & 0xff] ^ Td3[t1 & 0xff] ^ rk[32];
+    s1 = Td0[t1 >> 24] ^ Td1[(t0 >> 16) & 0xff] ^ Td2[(t3 >>  8) & 0xff] ^ Td3[t2 & 0xff] ^ rk[33];
+    s2 = Td0[t2 >> 24] ^ Td1[(t1 >> 16) & 0xff] ^ Td2[(t0 >>  8) & 0xff] ^ Td3[t3 & 0xff] ^ rk[34];
+    s3 = Td0[t3 >> 24] ^ Td1[(t2 >> 16) & 0xff] ^ Td2[(t1 >>  8) & 0xff] ^ Td3[t0 & 0xff] ^ rk[35];
+    /* round 9: */
+    t0 = Td0[s0 >> 24] ^ Td1[(s3 >> 16) & 0xff] ^ Td2[(s2 >>  8) & 0xff] ^ Td3[s1 & 0xff] ^ rk[36];
+    t1 = Td0[s1 >> 24] ^ Td1[(s0 >> 16) & 0xff] ^ Td2[(s3 >>  8) & 0xff] ^ Td3[s2 & 0xff] ^ rk[37];
+    t2 = Td0[s2 >> 24] ^ Td1[(s1 >> 16) & 0xff] ^ Td2[(s0 >>  8) & 0xff] ^ Td3[s3 & 0xff] ^ rk[38];
+    t3 = Td0[s3 >> 24] ^ Td1[(s2 >> 16) & 0xff] ^ Td2[(s1 >>  8) & 0xff] ^ Td3[s0 & 0xff] ^ rk[39];
+    if (Nr > 10) {
+        /* round 10: */
+        s0 = Td0[t0 >> 24] ^ Td1[(t3 >> 16) & 0xff] ^ Td2[(t2 >>  8) & 0xff] ^ Td3[t1 & 0xff] ^ rk[40];
+        s1 = Td0[t1 >> 24] ^ Td1[(t0 >> 16) & 0xff] ^ Td2[(t3 >>  8) & 0xff] ^ Td3[t2 & 0xff] ^ rk[41];
+        s2 = Td0[t2 >> 24] ^ Td1[(t1 >> 16) & 0xff] ^ Td2[(t0 >>  8) & 0xff] ^ Td3[t3 & 0xff] ^ rk[42];
+        s3 = Td0[t3 >> 24] ^ Td1[(t2 >> 16) & 0xff] ^ Td2[(t1 >>  8) & 0xff] ^ Td3[t0 & 0xff] ^ rk[43];
+        /* round 11: */
+        t0 = Td0[s0 >> 24] ^ Td1[(s3 >> 16) & 0xff] ^ Td2[(s2 >>  8) & 0xff] ^ Td3[s1 & 0xff] ^ rk[44];
+        t1 = Td0[s1 >> 24] ^ Td1[(s0 >> 16) & 0xff] ^ Td2[(s3 >>  8) & 0xff] ^ Td3[s2 & 0xff] ^ rk[45];
+        t2 = Td0[s2 >> 24] ^ Td1[(s1 >> 16) & 0xff] ^ Td2[(s0 >>  8) & 0xff] ^ Td3[s3 & 0xff] ^ rk[46];
+        t3 = Td0[s3 >> 24] ^ Td1[(s2 >> 16) & 0xff] ^ Td2[(s1 >>  8) & 0xff] ^ Td3[s0 & 0xff] ^ rk[47];
+        if (Nr > 12) {
+            /* round 12: */
+            s0 = Td0[t0 >> 24] ^ Td1[(t3 >> 16) & 0xff] ^ Td2[(t2 >>  8) & 0xff] ^ Td3[t1 & 0xff] ^ rk[48];
+            s1 = Td0[t1 >> 24] ^ Td1[(t0 >> 16) & 0xff] ^ Td2[(t3 >>  8) & 0xff] ^ Td3[t2 & 0xff] ^ rk[49];
+            s2 = Td0[t2 >> 24] ^ Td1[(t1 >> 16) & 0xff] ^ Td2[(t0 >>  8) & 0xff] ^ Td3[t3 & 0xff] ^ rk[50];
+            s3 = Td0[t3 >> 24] ^ Td1[(t2 >> 16) & 0xff] ^ Td2[(t1 >>  8) & 0xff] ^ Td3[t0 & 0xff] ^ rk[51];
+            /* round 13: */
+            t0 = Td0[s0 >> 24] ^ Td1[(s3 >> 16) & 0xff] ^ Td2[(s2 >>  8) & 0xff] ^ Td3[s1 & 0xff] ^ rk[52];
+            t1 = Td0[s1 >> 24] ^ Td1[(s0 >> 16) & 0xff] ^ Td2[(s3 >>  8) & 0xff] ^ Td3[s2 & 0xff] ^ rk[53];
+            t2 = Td0[s2 >> 24] ^ Td1[(s1 >> 16) & 0xff] ^ Td2[(s0 >>  8) & 0xff] ^ Td3[s3 & 0xff] ^ rk[54];
+            t3 = Td0[s3 >> 24] ^ Td1[(s2 >> 16) & 0xff] ^ Td2[(s1 >>  8) & 0xff] ^ Td3[s0 & 0xff] ^ rk[55];
+        }
+    }
+	rk += Nr << 2;
+#else  /* !FULL_UNROLL */
+    /*
+     * Nr - 1 full rounds:
+     */
+    r = Nr >> 1;
+    for (;;) {
+        t0 =
+            Td0[(s0 >> 24)       ] ^
+            Td1[(s3 >> 16) & 0xff] ^
+            Td2[(s2 >>  8) & 0xff] ^
+            Td3[(s1      ) & 0xff] ^
+            rk[4];
+        t1 =
+            Td0[(s1 >> 24)       ] ^
+            Td1[(s0 >> 16) & 0xff] ^
+            Td2[(s3 >>  8) & 0xff] ^
+            Td3[(s2      ) & 0xff] ^
+            rk[5];
+        t2 =
+            Td0[(s2 >> 24)       ] ^
+            Td1[(s1 >> 16) & 0xff] ^
+            Td2[(s0 >>  8) & 0xff] ^
+            Td3[(s3      ) & 0xff] ^
+            rk[6];
+        t3 =
+            Td0[(s3 >> 24)       ] ^
+            Td1[(s2 >> 16) & 0xff] ^
+            Td2[(s1 >>  8) & 0xff] ^
+            Td3[(s0      ) & 0xff] ^
+            rk[7];
+
+        rk += 8;
+        if (--r == 0) {
+            break;
+        }
+
+        s0 =
+            Td0[(t0 >> 24)       ] ^
+            Td1[(t3 >> 16) & 0xff] ^
+            Td2[(t2 >>  8) & 0xff] ^
+            Td3[(t1      ) & 0xff] ^
+            rk[0];
+        s1 =
+            Td0[(t1 >> 24)       ] ^
+            Td1[(t0 >> 16) & 0xff] ^
+            Td2[(t3 >>  8) & 0xff] ^
+            Td3[(t2      ) & 0xff] ^
+            rk[1];
+        s2 =
+            Td0[(t2 >> 24)       ] ^
+            Td1[(t1 >> 16) & 0xff] ^
+            Td2[(t0 >>  8) & 0xff] ^
+            Td3[(t3      ) & 0xff] ^
+            rk[2];
+        s3 =
+            Td0[(t3 >> 24)       ] ^
+            Td1[(t2 >> 16) & 0xff] ^
+            Td2[(t1 >>  8) & 0xff] ^
+            Td3[(t0      ) & 0xff] ^
+            rk[3];
+    }
+#endif /* ?FULL_UNROLL */
+    /*
+	 * apply last round and
+	 * map cipher state to byte array block:
+	 */
+   	s0 =
+   		(Td4[(t0 >> 24)       ] & 0xff000000) ^
+   		(Td4[(t3 >> 16) & 0xff] & 0x00ff0000) ^
+   		(Td4[(t2 >>  8) & 0xff] & 0x0000ff00) ^
+   		(Td4[(t1      ) & 0xff] & 0x000000ff) ^
+   		rk[0];
+	PUTU32(pt     , s0);
+   	s1 =
+   		(Td4[(t1 >> 24)       ] & 0xff000000) ^
+   		(Td4[(t0 >> 16) & 0xff] & 0x00ff0000) ^
+   		(Td4[(t3 >>  8) & 0xff] & 0x0000ff00) ^
+   		(Td4[(t2      ) & 0xff] & 0x000000ff) ^
+   		rk[1];
+	PUTU32(pt +  4, s1);
+   	s2 =
+   		(Td4[(t2 >> 24)       ] & 0xff000000) ^
+   		(Td4[(t1 >> 16) & 0xff] & 0x00ff0000) ^
+   		(Td4[(t0 >>  8) & 0xff] & 0x0000ff00) ^
+   		(Td4[(t3      ) & 0xff] & 0x000000ff) ^
+   		rk[2];
+	PUTU32(pt +  8, s2);
+   	s3 =
+   		(Td4[(t3 >> 24)       ] & 0xff000000) ^
+   		(Td4[(t2 >> 16) & 0xff] & 0x00ff0000) ^
+   		(Td4[(t1 >>  8) & 0xff] & 0x0000ff00) ^
+   		(Td4[(t0      ) & 0xff] & 0x000000ff) ^
+   		rk[3];
+	PUTU32(pt + 12, s3);
+}
+
+#ifdef INTERMEDIATE_VALUE_KAT
+
+void rijndaelEncryptRound(const u32 rk[/*4*(Nr + 1)*/], int Nr, u8 block[16], int rounds) {
+	int r;
+	u32 s0, s1, s2, s3, t0, t1, t2, t3;
+
+    /*
+	 * map byte array block to cipher state
+	 * and add initial round key:
+	 */
+	s0 = GETU32(block     ) ^ rk[0];
+	s1 = GETU32(block +  4) ^ rk[1];
+	s2 = GETU32(block +  8) ^ rk[2];
+	s3 = GETU32(block + 12) ^ rk[3];
+    rk += 4;
+
+    /*
+	 * Nr - 1 full rounds:
+	 */
+	for (r = (rounds < Nr ? rounds : Nr - 1); r > 0; r--) {
+		t0 =
+			Te0[(s0 >> 24)       ] ^
+			Te1[(s1 >> 16) & 0xff] ^
+			Te2[(s2 >>  8) & 0xff] ^
+			Te3[(s3      ) & 0xff] ^
+			rk[0];
+		t1 =
+			Te0[(s1 >> 24)       ] ^
+			Te1[(s2 >> 16) & 0xff] ^
+			Te2[(s3 >>  8) & 0xff] ^
+			Te3[(s0      ) & 0xff] ^
+			rk[1];
+		t2 =
+			Te0[(s2 >> 24)       ] ^
+			Te1[(s3 >> 16) & 0xff] ^
+			Te2[(s0 >>  8) & 0xff] ^
+			Te3[(s1      ) & 0xff] ^
+			rk[2];
+		t3 =
+			Te0[(s3 >> 24)       ] ^
+			Te1[(s0 >> 16) & 0xff] ^
+			Te2[(s1 >>  8) & 0xff] ^
+			Te3[(s2      ) & 0xff] ^
+			rk[3];
+
+		s0 = t0;
+		s1 = t1;
+		s2 = t2;
+		s3 = t3;
+		rk += 4;
+
+    }
+
+    /*
+	 * apply last round and
+	 * map cipher state to byte array block:
+	 */
+	if (rounds == Nr) {
+    	t0 =
+    		(Te4[(s0 >> 24)       ] & 0xff000000) ^
+    		(Te4[(s1 >> 16) & 0xff] & 0x00ff0000) ^
+    		(Te4[(s2 >>  8) & 0xff] & 0x0000ff00) ^
+    		(Te4[(s3      ) & 0xff] & 0x000000ff) ^
+    		rk[0];
+    	t1 =
+    		(Te4[(s1 >> 24)       ] & 0xff000000) ^
+    		(Te4[(s2 >> 16) & 0xff] & 0x00ff0000) ^
+    		(Te4[(s3 >>  8) & 0xff] & 0x0000ff00) ^
+    		(Te4[(s0      ) & 0xff] & 0x000000ff) ^
+    		rk[1];
+    	t2 =
+    		(Te4[(s2 >> 24)       ] & 0xff000000) ^
+    		(Te4[(s3 >> 16) & 0xff] & 0x00ff0000) ^
+    		(Te4[(s0 >>  8) & 0xff] & 0x0000ff00) ^
+    		(Te4[(s1      ) & 0xff] & 0x000000ff) ^
+    		rk[2];
+    	t3 =
+    		(Te4[(s3 >> 24)       ] & 0xff000000) ^
+    		(Te4[(s0 >> 16) & 0xff] & 0x00ff0000) ^
+    		(Te4[(s1 >>  8) & 0xff] & 0x0000ff00) ^
+    		(Te4[(s2      ) & 0xff] & 0x000000ff) ^
+    		rk[3];
+		
+		s0 = t0;
+		s1 = t1;
+		s2 = t2;
+		s3 = t3;
+	}
+
+	PUTU32(block     , s0);
+	PUTU32(block +  4, s1);
+	PUTU32(block +  8, s2);
+	PUTU32(block + 12, s3);
+}
+
+void rijndaelDecryptRound(const u32 rk[/*4*(Nr + 1)*/], int Nr, u8 block[16], int rounds) {
+	int r;
+	u32 s0, s1, s2, s3, t0, t1, t2, t3;
+
+    /*
+	 * map byte array block to cipher state
+	 * and add initial round key:
+	 */
+	s0 = GETU32(block     ) ^ rk[0];
+	s1 = GETU32(block +  4) ^ rk[1];
+	s2 = GETU32(block +  8) ^ rk[2];
+	s3 = GETU32(block + 12) ^ rk[3];
+    rk += 4;
+
+    /*
+	 * Nr - 1 full rounds:
+	 */
+	for (r = (rounds < Nr ? rounds : Nr) - 1; r > 0; r--) {
+		t0 =
+			Td0[(s0 >> 24)       ] ^
+			Td1[(s3 >> 16) & 0xff] ^
+			Td2[(s2 >>  8) & 0xff] ^
+			Td3[(s1      ) & 0xff] ^
+			rk[0];
+		t1 =
+			Td0[(s1 >> 24)       ] ^
+			Td1[(s0 >> 16) & 0xff] ^
+			Td2[(s3 >>  8) & 0xff] ^
+			Td3[(s2      ) & 0xff] ^
+			rk[1];
+		t2 =
+			Td0[(s2 >> 24)       ] ^
+			Td1[(s1 >> 16) & 0xff] ^
+			Td2[(s0 >>  8) & 0xff] ^
+			Td3[(s3      ) & 0xff] ^
+			rk[2];
+		t3 =
+			Td0[(s3 >> 24)       ] ^
+			Td1[(s2 >> 16) & 0xff] ^
+			Td2[(s1 >>  8) & 0xff] ^
+			Td3[(s0      ) & 0xff] ^
+			rk[3];
+
+		s0 = t0;
+		s1 = t1;
+		s2 = t2;
+		s3 = t3;
+		rk += 4;
+
+    }
+
+    /*
+	 * complete the last round and
+	 * map cipher state to byte array block:
+	 */
+	t0 =
+		(Td4[(s0 >> 24)       ] & 0xff000000) ^
+		(Td4[(s3 >> 16) & 0xff] & 0x00ff0000) ^
+		(Td4[(s2 >>  8) & 0xff] & 0x0000ff00) ^
+		(Td4[(s1      ) & 0xff] & 0x000000ff);
+	t1 =
+		(Td4[(s1 >> 24)       ] & 0xff000000) ^
+		(Td4[(s0 >> 16) & 0xff] & 0x00ff0000) ^
+		(Td4[(s3 >>  8) & 0xff] & 0x0000ff00) ^
+		(Td4[(s2      ) & 0xff] & 0x000000ff);
+	t2 =
+		(Td4[(s2 >> 24)       ] & 0xff000000) ^
+		(Td4[(s1 >> 16) & 0xff] & 0x00ff0000) ^
+		(Td4[(s0 >>  8) & 0xff] & 0x0000ff00) ^
+		(Td4[(s3      ) & 0xff] & 0x000000ff);
+	t3 =
+		(Td4[(s3 >> 24)       ] & 0xff000000) ^
+		(Td4[(s2 >> 16) & 0xff] & 0x00ff0000) ^
+		(Td4[(s1 >>  8) & 0xff] & 0x0000ff00) ^
+		(Td4[(s0      ) & 0xff] & 0x000000ff);
+
+	if (rounds == Nr) {
+	    t0 ^= rk[0];
+	    t1 ^= rk[1];
+	    t2 ^= rk[2];
+	    t3 ^= rk[3];
+	}
+
+	PUTU32(block     , t0);
+	PUTU32(block +  4, t1);
+	PUTU32(block +  8, t2);
+	PUTU32(block + 12, t3);
+}
+
+#endif /* INTERMEDIATE_VALUE_KAT */