DeforaNetworks/hashcat
3
0
Fork 0
Code Releases Activity

cosmetic: minor code style fixes

Browse Source
This commit is contained in:
philsmd
2020-06-13 11:19:00 +02:00
parent 323e7463b8
commit e59f61e8cf
120 changed files with 895 additions and 888 deletions
Download Patch File Download Diff File Expand all files Collapse all files
OpenCL/inc_cipher_serpent.cl
+22 -22
View File
@@ -383,29 +383,29 @@
/* the linear transformation and its inverse */
#define rot(a,b,c,d) \
a = hc_rotl32_S(a, 13); \
c = hc_rotl32_S(c, 3); \
d ^= c ^ (a << 3); \
b ^= a ^ c; \
d = hc_rotl32_S(d, 7); \
b = hc_rotl32_S(b, 1); \
a ^= b ^ d; \
c ^= d ^ (b << 7); \
a = hc_rotl32_S(a, 5); \
c = hc_rotl32_S(c, 22)
#define rot(a,b,c,d) \
a = hc_rotl32_S (a, 13); \
c = hc_rotl32_S (c, 3); \
d ^= c ^ (a << 3); \
b ^= a ^ c; \
d = hc_rotl32_S (d, 7); \
b = hc_rotl32_S (b, 1); \
a ^= b ^ d; \
c ^= d ^ (b << 7); \
a = hc_rotl32_S (a, 5); \
c = hc_rotl32_S (c, 22)
#define irot(a,b,c,d) \
c = hc_rotr32_S(c, 22); \
a = hc_rotr32_S(a, 5); \
c ^= d ^ (b << 7); \
a ^= b ^ d; \
d = hc_rotr32_S(d, 7); \
b = hc_rotr32_S(b, 1); \
d ^= c ^ (a << 3); \
b ^= a ^ c; \
c = hc_rotr32_S(c, 3); \
a = hc_rotr32_S(a, 13)
#define irot(a,b,c,d) \
c = hc_rotr32_S (c, 22); \
a = hc_rotr32_S (a, 5); \
c ^= d ^ (b << 7); \
a ^= b ^ d; \
d = hc_rotr32_S (d, 7); \
b = hc_rotr32_S (b, 1); \
d ^= c ^ (a << 3); \
b ^= a ^ c; \
c = hc_rotr32_S (c, 3); \
a = hc_rotr32_S (a, 13)
// 128 bit key
OpenCL/inc_rp.cl
+3 -3
View File
@@ -14,11 +14,11 @@
#endif
#ifdef REAL_SHM
#define COPY_PW(x) \
LOCAL_VK pw_t s_pws[64]; \
#define COPY_PW(x) \
LOCAL_VK pw_t s_pws[64]; \
s_pws[get_local_id (0)] = (x);
#else
#define COPY_PW(x) \
#define COPY_PW(x) \
pw_t pw = (x);
#endif
OpenCL/m00010_a3-optimized.cl
+2 -2
View File
@@ -17,7 +17,7 @@
#define MD5_STEP_REV(f,a,b,c,d,x,t,s) \
{ \
a -= b; \
a = hc_rotr32_S (a, s); \
a = hc_rotr32_S (a, s); \
a -= f (b, c, d); \
a -= x; \
a -= t; \
@@ -26,7 +26,7 @@
#define MD5_STEP_REV1(f,a,b,c,d,x,t,s) \
{ \
a -= b; \
a = hc_rotr32_S (a, s); \
a = hc_rotr32_S (a, s); \
a -= x; \
a -= t; \
}
OpenCL/m00030_a3-optimized.cl
+2 -2
View File
@@ -17,7 +17,7 @@
#define MD5_STEP_REV(f,a,b,c,d,x,t,s) \
{ \
a -= b; \
a = hc_rotr32_S (a, s); \
a = hc_rotr32_S (a, s); \
a -= f (b, c, d); \
a -= x; \
a -= t; \
@@ -26,7 +26,7 @@
#define MD5_STEP_REV1(f,a,b,c,d,x,t,s) \
{ \
a -= b; \
a = hc_rotr32_S (a, s); \
a = hc_rotr32_S (a, s); \
a -= x; \
a -= t; \
}
OpenCL/m00400-optimized.cl
+1 -1
View File
@@ -236,4 +236,4 @@ KERNEL_FQ void m00400_comp (KERN_ATTR_TMPS (phpass_tmp_t))
#ifdef KERNEL_STATIC
#include COMPARE_M
#endif
}
}
OpenCL/m00600_a0-optimized.cl
+14 -14
View File
@@ -38,7 +38,7 @@ typedef struct blake2
d = hc_rotr64 (d ^ a, 16); \
c = c + d; \
b = hc_rotr64 (b ^ c, 63); \
} while(0)
} while (0)
#define BLAKE2B_ROUND(c0,c1,c2,c3,c4,c5,c6,c7,c8,c9,ca,cb,cc,cd,ce,cf) \
do { \
@@ -50,7 +50,7 @@ typedef struct blake2
BLAKE2B_G ((ca),(cb),v[ 1],v[ 6],v[11],v[12]); \
BLAKE2B_G ((cc),(cd),v[ 2],v[ 7],v[ 8],v[13]); \
BLAKE2B_G ((ce),(cf),v[ 3],v[ 4],v[ 9],v[14]); \
} while(0)
} while (0)
DECLSPEC void blake2b_transform (u64x *h, u64x *t, u64x *f, u64x *m, u64x *v, const u32x *w0, const u32x *w1, const u32x *w2, const u32x *w3, const u32x out_len, const u8 isFinal)
{
@@ -195,7 +195,7 @@ KERNEL_FQ void m00600_m04 (KERN_ATTR_RULES_ESALT (blake2_t))
f[0] = tmp_f[0];
f[1] = tmp_f[1];
blake2b_transform(h, t, f, m, v, w0, w1, w2, w3, out_len, BLAKE2B_FINAL);
blake2b_transform (h, t, f, m, v, w0, w1, w2, w3, out_len, BLAKE2B_FINAL);
digest[0] = h[0];
digest[1] = h[1];
@@ -206,12 +206,12 @@ KERNEL_FQ void m00600_m04 (KERN_ATTR_RULES_ESALT (blake2_t))
digest[6] = h[6];
digest[7] = h[7];
const u32x r0 = h32_from_64(digest[0]);
const u32x r1 = l32_from_64(digest[0]);
const u32x r2 = h32_from_64(digest[1]);
const u32x r3 = l32_from_64(digest[1]);
const u32x r0 = h32_from_64 (digest[0]);
const u32x r1 = l32_from_64 (digest[0]);
const u32x r2 = h32_from_64 (digest[1]);
const u32x r3 = l32_from_64 (digest[1]);
COMPARE_M_SIMD(r0, r1, r2, r3);
COMPARE_M_SIMD (r0, r1, r2, r3);
}
}
@@ -314,7 +314,7 @@ KERNEL_FQ void m00600_s04 (KERN_ATTR_RULES_ESALT (blake2_t))
f[0] = tmp_f[0];
f[1] = tmp_f[1];
blake2b_transform(h, t, f, m, v, w0, w1, w2, w3, out_len, BLAKE2B_FINAL);
blake2b_transform (h, t, f, m, v, w0, w1, w2, w3, out_len, BLAKE2B_FINAL);
digest[0] = h[0];
digest[1] = h[1];
@@ -325,12 +325,12 @@ KERNEL_FQ void m00600_s04 (KERN_ATTR_RULES_ESALT (blake2_t))
digest[6] = h[6];
digest[7] = h[7];
const u32x r0 = h32_from_64(digest[0]);
const u32x r1 = l32_from_64(digest[0]);
const u32x r2 = h32_from_64(digest[1]);
const u32x r3 = l32_from_64(digest[1]);
const u32x r0 = h32_from_64 (digest[0]);
const u32x r1 = l32_from_64 (digest[0]);
const u32x r2 = h32_from_64 (digest[1]);
const u32x r3 = l32_from_64 (digest[1]);
COMPARE_S_SIMD(r0, r1, r2, r3);
COMPARE_S_SIMD (r0, r1, r2, r3);
}
}
OpenCL/m00600_a1-optimized.cl
+14 -14
View File
@@ -36,7 +36,7 @@ typedef struct blake2
d = hc_rotr64 (d ^ a, 16); \
c = c + d; \
b = hc_rotr64 (b ^ c, 63); \
} while(0)
} while (0)
#define BLAKE2B_ROUND(c0,c1,c2,c3,c4,c5,c6,c7,c8,c9,ca,cb,cc,cd,ce,cf) \
do { \
@@ -48,7 +48,7 @@ typedef struct blake2
BLAKE2B_G ((ca),(cb),v[ 1],v[ 6],v[11],v[12]); \
BLAKE2B_G ((cc),(cd),v[ 2],v[ 7],v[ 8],v[13]); \
BLAKE2B_G ((ce),(cf),v[ 3],v[ 4],v[ 9],v[14]); \
} while(0)
} while (0)
DECLSPEC void blake2b_transform (u64x *h, u64x *t, u64x *f, u64x *m, u64x *v, const u32x *w0, const u32x *w1, const u32x *w2, const u32x *w3, const u32x out_len, const u8 isFinal)
{
@@ -250,7 +250,7 @@ KERNEL_FQ void m00600_m04 (KERN_ATTR_ESALT (blake2_t))
f[0] = tmp_f[0];
f[1] = tmp_f[1];
blake2b_transform(h, t, f, m, v, w0, w1, w2, w3, out_len, BLAKE2B_FINAL);
blake2b_transform (h, t, f, m, v, w0, w1, w2, w3, out_len, BLAKE2B_FINAL);
digest[0] = h[0];
digest[1] = h[1];
@@ -261,12 +261,12 @@ KERNEL_FQ void m00600_m04 (KERN_ATTR_ESALT (blake2_t))
digest[6] = h[6];
digest[7] = h[7];
const u32x r0 = h32_from_64(digest[0]);
const u32x r1 = l32_from_64(digest[0]);
const u32x r2 = h32_from_64(digest[1]);
const u32x r3 = l32_from_64(digest[1]);
const u32x r0 = h32_from_64 (digest[0]);
const u32x r1 = l32_from_64 (digest[0]);
const u32x r2 = h32_from_64 (digest[1]);
const u32x r3 = l32_from_64 (digest[1]);
COMPARE_M_SIMD(r0, r1, r2, r3);
COMPARE_M_SIMD (r0, r1, r2, r3);
}
}
@@ -429,7 +429,7 @@ KERNEL_FQ void m00600_s04 (KERN_ATTR_ESALT (blake2_t))
f[0] = tmp_f[0];
f[1] = tmp_f[1];
blake2b_transform(h, t, f, m, v, w0, w1, w2, w3, out_len, BLAKE2B_FINAL);
blake2b_transform (h, t, f, m, v, w0, w1, w2, w3, out_len, BLAKE2B_FINAL);
digest[0] = h[0];
digest[1] = h[1];
@@ -440,12 +440,12 @@ KERNEL_FQ void m00600_s04 (KERN_ATTR_ESALT (blake2_t))
digest[6] = h[6];
digest[7] = h[7];
const u32x r0 = h32_from_64(digest[0]);
const u32x r1 = l32_from_64(digest[0]);
const u32x r2 = h32_from_64(digest[1]);
const u32x r3 = l32_from_64(digest[1]);
const u32x r0 = h32_from_64 (digest[0]);
const u32x r1 = l32_from_64 (digest[0]);
const u32x r2 = h32_from_64 (digest[1]);
const u32x r3 = l32_from_64 (digest[1]);
COMPARE_S_SIMD(r0, r1, r2, r3);
COMPARE_S_SIMD (r0, r1, r2, r3);
}
}
OpenCL/m00600_a3-optimized.cl
+38 -38
View File
@@ -36,7 +36,7 @@ typedef struct blake2
d = hc_rotr64 (d ^ a, 16); \
c = c + d; \
b = hc_rotr64 (b ^ c, 63); \
} while(0)
} while (0)
#define BLAKE2B_ROUND(c0,c1,c2,c3,c4,c5,c6,c7,c8,c9,ca,cb,cc,cd,ce,cf) \
do { \
@@ -48,7 +48,7 @@ typedef struct blake2
BLAKE2B_G ((ca),(cb),v[ 1],v[ 6],v[11],v[12]); \
BLAKE2B_G ((cc),(cd),v[ 2],v[ 7],v[ 8],v[13]); \
BLAKE2B_G ((ce),(cf),v[ 3],v[ 4],v[ 9],v[14]); \
} while(0)
} while (0)
DECLSPEC void blake2b_transform (u64x *h, u64x *t, u64x *f, u64x *m, u64x *v, const u32x *w0, const u32x *w1, const u32x *w2, const u32x *w3, const u32x out_len, const u8 isFinal)
{
@@ -198,7 +198,7 @@ KERNEL_FQ void m00600_m04 (KERN_ATTR_VECTOR_ESALT (blake2_t))
f[0] = tmp_f[0];
f[1] = tmp_f[1];
blake2b_transform(h, t, f, m, v, w0, w1, w2, w3, out_len, BLAKE2B_FINAL);
blake2b_transform (h, t, f, m, v, w0, w1, w2, w3, out_len, BLAKE2B_FINAL);
digest[0] = h[0];
digest[1] = h[1];
@@ -209,12 +209,12 @@ KERNEL_FQ void m00600_m04 (KERN_ATTR_VECTOR_ESALT (blake2_t))
digest[6] = h[6];
digest[7] = h[7];
const u32x r0 = h32_from_64(digest[0]);
const u32x r1 = l32_from_64(digest[0]);
const u32x r2 = h32_from_64(digest[1]);
const u32x r3 = l32_from_64(digest[1]);
const u32x r0 = h32_from_64 (digest[0]);
const u32x r1 = l32_from_64 (digest[0]);
const u32x r2 = h32_from_64 (digest[1]);
const u32x r3 = l32_from_64 (digest[1]);
COMPARE_M_SIMD(r0, r1, r2, r3);
COMPARE_M_SIMD (r0, r1, r2, r3);
}
}
@@ -302,7 +302,7 @@ KERNEL_FQ void m00600_m08 (KERN_ATTR_VECTOR_ESALT (blake2_t))
f[0] = tmp_f[0];
f[1] = tmp_f[1];
blake2b_transform(h, t, f, m, v, w0, w1, w2, w3, out_len, BLAKE2B_FINAL);
blake2b_transform (h, t, f, m, v, w0, w1, w2, w3, out_len, BLAKE2B_FINAL);
digest[0] = h[0];
digest[1] = h[1];
@@ -313,12 +313,12 @@ KERNEL_FQ void m00600_m08 (KERN_ATTR_VECTOR_ESALT (blake2_t))
digest[6] = h[6];
digest[7] = h[7];
const u32x r0 = h32_from_64(digest[0]);
const u32x r1 = l32_from_64(digest[0]);
const u32x r2 = h32_from_64(digest[1]);
const u32x r3 = l32_from_64(digest[1]);
const u32x r0 = h32_from_64 (digest[0]);
const u32x r1 = l32_from_64 (digest[0]);
const u32x r2 = h32_from_64 (digest[1]);
const u32x r3 = l32_from_64 (digest[1]);
COMPARE_M_SIMD(r0, r1, r2, r3);
COMPARE_M_SIMD (r0, r1, r2, r3);
}
}
@@ -406,7 +406,7 @@ KERNEL_FQ void m00600_m16 (KERN_ATTR_VECTOR_ESALT (blake2_t))
f[0] = tmp_f[0];
f[1] = tmp_f[1];
blake2b_transform(h, t, f, m, v, w0, w1, w2, w3, out_len, BLAKE2B_FINAL);
blake2b_transform (h, t, f, m, v, w0, w1, w2, w3, out_len, BLAKE2B_FINAL);
digest[0] = h[0];
digest[1] = h[1];
@@ -417,12 +417,12 @@ KERNEL_FQ void m00600_m16 (KERN_ATTR_VECTOR_ESALT (blake2_t))
digest[6] = h[6];
digest[7] = h[7];
const u32x r0 = h32_from_64(digest[0]);
const u32x r1 = l32_from_64(digest[0]);
const u32x r2 = h32_from_64(digest[1]);
const u32x r3 = l32_from_64(digest[1]);
const u32x r0 = h32_from_64 (digest[0]);
const u32x r1 = l32_from_64 (digest[0]);
const u32x r2 = h32_from_64 (digest[1]);
const u32x r3 = l32_from_64 (digest[1]);
COMPARE_M_SIMD(r0, r1, r2, r3);
COMPARE_M_SIMD (r0, r1, r2, r3);
}
}
@@ -522,7 +522,7 @@ KERNEL_FQ void m00600_s04 (KERN_ATTR_VECTOR_ESALT (blake2_t))
f[0] = tmp_f[0];
f[1] = tmp_f[1];
blake2b_transform(h, t, f, m, v, w0, w1, w2, w3, out_len, BLAKE2B_FINAL);
blake2b_transform (h, t, f, m, v, w0, w1, w2, w3, out_len, BLAKE2B_FINAL);
digest[0] = h[0];
digest[1] = h[1];
@@ -533,12 +533,12 @@ KERNEL_FQ void m00600_s04 (KERN_ATTR_VECTOR_ESALT (blake2_t))
digest[6] = h[6];
digest[7] = h[7];
const u32x r0 = h32_from_64(digest[0]);
const u32x r1 = l32_from_64(digest[0]);
const u32x r2 = h32_from_64(digest[1]);
const u32x r3 = l32_from_64(digest[1]);
const u32x r0 = h32_from_64 (digest[0]);
const u32x r1 = l32_from_64 (digest[0]);
const u32x r2 = h32_from_64 (digest[1]);
const u32x r3 = l32_from_64 (digest[1]);
COMPARE_S_SIMD(r0, r1, r2, r3);
COMPARE_S_SIMD (r0, r1, r2, r3);
}
}
@@ -638,7 +638,7 @@ KERNEL_FQ void m00600_s08 (KERN_ATTR_VECTOR_ESALT (blake2_t))
f[0] = tmp_f[0];
f[1] = tmp_f[1];
blake2b_transform(h, t, f, m, v, w0, w1, w2, w3, out_len, BLAKE2B_FINAL);
blake2b_transform (h, t, f, m, v, w0, w1, w2, w3, out_len, BLAKE2B_FINAL);
digest[0] = h[0];
digest[1] = h[1];
@@ -649,12 +649,12 @@ KERNEL_FQ void m00600_s08 (KERN_ATTR_VECTOR_ESALT (blake2_t))
digest[6] = h[6];
digest[7] = h[7];
const u32x r0 = h32_from_64(digest[0]);
const u32x r1 = l32_from_64(digest[0]);
const u32x r2 = h32_from_64(digest[1]);
const u32x r3 = l32_from_64(digest[1]);
const u32x r0 = h32_from_64 (digest[0]);
const u32x r1 = l32_from_64 (digest[0]);
const u32x r2 = h32_from_64 (digest[1]);
const u32x r3 = l32_from_64 (digest[1]);
COMPARE_S_SIMD(r0, r1, r2, r3);
COMPARE_S_SIMD (r0, r1, r2, r3);
}
}
@@ -754,7 +754,7 @@ KERNEL_FQ void m00600_s16 (KERN_ATTR_VECTOR_ESALT (blake2_t))
f[0] = tmp_f[0];
f[1] = tmp_f[1];
blake2b_transform(h, t, f, m, v, w0, w1, w2, w3, out_len, BLAKE2B_FINAL);
blake2b_transform (h, t, f, m, v, w0, w1, w2, w3, out_len, BLAKE2B_FINAL);
digest[0] = h[0];
digest[1] = h[1];
@@ -765,11 +765,11 @@ KERNEL_FQ void m00600_s16 (KERN_ATTR_VECTOR_ESALT (blake2_t))
digest[6] = h[6];
digest[7] = h[7];
const u32x r0 = h32_from_64(digest[0]);
const u32x r1 = l32_from_64(digest[0]);
const u32x r2 = h32_from_64(digest[1]);
const u32x r3 = l32_from_64(digest[1]);
const u32x r0 = h32_from_64 (digest[0]);
const u32x r1 = l32_from_64 (digest[0]);
const u32x r2 = h32_from_64 (digest[1]);
const u32x r3 = l32_from_64 (digest[1]);
COMPARE_S_SIMD(r0, r1, r2, r3);
COMPARE_S_SIMD (r0, r1, r2, r3);
}
}
OpenCL/m00900_a3-optimized.cl
+2 -2
View File
@@ -16,7 +16,7 @@
#define MD4_STEP_REV(f,a,b,c,d,x,t,s) \
{ \
a = hc_rotr32_S (a, s); \
a = hc_rotr32_S (a, s); \
a -= f (b, c, d); \
a -= x; \
a -= t; \
@@ -24,7 +24,7 @@
#define MD4_STEP_REV1(f,a,b,c,d,x,t,s) \
{ \
a = hc_rotr32_S (a, s); \
a = hc_rotr32_S (a, s); \
a -= x; \
a -= t; \
}
OpenCL/m01000_a3-optimized.cl
+2 -2
View File
@@ -16,7 +16,7 @@
#define MD4_STEP_REV(f,a,b,c,d,x,t,s) \
{ \
a = hc_rotr32_S (a, s); \
a = hc_rotr32_S (a, s); \
a -= f (b, c, d); \
a -= x; \
a -= t; \
@@ -24,7 +24,7 @@
#define MD4_STEP_REV1(f,a,b,c,d,x,t,s) \
{ \
a = hc_rotr32_S (a, s); \
a = hc_rotr32_S (a, s); \
a -= x; \
a -= t; \
}
OpenCL/m01500_a3-pure.cl
+220 -220
View File
@@ -57,31 +57,31 @@
DECLSPEC void s1 (const u32 a1, const u32 a2, const u32 a3, const u32 a4, const u32 a5, const u32 a6, u32 *out1, u32 *out2, u32 *out3, u32 *out4)
{
LUT(xAA55AA5500550055, a1, a4, a6, 0xC1)
LUT(xA55AA55AF0F5F0F5, a3, a6, xAA55AA5500550055, 0x9E)
LUT(x5F5F5F5FA5A5A5A5, a1, a3, a6, 0xD6)
LUT(xF5A0F5A0A55AA55A, a4, xAA55AA5500550055, x5F5F5F5FA5A5A5A5, 0x56)
LUT(x947A947AD1E7D1E7, a2, xA55AA55AF0F5F0F5, xF5A0F5A0A55AA55A, 0x6C)
LUT(x5FFF5FFFFFFAFFFA, a6, xAA55AA5500550055, x5F5F5F5FA5A5A5A5, 0x7B)
LUT(xB96CB96C69936993, a2, xF5A0F5A0A55AA55A, x5FFF5FFFFFFAFFFA, 0xD6)
LUT(x3, a5, x947A947AD1E7D1E7, xB96CB96C69936993, 0x6A)
LUT(x55EE55EE55EE55EE, a1, a2, a4, 0x7A)
LUT(x084C084CB77BB77B, a2, a6, xF5A0F5A0A55AA55A, 0xC9)
LUT(x9C329C32E295E295, x947A947AD1E7D1E7, x55EE55EE55EE55EE, x084C084CB77BB77B, 0x72)
LUT(xA51EA51E50E050E0, a3, a6, x55EE55EE55EE55EE, 0x29)
LUT(x4AD34AD3BE3CBE3C, a2, x947A947AD1E7D1E7, xA51EA51E50E050E0, 0x95)
LUT(x2, a5, x9C329C32E295E295, x4AD34AD3BE3CBE3C, 0xC6)
LUT(xD955D95595D195D1, a1, a2, x9C329C32E295E295, 0xD2)
LUT(x8058805811621162, x947A947AD1E7D1E7, x55EE55EE55EE55EE, x084C084CB77BB77B, 0x90)
LUT(x7D0F7D0FC4B3C4B3, xA51EA51E50E050E0, xD955D95595D195D1, x8058805811621162, 0x76)
LUT(x0805080500010001, a3, xAA55AA5500550055, xD955D95595D195D1, 0x80)
LUT(x4A964A96962D962D, xB96CB96C69936993, x4AD34AD3BE3CBE3C, x0805080500010001, 0xA6)
LUT(x4, a5, x7D0F7D0FC4B3C4B3, x4A964A96962D962D, 0xA6)
LUT(x148014807B087B08, a1, xAA55AA5500550055, x947A947AD1E7D1E7, 0x21)
LUT(x94D894D86B686B68, xA55AA55AF0F5F0F5, x8058805811621162, x148014807B087B08, 0x6A)
LUT(x5555555540044004, a1, a6, x084C084CB77BB77B, 0x70)
LUT(xAFB4AFB4BF5BBF5B, x5F5F5F5FA5A5A5A5, xA51EA51E50E050E0, x5555555540044004, 0x97)
LUT(x1, a5, x94D894D86B686B68, xAFB4AFB4BF5BBF5B, 0x6C)
LUT (xAA55AA5500550055, a1, a4, a6, 0xC1)
LUT (xA55AA55AF0F5F0F5, a3, a6, xAA55AA5500550055, 0x9E)
LUT (x5F5F5F5FA5A5A5A5, a1, a3, a6, 0xD6)
LUT (xF5A0F5A0A55AA55A, a4, xAA55AA5500550055, x5F5F5F5FA5A5A5A5, 0x56)
LUT (x947A947AD1E7D1E7, a2, xA55AA55AF0F5F0F5, xF5A0F5A0A55AA55A, 0x6C)
LUT (x5FFF5FFFFFFAFFFA, a6, xAA55AA5500550055, x5F5F5F5FA5A5A5A5, 0x7B)
LUT (xB96CB96C69936993, a2, xF5A0F5A0A55AA55A, x5FFF5FFFFFFAFFFA, 0xD6)
LUT (x3, a5, x947A947AD1E7D1E7, xB96CB96C69936993, 0x6A)
LUT (x55EE55EE55EE55EE, a1, a2, a4, 0x7A)
LUT (x084C084CB77BB77B, a2, a6, xF5A0F5A0A55AA55A, 0xC9)
LUT (x9C329C32E295E295, x947A947AD1E7D1E7, x55EE55EE55EE55EE, x084C084CB77BB77B, 0x72)
LUT (xA51EA51E50E050E0, a3, a6, x55EE55EE55EE55EE, 0x29)
LUT (x4AD34AD3BE3CBE3C, a2, x947A947AD1E7D1E7, xA51EA51E50E050E0, 0x95)
LUT (x2, a5, x9C329C32E295E295, x4AD34AD3BE3CBE3C, 0xC6)
LUT (xD955D95595D195D1, a1, a2, x9C329C32E295E295, 0xD2)
LUT (x8058805811621162, x947A947AD1E7D1E7, x55EE55EE55EE55EE, x084C084CB77BB77B, 0x90)
LUT (x7D0F7D0FC4B3C4B3, xA51EA51E50E050E0, xD955D95595D195D1, x8058805811621162, 0x76)
LUT (x0805080500010001, a3, xAA55AA5500550055, xD955D95595D195D1, 0x80)
LUT (x4A964A96962D962D, xB96CB96C69936993, x4AD34AD3BE3CBE3C, x0805080500010001, 0xA6)
LUT (x4, a5, x7D0F7D0FC4B3C4B3, x4A964A96962D962D, 0xA6)
LUT (x148014807B087B08, a1, xAA55AA5500550055, x947A947AD1E7D1E7, 0x21)
LUT (x94D894D86B686B68, xA55AA55AF0F5F0F5, x8058805811621162, x148014807B087B08, 0x6A)
LUT (x5555555540044004, a1, a6, x084C084CB77BB77B, 0x70)
LUT (xAFB4AFB4BF5BBF5B, x5F5F5F5FA5A5A5A5, xA51EA51E50E050E0, x5555555540044004, 0x97)
LUT (x1, a5, x94D894D86B686B68, xAFB4AFB4BF5BBF5B, 0x6C)
*out1 ^= x1;
*out2 ^= x2;
@@ -91,30 +91,30 @@ DECLSPEC void s1 (const u32 a1, const u32 a2, const u32 a3, const u32 a4, const
DECLSPEC void s2 (const u32 a1, const u32 a2, const u32 a3, const u32 a4, const u32 a5, const u32 a6, u32 *out1, u32 *out2, u32 *out3, u32 *out4)
{
LUT(xEEEEEEEE99999999, a1, a2, a6, 0x97)
LUT(xFFFFEEEE66666666, a5, a6, xEEEEEEEE99999999, 0x67)
LUT(x5555FFFFFFFF0000, a1, a5, a6, 0x76)
LUT(x6666DDDD5555AAAA, a2, xFFFFEEEE66666666, x5555FFFFFFFF0000, 0x69)
LUT(x6969D3D35353ACAC, a3, xFFFFEEEE66666666, x6666DDDD5555AAAA, 0x6A)
LUT(xCFCF3030CFCF3030, a2, a3, a5, 0x65)
LUT(xE4E4EEEE9999F0F0, a3, xEEEEEEEE99999999, x5555FFFFFFFF0000, 0x8D)
LUT(xE5E5BABACDCDB0B0, a1, xCFCF3030CFCF3030, xE4E4EEEE9999F0F0, 0xCA)
LUT(x3, a4, x6969D3D35353ACAC, xE5E5BABACDCDB0B0, 0xC6)
LUT(x3333CCCC00000000, a2, a5, a6, 0x14)
LUT(xCCCCDDDDFFFF0F0F, a5, xE4E4EEEE9999F0F0, x3333CCCC00000000, 0xB5)
LUT(x00000101F0F0F0F0, a3, a6, xFFFFEEEE66666666, 0x1C)
LUT(x9A9A64646A6A9595, a1, xCFCF3030CFCF3030, x00000101F0F0F0F0, 0x96)
LUT(x2, a4, xCCCCDDDDFFFF0F0F, x9A9A64646A6A9595, 0x6A)
LUT(x3333BBBB3333FFFF, a1, a2, x6666DDDD5555AAAA, 0xDE)
LUT(x1414141441410000, a1, a3, xE4E4EEEE9999F0F0, 0x90)
LUT(x7F7FF3F3F5F53939, x6969D3D35353ACAC, x9A9A64646A6A9595, x3333BBBB3333FFFF, 0x79)
LUT(x9494E3E34B4B3939, a5, x1414141441410000, x7F7FF3F3F5F53939, 0x29)
LUT(x1, a4, x3333BBBB3333FFFF, x9494E3E34B4B3939, 0xA6)
LUT(xB1B1BBBBCCCCA5A5, a1, a1, xE4E4EEEE9999F0F0, 0x4A)
LUT(xFFFFECECEEEEDDDD, a2, x3333CCCC00000000, x9A9A64646A6A9595, 0xEF)
LUT(xB1B1A9A9DCDC8787, xE5E5BABACDCDB0B0, xB1B1BBBBCCCCA5A5, xFFFFECECEEEEDDDD, 0x8D)
LUT(xFFFFCCCCEEEE4444, a2, a5, xFFFFEEEE66666666, 0x2B)
LUT(x4, a4, xB1B1A9A9DCDC8787, xFFFFCCCCEEEE4444, 0x6C)
LUT (xEEEEEEEE99999999, a1, a2, a6, 0x97)
LUT (xFFFFEEEE66666666, a5, a6, xEEEEEEEE99999999, 0x67)
LUT (x5555FFFFFFFF0000, a1, a5, a6, 0x76)
LUT (x6666DDDD5555AAAA, a2, xFFFFEEEE66666666, x5555FFFFFFFF0000, 0x69)
LUT (x6969D3D35353ACAC, a3, xFFFFEEEE66666666, x6666DDDD5555AAAA, 0x6A)
LUT (xCFCF3030CFCF3030, a2, a3, a5, 0x65)
LUT (xE4E4EEEE9999F0F0, a3, xEEEEEEEE99999999, x5555FFFFFFFF0000, 0x8D)
LUT (xE5E5BABACDCDB0B0, a1, xCFCF3030CFCF3030, xE4E4EEEE9999F0F0, 0xCA)
LUT (x3, a4, x6969D3D35353ACAC, xE5E5BABACDCDB0B0, 0xC6)
LUT (x3333CCCC00000000, a2, a5, a6, 0x14)
LUT (xCCCCDDDDFFFF0F0F, a5, xE4E4EEEE9999F0F0, x3333CCCC00000000, 0xB5)
LUT (x00000101F0F0F0F0, a3, a6, xFFFFEEEE66666666, 0x1C)
LUT (x9A9A64646A6A9595, a1, xCFCF3030CFCF3030, x00000101F0F0F0F0, 0x96)
LUT (x2, a4, xCCCCDDDDFFFF0F0F, x9A9A64646A6A9595, 0x6A)
LUT (x3333BBBB3333FFFF, a1, a2, x6666DDDD5555AAAA, 0xDE)
LUT (x1414141441410000, a1, a3, xE4E4EEEE9999F0F0, 0x90)
LUT (x7F7FF3F3F5F53939, x6969D3D35353ACAC, x9A9A64646A6A9595, x3333BBBB3333FFFF, 0x79)
LUT (x9494E3E34B4B3939, a5, x1414141441410000, x7F7FF3F3F5F53939, 0x29)
LUT (x1, a4, x3333BBBB3333FFFF, x9494E3E34B4B3939, 0xA6)
LUT (xB1B1BBBBCCCCA5A5, a1, a1, xE4E4EEEE9999F0F0, 0x4A)
LUT (xFFFFECECEEEEDDDD, a2, x3333CCCC00000000, x9A9A64646A6A9595, 0xEF)
LUT (xB1B1A9A9DCDC8787, xE5E5BABACDCDB0B0, xB1B1BBBBCCCCA5A5, xFFFFECECEEEEDDDD, 0x8D)
LUT (xFFFFCCCCEEEE4444, a2, a5, xFFFFEEEE66666666, 0x2B)
LUT (x4, a4, xB1B1A9A9DCDC8787, xFFFFCCCCEEEE4444, 0x6C)
*out1 ^= x1;
*out2 ^= x2;
@@ -124,31 +124,31 @@ DECLSPEC void s2 (const u32 a1, const u32 a2, const u32 a3, const u32 a4, const
DECLSPEC void s3 (const u32 a1, const u32 a2, const u32 a3, const u32 a4, const u32 a5, const u32 a6, u32 *out1, u32 *out2, u32 *out3, u32 *out4)
{
LUT(xA50FA50FA50FA50F, a1, a3, a4, 0xC9)
LUT(xF0F00F0FF0F0F0F0, a3, a5, a6, 0x4B)
LUT(xAF0FA0AAAF0FAF0F, a1, xA50FA50FA50FA50F, xF0F00F0FF0F0F0F0, 0x4D)
LUT(x5AA5A55A5AA55AA5, a1, a4, xF0F00F0FF0F0F0F0, 0x69)
LUT(xAA005FFFAA005FFF, a3, a5, xA50FA50FA50FA50F, 0xD6)
LUT(x5AA5A55A0F5AFAA5, a6, x5AA5A55A5AA55AA5, xAA005FFFAA005FFF, 0x9C)
LUT(x1, a2, xAF0FA0AAAF0FAF0F, x5AA5A55A0F5AFAA5, 0xA6)
LUT(xAA55AA5500AA00AA, a1, a4, a6, 0x49)
LUT(xFAFAA50FFAFAA50F, a1, a5, xA50FA50FA50FA50F, 0x9B)
LUT(x50AF0F5AFA50A5A5, a1, xAA55AA5500AA00AA, xFAFAA50FFAFAA50F, 0x66)
LUT(xAFAFAFAFFAFAFAFA, a1, a3, a6, 0x6F)
LUT(xAFAFFFFFFFFAFAFF, a4, x50AF0F5AFA50A5A5, xAFAFAFAFFAFAFAFA, 0xEB)
LUT(x4, a2, x50AF0F5AFA50A5A5, xAFAFFFFFFFFAFAFF, 0x6C)
LUT(x500F500F500F500F, a1, a3, a4, 0x98)
LUT(xF0505A0505A5050F, x5AA5A55A0F5AFAA5, xAA55AA5500AA00AA, xAFAFAFAFFAFAFAFA, 0x1D)
LUT(xF0505A05AA55AAFF, a6, x500F500F500F500F, xF0505A0505A5050F, 0x9A)
LUT(xFF005F55FF005F55, a1, a4, xAA005FFFAA005FFF, 0xB2)
LUT(xA55F5AF0A55F5AF0, a5, xA50FA50FA50FA50F, x5AA5A55A5AA55AA5, 0x3D)
LUT(x5A5F05A5A55F5AF0, a6, xFF005F55FF005F55, xA55F5AF0A55F5AF0, 0xA6)
LUT(x3, a2, xF0505A05AA55AAFF, x5A5F05A5A55F5AF0, 0xA6)
LUT(x0F0F0F0FA5A5A5A5, a1, a3, a6, 0xC6)
LUT(x5FFFFF5FFFA0FFA0, x5AA5A55A5AA55AA5, xAFAFAFAFFAFAFAFA, x0F0F0F0FA5A5A5A5, 0xDB)
LUT(xF5555AF500A05FFF, a5, xFAFAA50FFAFAA50F, xF0505A0505A5050F, 0xB9)
LUT(x05A5AAF55AFA55A5, xF0505A05AA55AAFF, x0F0F0F0FA5A5A5A5, xF5555AF500A05FFF, 0x9B)
LUT(x2, a2, x5FFFFF5FFFA0FFA0, x05A5AAF55AFA55A5, 0xA6)
LUT (xA50FA50FA50FA50F, a1, a3, a4, 0xC9)
LUT (xF0F00F0FF0F0F0F0, a3, a5, a6, 0x4B)
LUT (xAF0FA0AAAF0FAF0F, a1, xA50FA50FA50FA50F, xF0F00F0FF0F0F0F0, 0x4D)
LUT (x5AA5A55A5AA55AA5, a1, a4, xF0F00F0FF0F0F0F0, 0x69)
LUT (xAA005FFFAA005FFF, a3, a5, xA50FA50FA50FA50F, 0xD6)
LUT (x5AA5A55A0F5AFAA5, a6, x5AA5A55A5AA55AA5, xAA005FFFAA005FFF, 0x9C)
LUT (x1, a2, xAF0FA0AAAF0FAF0F, x5AA5A55A0F5AFAA5, 0xA6)
LUT (xAA55AA5500AA00AA, a1, a4, a6, 0x49)
LUT (xFAFAA50FFAFAA50F, a1, a5, xA50FA50FA50FA50F, 0x9B)
LUT (x50AF0F5AFA50A5A5, a1, xAA55AA5500AA00AA, xFAFAA50FFAFAA50F, 0x66)
LUT (xAFAFAFAFFAFAFAFA, a1, a3, a6, 0x6F)
LUT (xAFAFFFFFFFFAFAFF, a4, x50AF0F5AFA50A5A5, xAFAFAFAFFAFAFAFA, 0xEB)
LUT (x4, a2, x50AF0F5AFA50A5A5, xAFAFFFFFFFFAFAFF, 0x6C)
LUT (x500F500F500F500F, a1, a3, a4, 0x98)
LUT (xF0505A0505A5050F, x5AA5A55A0F5AFAA5, xAA55AA5500AA00AA, xAFAFAFAFFAFAFAFA, 0x1D)
LUT (xF0505A05AA55AAFF, a6, x500F500F500F500F, xF0505A0505A5050F, 0x9A)
LUT (xFF005F55FF005F55, a1, a4, xAA005FFFAA005FFF, 0xB2)
LUT (xA55F5AF0A55F5AF0, a5, xA50FA50FA50FA50F, x5AA5A55A5AA55AA5, 0x3D)
LUT (x5A5F05A5A55F5AF0, a6, xFF005F55FF005F55, xA55F5AF0A55F5AF0, 0xA6)
LUT (x3, a2, xF0505A05AA55AAFF, x5A5F05A5A55F5AF0, 0xA6)
LUT (x0F0F0F0FA5A5A5A5, a1, a3, a6, 0xC6)
LUT (x5FFFFF5FFFA0FFA0, x5AA5A55A5AA55AA5, xAFAFAFAFFAFAFAFA, x0F0F0F0FA5A5A5A5, 0xDB)
LUT (xF5555AF500A05FFF, a5, xFAFAA50FFAFAA50F, xF0505A0505A5050F, 0xB9)
LUT (x05A5AAF55AFA55A5, xF0505A05AA55AAFF, x0F0F0F0FA5A5A5A5, xF5555AF500A05FFF, 0x9B)
LUT (x2, a2, x5FFFFF5FFFA0FFA0, x05A5AAF55AFA55A5, 0xA6)
*out1 ^= x1;
*out2 ^= x2;
@@ -158,24 +158,24 @@ DECLSPEC void s3 (const u32 a1, const u32 a2, const u32 a3, const u32 a4, const
DECLSPEC void s4 (const u32 a1, const u32 a2, const u32 a3, const u32 a4, const u32 a5, const u32 a6, u32 *out1, u32 *out2, u32 *out3, u32 *out4)
{
LUT(x55F055F055F055F0, a1, a3, a4, 0x72)
LUT(xA500F5F0A500F5F0, a3, a5, x55F055F055F055F0, 0xAD)
LUT(xF50AF50AF50AF50A, a1, a3, a4, 0x59)
LUT(xF5FA0FFFF5FA0FFF, a3, a5, xF50AF50AF50AF50A, 0xE7)
LUT(x61C8F93C61C8F93C, a2, xA500F5F0A500F5F0, xF5FA0FFFF5FA0FFF, 0xC6)
LUT(x9999666699996666, a1, a2, a5, 0x69)
LUT(x22C022C022C022C0, a2, a4, x55F055F055F055F0, 0x18)
LUT(xB35C94A6B35C94A6, xF5FA0FFFF5FA0FFF, x9999666699996666, x22C022C022C022C0, 0x63)
LUT(x4, a6, x61C8F93C61C8F93C, xB35C94A6B35C94A6, 0x6A)
LUT(x4848484848484848, a1, a2, a3, 0x12)
LUT(x55500AAA55500AAA, a1, a5, xF5FA0FFFF5FA0FFF, 0x28)
LUT(x3C90B3D63C90B3D6, x61C8F93C61C8F93C, x4848484848484848, x55500AAA55500AAA, 0x1E)
LUT(x8484333384843333, a1, x9999666699996666, x4848484848484848, 0x14)
LUT(x4452F1AC4452F1AC, xF50AF50AF50AF50A, xF5FA0FFFF5FA0FFF, xB35C94A6B35C94A6, 0x78)
LUT(x9586CA379586CA37, x55500AAA55500AAA, x8484333384843333, x4452F1AC4452F1AC, 0xD6)
LUT(x2, a6, x3C90B3D63C90B3D6, x9586CA379586CA37, 0x6A)
LUT(x1, a6, x3C90B3D63C90B3D6, x9586CA379586CA37, 0xA9)
LUT(x3, a6, x61C8F93C61C8F93C, xB35C94A6B35C94A6, 0x56)
LUT (x55F055F055F055F0, a1, a3, a4, 0x72)
LUT (xA500F5F0A500F5F0, a3, a5, x55F055F055F055F0, 0xAD)
LUT (xF50AF50AF50AF50A, a1, a3, a4, 0x59)
LUT (xF5FA0FFFF5FA0FFF, a3, a5, xF50AF50AF50AF50A, 0xE7)
LUT (x61C8F93C61C8F93C, a2, xA500F5F0A500F5F0, xF5FA0FFFF5FA0FFF, 0xC6)
LUT (x9999666699996666, a1, a2, a5, 0x69)
LUT (x22C022C022C022C0, a2, a4, x55F055F055F055F0, 0x18)
LUT (xB35C94A6B35C94A6, xF5FA0FFFF5FA0FFF, x9999666699996666, x22C022C022C022C0, 0x63)
LUT (x4, a6, x61C8F93C61C8F93C, xB35C94A6B35C94A6, 0x6A)
LUT (x4848484848484848, a1, a2, a3, 0x12)
LUT (x55500AAA55500AAA, a1, a5, xF5FA0FFFF5FA0FFF, 0x28)
LUT (x3C90B3D63C90B3D6, x61C8F93C61C8F93C, x4848484848484848, x55500AAA55500AAA, 0x1E)
LUT (x8484333384843333, a1, x9999666699996666, x4848484848484848, 0x14)
LUT (x4452F1AC4452F1AC, xF50AF50AF50AF50A, xF5FA0FFFF5FA0FFF, xB35C94A6B35C94A6, 0x78)
LUT (x9586CA379586CA37, x55500AAA55500AAA, x8484333384843333, x4452F1AC4452F1AC, 0xD6)
LUT (x2, a6, x3C90B3D63C90B3D6, x9586CA379586CA37, 0x6A)
LUT (x1, a6, x3C90B3D63C90B3D6, x9586CA379586CA37, 0xA9)
LUT (x3, a6, x61C8F93C61C8F93C, xB35C94A6B35C94A6, 0x56)
*out1 ^= x1;
*out2 ^= x2;
@@ -185,31 +185,31 @@ DECLSPEC void s4 (const u32 a1, const u32 a2, const u32 a3, const u32 a4, const
DECLSPEC void s5 (const u32 a1, const u32 a2, const u32 a3, const u32 a4, const u32 a5, const u32 a6, u32 *out1, u32 *out2, u32 *out3, u32 *out4)
{
LUT(xA0A0A0A0FFFFFFFF, a1, a3, a6, 0xAB)
LUT(xFFFF00005555FFFF, a1, a5, a6, 0xB9)
LUT(xB3B320207777FFFF, a2, xA0A0A0A0FFFFFFFF, xFFFF00005555FFFF, 0xE8)
LUT(x50505A5A5A5A5050, a1, a3, xFFFF00005555FFFF, 0x34)
LUT(xA2A2FFFF2222FFFF, a1, a5, xB3B320207777FFFF, 0xCE)
LUT(x2E2E6969A4A46363, a2, x50505A5A5A5A5050, xA2A2FFFF2222FFFF, 0x29)
LUT(x3, a4, xB3B320207777FFFF, x2E2E6969A4A46363, 0xA6)
LUT(xA5A50A0AA5A50A0A, a1, a3, a5, 0x49)
LUT(x969639396969C6C6, a2, a6, xA5A50A0AA5A50A0A, 0x96)
LUT(x1B1B1B1B1B1B1B1B, a1, a2, a3, 0xCA)
LUT(xBFBFBFBFF6F6F9F9, a3, xA0A0A0A0FFFFFFFF, x969639396969C6C6, 0x7E)
LUT(x5B5BA4A4B8B81D1D, xFFFF00005555FFFF, x1B1B1B1B1B1B1B1B, xBFBFBFBFF6F6F9F9, 0x96)
LUT(x2, a4, x969639396969C6C6, x5B5BA4A4B8B81D1D, 0xCA)
LUT(x5555BBBBFFFF5555, a1, a2, xFFFF00005555FFFF, 0xE5)
LUT(x6D6D9C9C95956969, x50505A5A5A5A5050, xA2A2FFFF2222FFFF, x969639396969C6C6, 0x97)
LUT(x1A1A67676A6AB4B4, xA5A50A0AA5A50A0A, x5555BBBBFFFF5555, x6D6D9C9C95956969, 0x47)
LUT(xA0A0FFFFAAAA0000, a3, xFFFF00005555FFFF, xA5A50A0AA5A50A0A, 0x3B)
LUT(x36369C9CC1C1D6D6, x969639396969C6C6, x6D6D9C9C95956969, xA0A0FFFFAAAA0000, 0xD9)
LUT(x1, a4, x1A1A67676A6AB4B4, x36369C9CC1C1D6D6, 0xCA)
LUT(x5555F0F0F5F55555, a1, a3, xFFFF00005555FFFF, 0xB1)
LUT(x79790202DCDC0808, xA2A2FFFF2222FFFF, xA5A50A0AA5A50A0A, x969639396969C6C6, 0x47)
LUT(x6C6CF2F229295D5D, xBFBFBFBFF6F6F9F9, x5555F0F0F5F55555, x79790202DCDC0808, 0x6E)
LUT(xA3A3505010101A1A, a2, xA2A2FFFF2222FFFF, x36369C9CC1C1D6D6, 0x94)
LUT(x7676C7C74F4FC7C7, a1, x2E2E6969A4A46363, xA3A3505010101A1A, 0xD9)
LUT(x4, a4, x6C6CF2F229295D5D, x7676C7C74F4FC7C7, 0xC6)
LUT (xA0A0A0A0FFFFFFFF, a1, a3, a6, 0xAB)
LUT (xFFFF00005555FFFF, a1, a5, a6, 0xB9)
LUT (xB3B320207777FFFF, a2, xA0A0A0A0FFFFFFFF, xFFFF00005555FFFF, 0xE8)
LUT (x50505A5A5A5A5050, a1, a3, xFFFF00005555FFFF, 0x34)
LUT (xA2A2FFFF2222FFFF, a1, a5, xB3B320207777FFFF, 0xCE)
LUT (x2E2E6969A4A46363, a2, x50505A5A5A5A5050, xA2A2FFFF2222FFFF, 0x29)
LUT (x3, a4, xB3B320207777FFFF, x2E2E6969A4A46363, 0xA6)
LUT (xA5A50A0AA5A50A0A, a1, a3, a5, 0x49)
LUT (x969639396969C6C6, a2, a6, xA5A50A0AA5A50A0A, 0x96)
LUT (x1B1B1B1B1B1B1B1B, a1, a2, a3, 0xCA)
LUT (xBFBFBFBFF6F6F9F9, a3, xA0A0A0A0FFFFFFFF, x969639396969C6C6, 0x7E)
LUT (x5B5BA4A4B8B81D1D, xFFFF00005555FFFF, x1B1B1B1B1B1B1B1B, xBFBFBFBFF6F6F9F9, 0x96)
LUT (x2, a4, x969639396969C6C6, x5B5BA4A4B8B81D1D, 0xCA)
LUT (x5555BBBBFFFF5555, a1, a2, xFFFF00005555FFFF, 0xE5)
LUT (x6D6D9C9C95956969, x50505A5A5A5A5050, xA2A2FFFF2222FFFF, x969639396969C6C6, 0x97)
LUT (x1A1A67676A6AB4B4, xA5A50A0AA5A50A0A, x5555BBBBFFFF5555, x6D6D9C9C95956969, 0x47)
LUT (xA0A0FFFFAAAA0000, a3, xFFFF00005555FFFF, xA5A50A0AA5A50A0A, 0x3B)
LUT (x36369C9CC1C1D6D6, x969639396969C6C6, x6D6D9C9C95956969, xA0A0FFFFAAAA0000, 0xD9)
LUT (x1, a4, x1A1A67676A6AB4B4, x36369C9CC1C1D6D6, 0xCA)
LUT (x5555F0F0F5F55555, a1, a3, xFFFF00005555FFFF, 0xB1)
LUT (x79790202DCDC0808, xA2A2FFFF2222FFFF, xA5A50A0AA5A50A0A, x969639396969C6C6, 0x47)
LUT (x6C6CF2F229295D5D, xBFBFBFBFF6F6F9F9, x5555F0F0F5F55555, x79790202DCDC0808, 0x6E)
LUT (xA3A3505010101A1A, a2, xA2A2FFFF2222FFFF, x36369C9CC1C1D6D6, 0x94)
LUT (x7676C7C74F4FC7C7, a1, x2E2E6969A4A46363, xA3A3505010101A1A, 0xD9)
LUT (x4, a4, x6C6CF2F229295D5D, x7676C7C74F4FC7C7, 0xC6)
*out1 ^= x1;
*out2 ^= x2;
@@ -219,30 +219,30 @@ DECLSPEC void s5 (const u32 a1, const u32 a2, const u32 a3, const u32 a4, const
DECLSPEC void s6 (const u32 a1, const u32 a2, const u32 a3, const u32 a4, const u32 a5, const u32 a6, u32 *out1, u32 *out2, u32 *out3, u32 *out4)
{
LUT(x5050F5F55050F5F5, a1, a3, a5, 0xB2)
LUT(x6363C6C66363C6C6, a1, a2, x5050F5F55050F5F5, 0x66)
LUT(xAAAA5555AAAA5555, a1, a1, a5, 0xA9)
LUT(x3A3A65653A3A6565, a3, x6363C6C66363C6C6, xAAAA5555AAAA5555, 0xA9)
LUT(x5963A3C65963A3C6, a4, x6363C6C66363C6C6, x3A3A65653A3A6565, 0xC6)
LUT(xE7E76565E7E76565, a5, x6363C6C66363C6C6, x3A3A65653A3A6565, 0xAD)
LUT(x455D45DF455D45DF, a1, a4, xE7E76565E7E76565, 0xE4)
LUT(x4, a6, x5963A3C65963A3C6, x455D45DF455D45DF, 0x6C)
LUT(x1101220211012202, a2, xAAAA5555AAAA5555, x5963A3C65963A3C6, 0x20)
LUT(xF00F0FF0F00F0FF0, a3, a4, a5, 0x69)
LUT(x16E94A9716E94A97, xE7E76565E7E76565, x1101220211012202, xF00F0FF0F00F0FF0, 0x9E)
LUT(x2992922929929229, a1, a2, xF00F0FF0F00F0FF0, 0x49)
LUT(xAFAF9823AFAF9823, a5, x5050F5F55050F5F5, x2992922929929229, 0x93)
LUT(x3, a6, x16E94A9716E94A97, xAFAF9823AFAF9823, 0x6C)
LUT(x4801810248018102, a4, x5963A3C65963A3C6, x1101220211012202, 0xA4)
LUT(x5EE8FFFD5EE8FFFD, a5, x16E94A9716E94A97, x4801810248018102, 0x76)
LUT(xF0FF00FFF0FF00FF, a3, a4, a5, 0xCD)
LUT(x942D9A67942D9A67, x3A3A65653A3A6565, x5EE8FFFD5EE8FFFD, xF0FF00FFF0FF00FF, 0x86)
LUT(x1, a6, x5EE8FFFD5EE8FFFD, x942D9A67942D9A67, 0xA6)
LUT(x6A40D4ED6F4DD4EE, a2, x4, xAFAF9823AFAF9823, 0x2D)
LUT(x6CA89C7869A49C79, x1101220211012202, x16E94A9716E94A97, x6A40D4ED6F4DD4EE, 0x26)
LUT(xD6DE73F9D6DE73F9, a3, x6363C6C66363C6C6, x455D45DF455D45DF, 0x6B)
LUT(x925E63E1965A63E1, x3A3A65653A3A6565, x6CA89C7869A49C79, xD6DE73F9D6DE73F9, 0xA2)
LUT(x2, a6, x6CA89C7869A49C79, x925E63E1965A63E1, 0xCA)
LUT (x5050F5F55050F5F5, a1, a3, a5, 0xB2)
LUT (x6363C6C66363C6C6, a1, a2, x5050F5F55050F5F5, 0x66)
LUT (xAAAA5555AAAA5555, a1, a1, a5, 0xA9)
LUT (x3A3A65653A3A6565, a3, x6363C6C66363C6C6, xAAAA5555AAAA5555, 0xA9)
LUT (x5963A3C65963A3C6, a4, x6363C6C66363C6C6, x3A3A65653A3A6565, 0xC6)
LUT (xE7E76565E7E76565, a5, x6363C6C66363C6C6, x3A3A65653A3A6565, 0xAD)
LUT (x455D45DF455D45DF, a1, a4, xE7E76565E7E76565, 0xE4)
LUT (x4, a6, x5963A3C65963A3C6, x455D45DF455D45DF, 0x6C)
LUT (x1101220211012202, a2, xAAAA5555AAAA5555, x5963A3C65963A3C6, 0x20)
LUT (xF00F0FF0F00F0FF0, a3, a4, a5, 0x69)
LUT (x16E94A9716E94A97, xE7E76565E7E76565, x1101220211012202, xF00F0FF0F00F0FF0, 0x9E)
LUT (x2992922929929229, a1, a2, xF00F0FF0F00F0FF0, 0x49)
LUT (xAFAF9823AFAF9823, a5, x5050F5F55050F5F5, x2992922929929229, 0x93)
LUT (x3, a6, x16E94A9716E94A97, xAFAF9823AFAF9823, 0x6C)
LUT (x4801810248018102, a4, x5963A3C65963A3C6, x1101220211012202, 0xA4)
LUT (x5EE8FFFD5EE8FFFD, a5, x16E94A9716E94A97, x4801810248018102, 0x76)
LUT (xF0FF00FFF0FF00FF, a3, a4, a5, 0xCD)
LUT (x942D9A67942D9A67, x3A3A65653A3A6565, x5EE8FFFD5EE8FFFD, xF0FF00FFF0FF00FF, 0x86)
LUT (x1, a6, x5EE8FFFD5EE8FFFD, x942D9A67942D9A67, 0xA6)
LUT (x6A40D4ED6F4DD4EE, a2, x4, xAFAF9823AFAF9823, 0x2D)
LUT (x6CA89C7869A49C79, x1101220211012202, x16E94A9716E94A97, x6A40D4ED6F4DD4EE, 0x26)
LUT (xD6DE73F9D6DE73F9, a3, x6363C6C66363C6C6, x455D45DF455D45DF, 0x6B)
LUT (x925E63E1965A63E1, x3A3A65653A3A6565, x6CA89C7869A49C79, xD6DE73F9D6DE73F9, 0xA2)
LUT (x2, a6, x6CA89C7869A49C79, x925E63E1965A63E1, 0xCA)
*out1 ^= x1;
*out2 ^= x2;
@@ -252,30 +252,30 @@ DECLSPEC void s6 (const u32 a1, const u32 a2, const u32 a3, const u32 a4, const
DECLSPEC void s7 (const u32 a1, const u32 a2, const u32 a3, const u32 a4, const u32 a5, const u32 a6, u32 *out1, u32 *out2, u32 *out3, u32 *out4)
{
LUT(x88AA88AA88AA88AA, a1, a2, a4, 0x0B)
LUT(xAAAAFF00AAAAFF00, a1, a4, a5, 0x27)
LUT(xADAFF8A5ADAFF8A5, a3, x88AA88AA88AA88AA, xAAAAFF00AAAAFF00, 0x9E)
LUT(x0A0AF5F50A0AF5F5, a1, a3, a5, 0xA6)
LUT(x6B69C5DC6B69C5DC, a2, xADAFF8A5ADAFF8A5, x0A0AF5F50A0AF5F5, 0x6B)
LUT(x1C69B2DC1C69B2DC, a4, x88AA88AA88AA88AA, x6B69C5DC6B69C5DC, 0xA9)
LUT(x1, a6, xADAFF8A5ADAFF8A5, x1C69B2DC1C69B2DC, 0x6A)
LUT(x9C9C9C9C9C9C9C9C, a1, a2, a3, 0x63)
LUT(xE6E63BFDE6E63BFD, a2, xAAAAFF00AAAAFF00, x0A0AF5F50A0AF5F5, 0xE7)
LUT(x6385639E6385639E, a4, x9C9C9C9C9C9C9C9C, xE6E63BFDE6E63BFD, 0x93)
LUT(x5959C4CE5959C4CE, a2, x6B69C5DC6B69C5DC, xE6E63BFDE6E63BFD, 0x5D)
LUT(x5B53F53B5B53F53B, a4, x0A0AF5F50A0AF5F5, x5959C4CE5959C4CE, 0x6E)
LUT(x3, a6, x6385639E6385639E, x5B53F53B5B53F53B, 0xC6)
LUT(xFAF505FAFAF505FA, a3, a4, x0A0AF5F50A0AF5F5, 0x6D)
LUT(x6A65956A6A65956A, a3, x9C9C9C9C9C9C9C9C, xFAF505FAFAF505FA, 0xA6)
LUT(x8888CCCC8888CCCC, a1, a2, a5, 0x23)
LUT(x94E97A9494E97A94, x1C69B2DC1C69B2DC, x6A65956A6A65956A, x8888CCCC8888CCCC, 0x72)
LUT(x4, a6, x6A65956A6A65956A, x94E97A9494E97A94, 0xAC)
LUT(xA050A050A050A050, a1, a3, a4, 0x21)
LUT(xC1B87A2BC1B87A2B, xAAAAFF00AAAAFF00, x5B53F53B5B53F53B, x94E97A9494E97A94, 0xA4)
LUT(xE96016B7E96016B7, x8888CCCC8888CCCC, xA050A050A050A050, xC1B87A2BC1B87A2B, 0x96)
LUT(xE3CF1FD5E3CF1FD5, x88AA88AA88AA88AA, x6A65956A6A65956A, xE96016B7E96016B7, 0x3E)
LUT(x6776675B6776675B, xADAFF8A5ADAFF8A5, x94E97A9494E97A94, xE3CF1FD5E3CF1FD5, 0x6B)
LUT(x2, a6, xE96016B7E96016B7, x6776675B6776675B, 0xC6)
LUT (x88AA88AA88AA88AA, a1, a2, a4, 0x0B)
LUT (xAAAAFF00AAAAFF00, a1, a4, a5, 0x27)
LUT (xADAFF8A5ADAFF8A5, a3, x88AA88AA88AA88AA, xAAAAFF00AAAAFF00, 0x9E)
LUT (x0A0AF5F50A0AF5F5, a1, a3, a5, 0xA6)
LUT (x6B69C5DC6B69C5DC, a2, xADAFF8A5ADAFF8A5, x0A0AF5F50A0AF5F5, 0x6B)
LUT (x1C69B2DC1C69B2DC, a4, x88AA88AA88AA88AA, x6B69C5DC6B69C5DC, 0xA9)
LUT (x1, a6, xADAFF8A5ADAFF8A5, x1C69B2DC1C69B2DC, 0x6A)
LUT (x9C9C9C9C9C9C9C9C, a1, a2, a3, 0x63)
LUT (xE6E63BFDE6E63BFD, a2, xAAAAFF00AAAAFF00, x0A0AF5F50A0AF5F5, 0xE7)
LUT (x6385639E6385639E, a4, x9C9C9C9C9C9C9C9C, xE6E63BFDE6E63BFD, 0x93)
LUT (x5959C4CE5959C4CE, a2, x6B69C5DC6B69C5DC, xE6E63BFDE6E63BFD, 0x5D)
LUT (x5B53F53B5B53F53B, a4, x0A0AF5F50A0AF5F5, x5959C4CE5959C4CE, 0x6E)
LUT (x3, a6, x6385639E6385639E, x5B53F53B5B53F53B, 0xC6)
LUT (xFAF505FAFAF505FA, a3, a4, x0A0AF5F50A0AF5F5, 0x6D)
LUT (x6A65956A6A65956A, a3, x9C9C9C9C9C9C9C9C, xFAF505FAFAF505FA, 0xA6)
LUT (x8888CCCC8888CCCC, a1, a2, a5, 0x23)
LUT (x94E97A9494E97A94, x1C69B2DC1C69B2DC, x6A65956A6A65956A, x8888CCCC8888CCCC, 0x72)
LUT (x4, a6, x6A65956A6A65956A, x94E97A9494E97A94, 0xAC)
LUT (xA050A050A050A050, a1, a3, a4, 0x21)
LUT (xC1B87A2BC1B87A2B, xAAAAFF00AAAAFF00, x5B53F53B5B53F53B, x94E97A9494E97A94, 0xA4)
LUT (xE96016B7E96016B7, x8888CCCC8888CCCC, xA050A050A050A050, xC1B87A2BC1B87A2B, 0x96)
LUT (xE3CF1FD5E3CF1FD5, x88AA88AA88AA88AA, x6A65956A6A65956A, xE96016B7E96016B7, 0x3E)
LUT (x6776675B6776675B, xADAFF8A5ADAFF8A5, x94E97A9494E97A94, xE3CF1FD5E3CF1FD5, 0x6B)
LUT (x2, a6, xE96016B7E96016B7, x6776675B6776675B, 0xC6)
*out1 ^= x1;
*out2 ^= x2;
@@ -285,29 +285,29 @@ DECLSPEC void s7 (const u32 a1, const u32 a2, const u32 a3, const u32 a4, const
DECLSPEC void s8 (const u32 a1, const u32 a2, const u32 a3, const u32 a4, const u32 a5, const u32 a6, u32 *out1, u32 *out2, u32 *out3, u32 *out4)
{
LUT(xEEEE3333EEEE3333, a1, a2, a5, 0x9D)
LUT(xBBBBBBBBBBBBBBBB, a1, a1, a2, 0x83)
LUT(xDDDDAAAADDDDAAAA, a1, a2, a5, 0x5B)
LUT(x29295A5A29295A5A, a3, xBBBBBBBBBBBBBBBB, xDDDDAAAADDDDAAAA, 0x85)
LUT(xC729695AC729695A, a4, xEEEE3333EEEE3333, x29295A5A29295A5A, 0xA6)
LUT(x3BF77B7B3BF77B7B, a2, a5, xC729695AC729695A, 0xF9)
LUT(x2900FF002900FF00, a4, a5, x29295A5A29295A5A, 0x0E)
LUT(x56B3803F56B3803F, xBBBBBBBBBBBBBBBB, x3BF77B7B3BF77B7B, x2900FF002900FF00, 0x61)
LUT(x4, a6, xC729695AC729695A, x56B3803F56B3803F, 0x6C)
LUT(xFBFBFBFBFBFBFBFB, a1, a2, a3, 0xDF)
LUT(x3012B7B73012B7B7, a2, a5, xC729695AC729695A, 0xD4)
LUT(x34E9B34C34E9B34C, a4, xFBFBFBFBFBFBFBFB, x3012B7B73012B7B7, 0x69)
LUT(xBFEAEBBEBFEAEBBE, a1, x29295A5A29295A5A, x34E9B34C34E9B34C, 0x6F)
LUT(xFFAEAFFEFFAEAFFE, a3, xBBBBBBBBBBBBBBBB, xBFEAEBBEBFEAEBBE, 0xB9)
LUT(x2, a6, x34E9B34C34E9B34C, xFFAEAFFEFFAEAFFE, 0xC6)
LUT(xCFDE88BBCFDE88BB, a2, xDDDDAAAADDDDAAAA, x34E9B34C34E9B34C, 0x5C)
LUT(x3055574530555745, a1, xC729695AC729695A, xCFDE88BBCFDE88BB, 0x71)
LUT(x99DDEEEE99DDEEEE, a4, xBBBBBBBBBBBBBBBB, xDDDDAAAADDDDAAAA, 0xB9)
LUT(x693CD926693CD926, x3BF77B7B3BF77B7B, x34E9B34C34E9B34C, x99DDEEEE99DDEEEE, 0x69)
LUT(x3, a6, x3055574530555745, x693CD926693CD926, 0x6A)
LUT(x9955EE559955EE55, a1, a4, x99DDEEEE99DDEEEE, 0xE2)
LUT(x9D48FA949D48FA94, x3BF77B7B3BF77B7B, xBFEAEBBEBFEAEBBE, x9955EE559955EE55, 0x9C)
LUT(x1, a6, xC729695AC729695A, x9D48FA949D48FA94, 0x39)
LUT (xEEEE3333EEEE3333, a1, a2, a5, 0x9D)
LUT (xBBBBBBBBBBBBBBBB, a1, a1, a2, 0x83)
LUT (xDDDDAAAADDDDAAAA, a1, a2, a5, 0x5B)
LUT (x29295A5A29295A5A, a3, xBBBBBBBBBBBBBBBB, xDDDDAAAADDDDAAAA, 0x85)
LUT (xC729695AC729695A, a4, xEEEE3333EEEE3333, x29295A5A29295A5A, 0xA6)
LUT (x3BF77B7B3BF77B7B, a2, a5, xC729695AC729695A, 0xF9)
LUT (x2900FF002900FF00, a4, a5, x29295A5A29295A5A, 0x0E)
LUT (x56B3803F56B3803F, xBBBBBBBBBBBBBBBB, x3BF77B7B3BF77B7B, x2900FF002900FF00, 0x61)
LUT (x4, a6, xC729695AC729695A, x56B3803F56B3803F, 0x6C)
LUT (xFBFBFBFBFBFBFBFB, a1, a2, a3, 0xDF)
LUT (x3012B7B73012B7B7, a2, a5, xC729695AC729695A, 0xD4)
LUT (x34E9B34C34E9B34C, a4, xFBFBFBFBFBFBFBFB, x3012B7B73012B7B7, 0x69)
LUT (xBFEAEBBEBFEAEBBE, a1, x29295A5A29295A5A, x34E9B34C34E9B34C, 0x6F)
LUT (xFFAEAFFEFFAEAFFE, a3, xBBBBBBBBBBBBBBBB, xBFEAEBBEBFEAEBBE, 0xB9)
LUT (x2, a6, x34E9B34C34E9B34C, xFFAEAFFEFFAEAFFE, 0xC6)
LUT (xCFDE88BBCFDE88BB, a2, xDDDDAAAADDDDAAAA, x34E9B34C34E9B34C, 0x5C)
LUT (x3055574530555745, a1, xC729695AC729695A, xCFDE88BBCFDE88BB, 0x71)
LUT (x99DDEEEE99DDEEEE, a4, xBBBBBBBBBBBBBBBB, xDDDDAAAADDDDAAAA, 0xB9)
LUT (x693CD926693CD926, x3BF77B7B3BF77B7B, x34E9B34C34E9B34C, x99DDEEEE99DDEEEE, 0x69)
LUT (x3, a6, x3055574530555745, x693CD926693CD926, 0x6A)
LUT (x9955EE559955EE55, a1, a4, x99DDEEEE99DDEEEE, 0xE2)
LUT (x9D48FA949D48FA94, x3BF77B7B3BF77B7B, xBFEAEBBEBFEAEBBE, x9955EE559955EE55, 0x9C)
LUT (x1, a6, xC729695AC729695A, x9D48FA949D48FA94, 0x39)
*out1 ^= x1;
*out2 ^= x2;
@@ -1480,38 +1480,38 @@ DECLSPEC void s8 (const u32 a1, const u32 a2, const u32 a3, const u32 a4, const
#define SWAP(a, b) { u32 tmp=*a;*a=*b;*b=tmp; }
#define DATASWAP \
SWAP(D00, D32); \
SWAP(D01, D33); \
SWAP(D02, D34); \
SWAP(D03, D35); \
SWAP(D04, D36); \
SWAP(D05, D37); \
SWAP(D06, D38); \
SWAP(D07, D39); \
SWAP(D08, D40); \
SWAP(D09, D41); \
SWAP(D10, D42); \
SWAP(D11, D43); \
SWAP(D12, D44); \
SWAP(D13, D45); \
SWAP(D14, D46); \
SWAP(D15, D47); \
SWAP(D16, D48); \
SWAP(D17, D49); \
SWAP(D18, D50); \
SWAP(D19, D51); \
SWAP(D20, D52); \
SWAP(D21, D53); \
SWAP(D22, D54); \
SWAP(D23, D55); \
SWAP(D24, D56); \
SWAP(D25, D57); \
SWAP(D26, D58); \
SWAP(D27, D59); \
SWAP(D28, D60); \
SWAP(D29, D61); \
SWAP(D30, D62); \
SWAP(D31, D63);
SWAP (D00, D32); \
SWAP (D01, D33); \
SWAP (D02, D34); \
SWAP (D03, D35); \
SWAP (D04, D36); \
SWAP (D05, D37); \
SWAP (D06, D38); \
SWAP (D07, D39); \
SWAP (D08, D40); \
SWAP (D09, D41); \
SWAP (D10, D42); \
SWAP (D11, D43); \
SWAP (D12, D44); \
SWAP (D13, D45); \
SWAP (D14, D46); \
SWAP (D15, D47); \
SWAP (D16, D48); \
SWAP (D17, D49); \
SWAP (D18, D50); \
SWAP (D19, D51); \
SWAP (D20, D52); \
SWAP (D21, D53); \
SWAP (D22, D54); \
SWAP (D23, D55); \
SWAP (D24, D56); \
SWAP (D25, D57); \
SWAP (D26, D58); \
SWAP (D27, D59); \
SWAP (D28, D60); \
SWAP (D29, D61); \
SWAP (D30, D62); \
SWAP (D31, D63);
#define KEYSET00 { k00 = K08; k01 = K44; k02 = K29; k03 = K52; k04 = K42; k05 = K14; k06 = K28; k07 = K49; k08 = K01; k09 = K07; k10 = K16; k11 = K36; k12 = K02; k13 = K30; k14 = K22; k15 = K21; k16 = K38; k17 = K50; k18 = K51; k19 = K00; k20 = K31; k21 = K23; k22 = K15; k23 = K35; k24 = K19; k25 = K24; k26 = K34; k27 = K47; k28 = K32; k29 = K03; k30 = K41; k31 = K26; k32 = K04; k33 = K46; k34 = K20; k35 = K25; k36 = K53; k37 = K18; k38 = K33; k39 = K55; k40 = K13; k41 = K17; k42 = K39; k43 = K12; k44 = K11; k45 = K54; k46 = K48; k47 = K27; }
#define KEYSET10 { k00 = K49; k01 = K28; k02 = K45; k03 = K36; k04 = K01; k05 = K30; k06 = K44; k07 = K08; k08 = K42; k09 = K23; k10 = K00; k11 = K52; k12 = K43; k13 = K14; k14 = K38; k15 = K37; k16 = K22; k17 = K09; k18 = K35; k19 = K16; k20 = K15; k21 = K07; k22 = K31; k23 = K51; k24 = K03; k25 = K40; k26 = K46; k27 = K04; k28 = K20; k29 = K19; k30 = K53; k31 = K10; k32 = K47; k33 = K34; k34 = K32; k35 = K13; k36 = K41; k37 = K06; k38 = K17; k39 = K12; k40 = K25; k41 = K33; k42 = K27; k43 = K55; k44 = K54; k45 = K11; k46 = K05; k47 = K39; }
OpenCL/m03000_a3-pure.cl
+33 -33
View File
@@ -1478,39 +1478,39 @@ DECLSPEC void s8 (const u32 a1, const u32 a2, const u32 a3, const u32 a4, const
#define SWAP(a, b) { u32 tmp=*a;*a=*b;*b=tmp; }
#define DATASWAP \
SWAP(D00, D32); \
SWAP(D01, D33); \
SWAP(D02, D34); \
SWAP(D03, D35); \
SWAP(D04, D36); \
SWAP(D05, D37); \
SWAP(D06, D38); \
SWAP(D07, D39); \
SWAP(D08, D40); \
SWAP(D09, D41); \
SWAP(D10, D42); \
SWAP(D11, D43); \
SWAP(D12, D44); \
SWAP(D13, D45); \
SWAP(D14, D46); \
SWAP(D15, D47); \
SWAP(D16, D48); \
SWAP(D17, D49); \
SWAP(D18, D50); \
SWAP(D19, D51); \
SWAP(D20, D52); \
SWAP(D21, D53); \
SWAP(D22, D54); \
SWAP(D23, D55); \
SWAP(D24, D56); \
SWAP(D25, D57); \
SWAP(D26, D58); \
SWAP(D27, D59); \
SWAP(D28, D60); \
SWAP(D29, D61); \
SWAP(D30, D62); \
SWAP(D31, D63);
#define DATASWAP \
SWAP (D00, D32); \
SWAP (D01, D33); \
SWAP (D02, D34); \
SWAP (D03, D35); \
SWAP (D04, D36); \
SWAP (D05, D37); \
SWAP (D06, D38); \
SWAP (D07, D39); \
SWAP (D08, D40); \
SWAP (D09, D41); \
SWAP (D10, D42); \
SWAP (D11, D43); \
SWAP (D12, D44); \
SWAP (D13, D45); \
SWAP (D14, D46); \
SWAP (D15, D47); \
SWAP (D16, D48); \
SWAP (D17, D49); \
SWAP (D18, D50); \
SWAP (D19, D51); \
SWAP (D20, D52); \
SWAP (D21, D53); \
SWAP (D22, D54); \
SWAP (D23, D55); \
SWAP (D24, D56); \
SWAP (D25, D57); \
SWAP (D26, D58); \
SWAP (D27, D59); \
SWAP (D28, D60); \
SWAP (D29, D61); \
SWAP (D30, D62); \
SWAP (D31, D63);
#define KEYSET00 { k00 = K08; k01 = K44; k02 = K29; k03 = K52; k04 = K42; k05 = K14; k06 = K28; k07 = K49; k08 = K01; k09 = K07; k10 = K16; k11 = K36; k12 = K02; k13 = K30; k14 = K22; k15 = K21; k16 = K38; k17 = K50; k18 = K51; k19 = K00; k20 = K31; k21 = K23; k22 = K15; k23 = K35; k24 = K19; k25 = K24; k26 = K34; k27 = K47; k28 = K32; k29 = K03; k30 = K41; k31 = K26; k32 = K04; k33 = K46; k34 = K20; k35 = K25; k36 = K53; k37 = K18; k38 = K33; k39 = K55; k40 = K13; k41 = K17; k42 = K39; k43 = K12; k44 = K11; k45 = K54; k46 = K48; k47 = K27; }
#define KEYSET10 { k00 = K49; k01 = K28; k02 = K45; k03 = K36; k04 = K01; k05 = K30; k06 = K44; k07 = K08; k08 = K42; k09 = K23; k10 = K00; k11 = K52; k12 = K43; k13 = K14; k14 = K38; k15 = K37; k16 = K22; k17 = K09; k18 = K35; k19 = K16; k20 = K15; k21 = K07; k22 = K31; k23 = K51; k24 = K03; k25 = K40; k26 = K46; k27 = K04; k28 = K20; k29 = K19; k30 = K53; k31 = K10; k32 = K47; k33 = K34; k34 = K32; k35 = K13; k36 = K41; k37 = K06; k38 = K17; k39 = K12; k40 = K25; k41 = K33; k42 = K27; k43 = K55; k44 = K54; k45 = K11; k46 = K05; k47 = K39; }
OpenCL/m07700_a0-optimized.cl
+6 -6
View File
@@ -25,13 +25,13 @@
#define PUTCHAR(a,p,c) ((u8 *)(a))[(p)] = (u8) (c)
#endif
#define SETSHIFTEDINT(a,n,v) \
{ \
const u32 s = ((n) & 3) * 8; \
const u64 x = (u64) (v) << s; \
#define SETSHIFTEDINT(a,n,v) \
{ \
const u32 s = ((n) & 3) * 8; \
const u64 x = (u64) (v) << s; \
(a)[((n)/4)+0] &= ~(0xff << ((n & 3) * 8)); \
(a)[((n)/4)+0] |= x; \
(a)[((n)/4)+1] = x >> 32; \
(a)[((n)/4)+0] |= x; \
(a)[((n)/4)+1] = x >> 32; \
}
CONSTANT_VK u32a sapb_trans_tbl[256] =
OpenCL/m07700_a1-optimized.cl
+6 -6
View File
@@ -23,13 +23,13 @@
#define PUTCHAR(a,p,c) ((u8 *)(a))[(p)] = (u8) (c)
#endif
#define SETSHIFTEDINT(a,n,v) \
{ \
const u32 s = ((n) & 3) * 8; \
const u64 x = (u64) (v) << s; \
#define SETSHIFTEDINT(a,n,v) \
{ \
const u32 s = ((n) & 3) * 8; \
const u64 x = (u64) (v) << s; \
(a)[((n)/4)+0] &= ~(0xff << ((n & 3) * 8)); \
(a)[((n)/4)+0] |= x; \
(a)[((n)/4)+1] = x >> 32; \
(a)[((n)/4)+0] |= x; \
(a)[((n)/4)+1] = x >> 32; \
}
CONSTANT_VK u32a sapb_trans_tbl[256] =
OpenCL/m07701_a0-optimized.cl
+6 -6
View File
@@ -25,13 +25,13 @@
#define PUTCHAR(a,p,c) ((u8 *)(a))[(p)] = (u8) (c)
#endif
#define SETSHIFTEDINT(a,n,v) \
{ \
const u32 s = ((n) & 3) * 8; \
const u64 x = (u64) (v) << s; \
#define SETSHIFTEDINT(a,n,v) \
{ \
const u32 s = ((n) & 3) * 8; \
const u64 x = (u64) (v) << s; \
(a)[((n)/4)+0] &= ~(0xff << ((n & 3) * 8)); \
(a)[((n)/4)+0] |= x; \
(a)[((n)/4)+1] = x >> 32; \
(a)[((n)/4)+0] |= x; \
(a)[((n)/4)+1] = x >> 32; \
}
CONSTANT_VK u32a sapb_trans_tbl[256] =
OpenCL/m07701_a1-optimized.cl
+6 -6
View File
@@ -23,13 +23,13 @@
#define PUTCHAR(a,p,c) ((u8 *)(a))[(p)] = (u8) (c)
#endif
#define SETSHIFTEDINT(a,n,v) \
{ \
const u32 s = ((n) & 3) * 8; \
const u64 x = (u64) (v) << s; \
#define SETSHIFTEDINT(a,n,v) \
{ \
const u32 s = ((n) & 3) * 8; \
const u64 x = (u64) (v) << s; \
(a)[((n)/4)+0] &= ~(0xff << ((n & 3) * 8)); \
(a)[((n)/4)+0] |= x; \
(a)[((n)/4)+1] = x >> 32; \
(a)[((n)/4)+0] |= x; \
(a)[((n)/4)+1] = x >> 32; \
}
CONSTANT_VK u32a sapb_trans_tbl[256] =
OpenCL/m14000_a3-pure.cl
+33 -33
View File
@@ -1478,39 +1478,39 @@ DECLSPEC void s8 (const u32 a1, const u32 a2, const u32 a3, const u32 a4, const
#define SWAP(a, b) { u32 tmp=*a;*a=*b;*b=tmp; }
#define DATASWAP \
SWAP(D00, D32); \
SWAP(D01, D33); \
SWAP(D02, D34); \
SWAP(D03, D35); \
SWAP(D04, D36); \
SWAP(D05, D37); \
SWAP(D06, D38); \
SWAP(D07, D39); \
SWAP(D08, D40); \
SWAP(D09, D41); \
SWAP(D10, D42); \
SWAP(D11, D43); \
SWAP(D12, D44); \
SWAP(D13, D45); \
SWAP(D14, D46); \
SWAP(D15, D47); \
SWAP(D16, D48); \
SWAP(D17, D49); \
SWAP(D18, D50); \
SWAP(D19, D51); \
SWAP(D20, D52); \
SWAP(D21, D53); \
SWAP(D22, D54); \
SWAP(D23, D55); \
SWAP(D24, D56); \
SWAP(D25, D57); \
SWAP(D26, D58); \
SWAP(D27, D59); \
SWAP(D28, D60); \
SWAP(D29, D61); \
SWAP(D30, D62); \
SWAP(D31, D63);
#define DATASWAP \
SWAP (D00, D32); \
SWAP (D01, D33); \
SWAP (D02, D34); \
SWAP (D03, D35); \
SWAP (D04, D36); \
SWAP (D05, D37); \
SWAP (D06, D38); \
SWAP (D07, D39); \
SWAP (D08, D40); \
SWAP (D09, D41); \
SWAP (D10, D42); \
SWAP (D11, D43); \
SWAP (D12, D44); \
SWAP (D13, D45); \
SWAP (D14, D46); \
SWAP (D15, D47); \
SWAP (D16, D48); \
SWAP (D17, D49); \
SWAP (D18, D50); \
SWAP (D19, D51); \
SWAP (D20, D52); \
SWAP (D21, D53); \
SWAP (D22, D54); \
SWAP (D23, D55); \
SWAP (D24, D56); \
SWAP (D25, D57); \
SWAP (D26, D58); \
SWAP (D27, D59); \
SWAP (D28, D60); \
SWAP (D29, D61); \
SWAP (D30, D62); \
SWAP (D31, D63);
#define KEYSET00 { k00 = K08; k01 = K44; k02 = K29; k03 = K52; k04 = K42; k05 = K14; k06 = K28; k07 = K49; k08 = K01; k09 = K07; k10 = K16; k11 = K36; k12 = K02; k13 = K30; k14 = K22; k15 = K21; k16 = K38; k17 = K50; k18 = K51; k19 = K00; k20 = K31; k21 = K23; k22 = K15; k23 = K35; k24 = K19; k25 = K24; k26 = K34; k27 = K47; k28 = K32; k29 = K03; k30 = K41; k31 = K26; k32 = K04; k33 = K46; k34 = K20; k35 = K25; k36 = K53; k37 = K18; k38 = K33; k39 = K55; k40 = K13; k41 = K17; k42 = K39; k43 = K12; k44 = K11; k45 = K54; k46 = K48; k47 = K27; }
#define KEYSET10 { k00 = K49; k01 = K28; k02 = K45; k03 = K36; k04 = K01; k05 = K30; k06 = K44; k07 = K08; k08 = K42; k09 = K23; k10 = K00; k11 = K52; k12 = K43; k13 = K14; k14 = K38; k15 = K37; k16 = K22; k17 = K09; k18 = K35; k19 = K16; k20 = K15; k21 = K07; k22 = K31; k23 = K51; k24 = K03; k25 = K40; k26 = K46; k27 = K04; k28 = K20; k29 = K19; k30 = K53; k31 = K10; k32 = K47; k33 = K34; k34 = K32; k35 = K13; k36 = K41; k37 = K06; k38 = K17; k39 = K12; k40 = K25; k41 = K33; k42 = K27; k43 = K55; k44 = K54; k45 = K11; k46 = K05; k47 = K39; }
OpenCL/m15400_a0-optimized.cl
+28 -28
View File
@@ -29,16 +29,16 @@ typedef struct chacha20
#define CHACHA_CONST_02 0x79622d32
#define CHACHA_CONST_03 0x6b206574
#define QR(a, b, c, d) \
do { \
x[a] = x[a] + x[b]; \
x[d] = hc_rotl32(x[d] ^ x[a], 16); \
x[c] = x[c] + x[d]; \
x[b] = hc_rotl32(x[b] ^ x[c], 12); \
x[a] = x[a] + x[b]; \
x[d] = hc_rotl32(x[d] ^ x[a], 8); \
x[c] = x[c] + x[d]; \
x[b] = hc_rotl32(x[b] ^ x[c], 7); \
#define QR(a, b, c, d) \
do { \
x[a] = x[a] + x[b]; \
x[d] = hc_rotl32 (x[d] ^ x[a], 16); \
x[c] = x[c] + x[ d]; \
x[b] = hc_rotl32 (x[b] ^ x[c], 12); \
x[a] = x[a] + x[ b]; \
x[d] = hc_rotl32 (x[d] ^ x[a], 8); \
x[c] = x[c] + x[ d]; \
x[b] = hc_rotl32 (x[b] ^ x[c], 7); \
} while (0);
DECLSPEC void chacha20_transform (const u32x *w0, const u32x *w1, const u32 *position, const u32 offset, const u32 *iv, const u32 *plain, u32x *digest)
@@ -93,16 +93,16 @@ DECLSPEC void chacha20_transform (const u32x *w0, const u32x *w1, const u32 *pos
for (u8 i = 0; i < 10; i++)
{
/* Column round */
QR(0, 4, 8, 12);
QR(1, 5, 9, 13);
QR(2, 6, 10, 14);
QR(3, 7, 11, 15);
QR (0, 4, 8, 12);
QR (1, 5, 9, 13);
QR (2, 6, 10, 14);
QR (3, 7, 11, 15);
/* Diagonal round */
QR(0, 5, 10, 15);
QR(1, 6, 11, 12);
QR(2, 7, 8, 13);
QR(3, 4, 9, 14);
QR (0, 5, 10, 15);
QR (1, 6, 11, 12);
QR (2, 7, 8, 13);
QR (3, 4, 9, 14);
}
x[ 0] += ctx[ 0];
@@ -183,16 +183,16 @@ DECLSPEC void chacha20_transform (const u32x *w0, const u32x *w1, const u32 *pos
for (u8 i = 0; i < 10; i++)
{
/* Column round */
QR(16, 20, 24, 28);
QR(17, 21, 25, 29);
QR(18, 22, 26, 30);
QR(19, 23, 27, 31);
QR (16, 20, 24, 28);
QR (17, 21, 25, 29);
QR (18, 22, 26, 30);
QR (19, 23, 27, 31);
/* Diagonal round */
QR(16, 21, 26, 31);
QR(17, 22, 27, 28);
QR(18, 23, 24, 29);
QR(19, 20, 25, 30);
QR (16, 21, 26, 31);
QR (17, 22, 27, 28);
QR (18, 23, 24, 29);
QR (19, 20, 25, 30);
}
x[16] += ctx[ 0];
@@ -304,7 +304,7 @@ KERNEL_FQ void m15400_m04 (KERN_ATTR_RULES_ESALT (chacha20_t))
const u32x r2 = digest[2];
const u32x r3 = digest[3];
COMPARE_M_SIMD(r0, r1, r2, r3);
COMPARE_M_SIMD (r0, r1, r2, r3);
}
}
@@ -394,7 +394,7 @@ KERNEL_FQ void m15400_s04 (KERN_ATTR_RULES_ESALT (chacha20_t))
const u32x r2 = digest[2];
const u32x r3 = digest[3];
COMPARE_S_SIMD(r0, r1, r2, r3);
COMPARE_S_SIMD (r0, r1, r2, r3);
}
}
OpenCL/m15400_a1-optimized.cl
+28 -28
View File
@@ -27,16 +27,16 @@ typedef struct chacha20
#define CHACHA_CONST_02 0x79622d32
#define CHACHA_CONST_03 0x6b206574
#define QR(a, b, c, d) \
do { \
x[a] = x[a] + x[b]; \
x[d] = hc_rotl32(x[d] ^ x[a], 16); \
x[c] = x[c] + x[d]; \
x[b] = hc_rotl32(x[b] ^ x[c], 12); \
x[a] = x[a] + x[b]; \
x[d] = hc_rotl32(x[d] ^ x[a], 8); \
x[c] = x[c] + x[d]; \
x[b] = hc_rotl32(x[b] ^ x[c], 7); \
#define QR(a, b, c, d) \
do { \
x[a] = x[a] + x[b]; \
x[d] = hc_rotl32 (x[d] ^ x[a], 16); \
x[c] = x[c] + x[ d]; \
x[b] = hc_rotl32 (x[b] ^ x[c], 12); \
x[a] = x[a] + x[ b]; \
x[d] = hc_rotl32 (x[d] ^ x[a], 8); \
x[c] = x[c] + x[ d]; \
x[b] = hc_rotl32 (x[b] ^ x[c], 7); \
} while (0);
DECLSPEC void chacha20_transform (const u32x *w0, const u32x *w1, const u32 *position, const u32 offset, const u32 *iv, const u32 *plain, u32x *digest)
@@ -91,16 +91,16 @@ DECLSPEC void chacha20_transform (const u32x *w0, const u32x *w1, const u32 *pos
for (u8 i = 0; i < 10; i++)
{
/* Column round */
QR(0, 4, 8, 12);
QR(1, 5, 9, 13);
QR(2, 6, 10, 14);
QR(3, 7, 11, 15);
QR (0, 4, 8, 12);
QR (1, 5, 9, 13);
QR (2, 6, 10, 14);
QR (3, 7, 11, 15);
/* Diagonal round */
QR(0, 5, 10, 15);
QR(1, 6, 11, 12);
QR(2, 7, 8, 13);
QR(3, 4, 9, 14);
QR (0, 5, 10, 15);
QR (1, 6, 11, 12);
QR (2, 7, 8, 13);
QR (3, 4, 9, 14);
}
x[ 0] += ctx[ 0];
@@ -181,16 +181,16 @@ DECLSPEC void chacha20_transform (const u32x *w0, const u32x *w1, const u32 *pos
for (u8 i = 0; i < 10; i++)
{
/* Column round */
QR(16, 20, 24, 28);
QR(17, 21, 25, 29);
QR(18, 22, 26, 30);
QR(19, 23, 27, 31);
QR (16, 20, 24, 28);
QR (17, 21, 25, 29);
QR (18, 22, 26, 30);
QR (19, 23, 27, 31);
/* Diagonal round */
QR(16, 21, 26, 31);
QR(17, 22, 27, 28);
QR(18, 23, 24, 29);
QR(19, 20, 25, 30);
QR (16, 21, 26, 31);
QR (17, 22, 27, 28);
QR (18, 23, 24, 29);
QR (19, 20, 25, 30);
}
x[16] += ctx[ 0];
@@ -351,7 +351,7 @@ KERNEL_FQ void m15400_m04 (KERN_ATTR_ESALT (chacha20_t))
const u32x r2 = digest[2];
const u32x r3 = digest[3];
COMPARE_M_SIMD(r0, r1, r2, r3);
COMPARE_M_SIMD (r0, r1, r2, r3);
}
}
@@ -493,7 +493,7 @@ KERNEL_FQ void m15400_s04 (KERN_ATTR_ESALT (chacha20_t))
const u32x r2 = digest[2];
const u32x r3 = digest[3];
COMPARE_S_SIMD(r0, r1, r2, r3);
COMPARE_S_SIMD (r0, r1, r2, r3);
}
}
OpenCL/m15400_a3-optimized.cl
+28 -28
View File
@@ -27,16 +27,16 @@ typedef struct chacha20
#define CHACHA_CONST_02 0x79622d32
#define CHACHA_CONST_03 0x6b206574
#define QR(a, b, c, d) \
do { \
x[a] = x[a] + x[b]; \
x[d] = hc_rotl32(x[d] ^ x[a], 16); \
x[c] = x[c] + x[d]; \
x[b] = hc_rotl32(x[b] ^ x[c], 12); \
x[a] = x[a] + x[b]; \
x[d] = hc_rotl32(x[d] ^ x[a], 8); \
x[c] = x[c] + x[d]; \
x[b] = hc_rotl32(x[b] ^ x[c], 7); \
#define QR(a, b, c, d) \
do { \
x[a] = x[a] + x[b]; \
x[d] = hc_rotl32 (x[d] ^ x[a], 16); \
x[c] = x[c] + x[d]; \
x[b] = hc_rotl32 (x[b] ^ x[c], 12); \
x[a] = x[a] + x[b]; \
x[d] = hc_rotl32 (x[d] ^ x[a], 8); \
x[c] = x[c] + x[d]; \
x[b] = hc_rotl32 (x[b] ^ x[c], 7); \
} while (0);
DECLSPEC void chacha20_transform (const u32x *w0, const u32x *w1, const u32 *position, const u32 offset, const u32 *iv, const u32 *plain, u32x *digest)
@@ -91,16 +91,16 @@ DECLSPEC void chacha20_transform (const u32x *w0, const u32x *w1, const u32 *pos
for (u8 i = 0; i < 10; i++)
{
/* Column round */
QR(0, 4, 8, 12);
QR(1, 5, 9, 13);
QR(2, 6, 10, 14);
QR(3, 7, 11, 15);
QR (0, 4, 8, 12);
QR (1, 5, 9, 13);
QR (2, 6, 10, 14);
QR (3, 7, 11, 15);
/* Diagonal round */
QR(0, 5, 10, 15);
QR(1, 6, 11, 12);
QR(2, 7, 8, 13);
QR(3, 4, 9, 14);
QR (0, 5, 10, 15);
QR (1, 6, 11, 12);
QR (2, 7, 8, 13);
QR (3, 4, 9, 14);
}
x[ 0] += ctx[ 0];
@@ -181,16 +181,16 @@ DECLSPEC void chacha20_transform (const u32x *w0, const u32x *w1, const u32 *pos
for (u8 i = 0; i < 10; i++)
{
/* Column round */
QR(16, 20, 24, 28);
QR(17, 21, 25, 29);
QR(18, 22, 26, 30);
QR(19, 23, 27, 31);
QR (16, 20, 24, 28);
QR (17, 21, 25, 29);
QR (18, 22, 26, 30);
QR (19, 23, 27, 31);
/* Diagonal round */
QR(16, 21, 26, 31);
QR(17, 22, 27, 28);
QR(18, 23, 24, 29);
QR(19, 20, 25, 30);
QR (16, 21, 26, 31);
QR (17, 22, 27, 28);
QR (18, 23, 24, 29);
QR (19, 20, 25, 30);
}
x[16] += ctx[ 0];
@@ -320,7 +320,7 @@ KERNEL_FQ void m15400_m16 (KERN_ATTR_VECTOR_ESALT (chacha20_t))
const u32x r2 = digest[2];
const u32x r3 = digest[3];
COMPARE_M_SIMD(r0, r1, r2, r3);
COMPARE_M_SIMD (r0, r1, r2, r3);
}
}
@@ -420,6 +420,6 @@ KERNEL_FQ void m15400_s16 (KERN_ATTR_VECTOR_ESALT (chacha20_t))
const u32x r2 = digest[2];
const u32x r3 = digest[3];
COMPARE_S_SIMD(r0, r1, r2, r3);
COMPARE_S_SIMD (r0, r1, r2, r3);
}
}
OpenCL/m15700-pure.cl
+1 -1
View File
@@ -298,7 +298,7 @@ DECLSPEC void scrypt_smix (uint4 *X, uint4 *T, GLOBAL_AS uint4 *V0, GLOBAL_AS ui
u32 j = keccakf_piln[s]; \
u32 k = keccakf_rotc[s]; \
bc0 = st[j]; \
st[j] = hc_rotl64_S (t, k); \
st[j] = hc_rotl64_S (t, k); \
t = bc0; \
}
OpenCL/m16300-pure.cl
+1 -1
View File
@@ -68,7 +68,7 @@ CONSTANT_VK u64a keccakf_rndc[24] =
u32 j = keccakf_piln[s]; \
u32 k = keccakf_rotc[s]; \
bc0 = st[j]; \
st[j] = hc_rotl64_S (t, k); \
st[j] = hc_rotl64_S (t, k); \
t = bc0; \
}
OpenCL/m16400_a3-optimized.cl
+2 -2
View File
@@ -17,7 +17,7 @@
#define MD5_STEP_REV(f,a,b,c,d,x,t,s) \
{ \
a -= b; \
a = hc_rotr32_S (a, s); \
a = hc_rotr32_S (a, s); \
a -= f (b, c, d); \
a -= x; \
a -= t; \
@@ -26,7 +26,7 @@
#define MD5_STEP_REV1(f,a,b,c,d,x,t,s) \
{ \
a -= b; \
a = hc_rotr32_S (a, s); \
a = hc_rotr32_S (a, s); \
a -= x; \
a -= t; \
}
OpenCL/m17300_a0-optimized.cl
+2 -2
View File
@@ -108,7 +108,7 @@ KERNEL_FQ void m17300_m04 (KERN_ATTR_RULES ())
#define Rho_Pi(ad,r) \
bc0 = ad; \
ad = hc_rotl64 (t, r); \
ad = hc_rotl64 (t, r); \
t = bc0; \
#ifdef _unroll
@@ -338,7 +338,7 @@ KERNEL_FQ void m17300_s04 (KERN_ATTR_RULES ())
#define Rho_Pi(ad,r) \
bc0 = ad; \
ad = hc_rotl64 (t, r); \
ad = hc_rotl64 (t, r); \
t = bc0; \
#ifdef _unroll
OpenCL/m17300_a1-optimized.cl
+2 -2
View File
@@ -164,7 +164,7 @@ KERNEL_FQ void m17300_m04 (KERN_ATTR_BASIC ())
#define Rho_Pi(ad,r) \
bc0 = ad; \
ad = hc_rotl64 (t, r); \
ad = hc_rotl64 (t, r); \
t = bc0; \
#ifdef _unroll
@@ -453,7 +453,7 @@ KERNEL_FQ void m17300_s04 (KERN_ATTR_BASIC ())
#define Rho_Pi(ad,r) \
bc0 = ad; \
ad = hc_rotl64 (t, r); \
ad = hc_rotl64 (t, r); \
t = bc0; \
#ifdef _unroll
OpenCL/m17300_a3-optimized.cl
+2 -2
View File
@@ -82,7 +82,7 @@ DECLSPEC void m17300m (u32 *w0, u32 *w1, u32 *w2, u32 *w3, const u32 pw_len, KER
#define Rho_Pi(ad,r) \
bc0 = ad; \
ad = hc_rotl64 (t, r); \
ad = hc_rotl64 (t, r); \
t = bc0; \
#ifdef _unroll
@@ -280,7 +280,7 @@ DECLSPEC void m17300s (u32 *w0, u32 *w1, u32 *w2, u32 *w3, const u32 pw_len, KER
#define Rho_Pi(ad,r) \
bc0 = ad; \
ad = hc_rotl64 (t, r); \
ad = hc_rotl64 (t, r); \
t = bc0; \
#ifdef _unroll
OpenCL/m17400_a0-optimized.cl
+2 -2
View File
@@ -108,7 +108,7 @@ KERNEL_FQ void m17400_m04 (KERN_ATTR_RULES ())
#define Rho_Pi(ad,r) \
bc0 = ad; \
ad = hc_rotl64 (t, r); \
ad = hc_rotl64 (t, r); \
t = bc0; \
#ifdef _unroll
@@ -338,7 +338,7 @@ KERNEL_FQ void m17400_s04 (KERN_ATTR_RULES ())
#define Rho_Pi(ad,r) \
bc0 = ad; \
ad = hc_rotl64 (t, r); \
ad = hc_rotl64 (t, r); \
t = bc0; \
#ifdef _unroll
OpenCL/m17400_a1-optimized.cl
+2 -2
View File
@@ -164,7 +164,7 @@ KERNEL_FQ void m17400_m04 (KERN_ATTR_BASIC ())
#define Rho_Pi(ad,r) \
bc0 = ad; \
ad = hc_rotl64 (t, r); \
ad = hc_rotl64 (t, r); \
t = bc0; \
#ifdef _unroll
@@ -453,7 +453,7 @@ KERNEL_FQ void m17400_s04 (KERN_ATTR_BASIC ())
#define Rho_Pi(ad,r) \
bc0 = ad; \
ad = hc_rotl64 (t, r); \
ad = hc_rotl64 (t, r); \
t = bc0; \
#ifdef _unroll
OpenCL/m17400_a3-optimized.cl
+2 -3
View File
@@ -80,10 +80,9 @@ DECLSPEC void m17400m (u32 *w0, u32 *w1, u32 *w2, u32 *w3, const u32 pw_len, KER
u64x a43 = 0;
u64x a44 = 0;
#define Rho_Pi(ad,r) \
bc0 = ad; \
ad = hc_rotl64 (t, r); \
ad = hc_rotl64 (t, r); \
t = bc0; \
#ifdef _unroll
@@ -281,7 +280,7 @@ DECLSPEC void m17400s (u32 *w0, u32 *w1, u32 *w2, u32 *w3, const u32 pw_len, KER
#define Rho_Pi(ad,r) \
bc0 = ad; \
ad = hc_rotl64 (t, r); \
ad = hc_rotl64 (t, r); \
t = bc0; \
#ifdef _unroll
OpenCL/m17500_a0-optimized.cl
+2 -2
View File
@@ -108,7 +108,7 @@ KERNEL_FQ void m17500_m04 (KERN_ATTR_RULES ())
#define Rho_Pi(ad,r) \
bc0 = ad; \
ad = hc_rotl64 (t, r); \
ad = hc_rotl64 (t, r); \
t = bc0; \
#ifdef _unroll
@@ -338,7 +338,7 @@ KERNEL_FQ void m17500_s04 (KERN_ATTR_RULES ())
#define Rho_Pi(ad,r) \
bc0 = ad; \
ad = hc_rotl64 (t, r); \
ad = hc_rotl64 (t, r); \
t = bc0; \
#ifdef _unroll
OpenCL/m17500_a1-optimized.cl
+2 -2
View File
@@ -164,7 +164,7 @@ KERNEL_FQ void m17500_m04 (KERN_ATTR_BASIC ())
#define Rho_Pi(ad,r) \
bc0 = ad; \
ad = hc_rotl64 (t, r); \
ad = hc_rotl64 (t, r); \
t = bc0; \
#ifdef _unroll
@@ -453,7 +453,7 @@ KERNEL_FQ void m17500_s04 (KERN_ATTR_BASIC ())
#define Rho_Pi(ad,r) \
bc0 = ad; \
ad = hc_rotl64 (t, r); \
ad = hc_rotl64 (t, r); \
t = bc0; \
#ifdef _unroll
OpenCL/m17500_a3-optimized.cl
+2 -2
View File
@@ -82,7 +82,7 @@ DECLSPEC void m17500m (u32 *w0, u32 *w1, u32 *w2, u32 *w3, const u32 pw_len, KER
#define Rho_Pi(ad,r) \
bc0 = ad; \
ad = hc_rotl64 (t, r); \
ad = hc_rotl64 (t, r); \
t = bc0; \
#ifdef _unroll
@@ -280,7 +280,7 @@ DECLSPEC void m17500s (u32 *w0, u32 *w1, u32 *w2, u32 *w3, const u32 pw_len, KER
#define Rho_Pi(ad,r) \
bc0 = ad; \
ad = hc_rotl64 (t, r); \
ad = hc_rotl64 (t, r); \
t = bc0; \
#ifdef _unroll
OpenCL/m17600_a0-optimized.cl
+2 -2
View File
@@ -108,7 +108,7 @@ KERNEL_FQ void m17600_m04 (KERN_ATTR_RULES ())
#define Rho_Pi(ad,r) \
bc0 = ad; \
ad = hc_rotl64 (t, r); \
ad = hc_rotl64 (t, r); \
t = bc0; \
#ifdef _unroll
@@ -338,7 +338,7 @@ KERNEL_FQ void m17600_s04 (KERN_ATTR_RULES ())
#define Rho_Pi(ad,r) \
bc0 = ad; \
ad = hc_rotl64 (t, r); \
ad = hc_rotl64 (t, r); \
t = bc0; \
#ifdef _unroll
OpenCL/m17600_a1-optimized.cl
+2 -2
View File
@@ -164,7 +164,7 @@ KERNEL_FQ void m17600_m04 (KERN_ATTR_BASIC ())
#define Rho_Pi(ad,r) \
bc0 = ad; \
ad = hc_rotl64 (t, r); \
ad = hc_rotl64 (t, r); \
t = bc0; \
#ifdef _unroll
@@ -453,7 +453,7 @@ KERNEL_FQ void m17600_s04 (KERN_ATTR_BASIC ())
#define Rho_Pi(ad,r) \
bc0 = ad; \
ad = hc_rotl64 (t, r); \
ad = hc_rotl64 (t, r); \
t = bc0; \
#ifdef _unroll
OpenCL/m17600_a3-optimized.cl
+2 -3
View File
@@ -80,10 +80,9 @@ DECLSPEC void m17600m (u32 *w0, u32 *w1, u32 *w2, u32 *w3, const u32 pw_len, KER
u64x a43 = 0;
u64x a44 = 0;
#define Rho_Pi(ad,r) \
bc0 = ad; \
ad = hc_rotl64 (t, r); \
ad = hc_rotl64 (t, r); \
t = bc0; \
#ifdef _unroll
@@ -281,7 +280,7 @@ DECLSPEC void m17600s (u32 *w0, u32 *w1, u32 *w2, u32 *w3, const u32 pw_len, KER
#define Rho_Pi(ad,r) \
bc0 = ad; \
ad = hc_rotl64 (t, r); \
ad = hc_rotl64 (t, r); \
t = bc0; \
#ifdef _unroll
OpenCL/m17700_a0-optimized.cl
+2 -2
View File
@@ -108,7 +108,7 @@ KERNEL_FQ void m17700_m04 (KERN_ATTR_RULES ())
#define Rho_Pi(ad,r) \
bc0 = ad; \
ad = hc_rotl64 (t, r); \
ad = hc_rotl64 (t, r); \
t = bc0; \
#ifdef _unroll
@@ -338,7 +338,7 @@ KERNEL_FQ void m17700_s04 (KERN_ATTR_RULES ())
#define Rho_Pi(ad,r) \
bc0 = ad; \
ad = hc_rotl64 (t, r); \
ad = hc_rotl64 (t, r); \
t = bc0; \
#ifdef _unroll
OpenCL/m17700_a1-optimized.cl
+2 -2
View File
@@ -164,7 +164,7 @@ KERNEL_FQ void m17700_m04 (KERN_ATTR_BASIC ())
#define Rho_Pi(ad,r) \
bc0 = ad; \
ad = hc_rotl64 (t, r); \
ad = hc_rotl64 (t, r); \
t = bc0; \
#ifdef _unroll
@@ -453,7 +453,7 @@ KERNEL_FQ void m17700_s04 (KERN_ATTR_BASIC ())
#define Rho_Pi(ad,r) \
bc0 = ad; \
ad = hc_rotl64 (t, r); \
ad = hc_rotl64 (t, r); \
t = bc0; \
#ifdef _unroll
OpenCL/m17700_a3-optimized.cl
+2 -2
View File
@@ -82,7 +82,7 @@ DECLSPEC void m17300m (u32 *w0, u32 *w1, u32 *w2, u32 *w3, const u32 pw_len, KER
#define Rho_Pi(ad,r) \
bc0 = ad; \
ad = hc_rotl64 (t, r); \
ad = hc_rotl64 (t, r); \
t = bc0; \
#ifdef _unroll
@@ -280,7 +280,7 @@ DECLSPEC void m17300s (u32 *w0, u32 *w1, u32 *w2, u32 *w3, const u32 pw_len, KER
#define Rho_Pi(ad,r) \
bc0 = ad; \
ad = hc_rotl64 (t, r); \
ad = hc_rotl64 (t, r); \
t = bc0; \
#ifdef _unroll
OpenCL/m17800_a0-optimized.cl
+2 -2
View File
@@ -108,7 +108,7 @@ KERNEL_FQ void m17800_m04 (KERN_ATTR_RULES ())
#define Rho_Pi(ad,r) \
bc0 = ad; \
ad = hc_rotl64 (t, r); \
ad = hc_rotl64 (t, r); \
t = bc0; \
#ifdef _unroll
@@ -338,7 +338,7 @@ KERNEL_FQ void m17800_s04 (KERN_ATTR_RULES ())
#define Rho_Pi(ad,r) \
bc0 = ad; \
ad = hc_rotl64 (t, r); \
ad = hc_rotl64 (t, r); \
t = bc0; \
#ifdef _unroll
OpenCL/m17800_a1-optimized.cl
+2 -2
View File
@@ -164,7 +164,7 @@ KERNEL_FQ void m17800_m04 (KERN_ATTR_BASIC ())
#define Rho_Pi(ad,r) \
bc0 = ad; \
ad = hc_rotl64 (t, r); \
ad = hc_rotl64 (t, r); \
t = bc0; \
#ifdef _unroll
@@ -453,7 +453,7 @@ KERNEL_FQ void m17800_s04 (KERN_ATTR_BASIC ())
#define Rho_Pi(ad,r) \
bc0 = ad; \
ad = hc_rotl64 (t, r); \
ad = hc_rotl64 (t, r); \
t = bc0; \
#ifdef _unroll
OpenCL/m17800_a3-optimized.cl
+2 -2
View File
@@ -82,7 +82,7 @@ DECLSPEC void m17400m (u32 *w0, u32 *w1, u32 *w2, u32 *w3, const u32 pw_len, KER
#define Rho_Pi(ad,r) \
bc0 = ad; \
ad = hc_rotl64 (t, r); \
ad = hc_rotl64 (t, r); \
t = bc0; \
#ifdef _unroll
@@ -280,7 +280,7 @@ DECLSPEC void m17400s (u32 *w0, u32 *w1, u32 *w2, u32 *w3, const u32 pw_len, KER
#define Rho_Pi(ad,r) \
bc0 = ad; \
ad = hc_rotl64 (t, r); \
ad = hc_rotl64 (t, r); \
t = bc0; \
#ifdef _unroll
OpenCL/m17900_a0-optimized.cl
+2 -2
View File
@@ -108,7 +108,7 @@ KERNEL_FQ void m17900_m04 (KERN_ATTR_RULES ())
#define Rho_Pi(ad,r) \
bc0 = ad; \
ad = hc_rotl64 (t, r); \
ad = hc_rotl64 (t, r); \
t = bc0; \
#ifdef _unroll
@@ -338,7 +338,7 @@ KERNEL_FQ void m17900_s04 (KERN_ATTR_RULES ())
#define Rho_Pi(ad,r) \
bc0 = ad; \
ad = hc_rotl64 (t, r); \
ad = hc_rotl64 (t, r); \
t = bc0; \
#ifdef _unroll
OpenCL/m17900_a1-optimized.cl
+2 -2
View File
@@ -164,7 +164,7 @@ KERNEL_FQ void m17900_m04 (KERN_ATTR_BASIC ())
#define Rho_Pi(ad,r) \
bc0 = ad; \
ad = hc_rotl64 (t, r); \
ad = hc_rotl64 (t, r); \
t = bc0; \
#ifdef _unroll
@@ -453,7 +453,7 @@ KERNEL_FQ void m17900_s04 (KERN_ATTR_BASIC ())
#define Rho_Pi(ad,r) \
bc0 = ad; \
ad = hc_rotl64 (t, r); \
ad = hc_rotl64 (t, r); \
t = bc0; \
#ifdef _unroll
OpenCL/m18000_a0-optimized.cl
+2 -2
View File
@@ -108,7 +108,7 @@ KERNEL_FQ void m18000_m04 (KERN_ATTR_RULES ())
#define Rho_Pi(ad,r) \
bc0 = ad; \
ad = hc_rotl64 (t, r); \
ad = hc_rotl64 (t, r); \
t = bc0; \
#ifdef _unroll
@@ -338,7 +338,7 @@ KERNEL_FQ void m18000_s04 (KERN_ATTR_RULES ())
#define Rho_Pi(ad,r) \
bc0 = ad; \
ad = hc_rotl64 (t, r); \
ad = hc_rotl64 (t, r); \
t = bc0; \
#ifdef _unroll
OpenCL/m18000_a1-optimized.cl
+2 -2
View File
@@ -164,7 +164,7 @@ KERNEL_FQ void m18000_m04 (KERN_ATTR_BASIC ())
#define Rho_Pi(ad,r) \
bc0 = ad; \
ad = hc_rotl64 (t, r); \
ad = hc_rotl64 (t, r); \
t = bc0; \
#ifdef _unroll
@@ -453,7 +453,7 @@ KERNEL_FQ void m18000_s04 (KERN_ATTR_BASIC ())
#define Rho_Pi(ad,r) \
bc0 = ad; \
ad = hc_rotl64 (t, r); \
ad = hc_rotl64 (t, r); \
t = bc0; \
#ifdef _unroll
OpenCL/m18000_a3-optimized.cl
+2 -2
View File
@@ -82,7 +82,7 @@ DECLSPEC void m17600m (u32 *w0, u32 *w1, u32 *w2, u32 *w3, const u32 pw_len, KER
#define Rho_Pi(ad,r) \
bc0 = ad; \
ad = hc_rotl64 (t, r); \
ad = hc_rotl64 (t, r); \
t = bc0; \
#ifdef _unroll
@@ -280,7 +280,7 @@ DECLSPEC void m17600s (u32 *w0, u32 *w1, u32 *w2, u32 *w3, const u32 pw_len, KER
#define Rho_Pi(ad,r) \
bc0 = ad; \
ad = hc_rotl64 (t, r); \
ad = hc_rotl64 (t, r); \
t = bc0; \
#ifdef _unroll
OpenCL/m18500_a0-pure.cl
+32 -32
View File
@@ -116,22 +116,22 @@ KERNEL_FQ void m18500_mxx (KERN_ATTR_RULES ())
sha1_init (&ctx2);
ctx2.w0[0] = hc_swap32(uint_to_hex_lower8 ((e >> 0) & 255) << 0
| uint_to_hex_lower8 ((e >> 8) & 255) << 16);
ctx2.w0[1] = hc_swap32(uint_to_hex_lower8 ((e >> 16) & 255) << 0
| uint_to_hex_lower8 ((e >> 24) & 255) << 16);
ctx2.w0[2] = hc_swap32(uint_to_hex_lower8 ((f >> 0) & 255) << 0
| uint_to_hex_lower8 ((f >> 8) & 255) << 16);
ctx2.w0[3] = hc_swap32(uint_to_hex_lower8 ((f >> 16) & 255) << 0
| uint_to_hex_lower8 ((f >> 24) & 255) << 16);
ctx2.w1[0] = hc_swap32(uint_to_hex_lower8 ((g >> 0) & 255) << 0
| uint_to_hex_lower8 ((g >> 8) & 255) << 16);
ctx2.w1[1] = hc_swap32(uint_to_hex_lower8 ((g >> 16) & 255) << 0
| uint_to_hex_lower8 ((g >> 24) & 255) << 16);
ctx2.w1[2] = hc_swap32(uint_to_hex_lower8 ((h >> 0) & 255) << 0
| uint_to_hex_lower8 ((h >> 8) & 255) << 16);
ctx2.w1[3] = hc_swap32(uint_to_hex_lower8 ((h >> 16) & 255) << 0
| uint_to_hex_lower8 ((h >> 24) & 255) << 16);
ctx2.w0[0] = hc_swap32 (uint_to_hex_lower8 ((e >> 0) & 255) << 0
| uint_to_hex_lower8 ((e >> 8) & 255) << 16);
ctx2.w0[1] = hc_swap32 (uint_to_hex_lower8 ((e >> 16) & 255) << 0
| uint_to_hex_lower8 ((e >> 24) & 255) << 16);
ctx2.w0[2] = hc_swap32 (uint_to_hex_lower8 ((f >> 0) & 255) << 0
| uint_to_hex_lower8 ((f >> 8) & 255) << 16);
ctx2.w0[3] = hc_swap32 (uint_to_hex_lower8 ((f >> 16) & 255) << 0
| uint_to_hex_lower8 ((f >> 24) & 255) << 16);
ctx2.w1[0] = hc_swap32 (uint_to_hex_lower8 ((g >> 0) & 255) << 0
| uint_to_hex_lower8 ((g >> 8) & 255) << 16);
ctx2.w1[1] = hc_swap32 (uint_to_hex_lower8 ((g >> 16) & 255) << 0
| uint_to_hex_lower8 ((g >> 24) & 255) << 16);
ctx2.w1[2] = hc_swap32 (uint_to_hex_lower8 ((h >> 0) & 255) << 0
| uint_to_hex_lower8 ((h >> 8) & 255) << 16);
ctx2.w1[3] = hc_swap32 (uint_to_hex_lower8 ((h >> 16) & 255) << 0
| uint_to_hex_lower8 ((h >> 24) & 255) << 16);
ctx2.len = 32;
sha1_final (&ctx2);
@@ -244,22 +244,22 @@ KERNEL_FQ void m18500_sxx (KERN_ATTR_RULES ())
sha1_init (&ctx2);
ctx2.w0[0] = hc_swap32(uint_to_hex_lower8 ((e >> 0) & 255) << 0
| uint_to_hex_lower8 ((e >> 8) & 255) << 16);
ctx2.w0[1] = hc_swap32(uint_to_hex_lower8 ((e >> 16) & 255) << 0
| uint_to_hex_lower8 ((e >> 24) & 255) << 16);
ctx2.w0[2] = hc_swap32(uint_to_hex_lower8 ((f >> 0) & 255) << 0
| uint_to_hex_lower8 ((f >> 8) & 255) << 16);
ctx2.w0[3] = hc_swap32(uint_to_hex_lower8 ((f >> 16) & 255) << 0
| uint_to_hex_lower8 ((f >> 24) & 255) << 16);
ctx2.w1[0] = hc_swap32(uint_to_hex_lower8 ((g >> 0) & 255) << 0
| uint_to_hex_lower8 ((g >> 8) & 255) << 16);
ctx2.w1[1] = hc_swap32(uint_to_hex_lower8 ((g >> 16) & 255) << 0
| uint_to_hex_lower8 ((g >> 24) & 255) << 16);
ctx2.w1[2] = hc_swap32(uint_to_hex_lower8 ((h >> 0) & 255) << 0
| uint_to_hex_lower8 ((h >> 8) & 255) << 16);
ctx2.w1[3] = hc_swap32(uint_to_hex_lower8 ((h >> 16) & 255) << 0
| uint_to_hex_lower8 ((h >> 24) & 255) << 16);
ctx2.w0[0] = hc_swap32 (uint_to_hex_lower8 ((e >> 0) & 255) << 0
| uint_to_hex_lower8 ((e >> 8) & 255) << 16);
ctx2.w0[1] = hc_swap32 (uint_to_hex_lower8 ((e >> 16) & 255) << 0
| uint_to_hex_lower8 ((e >> 24) & 255) << 16);
ctx2.w0[2] = hc_swap32 (uint_to_hex_lower8 ((f >> 0) & 255) << 0
| uint_to_hex_lower8 ((f >> 8) & 255) << 16);
ctx2.w0[3] = hc_swap32 (uint_to_hex_lower8 ((f >> 16) & 255) << 0
| uint_to_hex_lower8 ((f >> 24) & 255) << 16);
ctx2.w1[0] = hc_swap32 (uint_to_hex_lower8 ((g >> 0) & 255) << 0
| uint_to_hex_lower8 ((g >> 8) & 255) << 16);
ctx2.w1[1] = hc_swap32 (uint_to_hex_lower8 ((g >> 16) & 255) << 0
| uint_to_hex_lower8 ((g >> 24) & 255) << 16);
ctx2.w1[2] = hc_swap32 (uint_to_hex_lower8 ((h >> 0) & 255) << 0
| uint_to_hex_lower8 ((h >> 8) & 255) << 16);
ctx2.w1[3] = hc_swap32 (uint_to_hex_lower8 ((h >> 16) & 255) << 0
| uint_to_hex_lower8 ((h >> 24) & 255) << 16);
ctx2.len = 32;
sha1_final (&ctx2);
OpenCL/m18500_a1-pure.cl
+32 -32
View File
@@ -115,22 +115,22 @@ KERNEL_FQ void m18500_mxx (KERN_ATTR_RULES ())
sha1_init (&ctx2);
ctx2.w0[0] = hc_swap32(uint_to_hex_lower8 ((e >> 0) & 255) << 0
| uint_to_hex_lower8 ((e >> 8) & 255) << 16);
ctx2.w0[1] = hc_swap32(uint_to_hex_lower8 ((e >> 16) & 255) << 0
| uint_to_hex_lower8 ((e >> 24) & 255) << 16);
ctx2.w0[2] = hc_swap32(uint_to_hex_lower8 ((f >> 0) & 255) << 0
| uint_to_hex_lower8 ((f >> 8) & 255) << 16);
ctx2.w0[3] = hc_swap32(uint_to_hex_lower8 ((f >> 16) & 255) << 0
| uint_to_hex_lower8 ((f >> 24) & 255) << 16);
ctx2.w1[0] = hc_swap32(uint_to_hex_lower8 ((g >> 0) & 255) << 0
| uint_to_hex_lower8 ((g >> 8) & 255) << 16);
ctx2.w1[1] = hc_swap32(uint_to_hex_lower8 ((g >> 16) & 255) << 0
| uint_to_hex_lower8 ((g >> 24) & 255) << 16);
ctx2.w1[2] = hc_swap32(uint_to_hex_lower8 ((h >> 0) & 255) << 0
| uint_to_hex_lower8 ((h >> 8) & 255) << 16);
ctx2.w1[3] = hc_swap32(uint_to_hex_lower8 ((h >> 16) & 255) << 0
| uint_to_hex_lower8 ((h >> 24) & 255) << 16);
ctx2.w0[0] = hc_swap32 (uint_to_hex_lower8 ((e >> 0) & 255) << 0
| uint_to_hex_lower8 ((e >> 8) & 255) << 16);
ctx2.w0[1] = hc_swap32 (uint_to_hex_lower8 ((e >> 16) & 255) << 0
| uint_to_hex_lower8 ((e >> 24) & 255) << 16);
ctx2.w0[2] = hc_swap32 (uint_to_hex_lower8 ((f >> 0) & 255) << 0
| uint_to_hex_lower8 ((f >> 8) & 255) << 16);
ctx2.w0[3] = hc_swap32 (uint_to_hex_lower8 ((f >> 16) & 255) << 0
| uint_to_hex_lower8 ((f >> 24) & 255) << 16);
ctx2.w1[0] = hc_swap32 (uint_to_hex_lower8 ((g >> 0) & 255) << 0
| uint_to_hex_lower8 ((g >> 8) & 255) << 16);
ctx2.w1[1] = hc_swap32 (uint_to_hex_lower8 ((g >> 16) & 255) << 0
| uint_to_hex_lower8 ((g >> 24) & 255) << 16);
ctx2.w1[2] = hc_swap32 (uint_to_hex_lower8 ((h >> 0) & 255) << 0
| uint_to_hex_lower8 ((h >> 8) & 255) << 16);
ctx2.w1[3] = hc_swap32 (uint_to_hex_lower8 ((h >> 16) & 255) << 0
| uint_to_hex_lower8 ((h >> 24) & 255) << 16);
ctx2.len = 32;
sha1_final (&ctx2);
@@ -242,22 +242,22 @@ KERNEL_FQ void m18500_sxx (KERN_ATTR_RULES ())
sha1_init (&ctx2);
ctx2.w0[0] = hc_swap32(uint_to_hex_lower8 ((e >> 0) & 255) << 0
| uint_to_hex_lower8 ((e >> 8) & 255) << 16);
ctx2.w0[1] = hc_swap32(uint_to_hex_lower8 ((e >> 16) & 255) << 0
| uint_to_hex_lower8 ((e >> 24) & 255) << 16);
ctx2.w0[2] = hc_swap32(uint_to_hex_lower8 ((f >> 0) & 255) << 0
| uint_to_hex_lower8 ((f >> 8) & 255) << 16);
ctx2.w0[3] = hc_swap32(uint_to_hex_lower8 ((f >> 16) & 255) << 0
| uint_to_hex_lower8 ((f >> 24) & 255) << 16);
ctx2.w1[0] = hc_swap32(uint_to_hex_lower8 ((g >> 0) & 255) << 0
| uint_to_hex_lower8 ((g >> 8) & 255) << 16);
ctx2.w1[1] = hc_swap32(uint_to_hex_lower8 ((g >> 16) & 255) << 0
| uint_to_hex_lower8 ((g >> 24) & 255) << 16);
ctx2.w1[2] = hc_swap32(uint_to_hex_lower8 ((h >> 0) & 255) << 0
| uint_to_hex_lower8 ((h >> 8) & 255) << 16);
ctx2.w1[3] = hc_swap32(uint_to_hex_lower8 ((h >> 16) & 255) << 0
| uint_to_hex_lower8 ((h >> 24) & 255) << 16);
ctx2.w0[0] = hc_swap32 (uint_to_hex_lower8 ((e >> 0) & 255) << 0
| uint_to_hex_lower8 ((e >> 8) & 255) << 16);
ctx2.w0[1] = hc_swap32 (uint_to_hex_lower8 ((e >> 16) & 255) << 0
| uint_to_hex_lower8 ((e >> 24) & 255) << 16);
ctx2.w0[2] = hc_swap32 (uint_to_hex_lower8 ((f >> 0) & 255) << 0
| uint_to_hex_lower8 ((f >> 8) & 255) << 16);
ctx2.w0[3] = hc_swap32 (uint_to_hex_lower8 ((f >> 16) & 255) << 0
| uint_to_hex_lower8 ((f >> 24) & 255) << 16);
ctx2.w1[0] = hc_swap32 (uint_to_hex_lower8 ((g >> 0) & 255) << 0
| uint_to_hex_lower8 ((g >> 8) & 255) << 16);
ctx2.w1[1] = hc_swap32 (uint_to_hex_lower8 ((g >> 16) & 255) << 0
| uint_to_hex_lower8 ((g >> 24) & 255) << 16);
ctx2.w1[2] = hc_swap32 (uint_to_hex_lower8 ((h >> 0) & 255) << 0
| uint_to_hex_lower8 ((h >> 8) & 255) << 16);
ctx2.w1[3] = hc_swap32 (uint_to_hex_lower8 ((h >> 16) & 255) << 0
| uint_to_hex_lower8 ((h >> 24) & 255) << 16);
ctx2.len = 32;
sha1_final (&ctx2);
OpenCL/m18500_a3-pure.cl
+32 -32
View File
@@ -125,22 +125,22 @@ KERNEL_FQ void m18500_mxx (KERN_ATTR_VECTOR ())
sha1_init (&ctx2);
ctx2.w0[0] = hc_swap32(uint_to_hex_lower8 ((e >> 0) & 255) << 0
| uint_to_hex_lower8 ((e >> 8) & 255) << 16);
ctx2.w0[1] = hc_swap32(uint_to_hex_lower8 ((e >> 16) & 255) << 0
| uint_to_hex_lower8 ((e >> 24) & 255) << 16);
ctx2.w0[2] = hc_swap32(uint_to_hex_lower8 ((f >> 0) & 255) << 0
| uint_to_hex_lower8 ((f >> 8) & 255) << 16);
ctx2.w0[3] = hc_swap32(uint_to_hex_lower8 ((f >> 16) & 255) << 0
| uint_to_hex_lower8 ((f >> 24) & 255) << 16);
ctx2.w1[0] = hc_swap32(uint_to_hex_lower8 ((g >> 0) & 255) << 0
| uint_to_hex_lower8 ((g >> 8) & 255) << 16);
ctx2.w1[1] = hc_swap32(uint_to_hex_lower8 ((g >> 16) & 255) << 0
| uint_to_hex_lower8 ((g >> 24) & 255) << 16);
ctx2.w1[2] = hc_swap32(uint_to_hex_lower8 ((h >> 0) & 255) << 0
| uint_to_hex_lower8 ((h >> 8) & 255) << 16);
ctx2.w1[3] = hc_swap32(uint_to_hex_lower8 ((h >> 16) & 255) << 0
| uint_to_hex_lower8 ((h >> 24) & 255) << 16);
ctx2.w0[0] = hc_swap32 (uint_to_hex_lower8 ((e >> 0) & 255) << 0
| uint_to_hex_lower8 ((e >> 8) & 255) << 16);
ctx2.w0[1] = hc_swap32 (uint_to_hex_lower8 ((e >> 16) & 255) << 0
| uint_to_hex_lower8 ((e >> 24) & 255) << 16);
ctx2.w0[2] = hc_swap32 (uint_to_hex_lower8 ((f >> 0) & 255) << 0
| uint_to_hex_lower8 ((f >> 8) & 255) << 16);
ctx2.w0[3] = hc_swap32 (uint_to_hex_lower8 ((f >> 16) & 255) << 0
| uint_to_hex_lower8 ((f >> 24) & 255) << 16);
ctx2.w1[0] = hc_swap32 (uint_to_hex_lower8 ((g >> 0) & 255) << 0
| uint_to_hex_lower8 ((g >> 8) & 255) << 16);
ctx2.w1[1] = hc_swap32 (uint_to_hex_lower8 ((g >> 16) & 255) << 0
| uint_to_hex_lower8 ((g >> 24) & 255) << 16);
ctx2.w1[2] = hc_swap32 (uint_to_hex_lower8 ((h >> 0) & 255) << 0
| uint_to_hex_lower8 ((h >> 8) & 255) << 16);
ctx2.w1[3] = hc_swap32 (uint_to_hex_lower8 ((h >> 16) & 255) << 0
| uint_to_hex_lower8 ((h >> 24) & 255) << 16);
ctx2.len = 32;
sha1_final (&ctx2);
@@ -264,22 +264,22 @@ KERNEL_FQ void m18500_sxx (KERN_ATTR_VECTOR ())
sha1_init (&ctx2);
ctx2.w0[0] = hc_swap32(uint_to_hex_lower8 ((e >> 0) & 255) << 0
| uint_to_hex_lower8 ((e >> 8) & 255) << 16);
ctx2.w0[1] = hc_swap32(uint_to_hex_lower8 ((e >> 16) & 255) << 0
| uint_to_hex_lower8 ((e >> 24) & 255) << 16);
ctx2.w0[2] = hc_swap32(uint_to_hex_lower8 ((f >> 0) & 255) << 0
| uint_to_hex_lower8 ((f >> 8) & 255) << 16);
ctx2.w0[3] = hc_swap32(uint_to_hex_lower8 ((f >> 16) & 255) << 0
| uint_to_hex_lower8 ((f >> 24) & 255) << 16);
ctx2.w1[0] = hc_swap32(uint_to_hex_lower8 ((g >> 0) & 255) << 0
| uint_to_hex_lower8 ((g >> 8) & 255) << 16);
ctx2.w1[1] = hc_swap32(uint_to_hex_lower8 ((g >> 16) & 255) << 0
| uint_to_hex_lower8 ((g >> 24) & 255) << 16);
ctx2.w1[2] = hc_swap32(uint_to_hex_lower8 ((h >> 0) & 255) << 0
| uint_to_hex_lower8 ((h >> 8) & 255) << 16);
ctx2.w1[3] = hc_swap32(uint_to_hex_lower8 ((h >> 16) & 255) << 0
| uint_to_hex_lower8 ((h >> 24) & 255) << 16);
ctx2.w0[0] = hc_swap32 (uint_to_hex_lower8 ((e >> 0) & 255) << 0
| uint_to_hex_lower8 ((e >> 8) & 255) << 16);
ctx2.w0[1] = hc_swap32 (uint_to_hex_lower8 ((e >> 16) & 255) << 0
| uint_to_hex_lower8 ((e >> 24) & 255) << 16);
ctx2.w0[2] = hc_swap32 (uint_to_hex_lower8 ((f >> 0) & 255) << 0
| uint_to_hex_lower8 ((f >> 8) & 255) << 16);
ctx2.w0[3] = hc_swap32 (uint_to_hex_lower8 ((f >> 16) & 255) << 0
| uint_to_hex_lower8 ((f >> 24) & 255) << 16);
ctx2.w1[0] = hc_swap32 (uint_to_hex_lower8 ((g >> 0) & 255) << 0
| uint_to_hex_lower8 ((g >> 8) & 255) << 16);
ctx2.w1[1] = hc_swap32 (uint_to_hex_lower8 ((g >> 16) & 255) << 0
| uint_to_hex_lower8 ((g >> 24) & 255) << 16);
ctx2.w1[2] = hc_swap32 (uint_to_hex_lower8 ((h >> 0) & 255) << 0
| uint_to_hex_lower8 ((h >> 8) & 255) << 16);
ctx2.w1[3] = hc_swap32 (uint_to_hex_lower8 ((h >> 16) & 255) << 0
| uint_to_hex_lower8 ((h >> 24) & 255) << 16);
ctx2.len = 32;
sha1_final (&ctx2);
OpenCL/m19600-pure.cl
+4 -4
View File
@@ -513,7 +513,7 @@ KERNEL_FQ void m19600_comp (KERN_ATTR_TMPS_ESALT (krb5tgs_17_tmp_t, krb5tgs_17_t
int last_block_size = edata2_len % 16;
if(last_block_size == 0)
if (last_block_size == 0)
{
last_block_size = 16;
}
@@ -991,9 +991,9 @@ KERNEL_FQ void m19600_comp (KERN_ATTR_TMPS_ESALT (krb5tgs_17_tmp_t, krb5tgs_17_t
sha1_hmac_update_64 (&sha1_hmac_ctx, w0, w1, w2, w3, 16 + last_block_size);
sha1_hmac_final(&sha1_hmac_ctx);
sha1_hmac_final (&sha1_hmac_ctx);
if(sha1_hmac_ctx.opad.h[0] == esalt_bufs[digests_offset].checksum[0]
if (sha1_hmac_ctx.opad.h[0] == esalt_bufs[digests_offset].checksum[0]
&& sha1_hmac_ctx.opad.h[1] == esalt_bufs[digests_offset].checksum[1]
&& sha1_hmac_ctx.opad.h[2] == esalt_bufs[digests_offset].checksum[2])
{
@@ -1005,4 +1005,4 @@ KERNEL_FQ void m19600_comp (KERN_ATTR_TMPS_ESALT (krb5tgs_17_tmp_t, krb5tgs_17_t
}
}
}
}
}
OpenCL/m19700-pure.cl
+4 -4
View File
@@ -590,7 +590,7 @@ KERNEL_FQ void m19700_comp (KERN_ATTR_TMPS_ESALT (krb5tgs_18_tmp_t, krb5tgs_18_t
int last_block_size = edata2_len % 16;
if(last_block_size == 0)
if (last_block_size == 0)
{
last_block_size = 16;
}
@@ -1055,9 +1055,9 @@ KERNEL_FQ void m19700_comp (KERN_ATTR_TMPS_ESALT (krb5tgs_18_tmp_t, krb5tgs_18_t
sha1_hmac_update_64 (&sha1_hmac_ctx, w0, w1, w2, w3, 16 + last_block_size);
sha1_hmac_final(&sha1_hmac_ctx);
sha1_hmac_final (&sha1_hmac_ctx);
if(sha1_hmac_ctx.opad.h[0] == esalt_bufs[digests_offset].checksum[0]
if (sha1_hmac_ctx.opad.h[0] == esalt_bufs[digests_offset].checksum[0]
&& sha1_hmac_ctx.opad.h[1] == esalt_bufs[digests_offset].checksum[1]
&& sha1_hmac_ctx.opad.h[2] == esalt_bufs[digests_offset].checksum[2])
{
@@ -1069,4 +1069,4 @@ KERNEL_FQ void m19700_comp (KERN_ATTR_TMPS_ESALT (krb5tgs_18_tmp_t, krb5tgs_18_t
}
}
}
}
}