#define _SAPB_
-#include "include/constants.h"
-#include "include/kernel_vendor.h"
+//too much register pressure
+//#define NEW_SIMD_CODE
+
+#include "inc_hash_constants.h"
+#include "inc_vendor.cl"
#define DGST_R0 0
#define DGST_R1 1
#define DGST_R2 2
#define DGST_R3 3
-#include "include/kernel_functions.c"
-#include "OpenCL/types_ocl.c"
-#include "OpenCL/common.c"
-
-#define COMPARE_S "OpenCL/check_single_comp4.c"
-#define COMPARE_M "OpenCL/check_multi_comp4.c"
+#include "inc_hash_functions.cl"
+#include "inc_types.cl"
+#include "inc_common.cl"
+#include "inc_simd.cl"
#define GETCHAR(a,p) (((a)[(p) / 4] >> (((p) & 3) * 8)) & 0xff)
#define PUTCHAR(a,p,c) ((a)[(p) / 4] = (((a)[(p) / 4] & ~(0xff << (((p) & 3) * 8))) | ((c) << (((p) & 3) * 8))))
0xe2, 0xb7, 0x33, 0x71, 0x8b, 0x9f, 0x5d, 0x01, 0x44, 0x70, 0xae, 0x11, 0xef, 0x28, 0xf0, 0x0d
};
-static u32 sapb_trans (const u32 in)
+u32 sapb_trans (const u32 in)
{
u32 out = 0;
return out;
}
-static u32 walld0rf_magic (const u32 w0[4], const u32 pw_len, const u32 salt_buf0[4], const u32 salt_len, const u32 a, const u32 b, const u32 c, const u32 d, u32 t[16])
+u32 walld0rf_magic (const u32 w0[4], const u32 pw_len, const u32 salt_buf0[4], const u32 salt_len, const u32 a, const u32 b, const u32 c, const u32 d, u32 t[16])
{
t[ 0] = 0;
t[ 1] = 0;
return sum20;
}
-static void m07700m (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], const u32 pw_len, __global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global u32 *bitmaps_buf_s1_a, __global u32 *bitmaps_buf_s1_b, __global u32 *bitmaps_buf_s1_c, __global u32 *bitmaps_buf_s1_d, __global u32 *bitmaps_buf_s2_a, __global u32 *bitmaps_buf_s2_b, __global u32 *bitmaps_buf_s2_c, __global u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global digest_t *digests_buf, __global u32 *hashes_shown, __global salt_t *salt_bufs, __global void *esalt_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 il_cnt, const u32 digests_cnt, const u32 digests_offset)
+void m07700m (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], const u32 pw_len, __global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global u32 *bitmaps_buf_s1_a, __global u32 *bitmaps_buf_s1_b, __global u32 *bitmaps_buf_s1_c, __global u32 *bitmaps_buf_s1_d, __global u32 *bitmaps_buf_s2_a, __global u32 *bitmaps_buf_s2_b, __global u32 *bitmaps_buf_s2_c, __global u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global digest_t *digests_buf, __global u32 *hashes_shown, __global salt_t *salt_bufs, __global void *esalt_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 il_cnt, const u32 digests_cnt, const u32 digests_offset)
{
/**
* modifier
const u32 salt_len = salt_bufs[salt_pos].salt_len;
u32 s0[4];
+ u32 s1[4];
+ u32 s2[4];
+ u32 s3[4];
s0[0] = salt_buf0[0];
s0[1] = salt_buf0[1];
s0[2] = salt_buf0[2];
s0[3] = 0;
-
- u32 s1[4];
-
s1[0] = 0;
s1[1] = 0;
s1[2] = 0;
s1[3] = 0;
-
- u32 s2[4];
-
s2[0] = 0;
s2[1] = 0;
s2[2] = 0;
s2[3] = 0;
-
- u32 s3[4];
-
s3[0] = 0;
s3[1] = 0;
s3[2] = 0;
u32 w0l = w0[0];
- for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
{
- const u32 w0r = sapb_trans (bfs_buf[il_pos].i);
+ const u32x w0r = sapb_trans (ix_create_bft (bfs_buf, il_pos));
+
+ const u32x w0lr = w0l | w0r;
- w0[0] = w0l | w0r;
+ w0[0] = w0lr;
u32 t[16];
a ^= c;
b ^= d;
+ c = 0;
+ d = 0;
- const u32 r0 = a;
- const u32 r1 = b;
- const u32 r2 = 0;
- const u32 r3 = 0;
-
- #include COMPARE_M
+ COMPARE_M_SIMD (a, b, c, d);
}
}
-static void m07700s (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], const u32 pw_len, __global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global u32 *bitmaps_buf_s1_a, __global u32 *bitmaps_buf_s1_b, __global u32 *bitmaps_buf_s1_c, __global u32 *bitmaps_buf_s1_d, __global u32 *bitmaps_buf_s2_a, __global u32 *bitmaps_buf_s2_b, __global u32 *bitmaps_buf_s2_c, __global u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global digest_t *digests_buf, __global u32 *hashes_shown, __global salt_t *salt_bufs, __global void *esalt_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 il_cnt, const u32 digests_cnt, const u32 digests_offset)
+void m07700s (u32 w0[4], u32 w1[4], u32 w2[4], u32 w3[4], const u32 pw_len, __global pw_t *pws, __global kernel_rule_t *rules_buf, __global comb_t *combs_buf, __global bf_t *bfs_buf, __global void *tmps, __global void *hooks, __global u32 *bitmaps_buf_s1_a, __global u32 *bitmaps_buf_s1_b, __global u32 *bitmaps_buf_s1_c, __global u32 *bitmaps_buf_s1_d, __global u32 *bitmaps_buf_s2_a, __global u32 *bitmaps_buf_s2_b, __global u32 *bitmaps_buf_s2_c, __global u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global digest_t *digests_buf, __global u32 *hashes_shown, __global salt_t *salt_bufs, __global void *esalt_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV_buf, const u32 bitmap_mask, const u32 bitmap_shift1, const u32 bitmap_shift2, const u32 salt_pos, const u32 loop_pos, const u32 loop_cnt, const u32 il_cnt, const u32 digests_cnt, const u32 digests_offset)
{
/**
* modifier
const u32 salt_len = salt_bufs[salt_pos].salt_len;
u32 s0[4];
+ u32 s1[4];
+ u32 s2[4];
+ u32 s3[4];
s0[0] = salt_buf0[0];
s0[1] = salt_buf0[1];
s0[2] = salt_buf0[2];
s0[3] = 0;
-
- u32 s1[4];
-
s1[0] = 0;
s1[1] = 0;
s1[2] = 0;
s1[3] = 0;
-
- u32 s2[4];
-
s2[0] = 0;
s2[1] = 0;
s2[2] = 0;
s2[3] = 0;
-
- u32 s3[4];
-
s3[0] = 0;
s3[1] = 0;
s3[2] = 0;
{
digests_buf[digests_offset].digest_buf[DGST_R0],
digests_buf[digests_offset].digest_buf[DGST_R1],
- digests_buf[digests_offset].digest_buf[DGST_R2],
- digests_buf[digests_offset].digest_buf[DGST_R3]
+ 0,
+ 0
};
/**
u32 w0l = w0[0];
- for (u32 il_pos = 0; il_pos < il_cnt; il_pos++)
+ for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
{
- const u32 w0r = sapb_trans (bfs_buf[il_pos].i);
+ const u32x w0r = sapb_trans (ix_create_bft (bfs_buf, il_pos));
+
+ const u32x w0lr = w0l | w0r;
- w0[0] = w0l | w0r;
+ w0[0] = w0lr;
u32 t[16];
a ^= c;
b ^= d;
+ c = 0;
+ d = 0;
- const u32 r0 = a;
- const u32 r1 = b;
- const u32 r2 = 0;
- const u32 r3 = 0;
-
- #include COMPARE_S
+ COMPARE_S_SIMD (a, b, c, d);
}
}