|
|
|
@ -25,7 +25,7 @@
|
|
|
|
|
#define uint_to_hex_lower8(i) (u32x) (l_bin2asc[(i).s0], l_bin2asc[(i).s1], l_bin2asc[(i).s2], l_bin2asc[(i).s3], l_bin2asc[(i).s4], l_bin2asc[(i).s5], l_bin2asc[(i).s6], l_bin2asc[(i).s7], l_bin2asc[(i).s8], l_bin2asc[(i).s9], l_bin2asc[(i).sa], l_bin2asc[(i).sb], l_bin2asc[(i).sc], l_bin2asc[(i).sd], l_bin2asc[(i).se], l_bin2asc[(i).sf])
|
|
|
|
|
#endif
|
|
|
|
|
|
|
|
|
|
__kernel void m02810_mxx (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __constant const u32x *words_buf_r, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const void *esalt_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV0_buf, __global u32 *d_scryptV1_buf, __global u32 *d_scryptV2_buf, __global u32 *d_scryptV3_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, const u32 combs_mode, const u32 gid_max)
|
|
|
|
|
__kernel void m02810_mxx (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __constant const u32 *words_buf_r, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const void *esalt_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV0_buf, __global u32 *d_scryptV1_buf, __global u32 *d_scryptV2_buf, __global u32 *d_scryptV3_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, const u32 combs_mode, const u32 gid_max)
|
|
|
|
|
{
|
|
|
|
|
/**
|
|
|
|
|
* modifier
|
|
|
|
@ -62,7 +62,7 @@ __kernel void m02810_mxx (__global pw_t *pws, __global const kernel_rule_t *rule
|
|
|
|
|
|
|
|
|
|
const u32 pw_lenv = ceil ((float) pw_len / 4);
|
|
|
|
|
|
|
|
|
|
u32x w[64] = { 0 };
|
|
|
|
|
u32 w[64] = { 0 };
|
|
|
|
|
|
|
|
|
|
for (int idx = 0; idx < pw_lenv; idx++)
|
|
|
|
|
{
|
|
|
|
@ -75,7 +75,7 @@ __kernel void m02810_mxx (__global pw_t *pws, __global const kernel_rule_t *rule
|
|
|
|
|
|
|
|
|
|
const u32 salt_lenv = ceil ((float) salt_len / 4);
|
|
|
|
|
|
|
|
|
|
u32x s[8] = { 0 };
|
|
|
|
|
u32 s[8] = { 0 };
|
|
|
|
|
|
|
|
|
|
for (int idx = 0; idx < salt_lenv; idx++)
|
|
|
|
|
{
|
|
|
|
@ -88,13 +88,13 @@ __kernel void m02810_mxx (__global pw_t *pws, __global const kernel_rule_t *rule
|
|
|
|
|
* loop
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
u32x w0l = w[0];
|
|
|
|
|
u32 w0l = w[0];
|
|
|
|
|
|
|
|
|
|
for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
|
|
|
|
|
{
|
|
|
|
|
const u32x w0r = words_buf_r[il_pos / VECT_SIZE];
|
|
|
|
|
const u32 w0r = words_buf_r[il_pos / VECT_SIZE];
|
|
|
|
|
|
|
|
|
|
const u32x w0lr = w0l | w0r;
|
|
|
|
|
const u32 w0lr = w0l | w0r;
|
|
|
|
|
|
|
|
|
|
w[0] = w0lr;
|
|
|
|
|
|
|
|
|
@ -106,10 +106,10 @@ __kernel void m02810_mxx (__global pw_t *pws, __global const kernel_rule_t *rule
|
|
|
|
|
|
|
|
|
|
md5_final_vector (&ctx0);
|
|
|
|
|
|
|
|
|
|
const u32x a = ctx0.h[0];
|
|
|
|
|
const u32x b = ctx0.h[1];
|
|
|
|
|
const u32x c = ctx0.h[2];
|
|
|
|
|
const u32x d = ctx0.h[3];
|
|
|
|
|
const u32 a = ctx0.h[0];
|
|
|
|
|
const u32 b = ctx0.h[1];
|
|
|
|
|
const u32 c = ctx0.h[2];
|
|
|
|
|
const u32 d = ctx0.h[3];
|
|
|
|
|
|
|
|
|
|
md5_ctx_vector_t ctx;
|
|
|
|
|
|
|
|
|
@ -161,16 +161,16 @@ __kernel void m02810_mxx (__global pw_t *pws, __global const kernel_rule_t *rule
|
|
|
|
|
|
|
|
|
|
md5_transform_vector (ctx.w0, ctx.w1, ctx.w2, ctx.w3, ctx.h);
|
|
|
|
|
|
|
|
|
|
const u32x r0 = ctx.h[DGST_R0];
|
|
|
|
|
const u32x r1 = ctx.h[DGST_R1];
|
|
|
|
|
const u32x r2 = ctx.h[DGST_R2];
|
|
|
|
|
const u32x r3 = ctx.h[DGST_R3];
|
|
|
|
|
const u32 r0 = ctx.h[DGST_R0];
|
|
|
|
|
const u32 r1 = ctx.h[DGST_R1];
|
|
|
|
|
const u32 r2 = ctx.h[DGST_R2];
|
|
|
|
|
const u32 r3 = ctx.h[DGST_R3];
|
|
|
|
|
|
|
|
|
|
COMPARE_M_SIMD (r0, r1, r2, r3);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
__kernel void m02810_sxx (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __constant const u32x *words_buf_r, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const void *esalt_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV0_buf, __global u32 *d_scryptV1_buf, __global u32 *d_scryptV2_buf, __global u32 *d_scryptV3_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, const u32 combs_mode, const u32 gid_max)
|
|
|
|
|
__kernel void m02810_sxx (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __constant const u32 *words_buf_r, __global void *tmps, __global void *hooks, __global const u32 *bitmaps_buf_s1_a, __global const u32 *bitmaps_buf_s1_b, __global const u32 *bitmaps_buf_s1_c, __global const u32 *bitmaps_buf_s1_d, __global const u32 *bitmaps_buf_s2_a, __global const u32 *bitmaps_buf_s2_b, __global const u32 *bitmaps_buf_s2_c, __global const u32 *bitmaps_buf_s2_d, __global plain_t *plains_buf, __global const digest_t *digests_buf, __global u32 *hashes_shown, __global const salt_t *salt_bufs, __global const void *esalt_bufs, __global u32 *d_return_buf, __global u32 *d_scryptV0_buf, __global u32 *d_scryptV1_buf, __global u32 *d_scryptV2_buf, __global u32 *d_scryptV3_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, const u32 combs_mode, const u32 gid_max)
|
|
|
|
|
{
|
|
|
|
|
/**
|
|
|
|
|
* modifier
|
|
|
|
@ -219,7 +219,7 @@ __kernel void m02810_sxx (__global pw_t *pws, __global const kernel_rule_t *rule
|
|
|
|
|
|
|
|
|
|
const u32 pw_lenv = ceil ((float) pw_len / 4);
|
|
|
|
|
|
|
|
|
|
u32x w[64] = { 0 };
|
|
|
|
|
u32 w[64] = { 0 };
|
|
|
|
|
|
|
|
|
|
for (int idx = 0; idx < pw_lenv; idx++)
|
|
|
|
|
{
|
|
|
|
@ -232,7 +232,7 @@ __kernel void m02810_sxx (__global pw_t *pws, __global const kernel_rule_t *rule
|
|
|
|
|
|
|
|
|
|
const u32 salt_lenv = ceil ((float) salt_len / 4);
|
|
|
|
|
|
|
|
|
|
u32x s[8] = { 0 };
|
|
|
|
|
u32 s[8] = { 0 };
|
|
|
|
|
|
|
|
|
|
for (int idx = 0; idx < salt_lenv; idx++)
|
|
|
|
|
{
|
|
|
|
@ -245,13 +245,13 @@ __kernel void m02810_sxx (__global pw_t *pws, __global const kernel_rule_t *rule
|
|
|
|
|
* loop
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
u32x w0l = w[0];
|
|
|
|
|
u32 w0l = w[0];
|
|
|
|
|
|
|
|
|
|
for (u32 il_pos = 0; il_pos < il_cnt; il_pos += VECT_SIZE)
|
|
|
|
|
{
|
|
|
|
|
const u32x w0r = words_buf_r[il_pos / VECT_SIZE];
|
|
|
|
|
const u32 w0r = words_buf_r[il_pos / VECT_SIZE];
|
|
|
|
|
|
|
|
|
|
const u32x w0lr = w0l | w0r;
|
|
|
|
|
const u32 w0lr = w0l | w0r;
|
|
|
|
|
|
|
|
|
|
w[0] = w0lr;
|
|
|
|
|
|
|
|
|
@ -263,10 +263,10 @@ __kernel void m02810_sxx (__global pw_t *pws, __global const kernel_rule_t *rule
|
|
|
|
|
|
|
|
|
|
md5_final_vector (&ctx0);
|
|
|
|
|
|
|
|
|
|
const u32x a = ctx0.h[0];
|
|
|
|
|
const u32x b = ctx0.h[1];
|
|
|
|
|
const u32x c = ctx0.h[2];
|
|
|
|
|
const u32x d = ctx0.h[3];
|
|
|
|
|
const u32 a = ctx0.h[0];
|
|
|
|
|
const u32 b = ctx0.h[1];
|
|
|
|
|
const u32 c = ctx0.h[2];
|
|
|
|
|
const u32 d = ctx0.h[3];
|
|
|
|
|
|
|
|
|
|
md5_ctx_vector_t ctx;
|
|
|
|
|
|
|
|
|
@ -318,10 +318,10 @@ __kernel void m02810_sxx (__global pw_t *pws, __global const kernel_rule_t *rule
|
|
|
|
|
|
|
|
|
|
md5_transform_vector (ctx.w0, ctx.w1, ctx.w2, ctx.w3, ctx.h);
|
|
|
|
|
|
|
|
|
|
const u32x r0 = ctx.h[DGST_R0];
|
|
|
|
|
const u32x r1 = ctx.h[DGST_R1];
|
|
|
|
|
const u32x r2 = ctx.h[DGST_R2];
|
|
|
|
|
const u32x r3 = ctx.h[DGST_R3];
|
|
|
|
|
const u32 r0 = ctx.h[DGST_R0];
|
|
|
|
|
const u32 r1 = ctx.h[DGST_R1];
|
|
|
|
|
const u32 r2 = ctx.h[DGST_R2];
|
|
|
|
|
const u32 r3 = ctx.h[DGST_R3];
|
|
|
|
|
|
|
|
|
|
COMPARE_S_SIMD (r0, r1, r2, r3);
|
|
|
|
|
}
|
|
|
|
|