Add -L support for -m 10800 in combination with -a 3

pull/1291/head
jsteube 7 years ago
parent 5de48182b4
commit e455561f77

@ -267,6 +267,19 @@
#define SHA384_F1o(x,y,z) (SHA384_F1 ((x), (y), (z))) #define SHA384_F1o(x,y,z) (SHA384_F1 ((x), (y), (z)))
#endif #endif
#define SHA384_STEP_S(F0,F1,a,b,c,d,e,f,g,h,x,K) \
{ \
h += K; \
h += x; \
h += SHA384_S1_S (e); \
h += F0 (e, f, g); \
d += h; \
h += SHA384_S0_S (a); \
h += F1 (a, b, c); \
}
#define SHA384_EXPAND_S(x,y,z,w) (SHA384_S3_S (x) + y + SHA384_S2_S (z) + w)
#define SHA384_STEP(F0,F1,a,b,c,d,e,f,g,h,x,K) \ #define SHA384_STEP(F0,F1,a,b,c,d,e,f,g,h,x,K) \
{ \ { \
h += K; \ h += K; \

File diff suppressed because it is too large Load Diff

@ -0,0 +1,144 @@
/**
* Author......: See docs/credits.txt
* License.....: MIT
*/
#define NEW_SIMD_CODE
#include "inc_vendor.cl"
#include "inc_hash_constants.h"
#include "inc_hash_functions.cl"
#include "inc_types.cl"
#include "inc_common.cl"
#include "inc_simd.cl"
#include "inc_hash_sha384.cl"
__kernel void m10800_mxx (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global 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)
{
/**
* modifier
*/
const u32 lid = get_local_id (0);
const u32 gid = get_global_id (0);
if (gid >= gid_max) return;
/**
* base
*/
const u32 pw_len = pws[gid].pw_len;
const u32 pw_lenv = ceil ((float) pw_len / 4);
u32x w[64] = { 0 };
for (int idx = 0; idx < pw_lenv; idx++)
{
w[idx] = pws[gid].i[idx];
barrier (CLK_GLOBAL_MEM_FENCE);
}
/**
* loop
*/
u32x 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 u32x w0 = w0l | w0r;
w[0] = w0;
sha384_ctx_vector_t ctx;
sha384_init_vector (&ctx);
sha384_update_vector (&ctx, w, pw_len);
sha384_final_vector (&ctx);
const u32x r0 = l32_from_64 (ctx.h[3]);
const u32x r1 = h32_from_64 (ctx.h[3]);
const u32x r2 = l32_from_64 (ctx.h[2]);
const u32x r3 = h32_from_64 (ctx.h[2]);
COMPARE_M_SIMD (r0, r1, r2, r3);
}
}
__kernel void m10800_sxx (__global pw_t *pws, __global const kernel_rule_t *rules_buf, __global const pw_t *combs_buf, __global 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)
{
/**
* modifier
*/
const u32 lid = get_local_id (0);
const u32 gid = get_global_id (0);
if (gid >= gid_max) return;
/**
* digest
*/
const u32 search[4] =
{
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]
};
/**
* base
*/
const u32 pw_len = pws[gid].pw_len;
const u32 pw_lenv = ceil ((float) pw_len / 4);
u32x w[64] = { 0 };
for (int idx = 0; idx < pw_lenv; idx++)
{
w[idx] = pws[gid].i[idx];
barrier (CLK_GLOBAL_MEM_FENCE);
}
/**
* loop
*/
u32x 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 u32x w0 = w0l | w0r;
w[0] = w0;
sha384_ctx_vector_t ctx;
sha384_init_vector (&ctx);
sha384_update_vector (&ctx, w, pw_len);
sha384_final_vector (&ctx);
const u32x r0 = l32_from_64 (ctx.h[3]);
const u32x r1 = h32_from_64 (ctx.h[3]);
const u32x r2 = l32_from_64 (ctx.h[2]);
const u32x r3 = h32_from_64 (ctx.h[2]);
COMPARE_S_SIMD (r0, r1, r2, r3);
}
}
Loading…
Cancel
Save