/** * 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_streebog256.cl" __kernel void m11700_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 u64 gid_max) { /** * modifier */ const u64 gid = get_global_id (0); const u64 lid = get_local_id (0); const u64 lsz = get_local_size (0); /** * shared lookup table */ #ifdef REAL_SHM __local u64a s_sbob_sl64[8][256]; for (MAYBE_VOLATILE u32 i = lid; i < 256; i += lsz) { s_sbob_sl64[0][i] = sbob_sl64[0][i]; s_sbob_sl64[1][i] = sbob_sl64[1][i]; s_sbob_sl64[2][i] = sbob_sl64[2][i]; s_sbob_sl64[3][i] = sbob_sl64[3][i]; s_sbob_sl64[4][i] = sbob_sl64[4][i]; s_sbob_sl64[5][i] = sbob_sl64[5][i]; s_sbob_sl64[6][i] = sbob_sl64[6][i]; s_sbob_sl64[7][i] = sbob_sl64[7][i]; } barrier (CLK_LOCAL_MEM_FENCE); #else __constant u64a (*s_sbob_sl64)[256] = sbob_sl64; #endif if (gid >= gid_max) return; /** * base */ const u32 pw_len = pws[gid].pw_len; u32x w[64] = { 0 }; for (int i = 0, idx = 0; i < pw_len; i += 4, idx += 1) { w[idx] = pws[gid].i[idx]; } /** * 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; streebog256_ctx_vector_t ctx; streebog256_init_vector (&ctx, s_sbob_sl64); streebog256_update_vector_swap (&ctx, w, pw_len); streebog256_final_vector (&ctx); const u32x r0 = l32_from_64 (ctx.h[0]); const u32x r1 = h32_from_64 (ctx.h[0]); const u32x r2 = l32_from_64 (ctx.h[1]); const u32x r3 = h32_from_64 (ctx.h[1]); COMPARE_M_SIMD (r0, r1, r2, r3); } } __kernel void m11700_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 u64 gid_max) { /** * modifier */ const u64 gid = get_global_id (0); const u64 lid = get_local_id (0); const u64 lsz = get_local_size (0); /** * shared lookup table */ #ifdef REAL_SHM __local u64a s_sbob_sl64[8][256]; for (MAYBE_VOLATILE u32 i = lid; i < 256; i += lsz) { s_sbob_sl64[0][i] = sbob_sl64[0][i]; s_sbob_sl64[1][i] = sbob_sl64[1][i]; s_sbob_sl64[2][i] = sbob_sl64[2][i]; s_sbob_sl64[3][i] = sbob_sl64[3][i]; s_sbob_sl64[4][i] = sbob_sl64[4][i]; s_sbob_sl64[5][i] = sbob_sl64[5][i]; s_sbob_sl64[6][i] = sbob_sl64[6][i]; s_sbob_sl64[7][i] = sbob_sl64[7][i]; } barrier (CLK_LOCAL_MEM_FENCE); #else __constant u64a (*s_sbob_sl64)[256] = sbob_sl64; #endif 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; u32x w[64] = { 0 }; for (int i = 0, idx = 0; i < pw_len; i += 4, idx += 1) { w[idx] = pws[gid].i[idx]; } /** * 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; streebog256_ctx_vector_t ctx; streebog256_init_vector (&ctx, s_sbob_sl64); streebog256_update_vector_swap (&ctx, w, pw_len); streebog256_final_vector (&ctx); const u32x r0 = l32_from_64 (ctx.h[0]); const u32x r1 = h32_from_64 (ctx.h[0]); const u32x r2 = l32_from_64 (ctx.h[1]); const u32x r3 = h32_from_64 (ctx.h[1]); COMPARE_S_SIMD (r0, r1, r2, r3); } }