arno/hashcat
1
0
Fork 0
mirror of https://github.com/hashcat/hashcat.git synced 2025-02-22 12:32:04 +00:00
Code Issues Releases Wiki Activity

Merge pull request #3620 from loukabvn/sm3

Browse Source 
Adding support for SM3
This commit is contained in:
Jens Steube 2023-02-20 15:35:52 +01:00 committed by GitHub
commit 71da2317f4
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
10 changed files with 3663 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1586
OpenCL/inc_hash_sm3.cl Normal file
View File

File diff suppressed because it is too large Load Diff

105
OpenCL/inc_hash_sm3.h Normal file
View File

@ -0,0 +1,105 @@
/**
* Author......: See docs/credits.txt
* License.....: MIT
*/
#ifndef INC_HASH_SM3_H
#define INC_HASH_SM3_H
#define SM3_P0_S(x) ((x) ^ hc_rotl32_S((x), 9) ^ hc_rotl32_S((x), 17))
#define SM3_P1_S(x) ((x) ^ hc_rotl32_S((x), 15) ^ hc_rotl32_S((x), 23))
#define SM3_P0(x) ((x) ^ hc_rotl32((x), 9) ^ hc_rotl32((x), 17))
#define SM3_P1(x) ((x) ^ hc_rotl32((x), 15) ^ hc_rotl32((x), 23))
#define SM3_FF0(x, y, z) ((x) ^ (y) ^ (z))
#define SM3_GG0(x, y, z) ((x) ^ (y) ^ (z))
#define SM3_FF1(x, y, z) (((x) & (y)) | (((x) | (y)) & (z)))
#define SM3_GG1(x, y, z) (((z) ^ ((x) & ((y) ^ (z)))))
#define SM3_EXPAND_S(a, b, c, d, e) (SM3_P1_S(a ^ b ^ hc_rotl32_S(c, 15)) ^ hc_rotl32_S(d, 7) ^ e)
#define SM3_EXPAND(a, b, c, d, e) (SM3_P1(a ^ b ^ hc_rotl32(c, 15)) ^ hc_rotl32(d, 7) ^ e)
// Only Wj need to be parenthesis because of operator priority
// (Wj = Wi ^ Wi+4)
#define SM3_ROUND_S(a, b, c, d, e, f, g, h, Tj, Wi, Wj, FF, GG) \
{ \
const u32 A_ROTL12 = hc_rotl32_S(a, 12); \
const u32 SS1 = hc_rotl32_S(A_ROTL12 + e + Tj, 7); \
const u32 TT1 = FF(a, b, c) + d + (SS1 ^ A_ROTL12) + (Wj); \
const u32 TT2 = GG(e, f, g) + h + SS1 + Wi; \
b = hc_rotl32_S(b, 9); \
d = TT1; \
f = hc_rotl32_S(f, 19); \
h = SM3_P0_S(TT2); \
}
#define SM3_ROUND(a, b, c, d, e, f, g, h, Tj, Wi, Wj, FF, GG) \
{ \
const u32x A_ROTL12 = hc_rotl32(a, 12); \
const u32x SS1 = hc_rotl32(A_ROTL12 + e + make_u32x(Tj), 7); \
const u32x TT1 = FF(a, b, c) + d + (SS1 ^ A_ROTL12) + (Wj); \
const u32x TT2 = GG(e, f, g) + h + SS1 + Wi; \
b = hc_rotl32(b, 9); \
d = TT1; \
f = hc_rotl32(f, 19); \
h = SM3_P0(TT2); \
}
#define SM3_ROUND1_S(a, b, c, d, e, f, g, h, Tj, Wi, Wj) SM3_ROUND_S(a, b, c, d, e, f, g, h, Tj, Wi, Wj, SM3_FF0, SM3_GG0)
#define SM3_ROUND1(a, b, c, d, e, f, g, h, Tj, Wi, Wj) SM3_ROUND(a, b, c, d, e, f, g, h, Tj, Wi, Wj, SM3_FF0, SM3_GG0)
#define SM3_ROUND2_S(a, b, c, d, e, f, g, h, Tj, Wi, Wj) SM3_ROUND_S(a, b, c, d, e, f, g, h, Tj, Wi, Wj, SM3_FF1, SM3_GG1)
#define SM3_ROUND2(a, b, c, d, e, f, g, h, Tj, Wi, Wj) SM3_ROUND(a, b, c, d, e, f, g, h, Tj, Wi, Wj, SM3_FF1, SM3_GG1)
typedef struct sm3_ctx
{
u32 h[8];
u32 w0[4];
u32 w1[4];
u32 w2[4];
u32 w3[4];
int len;
} sm3_ctx_t;
typedef struct sm3_ctx_vector
{
u32x h[8];
u32x w0[4];
u32x w1[4];
u32x w2[4];
u32x w3[4];
int len;
} sm3_ctx_vector_t;
DECLSPEC void sm3_transform (PRIVATE_AS const u32 *w0, PRIVATE_AS const u32 *w1, PRIVATE_AS const u32 *w2, PRIVATE_AS const u32 *w3, PRIVATE_AS u32 *digest);
DECLSPEC void sm3_init (PRIVATE_AS sm3_ctx_t *ctx);
DECLSPEC void sm3_update_64 (PRIVATE_AS sm3_ctx_t *ctx, PRIVATE_AS u32 *w0, PRIVATE_AS u32 *w1, PRIVATE_AS u32 *w2, PRIVATE_AS u32 *w3, const int len);
DECLSPEC void sm3_update (PRIVATE_AS sm3_ctx_t *ctx, PRIVATE_AS const u32 *w, const int len);
DECLSPEC void sm3_update_swap (PRIVATE_AS sm3_ctx_t *ctx, PRIVATE_AS const u32 *w, const int len);
DECLSPEC void sm3_update_utf16le (PRIVATE_AS sm3_ctx_t *ctx, PRIVATE_AS const u32 *w, const int len);
DECLSPEC void sm3_update_utf16le_swap (PRIVATE_AS sm3_ctx_t *ctx, PRIVATE_AS const u32 *w, const int len);
DECLSPEC void sm3_update_global (PRIVATE_AS sm3_ctx_t *ctx, GLOBAL_AS const u32 *w, const int len);
DECLSPEC void sm3_update_global_swap (PRIVATE_AS sm3_ctx_t *ctx, GLOBAL_AS const u32 *w, const int len);
DECLSPEC void sm3_update_global_utf16le (PRIVATE_AS sm3_ctx_t *ctx, GLOBAL_AS const u32 *w, const int len);
DECLSPEC void sm3_update_global_utf16le_swap (PRIVATE_AS sm3_ctx_t *ctx, GLOBAL_AS const u32 *w, const int len);
DECLSPEC void sm3_final (PRIVATE_AS sm3_ctx_t *ctx);
DECLSPEC void sm3_transform_vector (PRIVATE_AS const u32x *w0, PRIVATE_AS const u32x *w1, PRIVATE_AS const u32x *w2, PRIVATE_AS const u32x *w3, PRIVATE_AS u32x *digest);
DECLSPEC void sm3_init_vector (PRIVATE_AS sm3_ctx_vector_t *ctx);
DECLSPEC void sm3_init_vector_from_scalar (PRIVATE_AS sm3_ctx_vector_t *ctx, PRIVATE_AS sm3_ctx_t *ctx0);
DECLSPEC void sm3_update_vector_64 (PRIVATE_AS sm3_ctx_vector_t *ctx, PRIVATE_AS u32x *w0, PRIVATE_AS u32x *w1, PRIVATE_AS u32x *w2, PRIVATE_AS u32x *w3, const int len);
DECLSPEC void sm3_update_vector (PRIVATE_AS sm3_ctx_vector_t *ctx, PRIVATE_AS const u32x *w, const int len);
DECLSPEC void sm3_update_vector_swap (PRIVATE_AS sm3_ctx_vector_t *ctx, PRIVATE_AS const u32x *w, const int len);
DECLSPEC void sm3_update_vector_utf16le (PRIVATE_AS sm3_ctx_vector_t *ctx, PRIVATE_AS const u32x *w, const int len);
DECLSPEC void sm3_update_vector_utf16le_swap (PRIVATE_AS sm3_ctx_vector_t *ctx, PRIVATE_AS const u32x *w, const int len);
DECLSPEC void sm3_update_vector_utf16beN (PRIVATE_AS sm3_ctx_vector_t *ctx, PRIVATE_AS const u32x *w, const int len);
DECLSPEC void sm3_final_vector (PRIVATE_AS sm3_ctx_vector_t *ctx);
#endif

80
OpenCL/inc_types.h
View File

@ -1679,6 +1679,86 @@ typedef enum blake2s_constants
} blake2s_constants_t;
typedef enum sm3_constants
{
// SM3 Initial Hash Values
SM3_IV_A=0x7380166fUL,
SM3_IV_B=0x4914b2b9UL,
SM3_IV_C=0x172442d7UL,
SM3_IV_D=0xda8a0600UL,
SM3_IV_E=0xa96f30bcUL,
SM3_IV_F=0x163138aaUL,
SM3_IV_G=0xe38dee4dUL,
SM3_IV_H=0xb0fb0e4eUL,
// SM3 Tj round constants
SM3_T00=0x79CC4519UL,
SM3_T01=0xF3988A32UL,
SM3_T02=0xE7311465UL,
SM3_T03=0xCE6228CBUL,
SM3_T04=0x9CC45197UL,
SM3_T05=0x3988A32FUL,
SM3_T06=0x7311465EUL,
SM3_T07=0xE6228CBCUL,
SM3_T08=0xCC451979UL,
SM3_T09=0x988A32F3UL,
SM3_T10=0x311465E7UL,
SM3_T11=0x6228CBCEUL,
SM3_T12=0xC451979CUL,
SM3_T13=0x88A32F39UL,
SM3_T14=0x11465E73UL,
SM3_T15=0x228CBCE6UL,
SM3_T16=0x9D8A7A87UL,
SM3_T17=0x3B14F50FUL,
SM3_T18=0x7629EA1EUL,
SM3_T19=0xEC53D43CUL,
SM3_T20=0xD8A7A879UL,
SM3_T21=0xB14F50F3UL,
SM3_T22=0x629EA1E7UL,
SM3_T23=0xC53D43CEUL,
SM3_T24=0x8A7A879DUL,
SM3_T25=0x14F50F3BUL,
SM3_T26=0x29EA1E76UL,
SM3_T27=0x53D43CECUL,
SM3_T28=0xA7A879D8UL,
SM3_T29=0x4F50F3B1UL,
SM3_T30=0x9EA1E762UL,
SM3_T31=0x3D43CEC5UL,
SM3_T32=0x7A879D8AUL,
SM3_T33=0xF50F3B14UL,
SM3_T34=0xEA1E7629UL,
SM3_T35=0xD43CEC53UL,
SM3_T36=0xA879D8A7UL,
SM3_T37=0x50F3B14FUL,
SM3_T38=0xA1E7629EUL,
SM3_T39=0x43CEC53DUL,
SM3_T40=0x879D8A7AUL,
SM3_T41=0x0F3B14F5UL,
SM3_T42=0x1E7629EAUL,
SM3_T43=0x3CEC53D4UL,
SM3_T44=0x79D8A7A8UL,
SM3_T45=0xF3B14F50UL,
SM3_T46=0xE7629EA1UL,
SM3_T47=0xCEC53D43UL,
SM3_T48=0x9D8A7A87UL,
SM3_T49=0x3B14F50FUL,
SM3_T50=0x7629EA1EUL,
SM3_T51=0xEC53D43CUL,
SM3_T52=0xD8A7A879UL,
SM3_T53=0xB14F50F3UL,
SM3_T54=0x629EA1E7UL,
SM3_T55=0xC53D43CEUL,
SM3_T56=0x8A7A879DUL,
SM3_T57=0x14F50F3BUL,
SM3_T58=0x29EA1E76UL,
SM3_T59=0x53D43CECUL,
SM3_T60=0xA7A879D8UL,
SM3_T61=0x4F50F3B1UL,
SM3_T62=0x9EA1E762UL,
SM3_T63=0x3D43CEC5UL
} sm3_constants_t;
typedef enum combinator_mode
{
COMBINATOR_MODE_BASE_LEFT = 10001,

339
OpenCL/m31100_a0-optimized.cl Normal file
View File

@ -0,0 +1,339 @@
/**
* Author......: See docs/credits.txt
* License.....: MIT
*/
#define NEW_SIMD_CODE
#ifdef KERNEL_STATIC
#include M2S(INCLUDE_PATH/inc_vendor.h)
#include M2S(INCLUDE_PATH/inc_types.h)
#include M2S(INCLUDE_PATH/inc_platform.cl)
#include M2S(INCLUDE_PATH/inc_common.cl)
#include M2S(INCLUDE_PATH/inc_rp_optimized.h)
#include M2S(INCLUDE_PATH/inc_rp_optimized.cl)
#include M2S(INCLUDE_PATH/inc_simd.cl)
#include M2S(INCLUDE_PATH/inc_hash_sm3.cl)
#endif
KERNEL_FQ void m31100_m04 (KERN_ATTR_RULES ())
{
/**
* modifier
*/
const u64 lid = get_local_id (0);
/**
* base
*/
const u64 gid = get_global_id (0);
if (gid >= GID_CNT) return;
u32 pw_buf0[4];
u32 pw_buf1[4];
pw_buf0[0] = pws[gid].i[0];
pw_buf0[1] = pws[gid].i[1];
pw_buf0[2] = pws[gid].i[2];
pw_buf0[3] = pws[gid].i[3];
pw_buf1[0] = pws[gid].i[4];
pw_buf1[1] = pws[gid].i[5];
pw_buf1[2] = pws[gid].i[6];
pw_buf1[3] = pws[gid].i[7];
const u32 pw_len = pws[gid].pw_len & 63;
/**
* loop
*/
for (u32 il_pos = 0; il_pos < IL_CNT; il_pos += VECT_SIZE)
{
u32x w0[4] = { 0 };
u32x w1[4] = { 0 };
u32x w2[4] = { 0 };
u32x w3[4] = { 0 };
const u32x out_len = apply_rules_vect_optimized (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
append_0x80_2x4_VV (w0, w1, out_len);
/**
* sm3
*/
u32x w0_t = hc_swap32 (w0[0]);
u32x w1_t = hc_swap32 (w0[1]);
u32x w2_t = hc_swap32 (w0[2]);
u32x w3_t = hc_swap32 (w0[3]);
u32x w4_t = hc_swap32 (w1[0]);
u32x w5_t = hc_swap32 (w1[1]);
u32x w6_t = hc_swap32 (w1[2]);
u32x w7_t = hc_swap32 (w1[3]);
u32x w8_t = hc_swap32 (w2[0]);
u32x w9_t = hc_swap32 (w2[1]);
u32x wa_t = hc_swap32 (w2[2]);
u32x wb_t = hc_swap32 (w2[3]);
u32x wc_t = hc_swap32 (w3[0]);
u32x wd_t = hc_swap32 (w3[1]);
u32x we_t = 0;
u32x wf_t = out_len * 8;
u32x a = SM3_IV_A;
u32x b = SM3_IV_B;
u32x c = SM3_IV_C;
u32x d = SM3_IV_D;
u32x e = SM3_IV_E;
u32x f = SM3_IV_F;
u32x g = SM3_IV_G;
u32x h = SM3_IV_H;
SM3_ROUND1(a, b, c, d, e, f, g, h, SM3_T00, w0_t, w0_t ^ w4_t);
SM3_ROUND1(d, a, b, c, h, e, f, g, SM3_T01, w1_t, w1_t ^ w5_t);
SM3_ROUND1(c, d, a, b, g, h, e, f, SM3_T02, w2_t, w2_t ^ w6_t);
SM3_ROUND1(b, c, d, a, f, g, h, e, SM3_T03, w3_t, w3_t ^ w7_t);
SM3_ROUND1(a, b, c, d, e, f, g, h, SM3_T04, w4_t, w4_t ^ w8_t);
SM3_ROUND1(d, a, b, c, h, e, f, g, SM3_T05, w5_t, w5_t ^ w9_t);
SM3_ROUND1(c, d, a, b, g, h, e, f, SM3_T06, w6_t, w6_t ^ wa_t);
SM3_ROUND1(b, c, d, a, f, g, h, e, SM3_T07, w7_t, w7_t ^ wb_t);
SM3_ROUND1(a, b, c, d, e, f, g, h, SM3_T08, w8_t, w8_t ^ wc_t);
SM3_ROUND1(d, a, b, c, h, e, f, g, SM3_T09, w9_t, w9_t ^ wd_t);
SM3_ROUND1(c, d, a, b, g, h, e, f, SM3_T10, wa_t, wa_t ^ we_t);
SM3_ROUND1(b, c, d, a, f, g, h, e, SM3_T11, wb_t, wb_t ^ wf_t);
w0_t = SM3_EXPAND(w0_t, w7_t, wd_t, w3_t, wa_t); SM3_ROUND1(a, b, c, d, e, f, g, h, SM3_T12, wc_t, wc_t ^ w0_t);
w1_t = SM3_EXPAND(w1_t, w8_t, we_t, w4_t, wb_t); SM3_ROUND1(d, a, b, c, h, e, f, g, SM3_T13, wd_t, wd_t ^ w1_t);
w2_t = SM3_EXPAND(w2_t, w9_t, wf_t, w5_t, wc_t); SM3_ROUND1(c, d, a, b, g, h, e, f, SM3_T14, we_t, we_t ^ w2_t);
w3_t = SM3_EXPAND(w3_t, wa_t, w0_t, w6_t, wd_t); SM3_ROUND1(b, c, d, a, f, g, h, e, SM3_T15, wf_t, wf_t ^ w3_t);
w4_t = SM3_EXPAND(w4_t, wb_t, w1_t, w7_t, we_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T16, w0_t, w0_t ^ w4_t);
w5_t = SM3_EXPAND(w5_t, wc_t, w2_t, w8_t, wf_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T17, w1_t, w1_t ^ w5_t);
w6_t = SM3_EXPAND(w6_t, wd_t, w3_t, w9_t, w0_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T18, w2_t, w2_t ^ w6_t);
w7_t = SM3_EXPAND(w7_t, we_t, w4_t, wa_t, w1_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T19, w3_t, w3_t ^ w7_t);
w8_t = SM3_EXPAND(w8_t, wf_t, w5_t, wb_t, w2_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T20, w4_t, w4_t ^ w8_t);
w9_t = SM3_EXPAND(w9_t, w0_t, w6_t, wc_t, w3_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T21, w5_t, w5_t ^ w9_t);
wa_t = SM3_EXPAND(wa_t, w1_t, w7_t, wd_t, w4_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T22, w6_t, w6_t ^ wa_t);
wb_t = SM3_EXPAND(wb_t, w2_t, w8_t, we_t, w5_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T23, w7_t, w7_t ^ wb_t);
wc_t = SM3_EXPAND(wc_t, w3_t, w9_t, wf_t, w6_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T24, w8_t, w8_t ^ wc_t);
wd_t = SM3_EXPAND(wd_t, w4_t, wa_t, w0_t, w7_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T25, w9_t, w9_t ^ wd_t);
we_t = SM3_EXPAND(we_t, w5_t, wb_t, w1_t, w8_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T26, wa_t, wa_t ^ we_t);
wf_t = SM3_EXPAND(wf_t, w6_t, wc_t, w2_t, w9_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T27, wb_t, wb_t ^ wf_t);
w0_t = SM3_EXPAND(w0_t, w7_t, wd_t, w3_t, wa_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T28, wc_t, wc_t ^ w0_t);
w1_t = SM3_EXPAND(w1_t, w8_t, we_t, w4_t, wb_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T29, wd_t, wd_t ^ w1_t);
w2_t = SM3_EXPAND(w2_t, w9_t, wf_t, w5_t, wc_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T30, we_t, we_t ^ w2_t);
w3_t = SM3_EXPAND(w3_t, wa_t, w0_t, w6_t, wd_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T31, wf_t, wf_t ^ w3_t);
w4_t = SM3_EXPAND(w4_t, wb_t, w1_t, w7_t, we_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T32, w0_t, w0_t ^ w4_t);
w5_t = SM3_EXPAND(w5_t, wc_t, w2_t, w8_t, wf_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T33, w1_t, w1_t ^ w5_t);
w6_t = SM3_EXPAND(w6_t, wd_t, w3_t, w9_t, w0_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T34, w2_t, w2_t ^ w6_t);
w7_t = SM3_EXPAND(w7_t, we_t, w4_t, wa_t, w1_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T35, w3_t, w3_t ^ w7_t);
w8_t = SM3_EXPAND(w8_t, wf_t, w5_t, wb_t, w2_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T36, w4_t, w4_t ^ w8_t);
w9_t = SM3_EXPAND(w9_t, w0_t, w6_t, wc_t, w3_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T37, w5_t, w5_t ^ w9_t);
wa_t = SM3_EXPAND(wa_t, w1_t, w7_t, wd_t, w4_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T38, w6_t, w6_t ^ wa_t);
wb_t = SM3_EXPAND(wb_t, w2_t, w8_t, we_t, w5_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T39, w7_t, w7_t ^ wb_t);
wc_t = SM3_EXPAND(wc_t, w3_t, w9_t, wf_t, w6_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T40, w8_t, w8_t ^ wc_t);
wd_t = SM3_EXPAND(wd_t, w4_t, wa_t, w0_t, w7_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T41, w9_t, w9_t ^ wd_t);
we_t = SM3_EXPAND(we_t, w5_t, wb_t, w1_t, w8_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T42, wa_t, wa_t ^ we_t);
wf_t = SM3_EXPAND(wf_t, w6_t, wc_t, w2_t, w9_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T43, wb_t, wb_t ^ wf_t);
w0_t = SM3_EXPAND(w0_t, w7_t, wd_t, w3_t, wa_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T44, wc_t, wc_t ^ w0_t);
w1_t = SM3_EXPAND(w1_t, w8_t, we_t, w4_t, wb_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T45, wd_t, wd_t ^ w1_t);
w2_t = SM3_EXPAND(w2_t, w9_t, wf_t, w5_t, wc_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T46, we_t, we_t ^ w2_t);
w3_t = SM3_EXPAND(w3_t, wa_t, w0_t, w6_t, wd_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T47, wf_t, wf_t ^ w3_t);
w4_t = SM3_EXPAND(w4_t, wb_t, w1_t, w7_t, we_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T48, w0_t, w0_t ^ w4_t);
w5_t = SM3_EXPAND(w5_t, wc_t, w2_t, w8_t, wf_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T49, w1_t, w1_t ^ w5_t);
w6_t = SM3_EXPAND(w6_t, wd_t, w3_t, w9_t, w0_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T50, w2_t, w2_t ^ w6_t);
w7_t = SM3_EXPAND(w7_t, we_t, w4_t, wa_t, w1_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T51, w3_t, w3_t ^ w7_t);
w8_t = SM3_EXPAND(w8_t, wf_t, w5_t, wb_t, w2_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T52, w4_t, w4_t ^ w8_t);
w9_t = SM3_EXPAND(w9_t, w0_t, w6_t, wc_t, w3_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T53, w5_t, w5_t ^ w9_t);
wa_t = SM3_EXPAND(wa_t, w1_t, w7_t, wd_t, w4_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T54, w6_t, w6_t ^ wa_t);
wb_t = SM3_EXPAND(wb_t, w2_t, w8_t, we_t, w5_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T55, w7_t, w7_t ^ wb_t);
wc_t = SM3_EXPAND(wc_t, w3_t, w9_t, wf_t, w6_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T56, w8_t, w8_t ^ wc_t);
wd_t = SM3_EXPAND(wd_t, w4_t, wa_t, w0_t, w7_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T57, w9_t, w9_t ^ wd_t);
we_t = SM3_EXPAND(we_t, w5_t, wb_t, w1_t, w8_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T58, wa_t, wa_t ^ we_t);
wf_t = SM3_EXPAND(wf_t, w6_t, wc_t, w2_t, w9_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T59, wb_t, wb_t ^ wf_t);
w0_t = SM3_EXPAND(w0_t, w7_t, wd_t, w3_t, wa_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T60, wc_t, wc_t ^ w0_t);
w1_t = SM3_EXPAND(w1_t, w8_t, we_t, w4_t, wb_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T61, wd_t, wd_t ^ w1_t);
w2_t = SM3_EXPAND(w2_t, w9_t, wf_t, w5_t, wc_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T62, we_t, we_t ^ w2_t);
w3_t = SM3_EXPAND(w3_t, wa_t, w0_t, w6_t, wd_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T63, wf_t, wf_t ^ w3_t);
COMPARE_M_SIMD (d, h, c, g);
}
}
KERNEL_FQ void m31100_m08 (KERN_ATTR_RULES ())
{
}
KERNEL_FQ void m31100_m16 (KERN_ATTR_RULES ())
{
}
KERNEL_FQ void m31100_s04 (KERN_ATTR_RULES ())
{
/**
* modifier
*/
const u64 lid = get_local_id (0);
/**
* base
*/
const u64 gid = get_global_id (0);
if (gid >= GID_CNT) return;
u32 pw_buf0[4];
u32 pw_buf1[4];
pw_buf0[0] = pws[gid].i[0];
pw_buf0[1] = pws[gid].i[1];
pw_buf0[2] = pws[gid].i[2];
pw_buf0[3] = pws[gid].i[3];
pw_buf1[0] = pws[gid].i[4];
pw_buf1[1] = pws[gid].i[5];
pw_buf1[2] = pws[gid].i[6];
pw_buf1[3] = pws[gid].i[7];
const u32 pw_len = pws[gid].pw_len & 63;
/**
* digest
*/
const u32 search[4] =
{
digests_buf[DIGESTS_OFFSET_HOST].digest_buf[DGST_R0],
digests_buf[DIGESTS_OFFSET_HOST].digest_buf[DGST_R1],
digests_buf[DIGESTS_OFFSET_HOST].digest_buf[DGST_R2],
digests_buf[DIGESTS_OFFSET_HOST].digest_buf[DGST_R3]
};
/**
* loop
*/
for (u32 il_pos = 0; il_pos < IL_CNT; il_pos += VECT_SIZE)
{
u32x w0[4] = { 0 };
u32x w1[4] = { 0 };
u32x w2[4] = { 0 };
u32x w3[4] = { 0 };
const u32x out_len = apply_rules_vect_optimized (pw_buf0, pw_buf1, pw_len, rules_buf, il_pos, w0, w1);
append_0x80_2x4_VV (w0, w1, out_len);
/**
* sm3
*/
u32x w0_t = hc_swap32 (w0[0]);
u32x w1_t = hc_swap32 (w0[1]);
u32x w2_t = hc_swap32 (w0[2]);
u32x w3_t = hc_swap32 (w0[3]);
u32x w4_t = hc_swap32 (w1[0]);
u32x w5_t = hc_swap32 (w1[1]);
u32x w6_t = hc_swap32 (w1[2]);
u32x w7_t = hc_swap32 (w1[3]);
u32x w8_t = hc_swap32 (w2[0]);
u32x w9_t = hc_swap32 (w2[1]);
u32x wa_t = hc_swap32 (w2[2]);
u32x wb_t = hc_swap32 (w2[3]);
u32x wc_t = hc_swap32 (w3[0]);
u32x wd_t = hc_swap32 (w3[1]);
u32x we_t = 0;
u32x wf_t = out_len * 8;
u32x a = SM3_IV_A;
u32x b = SM3_IV_B;
u32x c = SM3_IV_C;
u32x d = SM3_IV_D;
u32x e = SM3_IV_E;
u32x f = SM3_IV_F;
u32x g = SM3_IV_G;
u32x h = SM3_IV_H;
SM3_ROUND1(a, b, c, d, e, f, g, h, SM3_T00, w0_t, w0_t ^ w4_t);
SM3_ROUND1(d, a, b, c, h, e, f, g, SM3_T01, w1_t, w1_t ^ w5_t);
SM3_ROUND1(c, d, a, b, g, h, e, f, SM3_T02, w2_t, w2_t ^ w6_t);
SM3_ROUND1(b, c, d, a, f, g, h, e, SM3_T03, w3_t, w3_t ^ w7_t);
SM3_ROUND1(a, b, c, d, e, f, g, h, SM3_T04, w4_t, w4_t ^ w8_t);
SM3_ROUND1(d, a, b, c, h, e, f, g, SM3_T05, w5_t, w5_t ^ w9_t);
SM3_ROUND1(c, d, a, b, g, h, e, f, SM3_T06, w6_t, w6_t ^ wa_t);
SM3_ROUND1(b, c, d, a, f, g, h, e, SM3_T07, w7_t, w7_t ^ wb_t);
SM3_ROUND1(a, b, c, d, e, f, g, h, SM3_T08, w8_t, w8_t ^ wc_t);
SM3_ROUND1(d, a, b, c, h, e, f, g, SM3_T09, w9_t, w9_t ^ wd_t);
SM3_ROUND1(c, d, a, b, g, h, e, f, SM3_T10, wa_t, wa_t ^ we_t);
SM3_ROUND1(b, c, d, a, f, g, h, e, SM3_T11, wb_t, wb_t ^ wf_t);
w0_t = SM3_EXPAND(w0_t, w7_t, wd_t, w3_t, wa_t); SM3_ROUND1(a, b, c, d, e, f, g, h, SM3_T12, wc_t, wc_t ^ w0_t);
w1_t = SM3_EXPAND(w1_t, w8_t, we_t, w4_t, wb_t); SM3_ROUND1(d, a, b, c, h, e, f, g, SM3_T13, wd_t, wd_t ^ w1_t);
w2_t = SM3_EXPAND(w2_t, w9_t, wf_t, w5_t, wc_t); SM3_ROUND1(c, d, a, b, g, h, e, f, SM3_T14, we_t, we_t ^ w2_t);
w3_t = SM3_EXPAND(w3_t, wa_t, w0_t, w6_t, wd_t); SM3_ROUND1(b, c, d, a, f, g, h, e, SM3_T15, wf_t, wf_t ^ w3_t);
w4_t = SM3_EXPAND(w4_t, wb_t, w1_t, w7_t, we_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T16, w0_t, w0_t ^ w4_t);
w5_t = SM3_EXPAND(w5_t, wc_t, w2_t, w8_t, wf_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T17, w1_t, w1_t ^ w5_t);
w6_t = SM3_EXPAND(w6_t, wd_t, w3_t, w9_t, w0_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T18, w2_t, w2_t ^ w6_t);
w7_t = SM3_EXPAND(w7_t, we_t, w4_t, wa_t, w1_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T19, w3_t, w3_t ^ w7_t);
w8_t = SM3_EXPAND(w8_t, wf_t, w5_t, wb_t, w2_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T20, w4_t, w4_t ^ w8_t);
w9_t = SM3_EXPAND(w9_t, w0_t, w6_t, wc_t, w3_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T21, w5_t, w5_t ^ w9_t);
wa_t = SM3_EXPAND(wa_t, w1_t, w7_t, wd_t, w4_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T22, w6_t, w6_t ^ wa_t);
wb_t = SM3_EXPAND(wb_t, w2_t, w8_t, we_t, w5_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T23, w7_t, w7_t ^ wb_t);
wc_t = SM3_EXPAND(wc_t, w3_t, w9_t, wf_t, w6_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T24, w8_t, w8_t ^ wc_t);
wd_t = SM3_EXPAND(wd_t, w4_t, wa_t, w0_t, w7_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T25, w9_t, w9_t ^ wd_t);
we_t = SM3_EXPAND(we_t, w5_t, wb_t, w1_t, w8_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T26, wa_t, wa_t ^ we_t);
wf_t = SM3_EXPAND(wf_t, w6_t, wc_t, w2_t, w9_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T27, wb_t, wb_t ^ wf_t);
w0_t = SM3_EXPAND(w0_t, w7_t, wd_t, w3_t, wa_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T28, wc_t, wc_t ^ w0_t);
w1_t = SM3_EXPAND(w1_t, w8_t, we_t, w4_t, wb_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T29, wd_t, wd_t ^ w1_t);
w2_t = SM3_EXPAND(w2_t, w9_t, wf_t, w5_t, wc_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T30, we_t, we_t ^ w2_t);
w3_t = SM3_EXPAND(w3_t, wa_t, w0_t, w6_t, wd_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T31, wf_t, wf_t ^ w3_t);
w4_t = SM3_EXPAND(w4_t, wb_t, w1_t, w7_t, we_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T32, w0_t, w0_t ^ w4_t);
w5_t = SM3_EXPAND(w5_t, wc_t, w2_t, w8_t, wf_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T33, w1_t, w1_t ^ w5_t);
w6_t = SM3_EXPAND(w6_t, wd_t, w3_t, w9_t, w0_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T34, w2_t, w2_t ^ w6_t);
w7_t = SM3_EXPAND(w7_t, we_t, w4_t, wa_t, w1_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T35, w3_t, w3_t ^ w7_t);
w8_t = SM3_EXPAND(w8_t, wf_t, w5_t, wb_t, w2_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T36, w4_t, w4_t ^ w8_t);
w9_t = SM3_EXPAND(w9_t, w0_t, w6_t, wc_t, w3_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T37, w5_t, w5_t ^ w9_t);
wa_t = SM3_EXPAND(wa_t, w1_t, w7_t, wd_t, w4_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T38, w6_t, w6_t ^ wa_t);
wb_t = SM3_EXPAND(wb_t, w2_t, w8_t, we_t, w5_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T39, w7_t, w7_t ^ wb_t);
wc_t = SM3_EXPAND(wc_t, w3_t, w9_t, wf_t, w6_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T40, w8_t, w8_t ^ wc_t);
wd_t = SM3_EXPAND(wd_t, w4_t, wa_t, w0_t, w7_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T41, w9_t, w9_t ^ wd_t);
we_t = SM3_EXPAND(we_t, w5_t, wb_t, w1_t, w8_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T42, wa_t, wa_t ^ we_t);
wf_t = SM3_EXPAND(wf_t, w6_t, wc_t, w2_t, w9_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T43, wb_t, wb_t ^ wf_t);
w0_t = SM3_EXPAND(w0_t, w7_t, wd_t, w3_t, wa_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T44, wc_t, wc_t ^ w0_t);
w1_t = SM3_EXPAND(w1_t, w8_t, we_t, w4_t, wb_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T45, wd_t, wd_t ^ w1_t);
w2_t = SM3_EXPAND(w2_t, w9_t, wf_t, w5_t, wc_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T46, we_t, we_t ^ w2_t);
w3_t = SM3_EXPAND(w3_t, wa_t, w0_t, w6_t, wd_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T47, wf_t, wf_t ^ w3_t);
w4_t = SM3_EXPAND(w4_t, wb_t, w1_t, w7_t, we_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T48, w0_t, w0_t ^ w4_t);
w5_t = SM3_EXPAND(w5_t, wc_t, w2_t, w8_t, wf_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T49, w1_t, w1_t ^ w5_t);
w6_t = SM3_EXPAND(w6_t, wd_t, w3_t, w9_t, w0_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T50, w2_t, w2_t ^ w6_t);
w7_t = SM3_EXPAND(w7_t, we_t, w4_t, wa_t, w1_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T51, w3_t, w3_t ^ w7_t);
w8_t = SM3_EXPAND(w8_t, wf_t, w5_t, wb_t, w2_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T52, w4_t, w4_t ^ w8_t);
w9_t = SM3_EXPAND(w9_t, w0_t, w6_t, wc_t, w3_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T53, w5_t, w5_t ^ w9_t);
wa_t = SM3_EXPAND(wa_t, w1_t, w7_t, wd_t, w4_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T54, w6_t, w6_t ^ wa_t);
wb_t = SM3_EXPAND(wb_t, w2_t, w8_t, we_t, w5_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T55, w7_t, w7_t ^ wb_t);
wc_t = SM3_EXPAND(wc_t, w3_t, w9_t, wf_t, w6_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T56, w8_t, w8_t ^ wc_t);
wd_t = SM3_EXPAND(wd_t, w4_t, wa_t, w0_t, w7_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T57, w9_t, w9_t ^ wd_t);
we_t = SM3_EXPAND(we_t, w5_t, wb_t, w1_t, w8_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T58, wa_t, wa_t ^ we_t);
wf_t = SM3_EXPAND(wf_t, w6_t, wc_t, w2_t, w9_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T59, wb_t, wb_t ^ wf_t);
w0_t = SM3_EXPAND(w0_t, w7_t, wd_t, w3_t, wa_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T60, wc_t, wc_t ^ w0_t);
w1_t = SM3_EXPAND(w1_t, w8_t, we_t, w4_t, wb_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T61, wd_t, wd_t ^ w1_t);
w2_t = SM3_EXPAND(w2_t, w9_t, wf_t, w5_t, wc_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T62, we_t, we_t ^ w2_t);
w3_t = SM3_EXPAND(w3_t, wa_t, w0_t, w6_t, wd_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T63, wf_t, wf_t ^ w3_t);
COMPARE_S_SIMD (d, h, c, g);
}
}
KERNEL_FQ void m31100_s08 (KERN_ATTR_RULES ())
{
}
KERNEL_FQ void m31100_s16 (KERN_ATTR_RULES ())
{
}

117
OpenCL/m31100_a0-pure.cl Normal file
View File

@ -0,0 +1,117 @@
/**
* Author......: See docs/credits.txt
* License.....: MIT
*/
//#define NEW_SIMD_CODE
#ifdef KERNEL_STATIC
#include M2S(INCLUDE_PATH/inc_vendor.h)
#include M2S(INCLUDE_PATH/inc_types.h)
#include M2S(INCLUDE_PATH/inc_platform.cl)
#include M2S(INCLUDE_PATH/inc_common.cl)
#include M2S(INCLUDE_PATH/inc_rp.h)
#include M2S(INCLUDE_PATH/inc_rp.cl)
#include M2S(INCLUDE_PATH/inc_scalar.cl)
#include M2S(INCLUDE_PATH/inc_hash_sm3.cl)
#endif
KERNEL_FQ void m31100_mxx (KERN_ATTR_RULES ())
{
/**
* modifier
*/
const u64 lid = get_local_id (0);
const u64 gid = get_global_id (0);
if (gid >= GID_CNT) return;
/**
* base
*/
COPY_PW (pws[gid]);
/**
* loop
*/
for (u32 il_pos = 0; il_pos < IL_CNT; il_pos++)
{
pw_t tmp = PASTE_PW;
tmp.pw_len = apply_rules (rules_buf[il_pos].cmds, tmp.i, tmp.pw_len);
sm3_ctx_t ctx;
sm3_init (&ctx);
sm3_update_swap (&ctx, tmp.i, tmp.pw_len);
sm3_final (&ctx);
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_SCALAR (r0, r1, r2, r3);
}
}
KERNEL_FQ void m31100_sxx (KERN_ATTR_RULES ())
{
/**
* modifier
*/
const u64 lid = get_local_id (0);
const u64 gid = get_global_id (0);
if (gid >= GID_CNT) return;
/**
* digest
*/
const u32 search[4] =
{
digests_buf[DIGESTS_OFFSET_HOST].digest_buf[DGST_R0],
digests_buf[DIGESTS_OFFSET_HOST].digest_buf[DGST_R1],
digests_buf[DIGESTS_OFFSET_HOST].digest_buf[DGST_R2],
digests_buf[DIGESTS_OFFSET_HOST].digest_buf[DGST_R3]
};
/**
* base
*/
COPY_PW (pws[gid]);
/**
* loop
*/
for (u32 il_pos = 0; il_pos < IL_CNT; il_pos++)
{
pw_t tmp = PASTE_PW;
tmp.pw_len = apply_rules (rules_buf[il_pos].cmds, tmp.i, tmp.pw_len);
sm3_ctx_t ctx;
sm3_init (&ctx);
sm3_update_swap (&ctx, tmp.i, tmp.pw_len);
sm3_final (&ctx);
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_SCALAR (r0, r1, r2, r3);
}
}

453
OpenCL/m31100_a1-optimized.cl Normal file
View File

@ -0,0 +1,453 @@
/**
* Author......: See docs/credits.txt
* License.....: MIT
*/
#define NEW_SIMD_CODE
#ifdef KERNEL_STATIC
#include M2S(INCLUDE_PATH/inc_vendor.h)
#include M2S(INCLUDE_PATH/inc_types.h)
#include M2S(INCLUDE_PATH/inc_platform.cl)
#include M2S(INCLUDE_PATH/inc_common.cl)
#include M2S(INCLUDE_PATH/inc_simd.cl)
#include M2S(INCLUDE_PATH/inc_hash_sm3.cl)
#endif
KERNEL_FQ void m31100_m04 (KERN_ATTR_BASIC ())
{
/**
* modifier
*/
const u64 lid = get_local_id (0);
/**
* base
*/
const u64 gid = get_global_id (0);
if (gid >= GID_CNT) return;
u32 pw_buf0[4];
u32 pw_buf1[4];
pw_buf0[0] = pws[gid].i[0];
pw_buf0[1] = pws[gid].i[1];
pw_buf0[2] = pws[gid].i[2];
pw_buf0[3] = pws[gid].i[3];
pw_buf1[0] = pws[gid].i[4];
pw_buf1[1] = pws[gid].i[5];
pw_buf1[2] = pws[gid].i[6];
pw_buf1[3] = pws[gid].i[7];
const u32 pw_l_len = pws[gid].pw_len & 63;
/**
* loop
*/
for (u32 il_pos = 0; il_pos < IL_CNT; il_pos += VECT_SIZE)
{
const u32x pw_r_len = pwlenx_create_combt (combs_buf, il_pos) & 63;
const u32x pw_len = (pw_l_len + pw_r_len) & 63;
/**
* concat password candidate
*/
u32x wordl0[4] = { 0 };
u32x wordl1[4] = { 0 };
u32x wordl2[4] = { 0 };
u32x wordl3[4] = { 0 };
wordl0[0] = pw_buf0[0];
wordl0[1] = pw_buf0[1];
wordl0[2] = pw_buf0[2];
wordl0[3] = pw_buf0[3];
wordl1[0] = pw_buf1[0];
wordl1[1] = pw_buf1[1];
wordl1[2] = pw_buf1[2];
wordl1[3] = pw_buf1[3];
u32x wordr0[4] = { 0 };
u32x wordr1[4] = { 0 };
u32x wordr2[4] = { 0 };
u32x wordr3[4] = { 0 };
wordr0[0] = ix_create_combt (combs_buf, il_pos, 0);
wordr0[1] = ix_create_combt (combs_buf, il_pos, 1);
wordr0[2] = ix_create_combt (combs_buf, il_pos, 2);
wordr0[3] = ix_create_combt (combs_buf, il_pos, 3);
wordr1[0] = ix_create_combt (combs_buf, il_pos, 4);
wordr1[1] = ix_create_combt (combs_buf, il_pos, 5);
wordr1[2] = ix_create_combt (combs_buf, il_pos, 6);
wordr1[3] = ix_create_combt (combs_buf, il_pos, 7);
if (COMBS_MODE == COMBINATOR_MODE_BASE_LEFT)
{
switch_buffer_by_offset_le_VV (wordr0, wordr1, wordr2, wordr3, pw_l_len);
}
else
{
switch_buffer_by_offset_le_VV (wordl0, wordl1, wordl2, wordl3, pw_r_len);
}
u32x w0[4];
u32x w1[4];
u32x w2[4];
u32x w3[4];
w0[0] = wordl0[0] | wordr0[0];
w0[1] = wordl0[1] | wordr0[1];
w0[2] = wordl0[2] | wordr0[2];
w0[3] = wordl0[3] | wordr0[3];
w1[0] = wordl1[0] | wordr1[0];
w1[1] = wordl1[1] | wordr1[1];
w1[2] = wordl1[2] | wordr1[2];
w1[3] = wordl1[3] | wordr1[3];
w2[0] = wordl2[0] | wordr2[0];
w2[1] = wordl2[1] | wordr2[1];
w2[2] = wordl2[2] | wordr2[2];
w2[3] = wordl2[3] | wordr2[3];
w3[0] = wordl3[0] | wordr3[0];
w3[1] = wordl3[1] | wordr3[1];
w3[2] = wordl3[2] | wordr3[2];
w3[3] = wordl3[3] | wordr3[3];
/**
* sm3
*/
u32x w0_t = hc_swap32 (w0[0]);
u32x w1_t = hc_swap32 (w0[1]);
u32x w2_t = hc_swap32 (w0[2]);
u32x w3_t = hc_swap32 (w0[3]);
u32x w4_t = hc_swap32 (w1[0]);
u32x w5_t = hc_swap32 (w1[1]);
u32x w6_t = hc_swap32 (w1[2]);
u32x w7_t = hc_swap32 (w1[3]);
u32x w8_t = hc_swap32 (w2[0]);
u32x w9_t = hc_swap32 (w2[1]);
u32x wa_t = hc_swap32 (w2[2]);
u32x wb_t = hc_swap32 (w2[3]);
u32x wc_t = hc_swap32 (w3[0]);
u32x wd_t = hc_swap32 (w3[1]);
u32x we_t = 0;
u32x wf_t = pw_len * 8;
u32x a = SM3_IV_A;
u32x b = SM3_IV_B;
u32x c = SM3_IV_C;
u32x d = SM3_IV_D;
u32x e = SM3_IV_E;
u32x f = SM3_IV_F;
u32x g = SM3_IV_G;
u32x h = SM3_IV_H;
SM3_ROUND1(a, b, c, d, e, f, g, h, SM3_T00, w0_t, w0_t ^ w4_t);
SM3_ROUND1(d, a, b, c, h, e, f, g, SM3_T01, w1_t, w1_t ^ w5_t);
SM3_ROUND1(c, d, a, b, g, h, e, f, SM3_T02, w2_t, w2_t ^ w6_t);
SM3_ROUND1(b, c, d, a, f, g, h, e, SM3_T03, w3_t, w3_t ^ w7_t);
SM3_ROUND1(a, b, c, d, e, f, g, h, SM3_T04, w4_t, w4_t ^ w8_t);
SM3_ROUND1(d, a, b, c, h, e, f, g, SM3_T05, w5_t, w5_t ^ w9_t);
SM3_ROUND1(c, d, a, b, g, h, e, f, SM3_T06, w6_t, w6_t ^ wa_t);
SM3_ROUND1(b, c, d, a, f, g, h, e, SM3_T07, w7_t, w7_t ^ wb_t);
SM3_ROUND1(a, b, c, d, e, f, g, h, SM3_T08, w8_t, w8_t ^ wc_t);
SM3_ROUND1(d, a, b, c, h, e, f, g, SM3_T09, w9_t, w9_t ^ wd_t);
SM3_ROUND1(c, d, a, b, g, h, e, f, SM3_T10, wa_t, wa_t ^ we_t);
SM3_ROUND1(b, c, d, a, f, g, h, e, SM3_T11, wb_t, wb_t ^ wf_t);
w0_t = SM3_EXPAND(w0_t, w7_t, wd_t, w3_t, wa_t); SM3_ROUND1(a, b, c, d, e, f, g, h, SM3_T12, wc_t, wc_t ^ w0_t);
w1_t = SM3_EXPAND(w1_t, w8_t, we_t, w4_t, wb_t); SM3_ROUND1(d, a, b, c, h, e, f, g, SM3_T13, wd_t, wd_t ^ w1_t);
w2_t = SM3_EXPAND(w2_t, w9_t, wf_t, w5_t, wc_t); SM3_ROUND1(c, d, a, b, g, h, e, f, SM3_T14, we_t, we_t ^ w2_t);
w3_t = SM3_EXPAND(w3_t, wa_t, w0_t, w6_t, wd_t); SM3_ROUND1(b, c, d, a, f, g, h, e, SM3_T15, wf_t, wf_t ^ w3_t);
w4_t = SM3_EXPAND(w4_t, wb_t, w1_t, w7_t, we_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T16, w0_t, w0_t ^ w4_t);
w5_t = SM3_EXPAND(w5_t, wc_t, w2_t, w8_t, wf_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T17, w1_t, w1_t ^ w5_t);
w6_t = SM3_EXPAND(w6_t, wd_t, w3_t, w9_t, w0_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T18, w2_t, w2_t ^ w6_t);
w7_t = SM3_EXPAND(w7_t, we_t, w4_t, wa_t, w1_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T19, w3_t, w3_t ^ w7_t);
w8_t = SM3_EXPAND(w8_t, wf_t, w5_t, wb_t, w2_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T20, w4_t, w4_t ^ w8_t);
w9_t = SM3_EXPAND(w9_t, w0_t, w6_t, wc_t, w3_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T21, w5_t, w5_t ^ w9_t);
wa_t = SM3_EXPAND(wa_t, w1_t, w7_t, wd_t, w4_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T22, w6_t, w6_t ^ wa_t);
wb_t = SM3_EXPAND(wb_t, w2_t, w8_t, we_t, w5_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T23, w7_t, w7_t ^ wb_t);
wc_t = SM3_EXPAND(wc_t, w3_t, w9_t, wf_t, w6_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T24, w8_t, w8_t ^ wc_t);
wd_t = SM3_EXPAND(wd_t, w4_t, wa_t, w0_t, w7_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T25, w9_t, w9_t ^ wd_t);
we_t = SM3_EXPAND(we_t, w5_t, wb_t, w1_t, w8_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T26, wa_t, wa_t ^ we_t);
wf_t = SM3_EXPAND(wf_t, w6_t, wc_t, w2_t, w9_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T27, wb_t, wb_t ^ wf_t);
w0_t = SM3_EXPAND(w0_t, w7_t, wd_t, w3_t, wa_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T28, wc_t, wc_t ^ w0_t);
w1_t = SM3_EXPAND(w1_t, w8_t, we_t, w4_t, wb_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T29, wd_t, wd_t ^ w1_t);
w2_t = SM3_EXPAND(w2_t, w9_t, wf_t, w5_t, wc_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T30, we_t, we_t ^ w2_t);
w3_t = SM3_EXPAND(w3_t, wa_t, w0_t, w6_t, wd_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T31, wf_t, wf_t ^ w3_t);
w4_t = SM3_EXPAND(w4_t, wb_t, w1_t, w7_t, we_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T32, w0_t, w0_t ^ w4_t);
w5_t = SM3_EXPAND(w5_t, wc_t, w2_t, w8_t, wf_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T33, w1_t, w1_t ^ w5_t);
w6_t = SM3_EXPAND(w6_t, wd_t, w3_t, w9_t, w0_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T34, w2_t, w2_t ^ w6_t);
w7_t = SM3_EXPAND(w7_t, we_t, w4_t, wa_t, w1_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T35, w3_t, w3_t ^ w7_t);
w8_t = SM3_EXPAND(w8_t, wf_t, w5_t, wb_t, w2_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T36, w4_t, w4_t ^ w8_t);
w9_t = SM3_EXPAND(w9_t, w0_t, w6_t, wc_t, w3_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T37, w5_t, w5_t ^ w9_t);
wa_t = SM3_EXPAND(wa_t, w1_t, w7_t, wd_t, w4_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T38, w6_t, w6_t ^ wa_t);
wb_t = SM3_EXPAND(wb_t, w2_t, w8_t, we_t, w5_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T39, w7_t, w7_t ^ wb_t);
wc_t = SM3_EXPAND(wc_t, w3_t, w9_t, wf_t, w6_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T40, w8_t, w8_t ^ wc_t);
wd_t = SM3_EXPAND(wd_t, w4_t, wa_t, w0_t, w7_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T41, w9_t, w9_t ^ wd_t);
we_t = SM3_EXPAND(we_t, w5_t, wb_t, w1_t, w8_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T42, wa_t, wa_t ^ we_t);
wf_t = SM3_EXPAND(wf_t, w6_t, wc_t, w2_t, w9_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T43, wb_t, wb_t ^ wf_t);
w0_t = SM3_EXPAND(w0_t, w7_t, wd_t, w3_t, wa_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T44, wc_t, wc_t ^ w0_t);
w1_t = SM3_EXPAND(w1_t, w8_t, we_t, w4_t, wb_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T45, wd_t, wd_t ^ w1_t);
w2_t = SM3_EXPAND(w2_t, w9_t, wf_t, w5_t, wc_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T46, we_t, we_t ^ w2_t);
w3_t = SM3_EXPAND(w3_t, wa_t, w0_t, w6_t, wd_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T47, wf_t, wf_t ^ w3_t);
w4_t = SM3_EXPAND(w4_t, wb_t, w1_t, w7_t, we_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T48, w0_t, w0_t ^ w4_t);
w5_t = SM3_EXPAND(w5_t, wc_t, w2_t, w8_t, wf_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T49, w1_t, w1_t ^ w5_t);
w6_t = SM3_EXPAND(w6_t, wd_t, w3_t, w9_t, w0_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T50, w2_t, w2_t ^ w6_t);
w7_t = SM3_EXPAND(w7_t, we_t, w4_t, wa_t, w1_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T51, w3_t, w3_t ^ w7_t);
w8_t = SM3_EXPAND(w8_t, wf_t, w5_t, wb_t, w2_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T52, w4_t, w4_t ^ w8_t);
w9_t = SM3_EXPAND(w9_t, w0_t, w6_t, wc_t, w3_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T53, w5_t, w5_t ^ w9_t);
wa_t = SM3_EXPAND(wa_t, w1_t, w7_t, wd_t, w4_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T54, w6_t, w6_t ^ wa_t);
wb_t = SM3_EXPAND(wb_t, w2_t, w8_t, we_t, w5_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T55, w7_t, w7_t ^ wb_t);
wc_t = SM3_EXPAND(wc_t, w3_t, w9_t, wf_t, w6_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T56, w8_t, w8_t ^ wc_t);
wd_t = SM3_EXPAND(wd_t, w4_t, wa_t, w0_t, w7_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T57, w9_t, w9_t ^ wd_t);
we_t = SM3_EXPAND(we_t, w5_t, wb_t, w1_t, w8_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T58, wa_t, wa_t ^ we_t);
wf_t = SM3_EXPAND(wf_t, w6_t, wc_t, w2_t, w9_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T59, wb_t, wb_t ^ wf_t);
w0_t = SM3_EXPAND(w0_t, w7_t, wd_t, w3_t, wa_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T60, wc_t, wc_t ^ w0_t);
w1_t = SM3_EXPAND(w1_t, w8_t, we_t, w4_t, wb_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T61, wd_t, wd_t ^ w1_t);
w2_t = SM3_EXPAND(w2_t, w9_t, wf_t, w5_t, wc_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T62, we_t, we_t ^ w2_t);
w3_t = SM3_EXPAND(w3_t, wa_t, w0_t, w6_t, wd_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T63, wf_t, wf_t ^ w3_t);
COMPARE_M_SIMD (d, h, c, g);
}
}
KERNEL_FQ void m31100_m08 (KERN_ATTR_BASIC ())
{
}
KERNEL_FQ void m31100_m16 (KERN_ATTR_BASIC ())
{
}
KERNEL_FQ void m31100_s04 (KERN_ATTR_BASIC ())
{
/**
* modifier
*/
const u64 lid = get_local_id (0);
/**
* base
*/
const u64 gid = get_global_id (0);
if (gid >= GID_CNT) return;
u32 pw_buf0[4];
u32 pw_buf1[4];
pw_buf0[0] = pws[gid].i[0];
pw_buf0[1] = pws[gid].i[1];
pw_buf0[2] = pws[gid].i[2];
pw_buf0[3] = pws[gid].i[3];
pw_buf1[0] = pws[gid].i[4];
pw_buf1[1] = pws[gid].i[5];
pw_buf1[2] = pws[gid].i[6];
pw_buf1[3] = pws[gid].i[7];
const u32 pw_l_len = pws[gid].pw_len & 63;
/**
* digest
*/
const u32 search[4] =
{
digests_buf[DIGESTS_OFFSET_HOST].digest_buf[DGST_R0],
digests_buf[DIGESTS_OFFSET_HOST].digest_buf[DGST_R1],
digests_buf[DIGESTS_OFFSET_HOST].digest_buf[DGST_R2],
digests_buf[DIGESTS_OFFSET_HOST].digest_buf[DGST_R3]
};
/**
* loop
*/
for (u32 il_pos = 0; il_pos < IL_CNT; il_pos += VECT_SIZE)
{
const u32x pw_r_len = pwlenx_create_combt (combs_buf, il_pos) & 63;
const u32x pw_len = (pw_l_len + pw_r_len) & 63;
/**
* concat password candidate
*/
u32x wordl0[4] = { 0 };
u32x wordl1[4] = { 0 };
u32x wordl2[4] = { 0 };
u32x wordl3[4] = { 0 };
wordl0[0] = pw_buf0[0];
wordl0[1] = pw_buf0[1];
wordl0[2] = pw_buf0[2];
wordl0[3] = pw_buf0[3];
wordl1[0] = pw_buf1[0];
wordl1[1] = pw_buf1[1];
wordl1[2] = pw_buf1[2];
wordl1[3] = pw_buf1[3];
u32x wordr0[4] = { 0 };
u32x wordr1[4] = { 0 };
u32x wordr2[4] = { 0 };
u32x wordr3[4] = { 0 };
wordr0[0] = ix_create_combt (combs_buf, il_pos, 0);
wordr0[1] = ix_create_combt (combs_buf, il_pos, 1);
wordr0[2] = ix_create_combt (combs_buf, il_pos, 2);
wordr0[3] = ix_create_combt (combs_buf, il_pos, 3);
wordr1[0] = ix_create_combt (combs_buf, il_pos, 4);
wordr1[1] = ix_create_combt (combs_buf, il_pos, 5);
wordr1[2] = ix_create_combt (combs_buf, il_pos, 6);
wordr1[3] = ix_create_combt (combs_buf, il_pos, 7);
if (COMBS_MODE == COMBINATOR_MODE_BASE_LEFT)
{
switch_buffer_by_offset_le_VV (wordr0, wordr1, wordr2, wordr3, pw_l_len);
}
else
{
switch_buffer_by_offset_le_VV (wordl0, wordl1, wordl2, wordl3, pw_r_len);
}
u32x w0[4];
u32x w1[4];
u32x w2[4];
u32x w3[4];
w0[0] = wordl0[0] | wordr0[0];
w0[1] = wordl0[1] | wordr0[1];
w0[2] = wordl0[2] | wordr0[2];
w0[3] = wordl0[3] | wordr0[3];
w1[0] = wordl1[0] | wordr1[0];
w1[1] = wordl1[1] | wordr1[1];
w1[2] = wordl1[2] | wordr1[2];
w1[3] = wordl1[3] | wordr1[3];
w2[0] = wordl2[0] | wordr2[0];
w2[1] = wordl2[1] | wordr2[1];
w2[2] = wordl2[2] | wordr2[2];
w2[3] = wordl2[3] | wordr2[3];
w3[0] = wordl3[0] | wordr3[0];
w3[1] = wordl3[1] | wordr3[1];
w3[2] = wordl3[2] | wordr3[2];
w3[3] = wordl3[3] | wordr3[3];
/**
* sm3
*/
u32x w0_t = hc_swap32 (w0[0]);
u32x w1_t = hc_swap32 (w0[1]);
u32x w2_t = hc_swap32 (w0[2]);
u32x w3_t = hc_swap32 (w0[3]);
u32x w4_t = hc_swap32 (w1[0]);
u32x w5_t = hc_swap32 (w1[1]);
u32x w6_t = hc_swap32 (w1[2]);
u32x w7_t = hc_swap32 (w1[3]);
u32x w8_t = hc_swap32 (w2[0]);
u32x w9_t = hc_swap32 (w2[1]);
u32x wa_t = hc_swap32 (w2[2]);
u32x wb_t = hc_swap32 (w2[3]);
u32x wc_t = hc_swap32 (w3[0]);
u32x wd_t = hc_swap32 (w3[1]);
u32x we_t = 0;
u32x wf_t = pw_len * 8;
u32x a = SM3_IV_A;
u32x b = SM3_IV_B;
u32x c = SM3_IV_C;
u32x d = SM3_IV_D;
u32x e = SM3_IV_E;
u32x f = SM3_IV_F;
u32x g = SM3_IV_G;
u32x h = SM3_IV_H;
SM3_ROUND1(a, b, c, d, e, f, g, h, SM3_T00, w0_t, w0_t ^ w4_t);
SM3_ROUND1(d, a, b, c, h, e, f, g, SM3_T01, w1_t, w1_t ^ w5_t);
SM3_ROUND1(c, d, a, b, g, h, e, f, SM3_T02, w2_t, w2_t ^ w6_t);
SM3_ROUND1(b, c, d, a, f, g, h, e, SM3_T03, w3_t, w3_t ^ w7_t);
SM3_ROUND1(a, b, c, d, e, f, g, h, SM3_T04, w4_t, w4_t ^ w8_t);
SM3_ROUND1(d, a, b, c, h, e, f, g, SM3_T05, w5_t, w5_t ^ w9_t);
SM3_ROUND1(c, d, a, b, g, h, e, f, SM3_T06, w6_t, w6_t ^ wa_t);
SM3_ROUND1(b, c, d, a, f, g, h, e, SM3_T07, w7_t, w7_t ^ wb_t);
SM3_ROUND1(a, b, c, d, e, f, g, h, SM3_T08, w8_t, w8_t ^ wc_t);
SM3_ROUND1(d, a, b, c, h, e, f, g, SM3_T09, w9_t, w9_t ^ wd_t);
SM3_ROUND1(c, d, a, b, g, h, e, f, SM3_T10, wa_t, wa_t ^ we_t);
SM3_ROUND1(b, c, d, a, f, g, h, e, SM3_T11, wb_t, wb_t ^ wf_t);
w0_t = SM3_EXPAND(w0_t, w7_t, wd_t, w3_t, wa_t); SM3_ROUND1(a, b, c, d, e, f, g, h, SM3_T12, wc_t, wc_t ^ w0_t);
w1_t = SM3_EXPAND(w1_t, w8_t, we_t, w4_t, wb_t); SM3_ROUND1(d, a, b, c, h, e, f, g, SM3_T13, wd_t, wd_t ^ w1_t);
w2_t = SM3_EXPAND(w2_t, w9_t, wf_t, w5_t, wc_t); SM3_ROUND1(c, d, a, b, g, h, e, f, SM3_T14, we_t, we_t ^ w2_t);
w3_t = SM3_EXPAND(w3_t, wa_t, w0_t, w6_t, wd_t); SM3_ROUND1(b, c, d, a, f, g, h, e, SM3_T15, wf_t, wf_t ^ w3_t);
w4_t = SM3_EXPAND(w4_t, wb_t, w1_t, w7_t, we_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T16, w0_t, w0_t ^ w4_t);
w5_t = SM3_EXPAND(w5_t, wc_t, w2_t, w8_t, wf_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T17, w1_t, w1_t ^ w5_t);
w6_t = SM3_EXPAND(w6_t, wd_t, w3_t, w9_t, w0_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T18, w2_t, w2_t ^ w6_t);
w7_t = SM3_EXPAND(w7_t, we_t, w4_t, wa_t, w1_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T19, w3_t, w3_t ^ w7_t);
w8_t = SM3_EXPAND(w8_t, wf_t, w5_t, wb_t, w2_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T20, w4_t, w4_t ^ w8_t);
w9_t = SM3_EXPAND(w9_t, w0_t, w6_t, wc_t, w3_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T21, w5_t, w5_t ^ w9_t);
wa_t = SM3_EXPAND(wa_t, w1_t, w7_t, wd_t, w4_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T22, w6_t, w6_t ^ wa_t);
wb_t = SM3_EXPAND(wb_t, w2_t, w8_t, we_t, w5_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T23, w7_t, w7_t ^ wb_t);
wc_t = SM3_EXPAND(wc_t, w3_t, w9_t, wf_t, w6_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T24, w8_t, w8_t ^ wc_t);
wd_t = SM3_EXPAND(wd_t, w4_t, wa_t, w0_t, w7_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T25, w9_t, w9_t ^ wd_t);
we_t = SM3_EXPAND(we_t, w5_t, wb_t, w1_t, w8_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T26, wa_t, wa_t ^ we_t);
wf_t = SM3_EXPAND(wf_t, w6_t, wc_t, w2_t, w9_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T27, wb_t, wb_t ^ wf_t);
w0_t = SM3_EXPAND(w0_t, w7_t, wd_t, w3_t, wa_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T28, wc_t, wc_t ^ w0_t);
w1_t = SM3_EXPAND(w1_t, w8_t, we_t, w4_t, wb_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T29, wd_t, wd_t ^ w1_t);
w2_t = SM3_EXPAND(w2_t, w9_t, wf_t, w5_t, wc_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T30, we_t, we_t ^ w2_t);
w3_t = SM3_EXPAND(w3_t, wa_t, w0_t, w6_t, wd_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T31, wf_t, wf_t ^ w3_t);
w4_t = SM3_EXPAND(w4_t, wb_t, w1_t, w7_t, we_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T32, w0_t, w0_t ^ w4_t);
w5_t = SM3_EXPAND(w5_t, wc_t, w2_t, w8_t, wf_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T33, w1_t, w1_t ^ w5_t);
w6_t = SM3_EXPAND(w6_t, wd_t, w3_t, w9_t, w0_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T34, w2_t, w2_t ^ w6_t);
w7_t = SM3_EXPAND(w7_t, we_t, w4_t, wa_t, w1_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T35, w3_t, w3_t ^ w7_t);
w8_t = SM3_EXPAND(w8_t, wf_t, w5_t, wb_t, w2_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T36, w4_t, w4_t ^ w8_t);
w9_t = SM3_EXPAND(w9_t, w0_t, w6_t, wc_t, w3_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T37, w5_t, w5_t ^ w9_t);
wa_t = SM3_EXPAND(wa_t, w1_t, w7_t, wd_t, w4_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T38, w6_t, w6_t ^ wa_t);
wb_t = SM3_EXPAND(wb_t, w2_t, w8_t, we_t, w5_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T39, w7_t, w7_t ^ wb_t);
wc_t = SM3_EXPAND(wc_t, w3_t, w9_t, wf_t, w6_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T40, w8_t, w8_t ^ wc_t);
wd_t = SM3_EXPAND(wd_t, w4_t, wa_t, w0_t, w7_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T41, w9_t, w9_t ^ wd_t);
we_t = SM3_EXPAND(we_t, w5_t, wb_t, w1_t, w8_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T42, wa_t, wa_t ^ we_t);
wf_t = SM3_EXPAND(wf_t, w6_t, wc_t, w2_t, w9_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T43, wb_t, wb_t ^ wf_t);
w0_t = SM3_EXPAND(w0_t, w7_t, wd_t, w3_t, wa_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T44, wc_t, wc_t ^ w0_t);
w1_t = SM3_EXPAND(w1_t, w8_t, we_t, w4_t, wb_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T45, wd_t, wd_t ^ w1_t);
w2_t = SM3_EXPAND(w2_t, w9_t, wf_t, w5_t, wc_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T46, we_t, we_t ^ w2_t);
w3_t = SM3_EXPAND(w3_t, wa_t, w0_t, w6_t, wd_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T47, wf_t, wf_t ^ w3_t);
w4_t = SM3_EXPAND(w4_t, wb_t, w1_t, w7_t, we_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T48, w0_t, w0_t ^ w4_t);
w5_t = SM3_EXPAND(w5_t, wc_t, w2_t, w8_t, wf_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T49, w1_t, w1_t ^ w5_t);
w6_t = SM3_EXPAND(w6_t, wd_t, w3_t, w9_t, w0_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T50, w2_t, w2_t ^ w6_t);
w7_t = SM3_EXPAND(w7_t, we_t, w4_t, wa_t, w1_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T51, w3_t, w3_t ^ w7_t);
w8_t = SM3_EXPAND(w8_t, wf_t, w5_t, wb_t, w2_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T52, w4_t, w4_t ^ w8_t);
w9_t = SM3_EXPAND(w9_t, w0_t, w6_t, wc_t, w3_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T53, w5_t, w5_t ^ w9_t);
wa_t = SM3_EXPAND(wa_t, w1_t, w7_t, wd_t, w4_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T54, w6_t, w6_t ^ wa_t);
wb_t = SM3_EXPAND(wb_t, w2_t, w8_t, we_t, w5_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T55, w7_t, w7_t ^ wb_t);
wc_t = SM3_EXPAND(wc_t, w3_t, w9_t, wf_t, w6_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T56, w8_t, w8_t ^ wc_t);
wd_t = SM3_EXPAND(wd_t, w4_t, wa_t, w0_t, w7_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T57, w9_t, w9_t ^ wd_t);
we_t = SM3_EXPAND(we_t, w5_t, wb_t, w1_t, w8_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T58, wa_t, wa_t ^ we_t);
wf_t = SM3_EXPAND(wf_t, w6_t, wc_t, w2_t, w9_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T59, wb_t, wb_t ^ wf_t);
w0_t = SM3_EXPAND(w0_t, w7_t, wd_t, w3_t, wa_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T60, wc_t, wc_t ^ w0_t);
w1_t = SM3_EXPAND(w1_t, w8_t, we_t, w4_t, wb_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T61, wd_t, wd_t ^ w1_t);
w2_t = SM3_EXPAND(w2_t, w9_t, wf_t, w5_t, wc_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T62, we_t, we_t ^ w2_t);
w3_t = SM3_EXPAND(w3_t, wa_t, w0_t, w6_t, wd_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T63, wf_t, wf_t ^ w3_t);
COMPARE_S_SIMD (d, h, c, g);
}
}
KERNEL_FQ void m31100_s08 (KERN_ATTR_BASIC ())
{
}
KERNEL_FQ void m31100_s16 (KERN_ATTR_BASIC ())
{
}

111
OpenCL/m31100_a1-pure.cl Normal file
View File

@ -0,0 +1,111 @@
/**
* Author......: See docs/credits.txt
* License.....: MIT
*/
//#define NEW_SIMD_CODE
#ifdef KERNEL_STATIC
#include M2S(INCLUDE_PATH/inc_vendor.h)
#include M2S(INCLUDE_PATH/inc_types.h)
#include M2S(INCLUDE_PATH/inc_platform.cl)
#include M2S(INCLUDE_PATH/inc_common.cl)
#include M2S(INCLUDE_PATH/inc_scalar.cl)
#include M2S(INCLUDE_PATH/inc_hash_sm3.cl)
#endif
KERNEL_FQ void m31100_mxx (KERN_ATTR_BASIC ())
{
/**
* modifier
*/
const u64 lid = get_local_id (0);
const u64 gid = get_global_id (0);
if (gid >= GID_CNT) return;
/**
* base
*/
sm3_ctx_t ctx0;
sm3_init (&ctx0);
sm3_update_global_swap (&ctx0, pws[gid].i, pws[gid].pw_len);
/**
* loop
*/
for (u32 il_pos = 0; il_pos < IL_CNT; il_pos++)
{
sm3_ctx_t ctx = ctx0;
sm3_update_global_swap (&ctx, combs_buf[il_pos].i, combs_buf[il_pos].pw_len);
sm3_final (&ctx);
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_SCALAR (r0, r1, r2, r3);
}
}
KERNEL_FQ void m31100_sxx (KERN_ATTR_BASIC ())
{
/**
* modifier
*/
const u64 lid = get_local_id (0);
const u64 gid = get_global_id (0);
if (gid >= GID_CNT) return;
/**
* digest
*/
const u32 search[4] =
{
digests_buf[DIGESTS_OFFSET_HOST].digest_buf[DGST_R0],
digests_buf[DIGESTS_OFFSET_HOST].digest_buf[DGST_R1],
digests_buf[DIGESTS_OFFSET_HOST].digest_buf[DGST_R2],
digests_buf[DIGESTS_OFFSET_HOST].digest_buf[DGST_R3]
};
/**
* base
*/
sm3_ctx_t ctx0;
sm3_init (&ctx0);
sm3_update_global_swap (&ctx0, pws[gid].i, pws[gid].pw_len);
/**
* loop
*/
for (u32 il_pos = 0; il_pos < IL_CNT; il_pos++)
{
sm3_ctx_t ctx = ctx0;
sm3_update_global_swap (&ctx, combs_buf[il_pos].i, combs_buf[il_pos].pw_len);
sm3_final (&ctx);
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_SCALAR (r0, r1, r2, r3);
}
}

499
OpenCL/m31100_a3-optimized.cl Normal file
View File

@ -0,0 +1,499 @@
/**
* Author......: See docs/credits.txt
* License.....: MIT
*/
#define NEW_SIMD_CODE
#ifdef KERNEL_STATIC
#include M2S(INCLUDE_PATH/inc_vendor.h)
#include M2S(INCLUDE_PATH/inc_types.h)
#include M2S(INCLUDE_PATH/inc_platform.cl)
#include M2S(INCLUDE_PATH/inc_common.cl)
#include M2S(INCLUDE_PATH/inc_simd.cl)
#include M2S(INCLUDE_PATH/inc_hash_sm3.cl)
#endif
DECLSPEC void m31100m (PRIVATE_AS u32 *w, const u32 pw_len, KERN_ATTR_FUNC_VECTOR ())
{
/**
* modifiers are taken from args
*/
/**
* loop
*/
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 u32x w0 = w0l | w0r;
u32x w0_t = w0;
u32x w1_t = w[ 1];
u32x w2_t = w[ 2];
u32x w3_t = w[ 3];
u32x w4_t = w[ 4];
u32x w5_t = w[ 5];
u32x w6_t = w[ 6];
u32x w7_t = w[ 7];
u32x w8_t = w[ 8];
u32x w9_t = w[ 9];
u32x wa_t = w[10];
u32x wb_t = w[11];
u32x wc_t = w[12];
u32x wd_t = w[13];
u32x we_t = w[14];
u32x wf_t = w[15];
u32x a = SM3_IV_A;
u32x b = SM3_IV_B;
u32x c = SM3_IV_C;
u32x d = SM3_IV_D;
u32x e = SM3_IV_E;
u32x f = SM3_IV_F;
u32x g = SM3_IV_G;
u32x h = SM3_IV_H;
SM3_ROUND1(a, b, c, d, e, f, g, h, SM3_T00, w0_t, w0_t ^ w4_t);
SM3_ROUND1(d, a, b, c, h, e, f, g, SM3_T01, w1_t, w1_t ^ w5_t);
SM3_ROUND1(c, d, a, b, g, h, e, f, SM3_T02, w2_t, w2_t ^ w6_t);
SM3_ROUND1(b, c, d, a, f, g, h, e, SM3_T03, w3_t, w3_t ^ w7_t);
SM3_ROUND1(a, b, c, d, e, f, g, h, SM3_T04, w4_t, w4_t ^ w8_t);
SM3_ROUND1(d, a, b, c, h, e, f, g, SM3_T05, w5_t, w5_t ^ w9_t);
SM3_ROUND1(c, d, a, b, g, h, e, f, SM3_T06, w6_t, w6_t ^ wa_t);
SM3_ROUND1(b, c, d, a, f, g, h, e, SM3_T07, w7_t, w7_t ^ wb_t);
SM3_ROUND1(a, b, c, d, e, f, g, h, SM3_T08, w8_t, w8_t ^ wc_t);
SM3_ROUND1(d, a, b, c, h, e, f, g, SM3_T09, w9_t, w9_t ^ wd_t);
SM3_ROUND1(c, d, a, b, g, h, e, f, SM3_T10, wa_t, wa_t ^ we_t);
SM3_ROUND1(b, c, d, a, f, g, h, e, SM3_T11, wb_t, wb_t ^ wf_t);
w0_t = SM3_EXPAND(w0_t, w7_t, wd_t, w3_t, wa_t); SM3_ROUND1(a, b, c, d, e, f, g, h, SM3_T12, wc_t, wc_t ^ w0_t);
w1_t = SM3_EXPAND(w1_t, w8_t, we_t, w4_t, wb_t); SM3_ROUND1(d, a, b, c, h, e, f, g, SM3_T13, wd_t, wd_t ^ w1_t);
w2_t = SM3_EXPAND(w2_t, w9_t, wf_t, w5_t, wc_t); SM3_ROUND1(c, d, a, b, g, h, e, f, SM3_T14, we_t, we_t ^ w2_t);
w3_t = SM3_EXPAND(w3_t, wa_t, w0_t, w6_t, wd_t); SM3_ROUND1(b, c, d, a, f, g, h, e, SM3_T15, wf_t, wf_t ^ w3_t);
w4_t = SM3_EXPAND(w4_t, wb_t, w1_t, w7_t, we_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T16, w0_t, w0_t ^ w4_t);
w5_t = SM3_EXPAND(w5_t, wc_t, w2_t, w8_t, wf_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T17, w1_t, w1_t ^ w5_t);
w6_t = SM3_EXPAND(w6_t, wd_t, w3_t, w9_t, w0_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T18, w2_t, w2_t ^ w6_t);
w7_t = SM3_EXPAND(w7_t, we_t, w4_t, wa_t, w1_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T19, w3_t, w3_t ^ w7_t);
w8_t = SM3_EXPAND(w8_t, wf_t, w5_t, wb_t, w2_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T20, w4_t, w4_t ^ w8_t);
w9_t = SM3_EXPAND(w9_t, w0_t, w6_t, wc_t, w3_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T21, w5_t, w5_t ^ w9_t);
wa_t = SM3_EXPAND(wa_t, w1_t, w7_t, wd_t, w4_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T22, w6_t, w6_t ^ wa_t);
wb_t = SM3_EXPAND(wb_t, w2_t, w8_t, we_t, w5_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T23, w7_t, w7_t ^ wb_t);
wc_t = SM3_EXPAND(wc_t, w3_t, w9_t, wf_t, w6_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T24, w8_t, w8_t ^ wc_t);
wd_t = SM3_EXPAND(wd_t, w4_t, wa_t, w0_t, w7_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T25, w9_t, w9_t ^ wd_t);
we_t = SM3_EXPAND(we_t, w5_t, wb_t, w1_t, w8_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T26, wa_t, wa_t ^ we_t);
wf_t = SM3_EXPAND(wf_t, w6_t, wc_t, w2_t, w9_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T27, wb_t, wb_t ^ wf_t);
w0_t = SM3_EXPAND(w0_t, w7_t, wd_t, w3_t, wa_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T28, wc_t, wc_t ^ w0_t);
w1_t = SM3_EXPAND(w1_t, w8_t, we_t, w4_t, wb_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T29, wd_t, wd_t ^ w1_t);
w2_t = SM3_EXPAND(w2_t, w9_t, wf_t, w5_t, wc_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T30, we_t, we_t ^ w2_t);
w3_t = SM3_EXPAND(w3_t, wa_t, w0_t, w6_t, wd_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T31, wf_t, wf_t ^ w3_t);
w4_t = SM3_EXPAND(w4_t, wb_t, w1_t, w7_t, we_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T32, w0_t, w0_t ^ w4_t);
w5_t = SM3_EXPAND(w5_t, wc_t, w2_t, w8_t, wf_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T33, w1_t, w1_t ^ w5_t);
w6_t = SM3_EXPAND(w6_t, wd_t, w3_t, w9_t, w0_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T34, w2_t, w2_t ^ w6_t);
w7_t = SM3_EXPAND(w7_t, we_t, w4_t, wa_t, w1_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T35, w3_t, w3_t ^ w7_t);
w8_t = SM3_EXPAND(w8_t, wf_t, w5_t, wb_t, w2_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T36, w4_t, w4_t ^ w8_t);
w9_t = SM3_EXPAND(w9_t, w0_t, w6_t, wc_t, w3_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T37, w5_t, w5_t ^ w9_t);
wa_t = SM3_EXPAND(wa_t, w1_t, w7_t, wd_t, w4_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T38, w6_t, w6_t ^ wa_t);
wb_t = SM3_EXPAND(wb_t, w2_t, w8_t, we_t, w5_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T39, w7_t, w7_t ^ wb_t);
wc_t = SM3_EXPAND(wc_t, w3_t, w9_t, wf_t, w6_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T40, w8_t, w8_t ^ wc_t);
wd_t = SM3_EXPAND(wd_t, w4_t, wa_t, w0_t, w7_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T41, w9_t, w9_t ^ wd_t);
we_t = SM3_EXPAND(we_t, w5_t, wb_t, w1_t, w8_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T42, wa_t, wa_t ^ we_t);
wf_t = SM3_EXPAND(wf_t, w6_t, wc_t, w2_t, w9_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T43, wb_t, wb_t ^ wf_t);
w0_t = SM3_EXPAND(w0_t, w7_t, wd_t, w3_t, wa_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T44, wc_t, wc_t ^ w0_t);
w1_t = SM3_EXPAND(w1_t, w8_t, we_t, w4_t, wb_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T45, wd_t, wd_t ^ w1_t);
w2_t = SM3_EXPAND(w2_t, w9_t, wf_t, w5_t, wc_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T46, we_t, we_t ^ w2_t);
w3_t = SM3_EXPAND(w3_t, wa_t, w0_t, w6_t, wd_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T47, wf_t, wf_t ^ w3_t);
w4_t = SM3_EXPAND(w4_t, wb_t, w1_t, w7_t, we_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T48, w0_t, w0_t ^ w4_t);
w5_t = SM3_EXPAND(w5_t, wc_t, w2_t, w8_t, wf_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T49, w1_t, w1_t ^ w5_t);
w6_t = SM3_EXPAND(w6_t, wd_t, w3_t, w9_t, w0_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T50, w2_t, w2_t ^ w6_t);
w7_t = SM3_EXPAND(w7_t, we_t, w4_t, wa_t, w1_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T51, w3_t, w3_t ^ w7_t);
w8_t = SM3_EXPAND(w8_t, wf_t, w5_t, wb_t, w2_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T52, w4_t, w4_t ^ w8_t);
w9_t = SM3_EXPAND(w9_t, w0_t, w6_t, wc_t, w3_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T53, w5_t, w5_t ^ w9_t);
wa_t = SM3_EXPAND(wa_t, w1_t, w7_t, wd_t, w4_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T54, w6_t, w6_t ^ wa_t);
wb_t = SM3_EXPAND(wb_t, w2_t, w8_t, we_t, w5_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T55, w7_t, w7_t ^ wb_t);
wc_t = SM3_EXPAND(wc_t, w3_t, w9_t, wf_t, w6_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T56, w8_t, w8_t ^ wc_t);
wd_t = SM3_EXPAND(wd_t, w4_t, wa_t, w0_t, w7_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T57, w9_t, w9_t ^ wd_t);
we_t = SM3_EXPAND(we_t, w5_t, wb_t, w1_t, w8_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T58, wa_t, wa_t ^ we_t);
wf_t = SM3_EXPAND(wf_t, w6_t, wc_t, w2_t, w9_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T59, wb_t, wb_t ^ wf_t);
w0_t = SM3_EXPAND(w0_t, w7_t, wd_t, w3_t, wa_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T60, wc_t, wc_t ^ w0_t);
w1_t = SM3_EXPAND(w1_t, w8_t, we_t, w4_t, wb_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T61, wd_t, wd_t ^ w1_t);
w2_t = SM3_EXPAND(w2_t, w9_t, wf_t, w5_t, wc_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T62, we_t, we_t ^ w2_t);
w3_t = SM3_EXPAND(w3_t, wa_t, w0_t, w6_t, wd_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T63, wf_t, wf_t ^ w3_t);
COMPARE_M_SIMD (d, h, c, g);
}
}
DECLSPEC void m31100s (PRIVATE_AS u32 *w, const u32 pw_len, KERN_ATTR_FUNC_VECTOR ())
{
/**
* modifiers are taken from args
*/
/**
* digest
*/
const u32 search[4] =
{
digests_buf[DIGESTS_OFFSET_HOST].digest_buf[DGST_R0],
digests_buf[DIGESTS_OFFSET_HOST].digest_buf[DGST_R1],
digests_buf[DIGESTS_OFFSET_HOST].digest_buf[DGST_R2],
digests_buf[DIGESTS_OFFSET_HOST].digest_buf[DGST_R3]
};
/**
* loop
*/
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 u32x w0 = w0l | w0r;
u32x w0_t = w0;
u32x w1_t = w[ 1];
u32x w2_t = w[ 2];
u32x w3_t = w[ 3];
u32x w4_t = w[ 4];
u32x w5_t = w[ 5];
u32x w6_t = w[ 6];
u32x w7_t = w[ 7];
u32x w8_t = w[ 8];
u32x w9_t = w[ 9];
u32x wa_t = w[10];
u32x wb_t = w[11];
u32x wc_t = w[12];
u32x wd_t = w[13];
u32x we_t = w[14];
u32x wf_t = w[15];
u32x a = SM3_IV_A;
u32x b = SM3_IV_B;
u32x c = SM3_IV_C;
u32x d = SM3_IV_D;
u32x e = SM3_IV_E;
u32x f = SM3_IV_F;
u32x g = SM3_IV_G;
u32x h = SM3_IV_H;
SM3_ROUND1(a, b, c, d, e, f, g, h, SM3_T00, w0_t, w0_t ^ w4_t);
SM3_ROUND1(d, a, b, c, h, e, f, g, SM3_T01, w1_t, w1_t ^ w5_t);
SM3_ROUND1(c, d, a, b, g, h, e, f, SM3_T02, w2_t, w2_t ^ w6_t);
SM3_ROUND1(b, c, d, a, f, g, h, e, SM3_T03, w3_t, w3_t ^ w7_t);
SM3_ROUND1(a, b, c, d, e, f, g, h, SM3_T04, w4_t, w4_t ^ w8_t);
SM3_ROUND1(d, a, b, c, h, e, f, g, SM3_T05, w5_t, w5_t ^ w9_t);
SM3_ROUND1(c, d, a, b, g, h, e, f, SM3_T06, w6_t, w6_t ^ wa_t);
SM3_ROUND1(b, c, d, a, f, g, h, e, SM3_T07, w7_t, w7_t ^ wb_t);
SM3_ROUND1(a, b, c, d, e, f, g, h, SM3_T08, w8_t, w8_t ^ wc_t);
SM3_ROUND1(d, a, b, c, h, e, f, g, SM3_T09, w9_t, w9_t ^ wd_t);
SM3_ROUND1(c, d, a, b, g, h, e, f, SM3_T10, wa_t, wa_t ^ we_t);
SM3_ROUND1(b, c, d, a, f, g, h, e, SM3_T11, wb_t, wb_t ^ wf_t);
w0_t = SM3_EXPAND(w0_t, w7_t, wd_t, w3_t, wa_t); SM3_ROUND1(a, b, c, d, e, f, g, h, SM3_T12, wc_t, wc_t ^ w0_t);
w1_t = SM3_EXPAND(w1_t, w8_t, we_t, w4_t, wb_t); SM3_ROUND1(d, a, b, c, h, e, f, g, SM3_T13, wd_t, wd_t ^ w1_t);
w2_t = SM3_EXPAND(w2_t, w9_t, wf_t, w5_t, wc_t); SM3_ROUND1(c, d, a, b, g, h, e, f, SM3_T14, we_t, we_t ^ w2_t);
w3_t = SM3_EXPAND(w3_t, wa_t, w0_t, w6_t, wd_t); SM3_ROUND1(b, c, d, a, f, g, h, e, SM3_T15, wf_t, wf_t ^ w3_t);
w4_t = SM3_EXPAND(w4_t, wb_t, w1_t, w7_t, we_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T16, w0_t, w0_t ^ w4_t);
w5_t = SM3_EXPAND(w5_t, wc_t, w2_t, w8_t, wf_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T17, w1_t, w1_t ^ w5_t);
w6_t = SM3_EXPAND(w6_t, wd_t, w3_t, w9_t, w0_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T18, w2_t, w2_t ^ w6_t);
w7_t = SM3_EXPAND(w7_t, we_t, w4_t, wa_t, w1_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T19, w3_t, w3_t ^ w7_t);
w8_t = SM3_EXPAND(w8_t, wf_t, w5_t, wb_t, w2_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T20, w4_t, w4_t ^ w8_t);
w9_t = SM3_EXPAND(w9_t, w0_t, w6_t, wc_t, w3_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T21, w5_t, w5_t ^ w9_t);
wa_t = SM3_EXPAND(wa_t, w1_t, w7_t, wd_t, w4_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T22, w6_t, w6_t ^ wa_t);
wb_t = SM3_EXPAND(wb_t, w2_t, w8_t, we_t, w5_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T23, w7_t, w7_t ^ wb_t);
wc_t = SM3_EXPAND(wc_t, w3_t, w9_t, wf_t, w6_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T24, w8_t, w8_t ^ wc_t);
wd_t = SM3_EXPAND(wd_t, w4_t, wa_t, w0_t, w7_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T25, w9_t, w9_t ^ wd_t);
we_t = SM3_EXPAND(we_t, w5_t, wb_t, w1_t, w8_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T26, wa_t, wa_t ^ we_t);
wf_t = SM3_EXPAND(wf_t, w6_t, wc_t, w2_t, w9_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T27, wb_t, wb_t ^ wf_t);
w0_t = SM3_EXPAND(w0_t, w7_t, wd_t, w3_t, wa_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T28, wc_t, wc_t ^ w0_t);
w1_t = SM3_EXPAND(w1_t, w8_t, we_t, w4_t, wb_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T29, wd_t, wd_t ^ w1_t);
w2_t = SM3_EXPAND(w2_t, w9_t, wf_t, w5_t, wc_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T30, we_t, we_t ^ w2_t);
w3_t = SM3_EXPAND(w3_t, wa_t, w0_t, w6_t, wd_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T31, wf_t, wf_t ^ w3_t);
w4_t = SM3_EXPAND(w4_t, wb_t, w1_t, w7_t, we_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T32, w0_t, w0_t ^ w4_t);
w5_t = SM3_EXPAND(w5_t, wc_t, w2_t, w8_t, wf_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T33, w1_t, w1_t ^ w5_t);
w6_t = SM3_EXPAND(w6_t, wd_t, w3_t, w9_t, w0_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T34, w2_t, w2_t ^ w6_t);
w7_t = SM3_EXPAND(w7_t, we_t, w4_t, wa_t, w1_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T35, w3_t, w3_t ^ w7_t);
w8_t = SM3_EXPAND(w8_t, wf_t, w5_t, wb_t, w2_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T36, w4_t, w4_t ^ w8_t);
w9_t = SM3_EXPAND(w9_t, w0_t, w6_t, wc_t, w3_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T37, w5_t, w5_t ^ w9_t);
wa_t = SM3_EXPAND(wa_t, w1_t, w7_t, wd_t, w4_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T38, w6_t, w6_t ^ wa_t);
wb_t = SM3_EXPAND(wb_t, w2_t, w8_t, we_t, w5_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T39, w7_t, w7_t ^ wb_t);
wc_t = SM3_EXPAND(wc_t, w3_t, w9_t, wf_t, w6_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T40, w8_t, w8_t ^ wc_t);
wd_t = SM3_EXPAND(wd_t, w4_t, wa_t, w0_t, w7_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T41, w9_t, w9_t ^ wd_t);
we_t = SM3_EXPAND(we_t, w5_t, wb_t, w1_t, w8_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T42, wa_t, wa_t ^ we_t);
wf_t = SM3_EXPAND(wf_t, w6_t, wc_t, w2_t, w9_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T43, wb_t, wb_t ^ wf_t);
w0_t = SM3_EXPAND(w0_t, w7_t, wd_t, w3_t, wa_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T44, wc_t, wc_t ^ w0_t);
w1_t = SM3_EXPAND(w1_t, w8_t, we_t, w4_t, wb_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T45, wd_t, wd_t ^ w1_t);
w2_t = SM3_EXPAND(w2_t, w9_t, wf_t, w5_t, wc_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T46, we_t, we_t ^ w2_t);
w3_t = SM3_EXPAND(w3_t, wa_t, w0_t, w6_t, wd_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T47, wf_t, wf_t ^ w3_t);
w4_t = SM3_EXPAND(w4_t, wb_t, w1_t, w7_t, we_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T48, w0_t, w0_t ^ w4_t);
w5_t = SM3_EXPAND(w5_t, wc_t, w2_t, w8_t, wf_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T49, w1_t, w1_t ^ w5_t);
w6_t = SM3_EXPAND(w6_t, wd_t, w3_t, w9_t, w0_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T50, w2_t, w2_t ^ w6_t);
w7_t = SM3_EXPAND(w7_t, we_t, w4_t, wa_t, w1_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T51, w3_t, w3_t ^ w7_t);
w8_t = SM3_EXPAND(w8_t, wf_t, w5_t, wb_t, w2_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T52, w4_t, w4_t ^ w8_t);
w9_t = SM3_EXPAND(w9_t, w0_t, w6_t, wc_t, w3_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T53, w5_t, w5_t ^ w9_t);
wa_t = SM3_EXPAND(wa_t, w1_t, w7_t, wd_t, w4_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T54, w6_t, w6_t ^ wa_t);
wb_t = SM3_EXPAND(wb_t, w2_t, w8_t, we_t, w5_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T55, w7_t, w7_t ^ wb_t);
wc_t = SM3_EXPAND(wc_t, w3_t, w9_t, wf_t, w6_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T56, w8_t, w8_t ^ wc_t);
wd_t = SM3_EXPAND(wd_t, w4_t, wa_t, w0_t, w7_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T57, w9_t, w9_t ^ wd_t);
we_t = SM3_EXPAND(we_t, w5_t, wb_t, w1_t, w8_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T58, wa_t, wa_t ^ we_t);
wf_t = SM3_EXPAND(wf_t, w6_t, wc_t, w2_t, w9_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T59, wb_t, wb_t ^ wf_t);
w0_t = SM3_EXPAND(w0_t, w7_t, wd_t, w3_t, wa_t); SM3_ROUND2(a, b, c, d, e, f, g, h, SM3_T60, wc_t, wc_t ^ w0_t);
w1_t = SM3_EXPAND(w1_t, w8_t, we_t, w4_t, wb_t); SM3_ROUND2(d, a, b, c, h, e, f, g, SM3_T61, wd_t, wd_t ^ w1_t);
w2_t = SM3_EXPAND(w2_t, w9_t, wf_t, w5_t, wc_t); SM3_ROUND2(c, d, a, b, g, h, e, f, SM3_T62, we_t, we_t ^ w2_t);
w3_t = SM3_EXPAND(w3_t, wa_t, w0_t, w6_t, wd_t); SM3_ROUND2(b, c, d, a, f, g, h, e, SM3_T63, wf_t, wf_t ^ w3_t);
COMPARE_S_SIMD (d, h, c, g);
}
}
KERNEL_FQ void m31100_m04 (KERN_ATTR_VECTOR ())
{
/**
* base
*/
const u64 lid = get_local_id (0);
const u64 gid = get_global_id (0);
const u64 lsz = get_local_size (0);
if (gid >= GID_CNT) return;
u32 w[16];
w[ 0] = pws[gid].i[ 0];
w[ 1] = pws[gid].i[ 1];
w[ 2] = pws[gid].i[ 2];
w[ 3] = pws[gid].i[ 3];
w[ 4] = 0;
w[ 5] = 0;
w[ 6] = 0;
w[ 7] = 0;
w[ 8] = 0;
w[ 9] = 0;
w[10] = 0;
w[11] = 0;
w[12] = 0;
w[13] = 0;
w[14] = 0;
w[15] = pws[gid].i[15];
const u32 pw_len = pws[gid].pw_len & 63;
/**
* main
*/
m31100m (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, kernel_param, gid, lid, lsz);
}
KERNEL_FQ void m31100_m08 (KERN_ATTR_VECTOR ())
{
/**
* base
*/
const u64 lid = get_local_id (0);
const u64 gid = get_global_id (0);
const u64 lsz = get_local_size (0);
if (gid >= GID_CNT) return;
u32 w[16];
w[ 0] = pws[gid].i[ 0];
w[ 1] = pws[gid].i[ 1];
w[ 2] = pws[gid].i[ 2];
w[ 3] = pws[gid].i[ 3];
w[ 4] = pws[gid].i[ 4];
w[ 5] = pws[gid].i[ 5];
w[ 6] = pws[gid].i[ 6];
w[ 7] = pws[gid].i[ 7];
w[ 8] = 0;
w[ 9] = 0;
w[10] = 0;
w[11] = 0;
w[12] = 0;
w[13] = 0;
w[14] = 0;
w[15] = pws[gid].i[15];
const u32 pw_len = pws[gid].pw_len & 63;
/**
* main
*/
m31100m (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, kernel_param, gid, lid, lsz);
}
KERNEL_FQ void m31100_m16 (KERN_ATTR_VECTOR ())
{
/**
* base
*/
const u64 lid = get_local_id (0);
const u64 gid = get_global_id (0);
const u64 lsz = get_local_size (0);
if (gid >= GID_CNT) return;
u32 w[16];
w[ 0] = pws[gid].i[ 0];
w[ 1] = pws[gid].i[ 1];
w[ 2] = pws[gid].i[ 2];
w[ 3] = pws[gid].i[ 3];
w[ 4] = pws[gid].i[ 4];
w[ 5] = pws[gid].i[ 5];
w[ 6] = pws[gid].i[ 6];
w[ 7] = pws[gid].i[ 7];
w[ 8] = pws[gid].i[ 8];
w[ 9] = pws[gid].i[ 9];
w[10] = pws[gid].i[10];
w[11] = pws[gid].i[11];
w[12] = pws[gid].i[12];
w[13] = pws[gid].i[13];
w[14] = pws[gid].i[14];
w[15] = pws[gid].i[15];
const u32 pw_len = pws[gid].pw_len & 63;
/**
* main
*/
m31100m (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, kernel_param, gid, lid, lsz);
}
KERNEL_FQ void m31100_s04 (KERN_ATTR_VECTOR ())
{
/**
* base
*/
const u64 lid = get_local_id (0);
const u64 gid = get_global_id (0);
const u64 lsz = get_local_size (0);
if (gid >= GID_CNT) return;
u32 w[16];
w[ 0] = pws[gid].i[ 0];
w[ 1] = pws[gid].i[ 1];
w[ 2] = pws[gid].i[ 2];
w[ 3] = pws[gid].i[ 3];
w[ 4] = 0;
w[ 5] = 0;
w[ 6] = 0;
w[ 7] = 0;
w[ 8] = 0;
w[ 9] = 0;
w[10] = 0;
w[11] = 0;
w[12] = 0;
w[13] = 0;
w[14] = 0;
w[15] = pws[gid].i[15];
const u32 pw_len = pws[gid].pw_len & 63;
/**
* main
*/
m31100s (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, kernel_param, gid, lid, lsz);
}
KERNEL_FQ void m31100_s08 (KERN_ATTR_VECTOR ())
{
/**
* base
*/
const u64 lid = get_local_id (0);
const u64 gid = get_global_id (0);
const u64 lsz = get_local_size (0);
if (gid >= GID_CNT) return;
u32 w[16];
w[ 0] = pws[gid].i[ 0];
w[ 1] = pws[gid].i[ 1];
w[ 2] = pws[gid].i[ 2];
w[ 3] = pws[gid].i[ 3];
w[ 4] = pws[gid].i[ 4];
w[ 5] = pws[gid].i[ 5];
w[ 6] = pws[gid].i[ 6];
w[ 7] = pws[gid].i[ 7];
w[ 8] = 0;
w[ 9] = 0;
w[10] = 0;
w[11] = 0;
w[12] = 0;
w[13] = 0;
w[14] = 0;
w[15] = pws[gid].i[15];
const u32 pw_len = pws[gid].pw_len & 63;
/**
* main
*/
m31100s (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, kernel_param, gid, lid, lsz);
}
KERNEL_FQ void m31100_s16 (KERN_ATTR_VECTOR ())
{
/**
* base
*/
const u64 lid = get_local_id (0);
const u64 gid = get_global_id (0);
const u64 lsz = get_local_size (0);
if (gid >= GID_CNT) return;
u32 w[16];
w[ 0] = pws[gid].i[ 0];
w[ 1] = pws[gid].i[ 1];
w[ 2] = pws[gid].i[ 2];
w[ 3] = pws[gid].i[ 3];
w[ 4] = pws[gid].i[ 4];
w[ 5] = pws[gid].i[ 5];
w[ 6] = pws[gid].i[ 6];
w[ 7] = pws[gid].i[ 7];
w[ 8] = pws[gid].i[ 8];
w[ 9] = pws[gid].i[ 9];
w[10] = pws[gid].i[10];
w[11] = pws[gid].i[11];
w[12] = pws[gid].i[12];
w[13] = pws[gid].i[13];
w[14] = pws[gid].i[14];
w[15] = pws[gid].i[15];
const u32 pw_len = pws[gid].pw_len & 63;
/**
* main
*/
m31100s (w, pw_len, pws, rules_buf, combs_buf, words_buf_r, tmps, hooks, bitmaps_buf_s1_a, bitmaps_buf_s1_b, bitmaps_buf_s1_c, bitmaps_buf_s1_d, bitmaps_buf_s2_a, bitmaps_buf_s2_b, bitmaps_buf_s2_c, bitmaps_buf_s2_d, plains_buf, digests_buf, hashes_shown, salt_bufs, esalt_bufs, d_return_buf, d_extra0_buf, d_extra1_buf, d_extra2_buf, d_extra3_buf, kernel_param, gid, lid, lsz);
}

137
OpenCL/m31100_a3-pure.cl Normal file
View File

@ -0,0 +1,137 @@
/**
* Author......: See docs/credits.txt
* License.....: MIT
*/
#define NEW_SIMD_CODE
#ifdef KERNEL_STATIC
#include M2S(INCLUDE_PATH/inc_vendor.h)
#include M2S(INCLUDE_PATH/inc_types.h)
#include M2S(INCLUDE_PATH/inc_platform.cl)
#include M2S(INCLUDE_PATH/inc_common.cl)
#include M2S(INCLUDE_PATH/inc_simd.cl)
#include M2S(INCLUDE_PATH/inc_hash_sm3.cl)
#endif
KERNEL_FQ void m31100_mxx (KERN_ATTR_VECTOR ())
{
/**
* modifier
*/
const u64 lid = get_local_id (0);
const u64 gid = get_global_id (0);
if (gid >= GID_CNT) return;
/**
* base
*/
const u32 pw_len = pws[gid].pw_len;
u32x w[64] = { 0 };
for (u32 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;
sm3_ctx_vector_t ctx;
sm3_init_vector (&ctx);
sm3_update_vector (&ctx, w, pw_len);
sm3_final_vector (&ctx);
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];
COMPARE_M_SIMD (r0, r1, r2, r3);
}
}
KERNEL_FQ void m31100_sxx (KERN_ATTR_VECTOR ())
{
/**
* modifier
*/
const u64 lid = get_local_id (0);
const u64 gid = get_global_id (0);
if (gid >= GID_CNT) return;
/**
* digest
*/
const u32 search[4] =
{
digests_buf[DIGESTS_OFFSET_HOST].digest_buf[DGST_R0],
digests_buf[DIGESTS_OFFSET_HOST].digest_buf[DGST_R1],
digests_buf[DIGESTS_OFFSET_HOST].digest_buf[DGST_R2],
digests_buf[DIGESTS_OFFSET_HOST].digest_buf[DGST_R3]
};
/**
* base
*/
const u32 pw_len = pws[gid].pw_len;
u32x w[64] = { 0 };
for (u32 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;
sm3_ctx_vector_t ctx;
sm3_init_vector (&ctx);
sm3_update_vector (&ctx, w, pw_len);
sm3_final_vector (&ctx);
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];
COMPARE_S_SIMD (r0, r1, r2, r3);
}
}

236
src/modules/module_31100.c Normal file
View File

@ -0,0 +1,236 @@
/**
* Author......: See docs/credits.txt
* License.....: MIT
*/
#include "common.h"
#include "types.h"
#include "modules.h"
#include "bitops.h"
#include "convert.h"
#include "shared.h"
static const u32 ATTACK_EXEC = ATTACK_EXEC_INSIDE_KERNEL;
static const u32 DGST_POS0 = 3;
static const u32 DGST_POS1 = 7;
static const u32 DGST_POS2 = 2;
static const u32 DGST_POS3 = 6;
static const u32 DGST_SIZE = DGST_SIZE_4_8;
static const u32 HASH_CATEGORY = HASH_CATEGORY_RAW_HASH;
static const char *HASH_NAME = "SM3";
static const u64 KERN_TYPE = 31100;
static const u32 OPTI_TYPE = OPTI_TYPE_ZERO_BYTE
| OPTI_TYPE_PRECOMPUTE_INIT
| OPTI_TYPE_EARLY_SKIP
| OPTI_TYPE_NOT_ITERATED
| OPTI_TYPE_NOT_SALTED
| OPTI_TYPE_RAW_HASH;
static const u64 OPTS_TYPE = OPTS_TYPE_STOCK_MODULE
| OPTS_TYPE_PT_GENERATE_BE
| OPTS_TYPE_PT_ADD80
| OPTS_TYPE_PT_ADDBITS15;
static const u32 SALT_TYPE = SALT_TYPE_NONE;
static const char *ST_PASS = "hashcat";
static const char *ST_HASH = "51227e48ea74827b77fc142c3ec21d25cc42c794e6ac422825cd47ad4ac7913d";
u32 module_attack_exec (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ATTACK_EXEC; }
u32 module_dgst_pos0 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS0; }
u32 module_dgst_pos1 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS1; }
u32 module_dgst_pos2 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS2; }
u32 module_dgst_pos3 (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_POS3; }
u32 module_dgst_size (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return DGST_SIZE; }
u32 module_hash_category (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return HASH_CATEGORY; }
const char *module_hash_name (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return HASH_NAME; }
u64 module_kern_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return KERN_TYPE; }
u32 module_opti_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return OPTI_TYPE; }
u64 module_opts_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return OPTS_TYPE; }
u32 module_salt_type (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return SALT_TYPE; }
const char *module_st_hash (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ST_HASH; }
const char *module_st_pass (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const user_options_t *user_options, MAYBE_UNUSED const user_options_extra_t *user_options_extra) { return ST_PASS; }
int module_hash_decode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED void *digest_buf, MAYBE_UNUSED salt_t *salt, MAYBE_UNUSED void *esalt_buf, MAYBE_UNUSED void *hook_salt_buf, MAYBE_UNUSED hashinfo_t *hash_info, const char *line_buf, MAYBE_UNUSED const int line_len)
{
u32 *digest = (u32 *) digest_buf;
hc_token_t token;
token.token_cnt = 1;
token.len_min[0] = 64;
token.len_max[0] = 64;
token.attr[0] = TOKEN_ATTR_VERIFY_LENGTH
| TOKEN_ATTR_VERIFY_HEX;
const int rc_tokenizer = input_tokenizer ((const u8 *) line_buf, line_len, &token);
if (rc_tokenizer != PARSER_OK) return (rc_tokenizer);
const u8 *hash_pos = token.buf[0];
digest[0] = hex_to_u32 (hash_pos + 0);
digest[1] = hex_to_u32 (hash_pos + 8);
digest[2] = hex_to_u32 (hash_pos + 16);
digest[3] = hex_to_u32 (hash_pos + 24);
digest[4] = hex_to_u32 (hash_pos + 32);
digest[5] = hex_to_u32 (hash_pos + 40);
digest[6] = hex_to_u32 (hash_pos + 48);
digest[7] = hex_to_u32 (hash_pos + 56);
digest[0] = byte_swap_32 (digest[0]);
digest[1] = byte_swap_32 (digest[1]);
digest[2] = byte_swap_32 (digest[2]);
digest[3] = byte_swap_32 (digest[3]);
digest[4] = byte_swap_32 (digest[4]);
digest[5] = byte_swap_32 (digest[5]);
digest[6] = byte_swap_32 (digest[6]);
digest[7] = byte_swap_32 (digest[7]);
if (hashconfig->opti_type & OPTI_TYPE_OPTIMIZED_KERNEL)
{
digest[0] ^= SM3_IV_A;
digest[1] ^= SM3_IV_B;
digest[2] ^= SM3_IV_C;
digest[3] ^= SM3_IV_D;
digest[4] ^= SM3_IV_E;
digest[5] ^= SM3_IV_F;
digest[6] ^= SM3_IV_G;
digest[7] ^= SM3_IV_H;
}
return (PARSER_OK);
}
int module_hash_encode (MAYBE_UNUSED const hashconfig_t *hashconfig, MAYBE_UNUSED const void *digest_buf, MAYBE_UNUSED const salt_t *salt, MAYBE_UNUSED const void *esalt_buf, MAYBE_UNUSED const void *hook_salt_buf, MAYBE_UNUSED const hashinfo_t *hash_info, char *line_buf, MAYBE_UNUSED const int line_size)
{
const u32 *digest = (const u32 *) digest_buf;
// we can not change anything in the original buffer, otherwise destroying sorting
// therefore create some local buffer
u32 tmp[8];
tmp[0] = digest[0];
tmp[1] = digest[1];
tmp[2] = digest[2];
tmp[3] = digest[3];
tmp[4] = digest[4];
tmp[5] = digest[5];
tmp[6] = digest[6];
tmp[7] = digest[7];
if (hashconfig->opti_type & OPTI_TYPE_OPTIMIZED_KERNEL)
{
tmp[0] ^= SM3_IV_A;
tmp[1] ^= SM3_IV_B;
tmp[2] ^= SM3_IV_C;
tmp[3] ^= SM3_IV_D;
tmp[4] ^= SM3_IV_E;
tmp[5] ^= SM3_IV_F;
tmp[6] ^= SM3_IV_G;
tmp[7] ^= SM3_IV_H;
}
tmp[0] = byte_swap_32 (tmp[0]);
tmp[1] = byte_swap_32 (tmp[1]);
tmp[2] = byte_swap_32 (tmp[2]);
tmp[3] = byte_swap_32 (tmp[3]);
tmp[4] = byte_swap_32 (tmp[4]);
tmp[5] = byte_swap_32 (tmp[5]);
tmp[6] = byte_swap_32 (tmp[6]);
tmp[7] = byte_swap_32 (tmp[7]);
u8 *out_buf = (u8 *) line_buf;
u32_to_hex (tmp[0], out_buf + 0);
u32_to_hex (tmp[1], out_buf + 8);
u32_to_hex (tmp[2], out_buf + 16);
u32_to_hex (tmp[3], out_buf + 24);
u32_to_hex (tmp[4], out_buf + 32);
u32_to_hex (tmp[5], out_buf + 40);
u32_to_hex (tmp[6], out_buf + 48);
u32_to_hex (tmp[7], out_buf + 56);
const int out_len = 64;
return out_len;
}
void module_init (module_ctx_t *module_ctx)
{
module_ctx->module_context_size = MODULE_CONTEXT_SIZE_CURRENT;
module_ctx->module_interface_version = MODULE_INTERFACE_VERSION_CURRENT;
module_ctx->module_attack_exec = module_attack_exec;
module_ctx->module_benchmark_esalt = MODULE_DEFAULT;
module_ctx->module_benchmark_hook_salt = MODULE_DEFAULT;
module_ctx->module_benchmark_mask = MODULE_DEFAULT;
module_ctx->module_benchmark_charset = MODULE_DEFAULT;
module_ctx->module_benchmark_salt = MODULE_DEFAULT;
module_ctx->module_build_plain_postprocess = MODULE_DEFAULT;
module_ctx->module_deep_comp_kernel = MODULE_DEFAULT;
module_ctx->module_deprecated_notice = MODULE_DEFAULT;
module_ctx->module_dgst_pos0 = module_dgst_pos0;
module_ctx->module_dgst_pos1 = module_dgst_pos1;
module_ctx->module_dgst_pos2 = module_dgst_pos2;
module_ctx->module_dgst_pos3 = module_dgst_pos3;
module_ctx->module_dgst_size = module_dgst_size;
module_ctx->module_dictstat_disable = MODULE_DEFAULT;
module_ctx->module_esalt_size = MODULE_DEFAULT;
module_ctx->module_extra_buffer_size = MODULE_DEFAULT;
module_ctx->module_extra_tmp_size = MODULE_DEFAULT;
module_ctx->module_extra_tuningdb_block = MODULE_DEFAULT;
module_ctx->module_forced_outfile_format = MODULE_DEFAULT;
module_ctx->module_hash_binary_count = MODULE_DEFAULT;
module_ctx->module_hash_binary_parse = MODULE_DEFAULT;
module_ctx->module_hash_binary_save = MODULE_DEFAULT;
module_ctx->module_hash_decode_postprocess = MODULE_DEFAULT;
module_ctx->module_hash_decode_potfile = MODULE_DEFAULT;
module_ctx->module_hash_decode_zero_hash = MODULE_DEFAULT;
module_ctx->module_hash_decode = module_hash_decode;
module_ctx->module_hash_encode_status = MODULE_DEFAULT;
module_ctx->module_hash_encode_potfile = MODULE_DEFAULT;
module_ctx->module_hash_encode = module_hash_encode;
module_ctx->module_hash_init_selftest = MODULE_DEFAULT;
module_ctx->module_hash_mode = MODULE_DEFAULT;
module_ctx->module_hash_category = module_hash_category;
module_ctx->module_hash_name = module_hash_name;
module_ctx->module_hashes_count_min = MODULE_DEFAULT;
module_ctx->module_hashes_count_max = MODULE_DEFAULT;
module_ctx->module_hlfmt_disable = MODULE_DEFAULT;
module_ctx->module_hook_extra_param_size = MODULE_DEFAULT;
module_ctx->module_hook_extra_param_init = MODULE_DEFAULT;
module_ctx->module_hook_extra_param_term = MODULE_DEFAULT;
module_ctx->module_hook12 = MODULE_DEFAULT;
module_ctx->module_hook23 = MODULE_DEFAULT;
module_ctx->module_hook_salt_size = MODULE_DEFAULT;
module_ctx->module_hook_size = MODULE_DEFAULT;
module_ctx->module_jit_build_options = MODULE_DEFAULT;
module_ctx->module_jit_cache_disable = MODULE_DEFAULT;
module_ctx->module_kernel_accel_max = MODULE_DEFAULT;
module_ctx->module_kernel_accel_min = MODULE_DEFAULT;
module_ctx->module_kernel_loops_max = MODULE_DEFAULT;
module_ctx->module_kernel_loops_min = MODULE_DEFAULT;
module_ctx->module_kernel_threads_max = MODULE_DEFAULT;
module_ctx->module_kernel_threads_min = MODULE_DEFAULT;
module_ctx->module_kern_type = module_kern_type;
module_ctx->module_kern_type_dynamic = MODULE_DEFAULT;
module_ctx->module_opti_type = module_opti_type;
module_ctx->module_opts_type = module_opts_type;
module_ctx->module_outfile_check_disable = MODULE_DEFAULT;
module_ctx->module_outfile_check_nocomp = MODULE_DEFAULT;
module_ctx->module_potfile_custom_check = MODULE_DEFAULT;
module_ctx->module_potfile_disable = MODULE_DEFAULT;
module_ctx->module_potfile_keep_all_hashes = MODULE_DEFAULT;
module_ctx->module_pwdump_column = MODULE_DEFAULT;
module_ctx->module_pw_max = MODULE_DEFAULT;
module_ctx->module_pw_min = MODULE_DEFAULT;
module_ctx->module_salt_max = MODULE_DEFAULT;
module_ctx->module_salt_min = MODULE_DEFAULT;
module_ctx->module_salt_type = module_salt_type;
module_ctx->module_separator = MODULE_DEFAULT;
module_ctx->module_st_hash = module_st_hash;
module_ctx->module_st_pass = module_st_pass;
module_ctx->module_tmp_size = MODULE_DEFAULT;
module_ctx->module_unstable_warning = MODULE_DEFAULT;
module_ctx->module_warmup_disable = MODULE_DEFAULT;
}