v23.11

RELEASE_NOTES

@@ -75,10 +75,6 @@ If not what makes it happen or not happen?
 Change Log
 ----------
 
-v23.12
-
-Several bugs fixes and speed improvements for x16r family for all CPU architectures.
-
 v23.11
 
 This is a release candidate for full AArch64 support, marking the end of the Beta phase.

algo/x16/hex.c

@@ -23,12 +23,13 @@ static void hex_getAlgoString(const uint32_t* prevblock, char *output)
    *sptr = '\0';
 }
 
+static __thread x16r_context_overlay hex_ctx;
 
 int hex_hash( void* output, const void* input, int thrid )
 {
    uint32_t _ALIGN(128) hash[16];
    x16r_context_overlay ctx;
-   memcpy( &ctx, &x16r_ref_ctx, sizeof(ctx) );
+   memcpy( &ctx, &hex_ctx, sizeof(ctx) );
    void *in = (void*) input;
    int size = 80;
 
@@ -86,7 +87,7 @@ int hex_hash( void* output, const void* input, int thrid )
          case LUFFA:
             if ( i == 0 )
             {
-              update_and_final_luffa( &ctx.luffa, hash, in+64, 16 );
+              update_and_final_luffa( &ctx.luffa, hash, (const void*)in+64, 16 );
             }
             else
             {
@@ -96,7 +97,7 @@ int hex_hash( void* output, const void* input, int thrid )
             break;
          case CUBEHASH:
             if ( i == 0 )
-               cubehashUpdateDigest( &ctx.cube, hash, in+64, 16 );
+               cubehashUpdateDigest( &ctx.cube, hash, (const void*)in+64, 16 );
             else
             {
                cubehashInit( &ctx.cube, 512, 16, 32 );
@@ -204,32 +205,32 @@ int scanhash_hex( struct work *work, uint32_t max_nonce,
    switch ( algo )
    {
       case JH:
-         sph_jh512_init( &x16r_ref_ctx.jh );
-         sph_jh512( &x16r_ref_ctx.jh, edata, 64 );
+         sph_jh512_init( &hex_ctx.jh );
+         sph_jh512( &hex_ctx.jh, edata, 64 );
       break;
       case SKEIN:
-         sph_skein512_init( &x16r_ref_ctx.skein );
-         sph_skein512( &x16r_ref_ctx.skein, edata, 64 );
+         sph_skein512_init( &hex_ctx.skein );
+         sph_skein512( &hex_ctx.skein, edata, 64 );
       break;
       case LUFFA:
-         init_luffa( &x16r_ref_ctx.luffa, 512 );
-         update_luffa( &x16r_ref_ctx.luffa, edata, 64 );
+         init_luffa( &hex_ctx.luffa, 512 );
+         update_luffa( &hex_ctx.luffa, edata, 64 );
       break;
       case CUBEHASH:
-         cubehashInit( &x16r_ref_ctx.cube, 512, 16, 32 );
-         cubehashUpdate( &x16r_ref_ctx.cube, edata, 64 );
+         cubehashInit( &hex_ctx.cube, 512, 16, 32 );
+         cubehashUpdate( &hex_ctx.cube, edata, 64 );
       break;
       case HAMSI:
-         sph_hamsi512_init( &x16r_ref_ctx.hamsi );
-         sph_hamsi512( &x16r_ref_ctx.hamsi, edata, 64 );
+         sph_hamsi512_init( &hex_ctx.hamsi );
+         sph_hamsi512( &hex_ctx.hamsi, edata, 64 );
       break;
       case SHABAL:
-         sph_shabal512_init( &x16r_ref_ctx.shabal );
-         sph_shabal512( &x16r_ref_ctx.shabal, edata, 64 );
+         sph_shabal512_init( &hex_ctx.shabal );
+         sph_shabal512( &hex_ctx.shabal, edata, 64 );
       break;
       case WHIRLPOOL:
-         sph_whirlpool_init( &x16r_ref_ctx.whirlpool );
-         sph_whirlpool( &x16r_ref_ctx.whirlpool, edata, 64 );
+         sph_whirlpool_init( &hex_ctx.whirlpool );
+         sph_whirlpool( &hex_ctx.whirlpool, edata, 64 );
       break;
    }
    

algo/x16/x16r-4way.c

@@ -1012,7 +1012,7 @@ void x16r_2x64_prehash( void *vdata, void *pdata )
       }
       break;
       case HAMSI:
-#if defined(__SSE4_2__) || defined(__ARM_NEON)
+#if defined(__SSE4_2__)
          v128_bswap32_intrlv80_2x64( vdata, pdata );
          hamsi512_2x64_init( &x16r_ctx.hamsi );
          hamsi512_2x64_update( &x16r_ctx.hamsi, vdata, 72 );
@@ -1144,7 +1144,6 @@ int x16r_2x64_hash_generic( void* output, const void* input, int thrid )
             if ( i == 0 )
             {
                update_and_final_luffa( &ctx.luffa, hash0, in0 + 64, 16 );
-               memcpy( &ctx, &x16r_ctx, sizeof(ctx) );
                update_and_final_luffa( &ctx.luffa, hash1, in1 + 64, 16 );
             }
             else
@@ -1157,7 +1156,6 @@ int x16r_2x64_hash_generic( void* output, const void* input, int thrid )
             if ( i == 0 )
             {
                cubehashUpdateDigest( &ctx.cube, hash0, in0 + 64, 16 );
-               memcpy( &ctx, &x16r_ctx, sizeof(ctx) );
                cubehashUpdateDigest( &ctx.cube, hash1, in1 + 64, 16 );
             }
             else

algo/x16/x16r-gate.h

@@ -55,7 +55,7 @@
   #define X16R_8WAY   1
 #elif defined(__AVX2__) && defined(__AES__)
   #define X16R_4WAY   1
-#elif defined(__SSE2__) || defined(__ARM_NEON)
+#elif defined(__SSE2__) || defined(__ARM_NEON__)
   #define X16R_2WAY   1
 #endif
 
@@ -63,7 +63,7 @@
   #define X16RV2_8WAY 1
 #elif defined(__AVX2__) && defined(__AES__)
   #define X16RV2_4WAY 1
-#elif defined(__SSE2__) || defined(__ARM_NEON)
+#elif defined(__SSE2__) || defined(__ARM_NEON__)
   #define X16RV2_2WAY 1
 #endif
 
@@ -72,7 +72,7 @@
   #define X16RT_8WAY  1
 #elif defined(__AVX2__) && defined(__AES__)
   #define X16RT_4WAY  1
-#elif defined(__SSE2__) || defined(__ARM_NEON)
+#elif defined(__SSE2__) || defined(__ARM_NEON__)
   #define X16RT_2WAY  1
 #endif
 
@@ -80,7 +80,7 @@
   #define X21S_8WAY   1
 #elif defined(__AVX2__) && defined(__AES__)
   #define X21S_4WAY   1
-#elif defined(__SSE2__) || defined(__ARM_NEON)
+#elif defined(__SSE2__) || defined(__ARM_NEON__)
   #define X21S_2WAY   1
 #endif
 
@@ -250,7 +250,6 @@ extern __thread x16r_2x64_context_overlay x16r_ctx;
 
 #endif
 
-// need a reference, add hooks for SSE2.
 // needed for hex
 union _x16r_context_overlay
 {
@@ -273,7 +272,11 @@ union _x16r_context_overlay
 #else
         sph_echo512_context     echo;
 #endif
+#if defined(__SSE4_2__) || defined(__ARM_NEON)
+        hamsi_2x64_context      hamsi;
+#else
         sph_hamsi512_context    hamsi;
+#endif
 #if defined(__AES__)
         hashState_fugue         fugue;
 #else

algo/x16/x16r.c

@@ -74,8 +74,8 @@ int x16r_hash_generic( void* output, const void* input, int thrid )
          break;
          case BMW:
             sph_bmw512_init( &ctx.bmw );
-            sph_bmw512( &ctx.bmw, in, size );
-            sph_bmw512_close( &ctx.bmw, hash );
+            sph_bmw512(&ctx.bmw, in, size);
+            sph_bmw512_close(&ctx.bmw, hash);
          break;
          case GROESTL:
 #if defined(__AES__)  // || defined(__ARM_FEATURE_AES)
@@ -88,13 +88,13 @@ int x16r_hash_generic( void* output, const void* input, int thrid )
          break;
          case JH:
             if ( i == 0 )
-               sph_jh512( &ctx.jh, in+64, 16 );
+               sph_jh512(&ctx.jh, in+64, 16 );
             else
             {
                sph_jh512_init( &ctx.jh );
-               sph_jh512( &ctx.jh, in, size );
+               sph_jh512(&ctx.jh, in, size );
             }
-            sph_jh512_close( &ctx.jh, hash );
+            sph_jh512_close(&ctx.jh, hash );
          break;
          case KECCAK:
             if ( i == 0 )
@@ -108,7 +108,7 @@ int x16r_hash_generic( void* output, const void* input, int thrid )
          break;
          case SKEIN:
             if ( i == 0 )
-               sph_skein512( &ctx.skein, in+64, 16 );
+               sph_skein512(&ctx.skein, in+64, 16 );
             else
             {
                sph_skein512_init( &ctx.skein );
@@ -133,8 +133,8 @@ int x16r_hash_generic( void* output, const void* input, int thrid )
          break;
          case SIMD:
             sph_simd512_init( &ctx.simd );
-            sph_simd512( &ctx.simd, hash, size );
-            sph_simd512_close( &ctx.simd, hash );
+            sph_simd512(&ctx.simd, hash, 64);
+            sph_simd512_close(&ctx.simd, hash);
          break;
          case ECHO:
 #if defined(__AES__)
@@ -147,7 +147,7 @@ int x16r_hash_generic( void* output, const void* input, int thrid )
          break;
          case HAMSI:
             if ( i == 0 )
-               sph_hamsi512( &ctx.hamsi, in+72, 8 );
+               sph_hamsi512( &ctx.hamsi, in+64, 16 );
             else
             {
                sph_hamsi512_init( &ctx.hamsi );

algo/x16/x16rv2-4way.c

@@ -395,7 +395,7 @@ int x16rv2_8way_hash( void* output, const void* input, int thrid )
          break;
          case HAMSI:
             if ( i == 0 )
-               hamsi512_8way_update( &ctx.hamsi, input + (72<<3), 8 );
+               hamsi512_8way_update( &ctx.hamsi, input + (64<<3), 16 );
             else
             {
                intrlv_8x64( vhash, in0, in1, in2, in3, in4, in5, in6, in7,
@@ -409,43 +409,14 @@ int x16rv2_8way_hash( void* output, const void* input, int thrid )
                           hash7, vhash );
          break;
          case FUGUE:
-            if ( i == 0 )
-            {
-               fugue512_update( &ctx.fugue, in0 + 76, 4 );
-               fugue512_final( &ctx.fugue, hash0 );
-               memcpy( &ctx, &x16rv2_ctx, sizeof(hashState_fugue) );
-               fugue512_update( &ctx.fugue, in1 + 76, 4 );
-               fugue512_final( &ctx.fugue, hash1 );
-               memcpy( &ctx, &x16rv2_ctx, sizeof(hashState_fugue) );
-               fugue512_update( &ctx.fugue, in2 + 76, 4 );
-               fugue512_final( &ctx.fugue, hash2 );
-               memcpy( &ctx, &x16rv2_ctx, sizeof(hashState_fugue) );
-               fugue512_update( &ctx.fugue, in3 + 76, 4 );
-               fugue512_final( &ctx.fugue, hash3 );
-               memcpy( &ctx, &x16rv2_ctx, sizeof(hashState_fugue) ); 
-               fugue512_update( &ctx.fugue, in4 + 76, 4 ); 
-               fugue512_final( &ctx.fugue, hash4 ); 
-               memcpy( &ctx, &x16rv2_ctx, sizeof(hashState_fugue) ); 
-               fugue512_update( &ctx.fugue, in5 + 76, 4 );
-               fugue512_final( &ctx.fugue, hash5 );
-               memcpy( &ctx, &x16rv2_ctx, sizeof(hashState_fugue) );
-               fugue512_update( &ctx.fugue, in6 + 76, 4 );
-               fugue512_final( &ctx.fugue, hash6 );
-               memcpy( &ctx, &x16rv2_ctx, sizeof(hashState_fugue) );
-               fugue512_update( &ctx.fugue, in7 + 76, 4 );
-               fugue512_final( &ctx.fugue, hash7 );
-            }
-            else
-            {
-               fugue512_full( &ctx.fugue, hash0, hash0, size );
-               fugue512_full( &ctx.fugue, hash1, hash1, size );
-               fugue512_full( &ctx.fugue, hash2, hash2, size );
-               fugue512_full( &ctx.fugue, hash3, hash3, size );
-               fugue512_full( &ctx.fugue, hash4, hash4, size );
-               fugue512_full( &ctx.fugue, hash5, hash5, size );
-               fugue512_full( &ctx.fugue, hash6, hash6, size );
-               fugue512_full( &ctx.fugue, hash7, hash7, size );
-            }
+            fugue512_full( &ctx.fugue, hash0, in0, size );
+            fugue512_full( &ctx.fugue, hash1, in1, size );
+            fugue512_full( &ctx.fugue, hash2, in2, size );
+            fugue512_full( &ctx.fugue, hash3, in3, size );
+            fugue512_full( &ctx.fugue, hash4, in4, size );
+            fugue512_full( &ctx.fugue, hash5, in5, size );
+            fugue512_full( &ctx.fugue, hash6, in6, size );
+            fugue512_full( &ctx.fugue, hash7, in7, size );
          break;
          case SHABAL:
             intrlv_8x32( vhash, in0, in1, in2, in3, in4, in5, in6, in7,
@@ -617,7 +588,7 @@ int scanhash_x16rv2_8way( struct work *work, uint32_t max_nonce,
    {
       x16_r_s_getAlgoString( (const uint8_t*)bedata1, x16r_hash_order );
       s_ntime = ntime;
-      if ( !opt_quiet && !thr_id )
+      if ( opt_debug && !thr_id )
          applog( LOG_INFO, "hash order %s (%08x)", x16r_hash_order, ntime );
    }
 
@@ -655,14 +626,7 @@ int scanhash_x16rv2_8way( struct work *work, uint32_t max_nonce,
       case HAMSI:
          mm512_bswap32_intrlv80_8x64( vdata, pdata );
          hamsi512_8way_init( &x16rv2_ctx.hamsi );
-         hamsi512_8way_update( &x16rv2_ctx.hamsi, vdata, 72 );
-      break;
-      case FUGUE:
-         v128_bswap32_80( edata, pdata );
-         fugue512_init( &x16rv2_ctx.fugue );
-         fugue512_update( &x16rv2_ctx.fugue, edata, 76 );
-         intrlv_8x64( vdata, edata, edata, edata, edata,
-                             edata, edata, edata, edata, 640 );
+         hamsi512_8way_update( &x16rv2_ctx.hamsi, vdata, 64 );
       break;
       case SHABAL:
          mm256_bswap32_intrlv80_8x32( vdata2, pdata );
@@ -860,8 +824,8 @@ int x16rv2_4way_hash( void* output, const void* input, int thrid )
                intrlv_4x64( vhash, in0, in1, in2, in3, size<<3 );
                skein512_4way_init( &ctx.skein );
                skein512_4way_update( &ctx.skein, vhash, size );
-               skein512_4way_close( &ctx.skein, vhash );
             }
+            skein512_4way_close( &ctx.skein, vhash );
             dintrlv_4x64_512( hash0, hash1, hash2, hash3, vhash );
          break;
          case LUFFA:
@@ -981,7 +945,7 @@ int x16rv2_4way_hash( void* output, const void* input, int thrid )
          break;
          case HAMSI:
             if ( i == 0 )
-               hamsi512_4way_update( &ctx.hamsi, input + (72<<2), 8 );
+               hamsi512_4way_update( &ctx.hamsi, input + (64<<2), 16 );
             else
             {
                intrlv_4x64( vhash, in0, in1, in2, in3, size<<3 );
@@ -992,27 +956,10 @@ int x16rv2_4way_hash( void* output, const void* input, int thrid )
             dintrlv_4x64_512( hash0, hash1, hash2, hash3, vhash );
          break;
          case FUGUE:
-            if ( i == 0 )
-            {
-               fugue512_update( &ctx.fugue, in0 + 76, 4 );
-               fugue512_final( &ctx.fugue, hash0 );
-               memcpy( &ctx, &x16rv2_ctx, sizeof(hashState_fugue) );
-               fugue512_update( &ctx.fugue, in1 + 76, 4 );
-               fugue512_final( &ctx.fugue, hash1 );
-               memcpy( &ctx, &x16rv2_ctx, sizeof(hashState_fugue) );
-               fugue512_update( &ctx.fugue, in2 + 76, 4 );
-               fugue512_final( &ctx.fugue, hash2 );
-               memcpy( &ctx, &x16rv2_ctx, sizeof(hashState_fugue) );
-               fugue512_update( &ctx.fugue, in3 + 76, 4 );
-               fugue512_final( &ctx.fugue, hash3 );
-            }
-            else
-            {
-               fugue512_full( &ctx.fugue, hash0, hash0, size );
-               fugue512_full( &ctx.fugue, hash1, hash1, size );
-               fugue512_full( &ctx.fugue, hash2, hash2, size );
-               fugue512_full( &ctx.fugue, hash3, hash3, size );
-            }
+            fugue512_full( &ctx.fugue, hash0, in0, size );
+            fugue512_full( &ctx.fugue, hash1, in1, size );
+            fugue512_full( &ctx.fugue, hash2, in2, size );
+            fugue512_full( &ctx.fugue, hash3, in3, size );
          break;
          case SHABAL:
              intrlv_4x32( vhash, in0, in1, in2, in3, size<<3 );
@@ -1130,7 +1077,7 @@ int scanhash_x16rv2_4way( struct work *work, uint32_t max_nonce,
    {
       x16_r_s_getAlgoString( (const uint8_t*)bedata1, x16r_hash_order );
       s_ntime = ntime;
-      if ( !opt_quiet && !thr_id )
+      if ( opt_debug && !thr_id )
          applog( LOG_INFO, "hash order %s (%08x)", x16r_hash_order, ntime );
    }
 
@@ -1154,7 +1101,7 @@ int scanhash_x16rv2_4way( struct work *work, uint32_t max_nonce,
       break;
       case SKEIN:
          mm256_bswap32_intrlv80_4x64( vdata, pdata );
-         skein512_4way_prehash64( &x16rv2_ctx.skein, vdata );
+         skein512_4way_prehash64( &x16r_ctx.skein, vdata );
       break;
       case CUBEHASH:
          v128_bswap32_80( edata, pdata );
@@ -1165,13 +1112,7 @@ int scanhash_x16rv2_4way( struct work *work, uint32_t max_nonce,
       case HAMSI:
          mm256_bswap32_intrlv80_4x64( vdata, pdata );
          hamsi512_4way_init( &x16rv2_ctx.hamsi );
-         hamsi512_4way_update( &x16rv2_ctx.hamsi, vdata, 72 );
-      break;
-      case FUGUE:
-         v128_bswap32_80( edata, pdata );
-         fugue512_init( &x16rv2_ctx.fugue );
-         fugue512_update( &x16rv2_ctx.fugue, edata, 76 );
-         intrlv_4x64( vdata, edata, edata, edata, edata, 640 );
+         hamsi512_4way_update( &x16rv2_ctx.hamsi, vdata, 64 );
       break;
       case SHABAL:
          v128_bswap32_intrlv80_4x32( vdata32, pdata );
@@ -1316,7 +1257,7 @@ int x16rv2_2x64_hash( void* output, const void* input, int thrid )
          break;
          case JH:
             if ( i == 0 )
-               jh512_2x64_update( &ctx.jh, input + (64<<1), 16 );
+               jh512_2x64_update( &ctx.jh, input + (64<<2), 16 );
             else
             {
                intrlv_2x64( vhash, in0, in1, size<<3 );
@@ -1355,12 +1296,14 @@ int x16rv2_2x64_hash( void* output, const void* input, int thrid )
          break;
          case SKEIN:
             if ( i == 0 )
-               skein512_2x64_final16( &ctx.skein, vhash, input + (64*2) );
+               skein512_2x64_final16( &ctx.skein, vhash, input + (64*4) );
             else
             {
                intrlv_2x64( vhash, in0, in1, size<<3 );
-               skein512_2x64_full( &ctx.skein, vhash, vhash,  size );
+               skein512_2x64_init( &ctx.skein );
+               skein512_2x64_update( &ctx.skein, vhash, size );
             }
+            skein512_2x64_close( &ctx.skein, vhash );
             dintrlv_2x64( hash0, hash1, vhash, 512 );
          break;
          case LUFFA:
@@ -1383,14 +1326,13 @@ int x16rv2_2x64_hash( void* output, const void* input, int thrid )
             }
             for ( int i = (24/4); i < (64/4); i++ )
                 hash0[i] = hash1[i] = 0;
-            luffa_full( &ctx.luffa, hash0, 512, hash0, 64 );
-            luffa_full( &ctx.luffa, hash1, 512, hash1, 64 );
+            luffa_full( &ctx.luffa, hash0, 512, hash0, size );
+            luffa_full( &ctx.luffa, hash1, 512, hash1, size );
          break;
          case CUBEHASH:
             if ( i == 0 )
             {
                cubehashUpdateDigest( &ctx.cube, hash0, in0 + 64, 16 );
-               memcpy( &ctx, &x16rv2_ctx, sizeof(ctx) );
                cubehashUpdateDigest( &ctx.cube, hash1, in1 + 64, 16 );
             }
             else
@@ -1437,7 +1379,7 @@ int x16rv2_2x64_hash( void* output, const void* input, int thrid )
             {
                sph_hamsi512( &ctx.hamsi, in0 + 72, 8 );
                sph_hamsi512_close( &ctx.hamsi, hash0 );
-               memcpy( &ctx, &x16rv2_ctx, sizeof(ctx) );
+               memcpy( &ctx, &x16r_ctx, sizeof(ctx) );
                sph_hamsi512( &ctx.hamsi, in1 + 72, 8 );
                sph_hamsi512_close( &ctx.hamsi, hash1 );
             }
@@ -1458,7 +1400,7 @@ int x16rv2_2x64_hash( void* output, const void* input, int thrid )
             {
                fugue512_update( &ctx.fugue, in0 + 76, 4 );
                fugue512_final( &ctx.fugue, hash0 );
-               memcpy( &ctx, &x16rv2_ctx, sizeof(hashState_fugue) );
+               memcpy( &ctx, &x16r_ctx, sizeof(hashState_fugue) );
                fugue512_update( &ctx.fugue, in1 + 76, 4 );
                fugue512_final( &ctx.fugue, hash1 );
             }
@@ -1472,7 +1414,7 @@ int x16rv2_2x64_hash( void* output, const void* input, int thrid )
             {
                sph_fugue512( &ctx.fugue, in0 + 76, 4 );
                sph_fugue512_close( &ctx.fugue, hash0 );
-               memcpy( &ctx, &x16rv2_ctx, sizeof(sph_fugue512_context) );
+               memcpy( &ctx, &x16r_ctx, sizeof(sph_fugue512_context) );
                sph_fugue512( &ctx.fugue, in1 + 76, 4 );
                sph_fugue512_close( &ctx.fugue, hash1 );
             }
@@ -1488,7 +1430,7 @@ int x16rv2_2x64_hash( void* output, const void* input, int thrid )
             {
                sph_shabal512( &ctx.shabal, in0 + 64, 16 );
                sph_shabal512_close( &ctx.shabal, hash0 );
-               memcpy( &ctx, &x16rv2_ctx, sizeof(ctx) );
+               memcpy( &ctx, &x16r_ctx, sizeof(ctx) );
                sph_shabal512( &ctx.shabal, in1 + 64, 16 );
                sph_shabal512_close( &ctx.shabal, hash1 );
             }
@@ -1572,7 +1514,7 @@ int scanhash_x16rv2_2x64( struct work *work, uint32_t max_nonce,
    {
       x16_r_s_getAlgoString( (const uint8_t*)bedata1, x16r_hash_order );
       s_ntime = ntime;
-      if ( !opt_quiet && !thr_id )
+      if ( opt_debug && !thr_id )
          applog( LOG_INFO, "hash order %s (%08x)", x16r_hash_order, ntime );
    }
 
@@ -1596,7 +1538,7 @@ int scanhash_x16rv2_2x64( struct work *work, uint32_t max_nonce,
       break;
       case SKEIN:
          v128_bswap32_intrlv80_2x64( vdata, pdata );
-         skein512_2x64_prehash64( &x16rv2_ctx.skein, vdata );
+         skein512_2x64_prehash64( &x16r_ctx.skein, vdata );
       break;
       case CUBEHASH:
          v128_bswap32_80( edata, pdata );
@@ -1605,32 +1547,32 @@ int scanhash_x16rv2_2x64( struct work *work, uint32_t max_nonce,
          intrlv_2x64( vdata, edata, edata, 640 );
       break;
       case HAMSI:
-#if defined(__SSE4_2__) || defined(__ARM_NEON)
+#if defined(__SSE4_2__)
          v128_bswap32_intrlv80_2x64( vdata, pdata );
-         hamsi512_2x64_init( &x16rv2_ctx.hamsi );
-         hamsi512_2x64_update( &x16rv2_ctx.hamsi, vdata, 72 );
+         hamsi512_2x64_init( &x16r_ctx.hamsi );
+         hamsi512_2x64_update( &x16r_ctx.hamsi, vdata, 72 );
 #else
          v128_bswap32_80( edata, pdata );
-         sph_hamsi512_init( &x16rv2_ctx.hamsi );
-         sph_hamsi512( &x16rv2_ctx.hamsi, edata, 72 );
+         sph_hamsi512_init( &x16r_ctx.hamsi );
+         sph_hamsi512( &x16r_ctx.hamsi, edata, 72 );
          intrlv_2x64( vdata, edata, edata, 640 );
 #endif
       break;
       case FUGUE:
          v128_bswap32_80( edata, pdata );
 #if defined(__AES__)
-         fugue512_init( &x16rv2_ctx.fugue );
-         fugue512_update( &x16rv2_ctx.fugue, edata, 76 );
+         fugue512_init( &x16r_ctx.fugue );
+         fugue512_update( &x16r_ctx.fugue, edata, 76 );
 #else
-         sph_fugue512_init( &x16rv2_ctx.fugue );
-         sph_fugue512( &x16rv2_ctx.fugue, edata, 76 );
+         sph_fugue512_init( &x16r_ctx.fugue );
+         sph_fugue512( &x16r_ctx.fugue, edata, 76 );
 #endif
          intrlv_2x64( vdata, edata, edata, 640 );
       break;
       case SHABAL:
          v128_bswap32_80( edata, pdata );
-         sph_shabal512_init( &x16rv2_ctx.shabal );
-         sph_shabal512( &x16rv2_ctx.shabal, edata, 64);
+         sph_shabal512_init( &x16r_ctx.shabal );
+         sph_shabal512( &x16r_ctx.shabal, edata, 64);
          intrlv_2x64( vdata, edata, edata, 640 );
       break;
       default:

algo/x17/x17-4way.c

@@ -1133,12 +1133,14 @@ int scanhash_x17_2x64( struct work *work, uint32_t max_nonce,
       {
          if ( unlikely( valid_hash( hash, ptarget ) && !bench ) )
          {
+applog(LOG_INFO,"Submitted Thread %d, lane %d",thr_id,0);
               pdata[19] = bswap_32( n );
 //            pdata[19] = n;
             submit_solution( work, hash, mythr );
          }
          if ( unlikely( valid_hash( hash+8, ptarget ) && !bench ) )
          {
+applog(LOG_INFO,"Submitted Thread %d, lane %d",thr_id,1);            
             pdata[19] = bswap_32( n+1 );
             submit_solution( work, hash+8, mythr );
          }

configure

@@ -1,6 +1,6 @@
 #! /bin/sh
 # Guess values for system-dependent variables and create Makefiles.
-# Generated by GNU Autoconf 2.71 for cpuminer-opt 23.12.
+# Generated by GNU Autoconf 2.71 for cpuminer-opt 23.11.
 #
 #
 # Copyright (C) 1992-1996, 1998-2017, 2020-2021 Free Software Foundation,
@@ -608,8 +608,8 @@ MAKEFLAGS=
 # Identity of this package.
 PACKAGE_NAME='cpuminer-opt'
 PACKAGE_TARNAME='cpuminer-opt'
-PACKAGE_VERSION='23.12'
-PACKAGE_STRING='cpuminer-opt 23.12'
+PACKAGE_VERSION='23.11'
+PACKAGE_STRING='cpuminer-opt 23.11'
 PACKAGE_BUGREPORT=''
 PACKAGE_URL=''
 
@@ -1360,7 +1360,7 @@ if test "$ac_init_help" = "long"; then
   # Omit some internal or obsolete options to make the list less imposing.
   # This message is too long to be a string in the A/UX 3.1 sh.
   cat <<_ACEOF
-\`configure' configures cpuminer-opt 23.12 to adapt to many kinds of systems.
+\`configure' configures cpuminer-opt 23.11 to adapt to many kinds of systems.
 
 Usage: $0 [OPTION]... [VAR=VALUE]...
 
@@ -1432,7 +1432,7 @@ fi
 
 if test -n "$ac_init_help"; then
   case $ac_init_help in
-     short | recursive ) echo "Configuration of cpuminer-opt 23.12:";;
+     short | recursive ) echo "Configuration of cpuminer-opt 23.11:";;
    esac
   cat <<\_ACEOF
 
@@ -1538,7 +1538,7 @@ fi
 test -n "$ac_init_help" && exit $ac_status
 if $ac_init_version; then
   cat <<\_ACEOF
-cpuminer-opt configure 23.12
+cpuminer-opt configure 23.11
 generated by GNU Autoconf 2.71
 
 Copyright (C) 2021 Free Software Foundation, Inc.
@@ -1985,7 +1985,7 @@ cat >config.log <<_ACEOF
 This file contains any messages produced by compilers while
 running configure, to aid debugging if configure makes a mistake.
 
-It was created by cpuminer-opt $as_me 23.12, which was
+It was created by cpuminer-opt $as_me 23.11, which was
 generated by GNU Autoconf 2.71.  Invocation command line was
 
   $ $0$ac_configure_args_raw
@@ -3593,7 +3593,7 @@ fi
 
 # Define the identity of the package.
  PACKAGE='cpuminer-opt'
- VERSION='23.12'
+ VERSION='23.11'
 
 
 printf "%s\n" "#define PACKAGE \"$PACKAGE\"" >>confdefs.h
@@ -7508,7 +7508,7 @@ cat >>$CONFIG_STATUS <<\_ACEOF || ac_write_fail=1
 # report actual input values of CONFIG_FILES etc. instead of their
 # values after options handling.
 ac_log="
-This file was extended by cpuminer-opt $as_me 23.12, which was
+This file was extended by cpuminer-opt $as_me 23.11, which was
 generated by GNU Autoconf 2.71.  Invocation command line was
 
   CONFIG_FILES    = $CONFIG_FILES
@@ -7576,7 +7576,7 @@ ac_cs_config_escaped=`printf "%s\n" "$ac_cs_config" | sed "s/^ //; s/'/'\\\\\\\\
 cat >>$CONFIG_STATUS <<_ACEOF || ac_write_fail=1
 ac_cs_config='$ac_cs_config_escaped'
 ac_cs_version="\\
-cpuminer-opt config.status 23.12
+cpuminer-opt config.status 23.11
 configured by $0, generated by GNU Autoconf 2.71,
   with options \\"\$ac_cs_config\\"
 

configure.ac

@@ -1,4 +1,4 @@
-AC_INIT([cpuminer-opt], [23.12])
+AC_INIT([cpuminer-opt], [23.11])
 
 AC_PREREQ([2.59c])
 AC_CANONICAL_SYSTEM