popov/cpuminer-opt-gpu
1
0
Fork 0
mirror of https://github.com/JayDDee/cpuminer-opt.git synced 2025-09-17 23:44:27 +00:00
Code Issues Packages Projects Releases Wiki Activity

v3.12.3

Browse Source
This commit is contained in:
Jay D Dee
2020-02-13 04:25:33 -05:00
parent 3da2b958cf
commit 19b0ac6d5c
34 changed files with 1754 additions and 2610 deletions
Download Patch File Download Diff File Expand all files Collapse all files

752
algo/x17/sonoa-4way.c
View File

@@ -127,40 +127,22 @@ void sonoa_8way_hash( void *state, const void *input )
#if defined(__VAES__)
shavite512_4way_init( &ctx.shavite );
shavite512_4way_update_close( &ctx.shavite, vhashA, vhashA, 64 );
shavite512_4way_init( &ctx.shavite );
shavite512_4way_update_close( &ctx.shavite, vhashB, vhashB, 64 );
shavite512_4way_full( &ctx.shavite, vhashA, vhashA, 64 );
shavite512_4way_full( &ctx.shavite, vhashB, vhashB, 64 );
#else
dintrlv_4x128_512( hash0, hash1, hash2, hash3, vhashA );
dintrlv_4x128_512( hash4, hash5, hash6, hash7, vhashB );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash0, 64 );
sph_shavite512_close( &ctx.shavite, hash0 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash1, 64 );
sph_shavite512_close( &ctx.shavite, hash1 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash2, 64 );
sph_shavite512_close( &ctx.shavite, hash2 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash3, 64 );
sph_shavite512_close( &ctx.shavite, hash3 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash4, 64 );
sph_shavite512_close( &ctx.shavite, hash4 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash5, 64 );
sph_shavite512_close( &ctx.shavite, hash5 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash6, 64 );
sph_shavite512_close( &ctx.shavite, hash6 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash7, 64 );
sph_shavite512_close( &ctx.shavite, hash7 );
shavite512_full( &ctx.shavite, hash0, hash0, 64 );
shavite512_full( &ctx.shavite, hash1, hash1, 64 );
shavite512_full( &ctx.shavite, hash2, hash2, 64 );
shavite512_full( &ctx.shavite, hash3, hash3, 64 );
shavite512_full( &ctx.shavite, hash4, hash4, 64 );
shavite512_full( &ctx.shavite, hash5, hash5, 64 );
shavite512_full( &ctx.shavite, hash6, hash6, 64 );
shavite512_full( &ctx.shavite, hash7, hash7, 64 );
intrlv_4x128_512( vhashA, hash0, hash1, hash2, hash3 );
intrlv_4x128_512( vhashB, hash4, hash5, hash6, hash7 );
@@ -236,9 +218,7 @@ void sonoa_8way_hash( void *state, const void *input )
#endif
skein512_8way_init( &ctx.skein );
skein512_8way_update( &ctx.skein, vhash, 64 );
skein512_8way_close( &ctx.skein, vhash );
skein512_8way_full( &ctx.skein, vhash, vhash, 64 );
jh512_8way_init( &ctx.jh );
jh512_8way_update( &ctx.jh, vhash, 64 );
@@ -258,40 +238,22 @@ void sonoa_8way_hash( void *state, const void *input )
#if defined(__VAES__)
shavite512_4way_init( &ctx.shavite );
shavite512_4way_update_close( &ctx.shavite, vhashA, vhashA, 64 );
shavite512_4way_init( &ctx.shavite );
shavite512_4way_update_close( &ctx.shavite, vhashB, vhashB, 64 );
shavite512_4way_full( &ctx.shavite, vhashA, vhashA, 64 );
shavite512_4way_full( &ctx.shavite, vhashB, vhashB, 64 );
#else
dintrlv_4x128_512( hash0, hash1, hash2, hash3, vhashA );
dintrlv_4x128_512( hash4, hash5, hash6, hash7, vhashB );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash0, 64 );
sph_shavite512_close( &ctx.shavite, hash0 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash1, 64 );
sph_shavite512_close( &ctx.shavite, hash1 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash2, 64 );
sph_shavite512_close( &ctx.shavite, hash2 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash3, 64 );
sph_shavite512_close( &ctx.shavite, hash3 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash4, 64 );
sph_shavite512_close( &ctx.shavite, hash4 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash5, 64 );
sph_shavite512_close( &ctx.shavite, hash5 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash6, 64 );
sph_shavite512_close( &ctx.shavite, hash6 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash7, 64 );
sph_shavite512_close( &ctx.shavite, hash7 );
shavite512_full( &ctx.shavite, hash0, hash0, 64 );
shavite512_full( &ctx.shavite, hash1, hash1, 64 );
shavite512_full( &ctx.shavite, hash2, hash2, 64 );
shavite512_full( &ctx.shavite, hash3, hash3, 64 );
shavite512_full( &ctx.shavite, hash4, hash4, 64 );
shavite512_full( &ctx.shavite, hash5, hash5, 64 );
shavite512_full( &ctx.shavite, hash6, hash6, 64 );
shavite512_full( &ctx.shavite, hash7, hash7, 64 );
intrlv_4x128_512( vhashA, hash0, hash1, hash2, hash3 );
intrlv_4x128_512( vhashB, hash4, hash5, hash6, hash7 );
@@ -393,40 +355,22 @@ void sonoa_8way_hash( void *state, const void *input )
#if defined(__VAES__)
shavite512_4way_init( &ctx.shavite );
shavite512_4way_update_close( &ctx.shavite, vhashA, vhashA, 64 );
shavite512_4way_init( &ctx.shavite );
shavite512_4way_update_close( &ctx.shavite, vhashB, vhashB, 64 );
shavite512_4way_full( &ctx.shavite, vhashA, vhashA, 64 );
shavite512_4way_full( &ctx.shavite, vhashB, vhashB, 64 );
#else
dintrlv_4x128_512( hash0, hash1, hash2, hash3, vhashA );
dintrlv_4x128_512( hash4, hash5, hash6, hash7, vhashB );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash0, 64 );
sph_shavite512_close( &ctx.shavite, hash0 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash1, 64 );
sph_shavite512_close( &ctx.shavite, hash1 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash2, 64 );
sph_shavite512_close( &ctx.shavite, hash2 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash3, 64 );
sph_shavite512_close( &ctx.shavite, hash3 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash4, 64 );
sph_shavite512_close( &ctx.shavite, hash4 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash5, 64 );
sph_shavite512_close( &ctx.shavite, hash5 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash6, 64 );
sph_shavite512_close( &ctx.shavite, hash6 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash7, 64 );
sph_shavite512_close( &ctx.shavite, hash7 );
shavite512_full( &ctx.shavite, hash0, hash0, 64 );
shavite512_full( &ctx.shavite, hash1, hash1, 64 );
shavite512_full( &ctx.shavite, hash2, hash2, 64 );
shavite512_full( &ctx.shavite, hash3, hash3, 64 );
shavite512_full( &ctx.shavite, hash4, hash4, 64 );
shavite512_full( &ctx.shavite, hash5, hash5, 64 );
shavite512_full( &ctx.shavite, hash6, hash6, 64 );
shavite512_full( &ctx.shavite, hash7, hash7, 64 );
intrlv_4x128_512( vhashA, hash0, hash1, hash2, hash3 );
intrlv_4x128_512( vhashB, hash4, hash5, hash6, hash7 );
@@ -477,30 +421,14 @@ void sonoa_8way_hash( void *state, const void *input )
dintrlv_8x64_512( hash0, hash1, hash2, hash3, hash4, hash5, hash6, hash7,
vhash );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash0, 64 );
sph_fugue512_close( &ctx.fugue, hash0 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash1, 64 );
sph_fugue512_close( &ctx.fugue, hash1 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash2, 64 );
sph_fugue512_close( &ctx.fugue, hash2 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash3, 64 );
sph_fugue512_close( &ctx.fugue, hash3 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash4, 64 );
sph_fugue512_close( &ctx.fugue, hash4 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash5, 64 );
sph_fugue512_close( &ctx.fugue, hash5 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash6, 64 );
sph_fugue512_close( &ctx.fugue, hash6 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash7, 64 );
sph_fugue512_close( &ctx.fugue, hash7 );
sph_fugue512_full( &ctx.fugue, hash0, hash0, 64 );
sph_fugue512_full( &ctx.fugue, hash1, hash1, 64 );
sph_fugue512_full( &ctx.fugue, hash2, hash2, 64 );
sph_fugue512_full( &ctx.fugue, hash3, hash3, 64 );
sph_fugue512_full( &ctx.fugue, hash4, hash4, 64 );
sph_fugue512_full( &ctx.fugue, hash5, hash5, 64 );
sph_fugue512_full( &ctx.fugue, hash6, hash6, 64 );
sph_fugue512_full( &ctx.fugue, hash7, hash7, 64 );
// 4
@@ -537,9 +465,7 @@ void sonoa_8way_hash( void *state, const void *input )
#endif
skein512_8way_init( &ctx.skein );
skein512_8way_update( &ctx.skein, vhash, 64 );
skein512_8way_close( &ctx.skein, vhash );
skein512_8way_full( &ctx.skein, vhash, vhash, 64 );
jh512_8way_init( &ctx.jh );
jh512_8way_update( &ctx.jh, vhash, 64 );
@@ -559,40 +485,22 @@ void sonoa_8way_hash( void *state, const void *input )
#if defined(__VAES__)
shavite512_4way_init( &ctx.shavite );
shavite512_4way_update_close( &ctx.shavite, vhashA, vhashA, 64 );
shavite512_4way_init( &ctx.shavite );
shavite512_4way_update_close( &ctx.shavite, vhashB, vhashB, 64 );
shavite512_4way_full( &ctx.shavite, vhashA, vhashA, 64 );
shavite512_4way_full( &ctx.shavite, vhashB, vhashB, 64 );
#else
dintrlv_4x128_512( hash0, hash1, hash2, hash3, vhashA );
dintrlv_4x128_512( hash4, hash5, hash6, hash7, vhashB );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash0, 64 );
sph_shavite512_close( &ctx.shavite, hash0 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash1, 64 );
sph_shavite512_close( &ctx.shavite, hash1 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash2, 64 );
sph_shavite512_close( &ctx.shavite, hash2 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash3, 64 );
sph_shavite512_close( &ctx.shavite, hash3 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash4, 64 );
sph_shavite512_close( &ctx.shavite, hash4 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash5, 64 );
sph_shavite512_close( &ctx.shavite, hash5 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash6, 64 );
sph_shavite512_close( &ctx.shavite, hash6 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash7, 64 );
sph_shavite512_close( &ctx.shavite, hash7 );
shavite512_full( &ctx.shavite, hash0, hash0, 64 );
shavite512_full( &ctx.shavite, hash1, hash1, 64 );
shavite512_full( &ctx.shavite, hash2, hash2, 64 );
shavite512_full( &ctx.shavite, hash3, hash3, 64 );
shavite512_full( &ctx.shavite, hash4, hash4, 64 );
shavite512_full( &ctx.shavite, hash5, hash5, 64 );
shavite512_full( &ctx.shavite, hash6, hash6, 64 );
shavite512_full( &ctx.shavite, hash7, hash7, 64 );
intrlv_4x128_512( vhashA, hash0, hash1, hash2, hash3 );
intrlv_4x128_512( vhashB, hash4, hash5, hash6, hash7 );
@@ -643,30 +551,14 @@ void sonoa_8way_hash( void *state, const void *input )
dintrlv_8x64_512( hash0, hash1, hash2, hash3, hash4, hash5, hash6, hash7,
vhash );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash0, 64 );
sph_fugue512_close( &ctx.fugue, hash0 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash1, 64 );
sph_fugue512_close( &ctx.fugue, hash1 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash2, 64 );
sph_fugue512_close( &ctx.fugue, hash2 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash3, 64 );
sph_fugue512_close( &ctx.fugue, hash3 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash4, 64 );
sph_fugue512_close( &ctx.fugue, hash4 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash5, 64 );
sph_fugue512_close( &ctx.fugue, hash5 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash6, 64 );
sph_fugue512_close( &ctx.fugue, hash6 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash7, 64 );
sph_fugue512_close( &ctx.fugue, hash7 );
sph_fugue512_full( &ctx.fugue, hash0, hash0, 64 );
sph_fugue512_full( &ctx.fugue, hash1, hash1, 64 );
sph_fugue512_full( &ctx.fugue, hash2, hash2, 64 );
sph_fugue512_full( &ctx.fugue, hash3, hash3, 64 );
sph_fugue512_full( &ctx.fugue, hash4, hash4, 64 );
sph_fugue512_full( &ctx.fugue, hash5, hash5, 64 );
sph_fugue512_full( &ctx.fugue, hash6, hash6, 64 );
sph_fugue512_full( &ctx.fugue, hash7, hash7, 64 );
intrlv_8x32_512( vhash, hash0, hash1, hash2, hash3, hash4, hash5, hash6,
hash7 );
@@ -714,39 +606,21 @@ void sonoa_8way_hash( void *state, const void *input )
#if defined(__VAES__)
shavite512_4way_init( &ctx.shavite );
shavite512_4way_update_close( &ctx.shavite, vhashA, vhashA, 64 );
shavite512_4way_init( &ctx.shavite );
shavite512_4way_update_close( &ctx.shavite, vhashB, vhashB, 64 );
shavite512_4way_full( &ctx.shavite, vhashA, vhashA, 64 );
shavite512_4way_full( &ctx.shavite, vhashB, vhashB, 64 );
rintrlv_4x128_8x64( vhash, vhashA, vhashB, 512 );
#else
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash0, 64 );
sph_shavite512_close( &ctx.shavite, hash0 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash1, 64 );
sph_shavite512_close( &ctx.shavite, hash1 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash2, 64 );
sph_shavite512_close( &ctx.shavite, hash2 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash3, 64 );
sph_shavite512_close( &ctx.shavite, hash3 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash4, 64 );
sph_shavite512_close( &ctx.shavite, hash4 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash5, 64 );
sph_shavite512_close( &ctx.shavite, hash5 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash6, 64 );
sph_shavite512_close( &ctx.shavite, hash6 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash7, 64 );
sph_shavite512_close( &ctx.shavite, hash7 );
shavite512_full( &ctx.shavite, hash0, hash0, 64 );
shavite512_full( &ctx.shavite, hash1, hash1, 64 );
shavite512_full( &ctx.shavite, hash2, hash2, 64 );
shavite512_full( &ctx.shavite, hash3, hash3, 64 );
shavite512_full( &ctx.shavite, hash4, hash4, 64 );
shavite512_full( &ctx.shavite, hash5, hash5, 64 );
shavite512_full( &ctx.shavite, hash6, hash6, 64 );
shavite512_full( &ctx.shavite, hash7, hash7, 64 );
intrlv_8x64_512( vhash, hash0, hash1, hash2, hash3, hash4, hash5, hash6,
hash7 );
@@ -791,9 +665,7 @@ void sonoa_8way_hash( void *state, const void *input )
#endif
skein512_8way_init( &ctx.skein );
skein512_8way_update( &ctx.skein, vhash, 64 );
skein512_8way_close( &ctx.skein, vhash );
skein512_8way_full( &ctx.skein, vhash, vhash, 64 );
jh512_8way_init( &ctx.jh );
jh512_8way_update( &ctx.jh, vhash, 64 );
@@ -813,40 +685,22 @@ void sonoa_8way_hash( void *state, const void *input )
#if defined(__VAES__)
shavite512_4way_init( &ctx.shavite );
shavite512_4way_update_close( &ctx.shavite, vhashA, vhashA, 64 );
shavite512_4way_init( &ctx.shavite );
shavite512_4way_update_close( &ctx.shavite, vhashB, vhashB, 64 );
shavite512_4way_full( &ctx.shavite, vhashA, vhashA, 64 );
shavite512_4way_full( &ctx.shavite, vhashB, vhashB, 64 );
#else
dintrlv_4x128_512( hash0, hash1, hash2, hash3, vhashA );
dintrlv_4x128_512( hash4, hash5, hash6, hash7, vhashB );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash0, 64 );
sph_shavite512_close( &ctx.shavite, hash0 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash1, 64 );
sph_shavite512_close( &ctx.shavite, hash1 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash2, 64 );
sph_shavite512_close( &ctx.shavite, hash2 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash3, 64 );
sph_shavite512_close( &ctx.shavite, hash3 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash4, 64 );
sph_shavite512_close( &ctx.shavite, hash4 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash5, 64 );
sph_shavite512_close( &ctx.shavite, hash5 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash6, 64 );
sph_shavite512_close( &ctx.shavite, hash6 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash7, 64 );
sph_shavite512_close( &ctx.shavite, hash7 );
shavite512_full( &ctx.shavite, hash0, hash0, 64 );
shavite512_full( &ctx.shavite, hash1, hash1, 64 );
shavite512_full( &ctx.shavite, hash2, hash2, 64 );
shavite512_full( &ctx.shavite, hash3, hash3, 64 );
shavite512_full( &ctx.shavite, hash4, hash4, 64 );
shavite512_full( &ctx.shavite, hash5, hash5, 64 );
shavite512_full( &ctx.shavite, hash6, hash6, 64 );
shavite512_full( &ctx.shavite, hash7, hash7, 64 );
intrlv_4x128_512( vhashA, hash0, hash1, hash2, hash3 );
intrlv_4x128_512( vhashB, hash4, hash5, hash6, hash7 );
@@ -897,30 +751,14 @@ void sonoa_8way_hash( void *state, const void *input )
dintrlv_8x64_512( hash0, hash1, hash2, hash3, hash4, hash5, hash6, hash7,
vhash );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash0, 64 );
sph_fugue512_close( &ctx.fugue, hash0 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash1, 64 );
sph_fugue512_close( &ctx.fugue, hash1 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash2, 64 );
sph_fugue512_close( &ctx.fugue, hash2 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash3, 64 );
sph_fugue512_close( &ctx.fugue, hash3 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash4, 64 );
sph_fugue512_close( &ctx.fugue, hash4 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash5, 64 );
sph_fugue512_close( &ctx.fugue, hash5 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash6, 64 );
sph_fugue512_close( &ctx.fugue, hash6 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash7, 64 );
sph_fugue512_close( &ctx.fugue, hash7 );
sph_fugue512_full( &ctx.fugue, hash0, hash0, 64 );
sph_fugue512_full( &ctx.fugue, hash1, hash1, 64 );
sph_fugue512_full( &ctx.fugue, hash2, hash2, 64 );
sph_fugue512_full( &ctx.fugue, hash3, hash3, 64 );
sph_fugue512_full( &ctx.fugue, hash4, hash4, 64 );
sph_fugue512_full( &ctx.fugue, hash5, hash5, 64 );
sph_fugue512_full( &ctx.fugue, hash6, hash6, 64 );
sph_fugue512_full( &ctx.fugue, hash7, hash7, 64 );
intrlv_8x32_512( vhash, hash0, hash1, hash2, hash3, hash4, hash5, hash6,
hash7 );
@@ -932,30 +770,14 @@ void sonoa_8way_hash( void *state, const void *input )
dintrlv_8x32_512( hash0, hash1, hash2, hash3, hash4, hash5, hash6, hash7,
vhash );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash0, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash0 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash1, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash1 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash2, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash2 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash3, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash3 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash4, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash4 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash5, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash5 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash6, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash6 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash7, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash7 );
sph_whirlpool512_full( &ctx.whirlpool, hash0, hash0, 64 );
sph_whirlpool512_full( &ctx.whirlpool, hash1, hash1, 64 );
sph_whirlpool512_full( &ctx.whirlpool, hash2, hash2, 64 );
sph_whirlpool512_full( &ctx.whirlpool, hash3, hash3, 64 );
sph_whirlpool512_full( &ctx.whirlpool, hash4, hash4, 64 );
sph_whirlpool512_full( &ctx.whirlpool, hash5, hash5, 64 );
sph_whirlpool512_full( &ctx.whirlpool, hash6, hash6, 64 );
sph_whirlpool512_full( &ctx.whirlpool, hash7, hash7, 64 );
// 6
@@ -992,9 +814,7 @@ void sonoa_8way_hash( void *state, const void *input )
#endif
skein512_8way_init( &ctx.skein );
skein512_8way_update( &ctx.skein, vhash, 64 );
skein512_8way_close( &ctx.skein, vhash );
skein512_8way_full( &ctx.skein, vhash, vhash, 64 );
jh512_8way_init( &ctx.jh );
jh512_8way_update( &ctx.jh, vhash, 64 );
@@ -1014,40 +834,22 @@ void sonoa_8way_hash( void *state, const void *input )
#if defined(__VAES__)
shavite512_4way_init( &ctx.shavite );
shavite512_4way_update_close( &ctx.shavite, vhashA, vhashA, 64 );
shavite512_4way_init( &ctx.shavite );
shavite512_4way_update_close( &ctx.shavite, vhashB, vhashB, 64 );
shavite512_4way_full( &ctx.shavite, vhashA, vhashA, 64 );
shavite512_4way_full( &ctx.shavite, vhashB, vhashB, 64 );
#else
dintrlv_4x128_512( hash0, hash1, hash2, hash3, vhashA );
dintrlv_4x128_512( hash4, hash5, hash6, hash7, vhashB );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash0, 64 );
sph_shavite512_close( &ctx.shavite, hash0 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash1, 64 );
sph_shavite512_close( &ctx.shavite, hash1 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash2, 64 );
sph_shavite512_close( &ctx.shavite, hash2 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash3, 64 );
sph_shavite512_close( &ctx.shavite, hash3 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash4, 64 );
sph_shavite512_close( &ctx.shavite, hash4 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash5, 64 );
sph_shavite512_close( &ctx.shavite, hash5 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash6, 64 );
sph_shavite512_close( &ctx.shavite, hash6 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash7, 64 );
sph_shavite512_close( &ctx.shavite, hash7 );
shavite512_full( &ctx.shavite, hash0, hash0, 64 );
shavite512_full( &ctx.shavite, hash1, hash1, 64 );
shavite512_full( &ctx.shavite, hash2, hash2, 64 );
shavite512_full( &ctx.shavite, hash3, hash3, 64 );
shavite512_full( &ctx.shavite, hash4, hash4, 64 );
shavite512_full( &ctx.shavite, hash5, hash5, 64 );
shavite512_full( &ctx.shavite, hash6, hash6, 64 );
shavite512_full( &ctx.shavite, hash7, hash7, 64 );
intrlv_4x128_512( vhashA, hash0, hash1, hash2, hash3 );
intrlv_4x128_512( vhashB, hash4, hash5, hash6, hash7 );
@@ -1098,30 +900,14 @@ void sonoa_8way_hash( void *state, const void *input )
dintrlv_8x64_512( hash0, hash1, hash2, hash3, hash4, hash5, hash6, hash7,
vhash );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash0, 64 );
sph_fugue512_close( &ctx.fugue, hash0 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash1, 64 );
sph_fugue512_close( &ctx.fugue, hash1 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash2, 64 );
sph_fugue512_close( &ctx.fugue, hash2 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash3, 64 );
sph_fugue512_close( &ctx.fugue, hash3 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash4, 64 );
sph_fugue512_close( &ctx.fugue, hash4 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash5, 64 );
sph_fugue512_close( &ctx.fugue, hash5 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash6, 64 );
sph_fugue512_close( &ctx.fugue, hash6 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash7, 64 );
sph_fugue512_close( &ctx.fugue, hash7 );
sph_fugue512_full( &ctx.fugue, hash0, hash0, 64 );
sph_fugue512_full( &ctx.fugue, hash1, hash1, 64 );
sph_fugue512_full( &ctx.fugue, hash2, hash2, 64 );
sph_fugue512_full( &ctx.fugue, hash3, hash3, 64 );
sph_fugue512_full( &ctx.fugue, hash4, hash4, 64 );
sph_fugue512_full( &ctx.fugue, hash5, hash5, 64 );
sph_fugue512_full( &ctx.fugue, hash6, hash6, 64 );
sph_fugue512_full( &ctx.fugue, hash7, hash7, 64 );
intrlv_8x32_512( vhash, hash0, hash1, hash2, hash3, hash4, hash5, hash6,
hash7 );
@@ -1133,30 +919,14 @@ void sonoa_8way_hash( void *state, const void *input )
dintrlv_8x32_512( hash0, hash1, hash2, hash3, hash4, hash5, hash6, hash7,
vhash );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash0, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash0 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash1, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash1 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash2, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash2 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash3, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash3 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash4, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash4 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash5, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash5 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash6, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash6 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash7, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash7 );
sph_whirlpool512_full( &ctx.whirlpool, hash0, hash0, 64 );
sph_whirlpool512_full( &ctx.whirlpool, hash1, hash1, 64 );
sph_whirlpool512_full( &ctx.whirlpool, hash2, hash2, 64 );
sph_whirlpool512_full( &ctx.whirlpool, hash3, hash3, 64 );
sph_whirlpool512_full( &ctx.whirlpool, hash4, hash4, 64 );
sph_whirlpool512_full( &ctx.whirlpool, hash5, hash5, 64 );
sph_whirlpool512_full( &ctx.whirlpool, hash6, hash6, 64 );
sph_whirlpool512_full( &ctx.whirlpool, hash7, hash7, 64 );
intrlv_8x64_512( vhash, hash0, hash1, hash2, hash3, hash4, hash5, hash6,
hash7 );
@@ -1168,30 +938,14 @@ void sonoa_8way_hash( void *state, const void *input )
dintrlv_8x64_512( hash0, hash1, hash2, hash3, hash4, hash5, hash6, hash7,
vhash );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash0, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash0 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash1, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash1 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash2, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash2 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash3, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash3 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash4, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash4 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash5, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash5 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash6, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash6 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash7, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash7 );
sph_whirlpool512_full( &ctx.whirlpool, hash0, hash0, 64 );
sph_whirlpool512_full( &ctx.whirlpool, hash1, hash1, 64 );
sph_whirlpool512_full( &ctx.whirlpool, hash2, hash2, 64 );
sph_whirlpool512_full( &ctx.whirlpool, hash3, hash3, 64 );
sph_whirlpool512_full( &ctx.whirlpool, hash4, hash4, 64 );
sph_whirlpool512_full( &ctx.whirlpool, hash5, hash5, 64 );
sph_whirlpool512_full( &ctx.whirlpool, hash6, hash6, 64 );
sph_whirlpool512_full( &ctx.whirlpool, hash7, hash7, 64 );
// 7
@@ -1248,40 +1002,22 @@ void sonoa_8way_hash( void *state, const void *input )
#if defined(__VAES__)
shavite512_4way_init( &ctx.shavite );
shavite512_4way_update_close( &ctx.shavite, vhashA, vhashA, 64 );
shavite512_4way_init( &ctx.shavite );
shavite512_4way_update_close( &ctx.shavite, vhashB, vhashB, 64 );
shavite512_4way_full( &ctx.shavite, vhashA, vhashA, 64 );
shavite512_4way_full( &ctx.shavite, vhashB, vhashB, 64 );
#else
dintrlv_4x128_512( hash0, hash1, hash2, hash3, vhashA );
dintrlv_4x128_512( hash4, hash5, hash6, hash7, vhashB );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash0, 64 );
sph_shavite512_close( &ctx.shavite, hash0 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash1, 64 );
sph_shavite512_close( &ctx.shavite, hash1 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash2, 64 );
sph_shavite512_close( &ctx.shavite, hash2 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash3, 64 );
sph_shavite512_close( &ctx.shavite, hash3 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash4, 64 );
sph_shavite512_close( &ctx.shavite, hash4 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash5, 64 );
sph_shavite512_close( &ctx.shavite, hash5 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash6, 64 );
sph_shavite512_close( &ctx.shavite, hash6 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash7, 64 );
sph_shavite512_close( &ctx.shavite, hash7 );
shavite512_full( &ctx.shavite, hash0, hash0, 64 );
shavite512_full( &ctx.shavite, hash1, hash1, 64 );
shavite512_full( &ctx.shavite, hash2, hash2, 64 );
shavite512_full( &ctx.shavite, hash3, hash3, 64 );
shavite512_full( &ctx.shavite, hash4, hash4, 64 );
shavite512_full( &ctx.shavite, hash5, hash5, 64 );
shavite512_full( &ctx.shavite, hash6, hash6, 64 );
shavite512_full( &ctx.shavite, hash7, hash7, 64 );
intrlv_4x128_512( vhashA, hash0, hash1, hash2, hash3 );
intrlv_4x128_512( vhashB, hash4, hash5, hash6, hash7 );
@@ -1332,30 +1068,14 @@ void sonoa_8way_hash( void *state, const void *input )
dintrlv_8x64_512( hash0, hash1, hash2, hash3, hash4, hash5, hash6, hash7,
vhash );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash0, 64 );
sph_fugue512_close( &ctx.fugue, hash0 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash1, 64 );
sph_fugue512_close( &ctx.fugue, hash1 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash2, 64 );
sph_fugue512_close( &ctx.fugue, hash2 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash3, 64 );
sph_fugue512_close( &ctx.fugue, hash3 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash4, 64 );
sph_fugue512_close( &ctx.fugue, hash4 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash5, 64 );
sph_fugue512_close( &ctx.fugue, hash5 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash6, 64 );
sph_fugue512_close( &ctx.fugue, hash6 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash7, 64 );
sph_fugue512_close( &ctx.fugue, hash7 );
sph_fugue512_full( &ctx.fugue, hash0, hash0, 64 );
sph_fugue512_full( &ctx.fugue, hash1, hash1, 64 );
sph_fugue512_full( &ctx.fugue, hash2, hash2, 64 );
sph_fugue512_full( &ctx.fugue, hash3, hash3, 64 );
sph_fugue512_full( &ctx.fugue, hash4, hash4, 64 );
sph_fugue512_full( &ctx.fugue, hash5, hash5, 64 );
sph_fugue512_full( &ctx.fugue, hash6, hash6, 64 );
sph_fugue512_full( &ctx.fugue, hash7, hash7, 64 );
intrlv_8x32_512( vhash, hash0, hash1, hash2, hash3, hash4, hash5, hash6,
hash7 );
@@ -1367,30 +1087,14 @@ void sonoa_8way_hash( void *state, const void *input )
dintrlv_8x32_512( hash0, hash1, hash2, hash3, hash4, hash5, hash6, hash7,
vhash );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash0, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash0 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash1, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash1 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash2, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash2 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash3, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash3 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash4, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash4 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash5, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash5 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash6, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash6 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash7, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash7 );
sph_whirlpool512_full( &ctx.whirlpool, hash0, hash0, 64 );
sph_whirlpool512_full( &ctx.whirlpool, hash1, hash1, 64 );
sph_whirlpool512_full( &ctx.whirlpool, hash2, hash2, 64 );
sph_whirlpool512_full( &ctx.whirlpool, hash3, hash3, 64 );
sph_whirlpool512_full( &ctx.whirlpool, hash4, hash4, 64 );
sph_whirlpool512_full( &ctx.whirlpool, hash5, hash5, 64 );
sph_whirlpool512_full( &ctx.whirlpool, hash6, hash6, 64 );
sph_whirlpool512_full( &ctx.whirlpool, hash7, hash7, 64 );
intrlv_8x64_512( vhash, hash0, hash1, hash2, hash3, hash4, hash5, hash6,
hash7 );
@@ -1657,18 +1361,10 @@ void sonoa_4way_hash( void *state, const void *input )
dintrlv_4x64_512( hash0, hash1, hash2, hash3, vhash );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash0, 64 );
sph_fugue512_close( &ctx.fugue, hash0 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash1, 64 );
sph_fugue512_close( &ctx.fugue, hash1 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash2, 64 );
sph_fugue512_close( &ctx.fugue, hash2 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash3, 64 );
sph_fugue512_close( &ctx.fugue, hash3 );
sph_fugue512_full( &ctx.fugue, hash0, hash0, 64 );
sph_fugue512_full( &ctx.fugue, hash1, hash1, 64 );
sph_fugue512_full( &ctx.fugue, hash2, hash2, 64 );
sph_fugue512_full( &ctx.fugue, hash3, hash3, 64 );
// 4
intrlv_4x64_512( vhash, hash0, hash1, hash2, hash3 );
@@ -1730,18 +1426,10 @@ void sonoa_4way_hash( void *state, const void *input )
dintrlv_4x64_512( hash0, hash1, hash2, hash3, vhash );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash0, 64 );
sph_fugue512_close( &ctx.fugue, hash0 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash1, 64 );
sph_fugue512_close( &ctx.fugue, hash1 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash2, 64 );
sph_fugue512_close( &ctx.fugue, hash2 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash3, 64 );
sph_fugue512_close( &ctx.fugue, hash3 );
sph_fugue512_full( &ctx.fugue, hash0, hash0, 64 );
sph_fugue512_full( &ctx.fugue, hash1, hash1, 64 );
sph_fugue512_full( &ctx.fugue, hash2, hash2, 64 );
sph_fugue512_full( &ctx.fugue, hash3, hash3, 64 );
intrlv_4x32_512( vhash, hash0, hash1, hash2, hash3 );
@@ -1840,18 +1528,10 @@ void sonoa_4way_hash( void *state, const void *input )
dintrlv_4x64_512( hash0, hash1, hash2, hash3, vhash );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash0, 64 );
sph_fugue512_close( &ctx.fugue, hash0 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash1, 64 );
sph_fugue512_close( &ctx.fugue, hash1 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash2, 64 );
sph_fugue512_close( &ctx.fugue, hash2 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash3, 64 );
sph_fugue512_close( &ctx.fugue, hash3 );
sph_fugue512_full( &ctx.fugue, hash0, hash0, 64 );
sph_fugue512_full( &ctx.fugue, hash1, hash1, 64 );
sph_fugue512_full( &ctx.fugue, hash2, hash2, 64 );
sph_fugue512_full( &ctx.fugue, hash3, hash3, 64 );
intrlv_4x32_512( vhash, hash0, hash1, hash2, hash3 );
@@ -1861,18 +1541,10 @@ void sonoa_4way_hash( void *state, const void *input )
dintrlv_4x32_512( hash0, hash1, hash2, hash3, vhash );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash0, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash0 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash1, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash1 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash2, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash2 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash3, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash3 );
sph_whirlpool512_full( &ctx.whirlpool, hash0, hash0, 64 );
sph_whirlpool512_full( &ctx.whirlpool, hash1, hash1, 64 );
sph_whirlpool512_full( &ctx.whirlpool, hash2, hash2, 64 );
sph_whirlpool512_full( &ctx.whirlpool, hash3, hash3, 64 );
// 6
@@ -1935,18 +1607,10 @@ void sonoa_4way_hash( void *state, const void *input )
dintrlv_4x64_512( hash0, hash1, hash2, hash3, vhash );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash0, 64 );
sph_fugue512_close( &ctx.fugue, hash0 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash1, 64 );
sph_fugue512_close( &ctx.fugue, hash1 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash2, 64 );
sph_fugue512_close( &ctx.fugue, hash2 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash3, 64 );
sph_fugue512_close( &ctx.fugue, hash3 );
sph_fugue512_full( &ctx.fugue, hash0, hash0, 64 );
sph_fugue512_full( &ctx.fugue, hash1, hash1, 64 );
sph_fugue512_full( &ctx.fugue, hash2, hash2, 64 );
sph_fugue512_full( &ctx.fugue, hash3, hash3, 64 );
intrlv_4x32_512( vhash, hash0, hash1, hash2, hash3 );
@@ -1956,18 +1620,10 @@ void sonoa_4way_hash( void *state, const void *input )
dintrlv_4x32_512( hash0, hash1, hash2, hash3, vhash );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash0, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash0 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash1, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash1 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash2, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash2 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash3, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash3 );
sph_whirlpool512_full( &ctx.whirlpool, hash0, hash0, 64 );
sph_whirlpool512_full( &ctx.whirlpool, hash1, hash1, 64 );
sph_whirlpool512_full( &ctx.whirlpool, hash2, hash2, 64 );
sph_whirlpool512_full( &ctx.whirlpool, hash3, hash3, 64 );
intrlv_4x64_512( vhash, hash0, hash1, hash2, hash3 );
@@ -1977,18 +1633,10 @@ void sonoa_4way_hash( void *state, const void *input )
dintrlv_4x64_512( hash0, hash1, hash2, hash3, vhash );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash0, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash0 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash1, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash1 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash2, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash2 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash3, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash3 );
sph_whirlpool512_full( &ctx.whirlpool, hash0, hash0, 64 );
sph_whirlpool512_full( &ctx.whirlpool, hash1, hash1, 64 );
sph_whirlpool512_full( &ctx.whirlpool, hash2, hash2, 64 );
sph_whirlpool512_full( &ctx.whirlpool, hash3, hash3, 64 );
// 7
@@ -2051,18 +1699,10 @@ void sonoa_4way_hash( void *state, const void *input )
dintrlv_4x64_512( hash0, hash1, hash2, hash3, vhash );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash0, 64 );
sph_fugue512_close( &ctx.fugue, hash0 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash1, 64 );
sph_fugue512_close( &ctx.fugue, hash1 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash2, 64 );
sph_fugue512_close( &ctx.fugue, hash2 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash3, 64 );
sph_fugue512_close( &ctx.fugue, hash3 );
sph_fugue512_full( &ctx.fugue, hash0, hash0, 64 );
sph_fugue512_full( &ctx.fugue, hash1, hash1, 64 );
sph_fugue512_full( &ctx.fugue, hash2, hash2, 64 );
sph_fugue512_full( &ctx.fugue, hash3, hash3, 64 );
intrlv_4x32_512( vhash, hash0, hash1, hash2, hash3 );
@@ -2072,18 +1712,10 @@ void sonoa_4way_hash( void *state, const void *input )
dintrlv_4x32_512( hash0, hash1, hash2, hash3, vhash );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash0, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash0 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash1, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash1 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash2, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash2 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash3, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash3 );
sph_whirlpool512_full( &ctx.whirlpool, hash0, hash0, 64 );
sph_whirlpool512_full( &ctx.whirlpool, hash1, hash1, 64 );
sph_whirlpool512_full( &ctx.whirlpool, hash2, hash2, 64 );
sph_whirlpool512_full( &ctx.whirlpool, hash3, hash3, 64 );
intrlv_4x64_512( vhash, hash0, hash1, hash2, hash3 );

152
algo/x17/x17-4way.c
View File

@@ -132,30 +132,14 @@ void x17_8way_hash( void *state, const void *input )
dintrlv_4x128_512( hash0, hash1, hash2, hash3, vhashA );
dintrlv_4x128_512( hash4, hash5, hash6, hash7, vhashB );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash0, 64 );
sph_shavite512_close( &ctx.shavite, hash0 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash1, 64 );
sph_shavite512_close( &ctx.shavite, hash1 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash2, 64 );
sph_shavite512_close( &ctx.shavite, hash2 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash3, 64 );
sph_shavite512_close( &ctx.shavite, hash3 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash4, 64 );
sph_shavite512_close( &ctx.shavite, hash4 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash5, 64 );
sph_shavite512_close( &ctx.shavite, hash5 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash6, 64 );
sph_shavite512_close( &ctx.shavite, hash6 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash7, 64 );
sph_shavite512_close( &ctx.shavite, hash7 );
shavite512_full( &ctx.shavite, hash0, hash0, 64 );
shavite512_full( &ctx.shavite, hash1, hash1, 64 );
shavite512_full( &ctx.shavite, hash2, hash2, 64 );
shavite512_full( &ctx.shavite, hash3, hash3, 64 );
shavite512_full( &ctx.shavite, hash4, hash4, 64 );
shavite512_full( &ctx.shavite, hash5, hash5, 64 );
shavite512_full( &ctx.shavite, hash6, hash6, 64 );
shavite512_full( &ctx.shavite, hash7, hash7, 64 );
intrlv_4x128_512( vhashA, hash0, hash1, hash2, hash3 );
intrlv_4x128_512( vhashB, hash4, hash5, hash6, hash7 );
@@ -206,30 +190,14 @@ void x17_8way_hash( void *state, const void *input )
dintrlv_8x64_512( hash0, hash1, hash2, hash3, hash4, hash5, hash6, hash7,
vhash );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash0, 64 );
sph_fugue512_close( &ctx.fugue, hash0 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash1, 64 );
sph_fugue512_close( &ctx.fugue, hash1 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash2, 64 );
sph_fugue512_close( &ctx.fugue, hash2 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash3, 64 );
sph_fugue512_close( &ctx.fugue, hash3 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash4, 64 );
sph_fugue512_close( &ctx.fugue, hash4 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash5, 64 );
sph_fugue512_close( &ctx.fugue, hash5 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash6, 64 );
sph_fugue512_close( &ctx.fugue, hash6 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash7, 64 );
sph_fugue512_close( &ctx.fugue, hash7 );
sph_fugue512_full( &ctx.fugue, hash0, hash0, 64 );
sph_fugue512_full( &ctx.fugue, hash1, hash1, 64 );
sph_fugue512_full( &ctx.fugue, hash2, hash2, 64 );
sph_fugue512_full( &ctx.fugue, hash3, hash3, 64 );
sph_fugue512_full( &ctx.fugue, hash4, hash4, 64 );
sph_fugue512_full( &ctx.fugue, hash5, hash5, 64 );
sph_fugue512_full( &ctx.fugue, hash6, hash6, 64 );
sph_fugue512_full( &ctx.fugue, hash7, hash7, 64 );
intrlv_8x32_512( vhash, hash0, hash1, hash2, hash3, hash4, hash5, hash6,
hash7 );
@@ -241,30 +209,14 @@ void x17_8way_hash( void *state, const void *input )
dintrlv_8x32_512( hash0, hash1, hash2, hash3, hash4, hash5, hash6, hash7,
vhash );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash0, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash0 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash1, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash1 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash2, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash2 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash3, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash3 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash4, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash4 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash5, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash5 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash6, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash6 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash7, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash7 );
sph_whirlpool512_full( &ctx.whirlpool, hash0, hash0, 64 );
sph_whirlpool512_full( &ctx.whirlpool, hash1, hash1, 64 );
sph_whirlpool512_full( &ctx.whirlpool, hash2, hash2, 64 );
sph_whirlpool512_full( &ctx.whirlpool, hash3, hash3, 64 );
sph_whirlpool512_full( &ctx.whirlpool, hash4, hash4, 64 );
sph_whirlpool512_full( &ctx.whirlpool, hash5, hash5, 64 );
sph_whirlpool512_full( &ctx.whirlpool, hash6, hash6, 64 );
sph_whirlpool512_full( &ctx.whirlpool, hash7, hash7, 64 );
intrlv_8x64_512( vhash, hash0, hash1, hash2, hash3, hash4, hash5, hash6,
hash7 );
@@ -283,10 +235,10 @@ void x17_8way_hash( void *state, const void *input )
int scanhash_x17_8way( struct work *work, uint32_t max_nonce,
uint64_t *hashes_done, struct thr_info *mythr )
{
uint32_t hash[8*8] __attribute__ ((aligned (128)));
uint32_t hash32[8*8] __attribute__ ((aligned (128)));
uint32_t vdata[20*8] __attribute__ ((aligned (64)));
uint32_t lane_hash[8] __attribute__ ((aligned (64)));
uint32_t *hashd7 = &(hash[7*8]);
uint32_t *hash32_d7 = &(hash32[7*8]);
uint32_t *pdata = work->data;
const uint32_t *ptarget = work->target;
const uint32_t first_nonce = pdata[19];
@@ -294,7 +246,7 @@ int scanhash_x17_8way( struct work *work, uint32_t max_nonce,
__m512i *noncev = (__m512i*)vdata + 9;
uint32_t n = first_nonce;
const int thr_id = mythr->id;
const uint32_t targ32 = ptarget[7];
const uint32_t targ32_d7 = ptarget[7];
const bool bench = opt_benchmark;
mm512_bswap32_intrlv80_8x64( vdata, pdata );
@@ -303,12 +255,12 @@ int scanhash_x17_8way( struct work *work, uint32_t max_nonce,
n+3, 0, n+2, 0, n+1, 0, n, 0 ), *noncev );
do
{
x17_8way_hash( hash, vdata );
x17_8way_hash( hash32, vdata );
for ( int lane = 0; lane < 8; lane++ )
if ( unlikely( ( hashd7[ lane ] <= targ32 ) && !bench ) )
if ( unlikely( ( hash32_d7[ lane ] <= targ32_d7 ) && !bench ) )
{
extr_lane_8x32( lane_hash, hash, lane, 256 );
extr_lane_8x32( lane_hash, hash32, lane, 256 );
if ( likely( valid_hash( lane_hash, ptarget ) ) )
{
pdata[19] = bswap_32( n + lane );
@@ -418,18 +370,10 @@ void x17_4way_hash( void *state, const void *input )
dintrlv_4x64_512( hash0, hash1, hash2, hash3, vhash );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash0, 64 );
sph_fugue512_close( &ctx.fugue, hash0 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash1, 64 );
sph_fugue512_close( &ctx.fugue, hash1 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash2, 64 );
sph_fugue512_close( &ctx.fugue, hash2 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash3, 64 );
sph_fugue512_close( &ctx.fugue, hash3 );
sph_fugue512_full( &ctx.fugue, hash0, hash0, 64 );
sph_fugue512_full( &ctx.fugue, hash1, hash1, 64 );
sph_fugue512_full( &ctx.fugue, hash2, hash2, 64 );
sph_fugue512_full( &ctx.fugue, hash3, hash3, 64 );
intrlv_4x32_512( vhash, hash0, hash1, hash2, hash3 );
@@ -439,18 +383,10 @@ void x17_4way_hash( void *state, const void *input )
dintrlv_4x32_512( hash0, hash1, hash2, hash3, vhash );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash0, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash0 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash1, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash1 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash2, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash2 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash3, 64 );
sph_whirlpool_close( &ctx.whirlpool, hash3 );
sph_whirlpool512_full( &ctx.whirlpool, hash0, hash0, 64 );
sph_whirlpool512_full( &ctx.whirlpool, hash1, hash1, 64 );
sph_whirlpool512_full( &ctx.whirlpool, hash2, hash2, 64 );
sph_whirlpool512_full( &ctx.whirlpool, hash3, hash3, 64 );
intrlv_4x64_512( vhash, hash0, hash1, hash2, hash3 );
@@ -468,10 +404,10 @@ void x17_4way_hash( void *state, const void *input )
int scanhash_x17_4way( struct work *work, uint32_t max_nonce,
uint64_t *hashes_done, struct thr_info *mythr )
{
uint32_t hash[8*4] __attribute__ ((aligned (64)));
uint32_t hash32[8*4] __attribute__ ((aligned (64)));
uint32_t vdata[20*4] __attribute__ ((aligned (64)));
uint32_t lane_hash[8] __attribute__ ((aligned (64)));
uint32_t *hashd7 = &(hash[ 7*4 ]);
uint32_t *hash32_d7 = &(hash32[ 7*4 ]);
uint32_t *pdata = work->data;
const uint32_t *ptarget = work->target;
const uint32_t first_nonce = pdata[19];
@@ -479,7 +415,7 @@ int scanhash_x17_4way( struct work *work, uint32_t max_nonce,
__m256i *noncev = (__m256i*)vdata + 9;
uint32_t n = first_nonce;
const int thr_id = mythr->id;
const uint32_t targ32 = ptarget[7];
const uint32_t targ32_d7 = ptarget[7];
const bool bench = opt_benchmark;
mm256_bswap32_intrlv80_4x64( vdata, pdata );
@@ -487,12 +423,12 @@ int scanhash_x17_4way( struct work *work, uint32_t max_nonce,
_mm256_set_epi32( n+3, 0, n+2, 0, n+1, 0, n, 0 ), *noncev );
do
{
x17_4way_hash( hash, vdata );
x17_4way_hash( hash32, vdata );
for ( int lane = 0; lane < 4; lane++ )
if ( unlikely( hashd7[ lane ] <= targ32 && !bench ) )
if ( unlikely( hash32_d7[ lane ] <= targ32_d7 && !bench ) )
{
extr_lane_4x32( lane_hash, hash, lane, 256 );
extr_lane_4x32( lane_hash, hash32, lane, 256 );
if ( valid_hash( lane_hash, ptarget ) )
{
pdata[19] = bswap_32( n + lane );

256
algo/x17/xevan-4way.c
View File

@@ -134,30 +134,14 @@ void xevan_8way_hash( void *output, const void *input )
dintrlv_4x128( hash0, hash1, hash2, hash3, vhashA, dataLen<<3 );
dintrlv_4x128( hash4, hash5, hash6, hash7, vhashB, dataLen<<3 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash0, dataLen );
sph_shavite512_close( &ctx.shavite, hash0 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash1, dataLen );
sph_shavite512_close( &ctx.shavite, hash1 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash2, dataLen );
sph_shavite512_close( &ctx.shavite, hash2 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash3, dataLen );
sph_shavite512_close( &ctx.shavite, hash3 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash4, dataLen );
sph_shavite512_close( &ctx.shavite, hash4 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash5, dataLen );
sph_shavite512_close( &ctx.shavite, hash5 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash6, dataLen );
sph_shavite512_close( &ctx.shavite, hash6 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash7, dataLen );
sph_shavite512_close( &ctx.shavite, hash7 );
shavite512_full( &ctx.shavite, hash0, hash0, dataLen );
shavite512_full( &ctx.shavite, hash1, hash1, dataLen );
shavite512_full( &ctx.shavite, hash2, hash2, dataLen );
shavite512_full( &ctx.shavite, hash3, hash3, dataLen );
shavite512_full( &ctx.shavite, hash4, hash4, dataLen );
shavite512_full( &ctx.shavite, hash5, hash5, dataLen );
shavite512_full( &ctx.shavite, hash6, hash6, dataLen );
shavite512_full( &ctx.shavite, hash7, hash7, dataLen );
intrlv_4x128( vhashA, hash0, hash1, hash2, hash3, dataLen<<3 );
intrlv_4x128( vhashB, hash4, hash5, hash6, hash7, dataLen<<3 );
@@ -208,30 +192,14 @@ void xevan_8way_hash( void *output, const void *input )
dintrlv_8x64( hash0, hash1, hash2, hash3, hash4, hash5, hash6, hash7,
vhash, dataLen<<3 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash0, dataLen );
sph_fugue512_close( &ctx.fugue, hash0 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash1, dataLen );
sph_fugue512_close( &ctx.fugue, hash1 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash2, dataLen );
sph_fugue512_close( &ctx.fugue, hash2 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash3, dataLen );
sph_fugue512_close( &ctx.fugue, hash3 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash4, dataLen );
sph_fugue512_close( &ctx.fugue, hash4 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash5, dataLen );
sph_fugue512_close( &ctx.fugue, hash5 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash6, dataLen );
sph_fugue512_close( &ctx.fugue, hash6 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash7, dataLen );
sph_fugue512_close( &ctx.fugue, hash7 );
sph_fugue512_full( &ctx.fugue, hash0, hash0, dataLen );
sph_fugue512_full( &ctx.fugue, hash1, hash1, dataLen );
sph_fugue512_full( &ctx.fugue, hash2, hash2, dataLen );
sph_fugue512_full( &ctx.fugue, hash3, hash3, dataLen );
sph_fugue512_full( &ctx.fugue, hash4, hash4, dataLen );
sph_fugue512_full( &ctx.fugue, hash5, hash5, dataLen );
sph_fugue512_full( &ctx.fugue, hash6, hash6, dataLen );
sph_fugue512_full( &ctx.fugue, hash7, hash7, dataLen );
intrlv_8x32( vhash, hash0, hash1, hash2, hash3, hash4, hash5, hash6,
hash7, dataLen<<3 );
@@ -243,30 +211,14 @@ void xevan_8way_hash( void *output, const void *input )
dintrlv_8x32( hash0, hash1, hash2, hash3, hash4, hash5, hash6, hash7,
vhash, dataLen<<3 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash0, dataLen );
sph_whirlpool_close( &ctx.whirlpool, hash0 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash1, dataLen );
sph_whirlpool_close( &ctx.whirlpool, hash1 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash2, dataLen );
sph_whirlpool_close( &ctx.whirlpool, hash2 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash3, dataLen );
sph_whirlpool_close( &ctx.whirlpool, hash3 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash4, dataLen );
sph_whirlpool_close( &ctx.whirlpool, hash4 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash5, dataLen );
sph_whirlpool_close( &ctx.whirlpool, hash5 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash6, dataLen );
sph_whirlpool_close( &ctx.whirlpool, hash6 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash7, dataLen );
sph_whirlpool_close( &ctx.whirlpool, hash7 );
sph_whirlpool512_full( &ctx.whirlpool, hash0, hash0, dataLen );
sph_whirlpool512_full( &ctx.whirlpool, hash1, hash1, dataLen );
sph_whirlpool512_full( &ctx.whirlpool, hash2, hash2, dataLen );
sph_whirlpool512_full( &ctx.whirlpool, hash3, hash3, dataLen );
sph_whirlpool512_full( &ctx.whirlpool, hash4, hash4, dataLen );
sph_whirlpool512_full( &ctx.whirlpool, hash5, hash5, dataLen );
sph_whirlpool512_full( &ctx.whirlpool, hash6, hash6, dataLen );
sph_whirlpool512_full( &ctx.whirlpool, hash7, hash7, dataLen );
intrlv_8x64( vhash, hash0, hash1, hash2, hash3, hash4, hash5, hash6,
hash7, dataLen<<3 );
@@ -345,30 +297,14 @@ void xevan_8way_hash( void *output, const void *input )
dintrlv_4x128( hash0, hash1, hash2, hash3, vhashA, dataLen<<3 );
dintrlv_4x128( hash4, hash5, hash6, hash7, vhashB, dataLen<<3 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash0, dataLen );
sph_shavite512_close( &ctx.shavite, hash0 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash1, dataLen );
sph_shavite512_close( &ctx.shavite, hash1 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash2, dataLen );
sph_shavite512_close( &ctx.shavite, hash2 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash3, dataLen );
sph_shavite512_close( &ctx.shavite, hash3 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash4, dataLen );
sph_shavite512_close( &ctx.shavite, hash4 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash5, dataLen );
sph_shavite512_close( &ctx.shavite, hash5 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash6, dataLen );
sph_shavite512_close( &ctx.shavite, hash6 );
sph_shavite512_init( &ctx.shavite );
sph_shavite512( &ctx.shavite, hash7, dataLen );
sph_shavite512_close( &ctx.shavite, hash7 );
shavite512_full( &ctx.shavite, hash0, hash0, dataLen );
shavite512_full( &ctx.shavite, hash1, hash1, dataLen );
shavite512_full( &ctx.shavite, hash2, hash2, dataLen );
shavite512_full( &ctx.shavite, hash3, hash3, dataLen );
shavite512_full( &ctx.shavite, hash4, hash4, dataLen );
shavite512_full( &ctx.shavite, hash5, hash5, dataLen );
shavite512_full( &ctx.shavite, hash6, hash6, dataLen );
shavite512_full( &ctx.shavite, hash7, hash7, dataLen );
intrlv_4x128( vhashA, hash0, hash1, hash2, hash3, dataLen<<3 );
intrlv_4x128( vhashB, hash4, hash5, hash6, hash7, dataLen<<3 );
@@ -419,30 +355,14 @@ void xevan_8way_hash( void *output, const void *input )
dintrlv_8x64( hash0, hash1, hash2, hash3, hash4, hash5, hash6, hash7,
vhash, dataLen<<3 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash0, dataLen );
sph_fugue512_close( &ctx.fugue, hash0 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash1, dataLen );
sph_fugue512_close( &ctx.fugue, hash1 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash2, dataLen );
sph_fugue512_close( &ctx.fugue, hash2 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash3, dataLen );
sph_fugue512_close( &ctx.fugue, hash3 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash4, dataLen );
sph_fugue512_close( &ctx.fugue, hash4 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash5, dataLen );
sph_fugue512_close( &ctx.fugue, hash5 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash6, dataLen );
sph_fugue512_close( &ctx.fugue, hash6 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash7, dataLen );
sph_fugue512_close( &ctx.fugue, hash7 );
sph_fugue512_full( &ctx.fugue, hash0, hash0, dataLen );
sph_fugue512_full( &ctx.fugue, hash1, hash1, dataLen );
sph_fugue512_full( &ctx.fugue, hash2, hash2, dataLen );
sph_fugue512_full( &ctx.fugue, hash3, hash3, dataLen );
sph_fugue512_full( &ctx.fugue, hash4, hash4, dataLen );
sph_fugue512_full( &ctx.fugue, hash5, hash5, dataLen );
sph_fugue512_full( &ctx.fugue, hash6, hash6, dataLen );
sph_fugue512_full( &ctx.fugue, hash7, hash7, dataLen );
intrlv_8x32( vhash, hash0, hash1, hash2, hash3, hash4, hash5, hash6,
hash7, dataLen<<3 );
@@ -454,30 +374,14 @@ void xevan_8way_hash( void *output, const void *input )
dintrlv_8x32( hash0, hash1, hash2, hash3, hash4, hash5, hash6, hash7,
vhash, dataLen<<3 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash0, dataLen );
sph_whirlpool_close( &ctx.whirlpool, hash0 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash1, dataLen );
sph_whirlpool_close( &ctx.whirlpool, hash1 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash2, dataLen );
sph_whirlpool_close( &ctx.whirlpool, hash2 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash3, dataLen );
sph_whirlpool_close( &ctx.whirlpool, hash3 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash4, dataLen );
sph_whirlpool_close( &ctx.whirlpool, hash4 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash5, dataLen );
sph_whirlpool_close( &ctx.whirlpool, hash5 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash6, dataLen );
sph_whirlpool_close( &ctx.whirlpool, hash6 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash7, dataLen );
sph_whirlpool_close( &ctx.whirlpool, hash7 );
sph_whirlpool512_full( &ctx.whirlpool, hash0, hash0, dataLen );
sph_whirlpool512_full( &ctx.whirlpool, hash1, hash1, dataLen );
sph_whirlpool512_full( &ctx.whirlpool, hash2, hash2, dataLen );
sph_whirlpool512_full( &ctx.whirlpool, hash3, hash3, dataLen );
sph_whirlpool512_full( &ctx.whirlpool, hash4, hash4, dataLen );
sph_whirlpool512_full( &ctx.whirlpool, hash5, hash5, dataLen );
sph_whirlpool512_full( &ctx.whirlpool, hash6, hash6, dataLen );
sph_whirlpool512_full( &ctx.whirlpool, hash7, hash7, dataLen );
intrlv_8x64( vhash, hash0, hash1, hash2, hash3, hash4, hash5, hash6,
hash7, dataLen<<3 );
@@ -636,18 +540,10 @@ void xevan_4way_hash( void *output, const void *input )
dintrlv_4x64( hash0, hash1, hash2, hash3, vhash, dataLen<<3 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash0, dataLen );
sph_fugue512_close( &ctx.fugue, hash0 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash1, dataLen );
sph_fugue512_close( &ctx.fugue, hash1 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash2, dataLen );
sph_fugue512_close( &ctx.fugue, hash2 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash3, dataLen );
sph_fugue512_close( &ctx.fugue, hash3 );
sph_fugue512_full( &ctx.fugue, hash0, hash0, 64 );
sph_fugue512_full( &ctx.fugue, hash1, hash1, 64 );
sph_fugue512_full( &ctx.fugue, hash2, hash2, 64 );
sph_fugue512_full( &ctx.fugue, hash3, hash3, 64 );
// Parallel 4way 32 bit
intrlv_4x32( vhash, hash0, hash1, hash2, hash3, dataLen<<3 );
@@ -659,18 +555,10 @@ void xevan_4way_hash( void *output, const void *input )
dintrlv_4x32( hash0, hash1, hash2, hash3, vhash, dataLen<<3 );
// Serial
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash0, dataLen );
sph_whirlpool_close( &ctx.whirlpool, hash0 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash1, dataLen );
sph_whirlpool_close( &ctx.whirlpool, hash1 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash2, dataLen );
sph_whirlpool_close( &ctx.whirlpool, hash2 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash3, dataLen );
sph_whirlpool_close( &ctx.whirlpool, hash3 );
sph_whirlpool512_full( &ctx.whirlpool, hash0, hash0, dataLen );
sph_whirlpool512_full( &ctx.whirlpool, hash1, hash1, dataLen );
sph_whirlpool512_full( &ctx.whirlpool, hash2, hash2, dataLen );
sph_whirlpool512_full( &ctx.whirlpool, hash3, hash3, dataLen );
intrlv_4x64( vhash, hash0, hash1, hash2, hash3, dataLen<<3 );
@@ -749,18 +637,10 @@ void xevan_4way_hash( void *output, const void *input )
dintrlv_4x64( hash0, hash1, hash2, hash3, vhash, dataLen<<3 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash0, dataLen );
sph_fugue512_close( &ctx.fugue, hash0 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash1, dataLen );
sph_fugue512_close( &ctx.fugue, hash1 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash2, dataLen );
sph_fugue512_close( &ctx.fugue, hash2 );
sph_fugue512_init( &ctx.fugue );
sph_fugue512( &ctx.fugue, hash3, dataLen );
sph_fugue512_close( &ctx.fugue, hash3 );
sph_fugue512_full( &ctx.fugue, hash0, hash0, 64 );
sph_fugue512_full( &ctx.fugue, hash1, hash1, 64 );
sph_fugue512_full( &ctx.fugue, hash2, hash2, 64 );
sph_fugue512_full( &ctx.fugue, hash3, hash3, 64 );
intrlv_4x32( vhash, hash0, hash1, hash2, hash3, dataLen<<3 );
@@ -770,18 +650,10 @@ void xevan_4way_hash( void *output, const void *input )
dintrlv_4x32( hash0, hash1, hash2, hash3, vhash, dataLen<<3 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash0, dataLen );
sph_whirlpool_close( &ctx.whirlpool, hash0 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash1, dataLen );
sph_whirlpool_close( &ctx.whirlpool, hash1 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash2, dataLen );
sph_whirlpool_close( &ctx.whirlpool, hash2 );
sph_whirlpool_init( &ctx.whirlpool );
sph_whirlpool( &ctx.whirlpool, hash3, dataLen );
sph_whirlpool_close( &ctx.whirlpool, hash3 );
sph_whirlpool512_full( &ctx.whirlpool, hash0, hash0, dataLen );
sph_whirlpool512_full( &ctx.whirlpool, hash1, hash1, dataLen );
sph_whirlpool512_full( &ctx.whirlpool, hash2, hash2, dataLen );
sph_whirlpool512_full( &ctx.whirlpool, hash3, hash3, dataLen );
intrlv_4x64( vhash, hash0, hash1, hash2, hash3, dataLen<<3 );