Compare commits

...

11 Commits

Author SHA1 Message Date
Jay D Dee
cdd587537e v3.14.3 2020-06-18 17:30:26 -04:00
Jay D Dee
51a1d91abd v3.14.2 2020-05-30 21:20:44 -04:00
Jay D Dee
13563e2598 v3.14.1 2020-05-21 13:00:29 -04:00
Jay D Dee
9571f85d53 v3.14.0 2020-05-20 13:56:35 -04:00
Jay D Dee
0e69756634 v3.13.2-segwit-test 2020-05-18 18:17:27 -04:00
Jay D Dee
9653bca1e2 v3.13.1.1 2020-05-17 19:21:37 -04:00
Jay D Dee
1c0719e8a4 v3.13.1 2020-05-10 21:34:55 -04:00
Jay D Dee
8b4b4dc613 v3.13.0.1 2020-05-07 17:57:04 -04:00
Jay D Dee
e76feaced8 v3.13.0 2020-05-06 00:53:43 -04:00
Jay D Dee
5e088d00d0 v3.12.8.2 2020-04-24 21:18:56 -04:00
Jay D Dee
972d4d70db v3.12.8.1 2020-04-17 16:12:45 -04:00
49 changed files with 1667 additions and 1162 deletions

Binary file not shown.

View File

@@ -257,6 +257,7 @@ cpuminer_SOURCES = \
algo/x16/hex.c \
algo/x16/x21s-4way.c \
algo/x16/x21s.c \
algo/x16/minotaur.c \
algo/x17/x17-gate.c \
algo/x17/x17.c \
algo/x17/x17-4way.c \

View File

@@ -93,6 +93,7 @@ Supported Algorithms
lyra2z
lyra2z330 Lyra2 330 rows, Zoin (ZOI)
m7m Magi (XMG)
minotaur Ringcoin (RNG)
myr-gr Myriad-Groestl
neoscrypt NeoScrypt(128, 2, 1)
nist5 Nist5

View File

@@ -1,8 +1,8 @@
This file is included in the Windows binary package. Compile instructions
for Linux and Windows can be found in RELEASE_NOTES.
cpuminer is a console program that is executed from a DOS command prompt.
There is no GUI and no mouse support.
cpuminer is a console program that is executed from a DOS or Powershell
prompt. There is no GUI and no mouse support.
Miner programs are often flagged as malware by antivirus programs. This is
a false positive, they are flagged simply because they are cryptocurrency
@@ -15,8 +15,8 @@ the features listed at cpuminer startup to ensure you are mining at
optimum speed using the best available features.
Architecture names and compile options used are only provided for Intel
Core series. Budget CPUs like Pentium and Celeron are often missing the
latest features.
Core series. Budget CPUs like Pentium and Celeron are often missing some
features.
AMD CPUs older than Piledriver, including Athlon x2 and Phenom II x4, are not
supported by cpuminer-opt due to an incompatible implementation of SSE2 on
@@ -31,14 +31,29 @@ https://en.wikipedia.org/wiki/List_of_Intel_CPU_microarchitectures
https://en.wikipedia.org/wiki/List_of_AMD_CPU_microarchitectures
Exe name Compile flags Arch name
Exe file name Compile flags Arch name
cpuminer-sse2.exe "-msse2" Core2, Nehalem
cpuminer-aes-sse42.exe "-march=westmere" Westmere
cpuminer-avx.exe "-march=corei7-avx" Sandybridge
cpuminer-avx2.exe "-march=core-avx2 -maes" Haswell, Skylake, Coffeelake
cpuminer-avx512.exe "-march=skylake-avx512" Skylake-X, Cascadelake-X
cpuminer-zen "-march=znver1" AMD Ryzen, Threadripper
cpuminer-sse2.exe "-msse2" Core2, Nehalem
cpuminer-aes-sse42.exe "-march=westmere" Westmere
cpuminer-avx.exe "-march=corei7-avx" Sandybridge, Ivybridge
cpuminer-avx2.exe "-march=core-avx2 -maes" Haswell*
cpuminer-avx512.exe "-march=skylake-avx512" Skylake-X, Cascadelake-X
cpuminer-zen.exe "-march=znver1" AMD Ryzen, Threadripper
cpuminer-avx512-sha-vaes.exe "-march=icelake-client" Icelake*
* Haswell includes Broadwell, Skylake, Kabylake, Coffeelake & Cometlake.
Icelake is only available on some laptops. Mining with a laptop is not
recommended. The icelake build is included in anticipation of Intel eventually
releasing a desktop CPU with a microarchitecture newer than Skylake.
Notes about included DLL files:
Downloading DLL files from alternative sources presents an inherent
security risk if their source is unknown. All DLL files included have
been copied from the Ubuntu-20.04 instalation or compiled by me from
source code obtained from the author's official repository. The exact
procedure is documented in the build instructions for Windows:
https://github.com/JayDDee/cpuminer-opt/wiki/Compiling-from-source
If you like this software feel free to donate:

View File

@@ -65,6 +65,74 @@ If not what makes it happen or not happen?
Change Log
----------
v3.14.3
#265: more mutex changes to reduce blocking with high thread count.
#267: fixed hodl algo potential memory alignment issue,
add warning when thread count is not valid for mining hodl algo.
v3.14.2
The second line of the Share Accepted log is no longer displayed,
new Xnonce log is added and other small log tweaks.
#265: Cleanup use of mutex.
v3.14.1
GBT and getwork log changes:
fixed missing TTF in New Block log,
ntime no longer byte-swapped for display in New Work log,
fixed zero effective hash rate in Periodic Report log,
deleted "Current block is..." log.
Renamed stratum "New Job" log to "New Work" to be consistent with the solo
version of the log. Added more data to both versions.
v3.14.0
Changes to solo mining:
- segwit is supported by getblocktemplate,
- longpolling is not working and is disabled,
- Periodic Report log is output,
- New Block log includes TTF estimates,
- Stratum thread no longer created when using getwork or GBT.
Fixed BUG log mining sha256d.
v3.13.1.1
Fixed Windows crash mining minotaur algo.
Fixed GCC 10 compile again.
Added -fno-common to testing to be consistent with GCC 10 default.
v3.13.1
Added minotaur algo for Ringcoin.
v3.13.0.1
Issue #262: Fixed xevan AVX2 invalid shares.
v3.13.0
Updated Windows binaries compiled with GCC 9. Included DLLs also updated.
Icelake build (cpuminer-avx512-sha-vaes.exe) now included in Windows
binaries package.
No source code changes.
v3.12.8.2
Fixed x12 AVX2 rejects.
Fixed phi AVX2 crash.
v3.12.8.1
Issue #261: Fixed yescryptr8g invalid shares.
v3.12.8
Yespower sha256 prehash made thread safe.

193
aclocal.m4 vendored
View File

@@ -1,6 +1,6 @@
# generated automatically by aclocal 1.15.1 -*- Autoconf -*-
# generated automatically by aclocal 1.16.1 -*- Autoconf -*-
# Copyright (C) 1996-2017 Free Software Foundation, Inc.
# Copyright (C) 1996-2018 Free Software Foundation, Inc.
# This file is free software; the Free Software Foundation
# gives unlimited permission to copy and/or distribute it,
@@ -20,7 +20,7 @@ You have another version of autoconf. It may work, but is not guaranteed to.
If you have problems, you may need to regenerate the build system entirely.
To do so, use the procedure documented by the package, typically 'autoreconf'.])])
# Copyright (C) 2002-2017 Free Software Foundation, Inc.
# Copyright (C) 2002-2018 Free Software Foundation, Inc.
#
# This file is free software; the Free Software Foundation
# gives unlimited permission to copy and/or distribute it,
@@ -32,10 +32,10 @@ To do so, use the procedure documented by the package, typically 'autoreconf'.])
# generated from the m4 files accompanying Automake X.Y.
# (This private macro should not be called outside this file.)
AC_DEFUN([AM_AUTOMAKE_VERSION],
[am__api_version='1.15'
[am__api_version='1.16'
dnl Some users find AM_AUTOMAKE_VERSION and mistake it for a way to
dnl require some minimum version. Point them to the right macro.
m4_if([$1], [1.15.1], [],
m4_if([$1], [1.16.1], [],
[AC_FATAL([Do not call $0, use AM_INIT_AUTOMAKE([$1]).])])dnl
])
@@ -51,14 +51,14 @@ m4_define([_AM_AUTOCONF_VERSION], [])
# Call AM_AUTOMAKE_VERSION and AM_AUTOMAKE_VERSION so they can be traced.
# This function is AC_REQUIREd by AM_INIT_AUTOMAKE.
AC_DEFUN([AM_SET_CURRENT_AUTOMAKE_VERSION],
[AM_AUTOMAKE_VERSION([1.15.1])dnl
[AM_AUTOMAKE_VERSION([1.16.1])dnl
m4_ifndef([AC_AUTOCONF_VERSION],
[m4_copy([m4_PACKAGE_VERSION], [AC_AUTOCONF_VERSION])])dnl
_AM_AUTOCONF_VERSION(m4_defn([AC_AUTOCONF_VERSION]))])
# Figure out how to run the assembler. -*- Autoconf -*-
# Copyright (C) 2001-2017 Free Software Foundation, Inc.
# Copyright (C) 2001-2018 Free Software Foundation, Inc.
#
# This file is free software; the Free Software Foundation
# gives unlimited permission to copy and/or distribute it,
@@ -78,7 +78,7 @@ _AM_IF_OPTION([no-dependencies],, [_AM_DEPENDENCIES([CCAS])])dnl
# AM_AUX_DIR_EXPAND -*- Autoconf -*-
# Copyright (C) 2001-2017 Free Software Foundation, Inc.
# Copyright (C) 2001-2018 Free Software Foundation, Inc.
#
# This file is free software; the Free Software Foundation
# gives unlimited permission to copy and/or distribute it,
@@ -130,7 +130,7 @@ am_aux_dir=`cd "$ac_aux_dir" && pwd`
# AM_CONDITIONAL -*- Autoconf -*-
# Copyright (C) 1997-2017 Free Software Foundation, Inc.
# Copyright (C) 1997-2018 Free Software Foundation, Inc.
#
# This file is free software; the Free Software Foundation
# gives unlimited permission to copy and/or distribute it,
@@ -161,7 +161,7 @@ AC_CONFIG_COMMANDS_PRE(
Usually this means the macro was only invoked conditionally.]])
fi])])
# Copyright (C) 1999-2017 Free Software Foundation, Inc.
# Copyright (C) 1999-2018 Free Software Foundation, Inc.
#
# This file is free software; the Free Software Foundation
# gives unlimited permission to copy and/or distribute it,
@@ -352,13 +352,12 @@ _AM_SUBST_NOTMAKE([am__nodep])dnl
# Generate code to set up dependency tracking. -*- Autoconf -*-
# Copyright (C) 1999-2017 Free Software Foundation, Inc.
# Copyright (C) 1999-2018 Free Software Foundation, Inc.
#
# This file is free software; the Free Software Foundation
# gives unlimited permission to copy and/or distribute it,
# with or without modifications, as long as this notice is preserved.
# _AM_OUTPUT_DEPENDENCY_COMMANDS
# ------------------------------
AC_DEFUN([_AM_OUTPUT_DEPENDENCY_COMMANDS],
@@ -366,49 +365,41 @@ AC_DEFUN([_AM_OUTPUT_DEPENDENCY_COMMANDS],
# Older Autoconf quotes --file arguments for eval, but not when files
# are listed without --file. Let's play safe and only enable the eval
# if we detect the quoting.
case $CONFIG_FILES in
*\'*) eval set x "$CONFIG_FILES" ;;
*) set x $CONFIG_FILES ;;
esac
# TODO: see whether this extra hack can be removed once we start
# requiring Autoconf 2.70 or later.
AS_CASE([$CONFIG_FILES],
[*\'*], [eval set x "$CONFIG_FILES"],
[*], [set x $CONFIG_FILES])
shift
for mf
# Used to flag and report bootstrapping failures.
am_rc=0
for am_mf
do
# Strip MF so we end up with the name of the file.
mf=`echo "$mf" | sed -e 's/:.*$//'`
# Check whether this is an Automake generated Makefile or not.
# We used to match only the files named 'Makefile.in', but
# some people rename them; so instead we look at the file content.
# Grep'ing the first line is not enough: some people post-process
# each Makefile.in and add a new line on top of each file to say so.
# Grep'ing the whole file is not good either: AIX grep has a line
am_mf=`AS_ECHO(["$am_mf"]) | sed -e 's/:.*$//'`
# Check whether this is an Automake generated Makefile which includes
# dependency-tracking related rules and includes.
# Grep'ing the whole file directly is not great: AIX grep has a line
# limit of 2048, but all sed's we know have understand at least 4000.
if sed -n 's,^#.*generated by automake.*,X,p' "$mf" | grep X >/dev/null 2>&1; then
dirpart=`AS_DIRNAME("$mf")`
else
continue
fi
# Extract the definition of DEPDIR, am__include, and am__quote
# from the Makefile without running 'make'.
DEPDIR=`sed -n 's/^DEPDIR = //p' < "$mf"`
test -z "$DEPDIR" && continue
am__include=`sed -n 's/^am__include = //p' < "$mf"`
test -z "$am__include" && continue
am__quote=`sed -n 's/^am__quote = //p' < "$mf"`
# Find all dependency output files, they are included files with
# $(DEPDIR) in their names. We invoke sed twice because it is the
# simplest approach to changing $(DEPDIR) to its actual value in the
# expansion.
for file in `sed -n "
s/^$am__include $am__quote\(.*(DEPDIR).*\)$am__quote"'$/\1/p' <"$mf" | \
sed -e 's/\$(DEPDIR)/'"$DEPDIR"'/g'`; do
# Make sure the directory exists.
test -f "$dirpart/$file" && continue
fdir=`AS_DIRNAME(["$file"])`
AS_MKDIR_P([$dirpart/$fdir])
# echo "creating $dirpart/$file"
echo '# dummy' > "$dirpart/$file"
done
sed -n 's,^am--depfiles:.*,X,p' "$am_mf" | grep X >/dev/null 2>&1 \
|| continue
am_dirpart=`AS_DIRNAME(["$am_mf"])`
am_filepart=`AS_BASENAME(["$am_mf"])`
AM_RUN_LOG([cd "$am_dirpart" \
&& sed -e '/# am--include-marker/d' "$am_filepart" \
| $MAKE -f - am--depfiles]) || am_rc=$?
done
if test $am_rc -ne 0; then
AC_MSG_FAILURE([Something went wrong bootstrapping makefile fragments
for automatic dependency tracking. Try re-running configure with the
'--disable-dependency-tracking' option to at least be able to build
the package (albeit without support for automatic dependency tracking).])
fi
AS_UNSET([am_dirpart])
AS_UNSET([am_filepart])
AS_UNSET([am_mf])
AS_UNSET([am_rc])
rm -f conftest-deps.mk
}
])# _AM_OUTPUT_DEPENDENCY_COMMANDS
@@ -417,18 +408,17 @@ AC_DEFUN([_AM_OUTPUT_DEPENDENCY_COMMANDS],
# -----------------------------
# This macro should only be invoked once -- use via AC_REQUIRE.
#
# This code is only required when automatic dependency tracking
# is enabled. FIXME. This creates each '.P' file that we will
# need in order to bootstrap the dependency handling code.
# This code is only required when automatic dependency tracking is enabled.
# This creates each '.Po' and '.Plo' makefile fragment that we'll need in
# order to bootstrap the dependency handling code.
AC_DEFUN([AM_OUTPUT_DEPENDENCY_COMMANDS],
[AC_CONFIG_COMMANDS([depfiles],
[test x"$AMDEP_TRUE" != x"" || _AM_OUTPUT_DEPENDENCY_COMMANDS],
[AMDEP_TRUE="$AMDEP_TRUE" ac_aux_dir="$ac_aux_dir"])
])
[AMDEP_TRUE="$AMDEP_TRUE" MAKE="${MAKE-make}"])])
# Do all the work for Automake. -*- Autoconf -*-
# Copyright (C) 1996-2017 Free Software Foundation, Inc.
# Copyright (C) 1996-2018 Free Software Foundation, Inc.
#
# This file is free software; the Free Software Foundation
# gives unlimited permission to copy and/or distribute it,
@@ -515,8 +505,8 @@ AC_REQUIRE([AM_PROG_INSTALL_STRIP])dnl
AC_REQUIRE([AC_PROG_MKDIR_P])dnl
# For better backward compatibility. To be removed once Automake 1.9.x
# dies out for good. For more background, see:
# <http://lists.gnu.org/archive/html/automake/2012-07/msg00001.html>
# <http://lists.gnu.org/archive/html/automake/2012-07/msg00014.html>
# <https://lists.gnu.org/archive/html/automake/2012-07/msg00001.html>
# <https://lists.gnu.org/archive/html/automake/2012-07/msg00014.html>
AC_SUBST([mkdir_p], ['$(MKDIR_P)'])
# We need awk for the "check" target (and possibly the TAP driver). The
# system "awk" is bad on some platforms.
@@ -583,7 +573,7 @@ END
Aborting the configuration process, to ensure you take notice of the issue.
You can download and install GNU coreutils to get an 'rm' implementation
that behaves properly: <http://www.gnu.org/software/coreutils/>.
that behaves properly: <https://www.gnu.org/software/coreutils/>.
If you want to complete the configuration process using your problematic
'rm' anyway, export the environment variable ACCEPT_INFERIOR_RM_PROGRAM
@@ -625,7 +615,7 @@ for _am_header in $config_headers :; do
done
echo "timestamp for $_am_arg" >`AS_DIRNAME(["$_am_arg"])`/stamp-h[]$_am_stamp_count])
# Copyright (C) 2001-2017 Free Software Foundation, Inc.
# Copyright (C) 2001-2018 Free Software Foundation, Inc.
#
# This file is free software; the Free Software Foundation
# gives unlimited permission to copy and/or distribute it,
@@ -646,7 +636,7 @@ if test x"${install_sh+set}" != xset; then
fi
AC_SUBST([install_sh])])
# Copyright (C) 2003-2017 Free Software Foundation, Inc.
# Copyright (C) 2003-2018 Free Software Foundation, Inc.
#
# This file is free software; the Free Software Foundation
# gives unlimited permission to copy and/or distribute it,
@@ -668,7 +658,7 @@ AC_SUBST([am__leading_dot])])
# Add --enable-maintainer-mode option to configure. -*- Autoconf -*-
# From Jim Meyering
# Copyright (C) 1996-2017 Free Software Foundation, Inc.
# Copyright (C) 1996-2018 Free Software Foundation, Inc.
#
# This file is free software; the Free Software Foundation
# gives unlimited permission to copy and/or distribute it,
@@ -703,7 +693,7 @@ AC_MSG_CHECKING([whether to enable maintainer-specific portions of Makefiles])
# Check to see how 'make' treats includes. -*- Autoconf -*-
# Copyright (C) 2001-2017 Free Software Foundation, Inc.
# Copyright (C) 2001-2018 Free Software Foundation, Inc.
#
# This file is free software; the Free Software Foundation
# gives unlimited permission to copy and/or distribute it,
@@ -711,49 +701,42 @@ AC_MSG_CHECKING([whether to enable maintainer-specific portions of Makefiles])
# AM_MAKE_INCLUDE()
# -----------------
# Check to see how make treats includes.
# Check whether make has an 'include' directive that can support all
# the idioms we need for our automatic dependency tracking code.
AC_DEFUN([AM_MAKE_INCLUDE],
[am_make=${MAKE-make}
cat > confinc << 'END'
[AC_MSG_CHECKING([whether ${MAKE-make} supports the include directive])
cat > confinc.mk << 'END'
am__doit:
@echo this is the am__doit target
@echo this is the am__doit target >confinc.out
.PHONY: am__doit
END
# If we don't find an include directive, just comment out the code.
AC_MSG_CHECKING([for style of include used by $am_make])
am__include="#"
am__quote=
_am_result=none
# First try GNU make style include.
echo "include confinc" > confmf
# Ignore all kinds of additional output from 'make'.
case `$am_make -s -f confmf 2> /dev/null` in #(
*the\ am__doit\ target*)
am__include=include
am__quote=
_am_result=GNU
;;
esac
# Now try BSD make style include.
if test "$am__include" = "#"; then
echo '.include "confinc"' > confmf
case `$am_make -s -f confmf 2> /dev/null` in #(
*the\ am__doit\ target*)
am__include=.include
am__quote="\""
_am_result=BSD
;;
esac
fi
AC_SUBST([am__include])
AC_SUBST([am__quote])
AC_MSG_RESULT([$_am_result])
rm -f confinc confmf
])
# BSD make does it like this.
echo '.include "confinc.mk" # ignored' > confmf.BSD
# Other make implementations (GNU, Solaris 10, AIX) do it like this.
echo 'include confinc.mk # ignored' > confmf.GNU
_am_result=no
for s in GNU BSD; do
AM_RUN_LOG([${MAKE-make} -f confmf.$s && cat confinc.out])
AS_CASE([$?:`cat confinc.out 2>/dev/null`],
['0:this is the am__doit target'],
[AS_CASE([$s],
[BSD], [am__include='.include' am__quote='"'],
[am__include='include' am__quote=''])])
if test "$am__include" != "#"; then
_am_result="yes ($s style)"
break
fi
done
rm -f confinc.* confmf.*
AC_MSG_RESULT([${_am_result}])
AC_SUBST([am__include])])
AC_SUBST([am__quote])])
# Fake the existence of programs that GNU maintainers use. -*- Autoconf -*-
# Copyright (C) 1997-2017 Free Software Foundation, Inc.
# Copyright (C) 1997-2018 Free Software Foundation, Inc.
#
# This file is free software; the Free Software Foundation
# gives unlimited permission to copy and/or distribute it,
@@ -792,7 +775,7 @@ fi
# Helper functions for option handling. -*- Autoconf -*-
# Copyright (C) 2001-2017 Free Software Foundation, Inc.
# Copyright (C) 2001-2018 Free Software Foundation, Inc.
#
# This file is free software; the Free Software Foundation
# gives unlimited permission to copy and/or distribute it,
@@ -821,7 +804,7 @@ AC_DEFUN([_AM_SET_OPTIONS],
AC_DEFUN([_AM_IF_OPTION],
[m4_ifset(_AM_MANGLE_OPTION([$1]), [$2], [$3])])
# Copyright (C) 1999-2017 Free Software Foundation, Inc.
# Copyright (C) 1999-2018 Free Software Foundation, Inc.
#
# This file is free software; the Free Software Foundation
# gives unlimited permission to copy and/or distribute it,
@@ -868,7 +851,7 @@ AC_LANG_POP([C])])
# For backward compatibility.
AC_DEFUN_ONCE([AM_PROG_CC_C_O], [AC_REQUIRE([AC_PROG_CC])])
# Copyright (C) 2001-2017 Free Software Foundation, Inc.
# Copyright (C) 2001-2018 Free Software Foundation, Inc.
#
# This file is free software; the Free Software Foundation
# gives unlimited permission to copy and/or distribute it,
@@ -887,7 +870,7 @@ AC_DEFUN([AM_RUN_LOG],
# Check to make sure that the build environment is sane. -*- Autoconf -*-
# Copyright (C) 1996-2017 Free Software Foundation, Inc.
# Copyright (C) 1996-2018 Free Software Foundation, Inc.
#
# This file is free software; the Free Software Foundation
# gives unlimited permission to copy and/or distribute it,
@@ -968,7 +951,7 @@ AC_CONFIG_COMMANDS_PRE(
rm -f conftest.file
])
# Copyright (C) 2009-2017 Free Software Foundation, Inc.
# Copyright (C) 2009-2018 Free Software Foundation, Inc.
#
# This file is free software; the Free Software Foundation
# gives unlimited permission to copy and/or distribute it,
@@ -1028,7 +1011,7 @@ AC_SUBST([AM_BACKSLASH])dnl
_AM_SUBST_NOTMAKE([AM_BACKSLASH])dnl
])
# Copyright (C) 2001-2017 Free Software Foundation, Inc.
# Copyright (C) 2001-2018 Free Software Foundation, Inc.
#
# This file is free software; the Free Software Foundation
# gives unlimited permission to copy and/or distribute it,
@@ -1056,7 +1039,7 @@ fi
INSTALL_STRIP_PROGRAM="\$(install_sh) -c -s"
AC_SUBST([INSTALL_STRIP_PROGRAM])])
# Copyright (C) 2006-2017 Free Software Foundation, Inc.
# Copyright (C) 2006-2018 Free Software Foundation, Inc.
#
# This file is free software; the Free Software Foundation
# gives unlimited permission to copy and/or distribute it,
@@ -1075,7 +1058,7 @@ AC_DEFUN([AM_SUBST_NOTMAKE], [_AM_SUBST_NOTMAKE($@)])
# Check how to create a tarball. -*- Autoconf -*-
# Copyright (C) 2004-2017 Free Software Foundation, Inc.
# Copyright (C) 2004-2018 Free Software Foundation, Inc.
#
# This file is free software; the Free Software Foundation
# gives unlimited permission to copy and/or distribute it,

View File

@@ -90,13 +90,157 @@ void algo_not_implemented()
}
// default null functions
// deprecated, use generic as default
int null_scanhash()
{
applog(LOG_WARNING,"SWERR: undefined scanhash function in algo_gate");
return 0;
}
// Default generic scanhash can be used in many cases.
int scanhash_generic( struct work *work, uint32_t max_nonce,
uint64_t *hashes_done, struct thr_info *mythr )
{
uint32_t edata[20] __attribute__((aligned(64)));
uint32_t hash[8] __attribute__((aligned(64)));
uint32_t *pdata = work->data;
uint32_t *ptarget = work->target;
const uint32_t first_nonce = pdata[19];
const uint32_t last_nonce = max_nonce - 1;
uint32_t n = first_nonce;
const int thr_id = mythr->id;
const bool bench = opt_benchmark;
mm128_bswap32_80( edata, pdata );
do
{
edata[19] = n;
if ( likely( algo_gate.hash( hash, edata, thr_id ) ) )
if ( unlikely( valid_hash( hash, ptarget ) && !bench ) )
{
pdata[19] = bswap_32( n );
submit_solution( work, hash, mythr );
}
n++;
} while ( n < last_nonce && !work_restart[thr_id].restart );
*hashes_done = n - first_nonce;
pdata[19] = n;
return 0;
}
#if defined(__AVX2__)
//int scanhash_4way_64_64( struct work *work, uint32_t max_nonce,
// uint64_t *hashes_done, struct thr_info *mythr )
//int scanhash_4way_64_640( struct work *work, uint32_t max_nonce,
// uint64_t *hashes_done, struct thr_info *mythr )
int scanhash_4way_64in_32out( struct work *work, uint32_t max_nonce,
uint64_t *hashes_done, struct thr_info *mythr )
{
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 *hash32_d7 = &(hash32[ 7*4 ]);
uint32_t *pdata = work->data;
const uint32_t *ptarget = work->target;
const uint32_t first_nonce = pdata[19];
const uint32_t last_nonce = max_nonce - 4;
__m256i *noncev = (__m256i*)vdata + 9;
uint32_t n = first_nonce;
const int thr_id = mythr->id;
const uint32_t targ32_d7 = ptarget[7];
const bool bench = opt_benchmark;
mm256_bswap32_intrlv80_4x64( vdata, pdata );
*noncev = mm256_intrlv_blend_32(
_mm256_set_epi32( n+3, 0, n+2, 0, n+1, 0, n, 0 ), *noncev );
do
{
if ( likely( algo_gate.hash( hash32, vdata, thr_id ) ) )
for ( int lane = 0; lane < 4; lane++ )
if ( unlikely( hash32_d7[ lane ] <= targ32_d7 && !bench ) )
{
extr_lane_4x32( lane_hash, hash32, lane, 256 );
if ( valid_hash( lane_hash, ptarget ) )
{
pdata[19] = bswap_32( n + lane );
submit_solution( work, lane_hash, mythr );
}
}
*noncev = _mm256_add_epi32( *noncev,
m256_const1_64( 0x0000000400000000 ) );
n += 4;
} while ( likely( ( n <= last_nonce ) && !work_restart[thr_id].restart ) );
pdata[19] = n;
*hashes_done = n - first_nonce;
return 0;
}
//int scanhash_8way_32_32( struct work *work, uint32_t max_nonce,
// uint64_t *hashes_done, struct thr_info *mythr )
#endif
#if defined(__AVX512F__) && defined(__AVX512VL__) && defined(__AVX512DQ__) && defined(__AVX512BW__)
//int scanhash_8way_64_64( struct work *work, uint32_t max_nonce,
// uint64_t *hashes_done, struct thr_info *mythr )
//int scanhash_8way_64_640( struct work *work, uint32_t max_nonce,
// uint64_t *hashes_done, struct thr_info *mythr )
int scanhash_8way_64in_32out( struct work *work, uint32_t max_nonce,
uint64_t *hashes_done, struct thr_info *mythr )
{
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 *hash32_d7 = &(hash32[7*8]);
uint32_t *pdata = work->data;
const uint32_t *ptarget = work->target;
const uint32_t first_nonce = pdata[19];
const uint32_t last_nonce = max_nonce - 8;
__m512i *noncev = (__m512i*)vdata + 9;
uint32_t n = first_nonce;
const int thr_id = mythr->id;
const uint32_t targ32_d7 = ptarget[7];
const bool bench = opt_benchmark;
mm512_bswap32_intrlv80_8x64( vdata, pdata );
*noncev = mm512_intrlv_blend_32(
_mm512_set_epi32( n+7, 0, n+6, 0, n+5, 0, n+4, 0,
n+3, 0, n+2, 0, n+1, 0, n, 0 ), *noncev );
do
{
if ( likely( algo_gate.hash( hash32, vdata, thr_id ) ) )
for ( int lane = 0; lane < 8; lane++ )
if ( unlikely( ( hash32_d7[ lane ] <= targ32_d7 ) && !bench ) )
{
extr_lane_8x32( lane_hash, hash32, lane, 256 );
if ( likely( valid_hash( lane_hash, ptarget ) ) )
{
pdata[19] = bswap_32( n + lane );
submit_solution( work, lane_hash, mythr );
}
}
*noncev = _mm512_add_epi32( *noncev,
m512_const1_64( 0x0000000800000000 ) );
n += 8;
} while ( likely( ( n < last_nonce ) && !work_restart[thr_id].restart ) );
pdata[19] = n;
*hashes_done = n - first_nonce;
return 0;
}
//int scanhash_16way_32_32( struct work *work, uint32_t max_nonce,
// uint64_t *hashes_done, struct thr_info *mythr )
#endif
int null_hash()
{
applog(LOG_WARNING,"SWERR: null_hash unsafe null function");
@@ -106,7 +250,7 @@ int null_hash()
void init_algo_gate( algo_gate_t* gate )
{
gate->miner_thread_init = (void*)&return_true;
gate->scanhash = (void*)&null_scanhash;
gate->scanhash = (void*)&scanhash_generic;
gate->hash = (void*)&null_hash;
gate->get_new_work = (void*)&std_get_new_work;
gate->work_decode = (void*)&std_le_work_decode;
@@ -179,6 +323,7 @@ bool register_algo_gate( int algo, algo_gate_t *gate )
case ALGO_LYRA2Z: register_lyra2z_algo ( gate ); break;
case ALGO_LYRA2Z330: register_lyra2z330_algo ( gate ); break;
case ALGO_M7M: register_m7m_algo ( gate ); break;
case ALGO_MINOTAUR: register_minotaur_algo ( gate ); break;
case ALGO_MYR_GR: register_myriad_algo ( gate ); break;
case ALGO_NEOSCRYPT: register_neoscrypt_algo ( gate ); break;
case ALGO_NIST5: register_nist5_algo ( gate ); break;
@@ -251,7 +396,6 @@ bool register_algo_gate( int algo, algo_gate_t *gate )
// restore warnings
#pragma GCC diagnostic pop
// run the alternate hash function for a specific algo
void exec_hash_function( int algo, void *output, const void *pdata )
{
algo_gate_t gate;

View File

@@ -110,11 +110,13 @@ inline bool set_excl ( set_t a, set_t b ) { return (a & b) == 0; }
typedef struct
{
// mandatory function, must be overwritten
// Mandatory functions, one of these is mandatory. If a generic scanhash
// is used a custom hash function must be registered, with a custom scanhash
// the custom hash function can be called directly and doesn't need to be
// registered in the gate.
int ( *scanhash ) ( struct work*, uint32_t, uint64_t*, struct thr_info* );
// Deprecated, will be removed
int ( *hash ) ( void*, const void*, uint32_t ) ;
int ( *hash ) ( void*, const void*, int );
//optional, safe to use default in most cases
@@ -126,7 +128,7 @@ bool ( *miner_thread_init ) ( int );
void ( *get_new_work ) ( struct work*, struct work*, int, uint32_t* );
// Decode getwork blockheader
bool ( *work_decode ) ( const json_t*, struct work* );
bool ( *work_decode ) ( struct work* );
// Extra getwork data
void ( *decode_extra_data ) ( struct work*, uint64_t* );
@@ -201,15 +203,61 @@ void four_way_not_tested();
#define STD_WORK_DATA_SIZE 128
#define STD_WORK_CMP_SIZE 76
#define JR2_NONCE_INDEX 39 // 8 bit offset
//#define JR2_NONCE_INDEX 39 // 8 bit offset
// These indexes are only used with JSON RPC2 and are not gated.
#define JR2_WORK_CMP_INDEX_2 43
#define JR2_WORK_CMP_SIZE_2 33
//#define JR2_WORK_CMP_INDEX_2 43
//#define JR2_WORK_CMP_SIZE_2 33
// allways returns failure
// deprecated, use generic instead
int null_scanhash();
// Default generic, may be used in many cases.
// N-way is more complicated, requires many different implementations
// depending on architecture, input format, and output format.
// Naming convention is scanhash_[N]way_[input format]in_[output format]out
// N = number of lanes
// input/output format:
// 32: 32 bit interleaved parallel lanes
// 64: 64 bit interleaved parallel lanes
// 640: input only, not interleaved, contiguous serial 640 bit lanes.
// 256: output only, not interleaved, contiguous serial 256 bit lanes.
int scanhash_generic( struct work *work, uint32_t max_nonce,
uint64_t *hashes_done, struct thr_info *mythr );
#if defined(__AVX2__)
//int scanhash_4way_64in_64out( struct work *work, uint32_t max_nonce,
// uint64_t *hashes_done, struct thr_info *mythr );
//int scanhash_4way_64in_256out( struct work *work, uint32_t max_nonce,
// uint64_t *hashes_done, struct thr_info *mythr );
int scanhash_4way_64in_32out( struct work *work, uint32_t max_nonce,
uint64_t *hashes_done, struct thr_info *mythr );
//int scanhash_8way_32in_32out( struct work *work, uint32_t max_nonce,
// uint64_t *hashes_done, struct thr_info *mythr );
#endif
#if defined(__AVX512F__) && defined(__AVX512VL__) && defined(__AVX512DQ__) && defined(__AVX512BW__)
//int scanhash_8way_64in_64out( struct work *work, uint32_t max_nonce,
// uint64_t *hashes_done, struct thr_info *mythr );
//int scanhash_8way_64in_256out( struct work *work, uint32_t max_nonce,
// uint64_t *hashes_done, struct thr_info *mythr );
int scanhash_8way_64in_32out( struct work *work, uint32_t max_nonce,
uint64_t *hashes_done, struct thr_info *mythr );
//int scanhash_16way_32in_32out( struct work *work, uint32_t max_nonce,
// uint64_t *hashes_done, struct thr_info *mythr );
#endif
// displays warning
int null_hash ();
@@ -221,8 +269,8 @@ void std_get_new_work( struct work *work, struct work *g_work, int thr_id,
void sha256d_gen_merkle_root( char *merkle_root, struct stratum_ctx *sctx );
void SHA256_gen_merkle_root ( char *merkle_root, struct stratum_ctx *sctx );
bool std_le_work_decode( const json_t *val, struct work *work );
bool std_be_work_decode( const json_t *val, struct work *work );
bool std_le_work_decode( struct work *work );
bool std_be_work_decode( struct work *work );
bool std_le_submit_getwork_result( CURL *curl, struct work *work );
bool std_be_submit_getwork_result( CURL *curl, struct work *work );
@@ -257,7 +305,7 @@ int std_get_work_data_size();
// by calling the algo's register function.
bool register_algo_gate( int algo, algo_gate_t *gate );
// Called by algos toverride any default gate functions that are applicable
// Called by algos to verride any default gate functions that are applicable
// and do any other algo-specific initialization.
// The register functions for all the algos can be declared here to reduce
// compiler warnings but that's just more work for devs adding new algos.

View File

@@ -78,7 +78,6 @@ void decred_build_extraheader( struct work* g_work, struct stratum_ctx* sctx )
uint32_t extraheader[32] = { 0 };
int headersize = 0;
uint32_t* extradata = (uint32_t*) sctx->xnonce1;
size_t t;
int i;
// getwork over stratum, getwork merkle + header passed in coinb1
@@ -87,9 +86,6 @@ void decred_build_extraheader( struct work* g_work, struct stratum_ctx* sctx )
sizeof(extraheader) );
memcpy( extraheader, &sctx->job.coinbase[32], headersize );
// Increment extranonce2
for ( t = 0; t < sctx->xnonce2_size && !( ++sctx->job.xnonce2[t] ); t++ );
// Assemble block header
memset( g_work->data, 0, sizeof(g_work->data) );
g_work->data[0] = le32dec( sctx->job.version );

View File

@@ -99,9 +99,13 @@ void hodl_build_block_header( struct work* g_work, uint32_t version,
// called only by thread 0, saves a backup of g_work
void hodl_get_new_work( struct work* work, struct work* g_work)
{
work_free( &hodl_work );
work_copy( &hodl_work, g_work );
hodl_work.data[ algo_gate.nonce_index ] = ( clock() + rand() ) % 9999;
pthread_rwlock_rdlock( &g_work_lock );
work_free( &hodl_work );
work_copy( &hodl_work, g_work );
hodl_work.data[ algo_gate.nonce_index ] = ( clock() + rand() ) % 9999;
pthread_rwlock_unlock( &g_work_lock );
}
json_t *hodl_longpoll_rpc_call( CURL *curl, int *err, char* lp_url )
@@ -155,11 +159,10 @@ bool register_hodl_algo( algo_gate_t* gate )
applog( LOG_ERR, "Only CPUs with AES are supported, use legacy version.");
return false;
#endif
// if ( TOTAL_CHUNKS % opt_n_threads )
// {
// applog(LOG_ERR,"Thread count must be power of 2.");
// return false;
// }
if ( GARBAGE_SIZE % opt_n_threads )
applog( LOG_WARNING,"WARNING: Thread count must be power of 2. Miner may crash or produce invalid hash!" );
pthread_barrier_init( &hodl_barrier, NULL, opt_n_threads );
gate->optimizations = SSE42_OPT | AES_OPT | AVX2_OPT;
gate->scanhash = (void*)&hodl_scanhash;
@@ -171,7 +174,7 @@ bool register_hodl_algo( algo_gate_t* gate )
gate->resync_threads = (void*)&hodl_resync_threads;
gate->do_this_thread = (void*)&hodl_do_this_thread;
gate->work_cmp_size = 76;
hodl_scratchbuf = (unsigned char*)malloc( 1 << 30 );
hodl_scratchbuf = (unsigned char*)_mm_malloc( 1 << 30, 64 );
allow_getwork = false;
opt_target_factor = 8388608.0;
return ( hodl_scratchbuf != NULL );

View File

@@ -70,7 +70,7 @@ int scanhash_hodl_wolf( struct work* work, uint32_t max_nonce,
uint32_t *ptarget = work->target;
int threadNumber = mythr->id;
CacheEntry *Garbage = (CacheEntry*)hodl_scratchbuf;
CacheEntry Cache[AES_PARALLEL_N];
CacheEntry Cache[AES_PARALLEL_N] __attribute__ ((aligned (64)));
__m128i* data[AES_PARALLEL_N];
const __m128i* next[AES_PARALLEL_N];
uint32_t CollisionCount = 0;

View File

@@ -215,9 +215,6 @@ void phi2_build_extraheader( struct work* g_work, struct stratum_ctx* sctx )
size_t t;
algo_gate.gen_merkle_root( merkle_tree, sctx );
// Increment extranonce2
for ( t = 0; t < sctx->xnonce2_size && !( ++sctx->job.xnonce2[t] ); t++ );
// Assemble block header
algo_gate.build_block_header( g_work, le32dec( sctx->job.version ),
(uint32_t*) sctx->job.prevhash, (uint32_t*) merkle_tree,
le32dec( sctx->job.ntime ), le32dec(sctx->job.nbits), NULL );
@@ -225,7 +222,6 @@ void phi2_build_extraheader( struct work* g_work, struct stratum_ctx* sctx )
g_work->data[ 20+t ] = ((uint32_t*)sctx->job.extra)[t];
}
bool register_phi2_algo( algo_gate_t* gate )
{
gate->optimizations = SSE2_OPT | AES_OPT | AVX2_OPT | AVX512_OPT | VAES_OPT;

View File

@@ -156,6 +156,8 @@ int scanhash_zr5( struct work *work, uint32_t max_nonce,
void zr5_get_new_work( struct work* work, struct work* g_work, int thr_id,
uint32_t* end_nonce_ptr )
{
pthread_rwlock_rdlock( &g_work_lock );
// ignore POK in first word
const int wkcmp_sz = 72; // (19-1) * sizeof(uint32_t)
uint32_t *nonceptr = work->data + algo_gate.nonce_index;
@@ -171,6 +173,8 @@ void zr5_get_new_work( struct work* work, struct work* g_work, int thr_id,
}
else
++(*nonceptr);
pthread_rwlock_unlock( &g_work_lock );
}
void zr5_display_pok( struct work* work )

View File

@@ -69,13 +69,9 @@ void lbry_build_block_header( struct work* g_work, uint32_t version,
void lbry_build_extraheader( struct work* g_work, struct stratum_ctx* sctx )
{
unsigned char merkle_root[64] = { 0 };
size_t t;
int i;
algo_gate.gen_merkle_root( merkle_root, sctx );
// Increment extranonce2
for ( t = 0; t < sctx->xnonce2_size && !( ++sctx->job.xnonce2[t] ); t++ );
// Assemble block header
memset( g_work->data, 0, sizeof(g_work->data) );
g_work->data[0] = le32dec( sctx->job.version );

View File

@@ -479,8 +479,8 @@ static inline void sha256d_ms(uint32_t *hash, uint32_t *W,
void sha256d_ms_4way(uint32_t *hash, uint32_t *data,
const uint32_t *midstate, const uint32_t *prehash);
static inline int scanhash_sha256d_4way(int thr_id, struct work *work,
uint32_t max_nonce, uint64_t *hashes_done)
static inline int scanhash_sha256d_4way( struct work *work,
uint32_t max_nonce, uint64_t *hashes_done, struct thr_info *mythr )
{
uint32_t *pdata = work->data;
uint32_t *ptarget = work->target;
@@ -492,6 +492,7 @@ static inline int scanhash_sha256d_4way(int thr_id, struct work *work,
uint32_t n = pdata[19] - 1;
const uint32_t first_nonce = pdata[19];
const uint32_t Htarg = ptarget[7];
int thr_id = mythr->id;
int i, j;
memcpy(data, pdata + 16, 64);
@@ -521,10 +522,8 @@ static inline int scanhash_sha256d_4way(int thr_id, struct work *work,
if (swab32(hash[4 * 7 + i]) <= Htarg) {
pdata[19] = data[4 * 3 + i];
sha256d_80_swap(hash, pdata);
if (fulltest(hash, ptarget)) {
*hashes_done = n - first_nonce + 1;
return 1;
}
if ( fulltest( hash, ptarget ) && !opt_benchmark )
submit_solution( work, hash, mythr );
}
}
} while (n < max_nonce && !work_restart[thr_id].restart);
@@ -541,8 +540,8 @@ static inline int scanhash_sha256d_4way(int thr_id, struct work *work,
void sha256d_ms_8way(uint32_t *hash, uint32_t *data,
const uint32_t *midstate, const uint32_t *prehash);
static inline int scanhash_sha256d_8way(int thr_id, struct work *work,
uint32_t max_nonce, uint64_t *hashes_done)
static inline int scanhash_sha256d_8way( struct work *work,
uint32_t max_nonce, uint64_t *hashes_done, struct thr_info *mythr )
{
uint32_t *pdata = work->data;
uint32_t *ptarget = work->target;
@@ -554,6 +553,7 @@ static inline int scanhash_sha256d_8way(int thr_id, struct work *work,
uint32_t n = pdata[19] - 1;
const uint32_t first_nonce = pdata[19];
const uint32_t Htarg = ptarget[7];
int thr_id = mythr->id;
int i, j;
memcpy(data, pdata + 16, 64);
@@ -583,10 +583,8 @@ static inline int scanhash_sha256d_8way(int thr_id, struct work *work,
if (swab32(hash[8 * 7 + i]) <= Htarg) {
pdata[19] = data[8 * 3 + i];
sha256d_80_swap(hash, pdata);
if (fulltest(hash, ptarget)) {
*hashes_done = n - first_nonce + 1;
return 1;
}
if ( fulltest( hash, ptarget ) && !opt_benchmark )
submit_solution( work, hash, mythr );
}
}
} while (n < max_nonce && !work_restart[thr_id].restart);
@@ -614,13 +612,11 @@ int scanhash_sha256d( struct work *work,
#ifdef HAVE_SHA256_8WAY
if (sha256_use_8way())
return scanhash_sha256d_8way(thr_id, work,
max_nonce, hashes_done);
return scanhash_sha256d_8way( work, max_nonce, hashes_done, mythr );
#endif
#ifdef HAVE_SHA256_4WAY
if (sha256_use_4way())
return scanhash_sha256d_4way(thr_id, work,
max_nonce, hashes_done);
return scanhash_sha256d_4way( work, max_nonce, hashes_done, mythr );
#endif
memcpy(data, pdata + 16, 64);
@@ -657,7 +653,7 @@ int scanhash_SHA256d( struct work *work, const uint32_t max_nonce,
uint32_t n = pdata[19] - 1;
const uint32_t first_nonce = pdata[19];
const uint32_t Htarg = ptarget[7];
int thr_id = mythr->id; // thr_id arg is deprecated
int thr_id = mythr->id;
memcpy( data, pdata, 80 );

View File

@@ -731,7 +731,7 @@ void skein512_8way_full( skein512_8way_context *sc, void *out, const void *data,
void
skein512_8way_prehash64( skein512_8way_context *sc, const void *data )
{
__m512i *vdata = (__m512*)data;
__m512i *vdata = (__m512i*)data;
__m512i *buf = sc->buf;
buf[0] = vdata[0];
buf[1] = vdata[1];
@@ -1099,6 +1099,7 @@ skein512_4way_final16( skein512_4way_context *sc, void *out, const void *data )
casti_m256i( out, 7 ) = h7;
}
// Broken for 80 bytes, use prehash.
void
skein256_4way_update(void *cc, const void *data, size_t len)
{

View File

@@ -170,6 +170,9 @@ void x12_8way_hash( void *state, const void *input )
dintrlv_4x128_512( hash0, hash1, hash2, hash3, vhashA );
dintrlv_4x128_512( hash4, hash5, hash6, hash7, vhashB );
update_final_echo( &ctx.echo, (BitSequence *)hash0,
(const BitSequence *) hash0, 512 );
memcpy( &ctx.echo, &x12_8way_ctx.echo, sizeof(hashState_echo) );
update_final_echo( &ctx.echo, (BitSequence *)hash1,
(const BitSequence *) hash1, 512 );
memcpy( &ctx.echo, &x12_8way_ctx.echo, sizeof(hashState_echo) );
@@ -363,6 +366,18 @@ void x12_4way_hash( void *state, const void *input )
simd_2way_update_close( &ctx.simd, vhash, vhash, 512 );
dintrlv_2x128( hash2, hash3, vhash, 512 );
update_final_echo( &ctx.echo, (BitSequence *)hash0,
(const BitSequence *) hash0, 512 );
memcpy( &ctx.echo, &x12_4way_ctx.echo, sizeof(hashState_echo) );
update_final_echo( &ctx.echo, (BitSequence *)hash1,
(const BitSequence *) hash1, 512 );
memcpy( &ctx.echo, &x12_4way_ctx.echo, sizeof(hashState_echo) );
update_final_echo( &ctx.echo, (BitSequence *)hash2,
(const BitSequence *) hash2, 512 );
memcpy( &ctx.echo, &x12_4way_ctx.echo, sizeof(hashState_echo) );
update_final_echo( &ctx.echo, (BitSequence *)hash3,
(const BitSequence *) hash3, 512 );
update_and_final_groestl( &ctx.groestl, (char*)hash0, (char*)hash0, 512 );
memcpy( &ctx.groestl, &x12_4way_ctx.groestl, sizeof(hashState_groestl) );
update_and_final_groestl( &ctx.groestl, (char*)hash1, (char*)hash1, 512 );

View File

@@ -251,8 +251,12 @@ void phi1612_4way_hash( void *state, const void *input )
memcpy( &ctx, &phi1612_4way_ctx, sizeof(phi1612_4way_ctx) );
// Skein parallel 4way
skein512_4way_update( &ctx.skein, input, 80 );
skein512_4way_close( &ctx.skein, vhash );
// skein 4way is broken for 80 bytes
// skein512_4way_update( &ctx.skein, input, 80 );
// skein512_4way_close( &ctx.skein, vhash );
skein512_4way_prehash64( &ctx.skein, input );
skein512_4way_final16( &ctx.skein, vhash, input + (64*4) );
// JH
jh512_4way_update( &ctx.jh, vhash, 64 );

258
algo/x16/minotaur.c Normal file
View File

@@ -0,0 +1,258 @@
// Minotaur hash
#include "algo-gate-api.h"
#include <stdlib.h>
#include <stdint.h>
#include <string.h>
#include <stdio.h>
#include "algo/blake/sph_blake.h"
#include "algo/bmw/sph_bmw.h"
#include "algo/jh/sph_jh.h"
#include "algo/keccak/sph_keccak.h"
#include "algo/skein/sph_skein.h"
#include "algo/shavite/sph_shavite.h"
#include "algo/luffa/luffa_for_sse2.h"
#include "algo/cubehash/cubehash_sse2.h"
#include "algo/simd/nist.h"
#include "algo/hamsi/sph_hamsi.h"
#include "algo/fugue/sph_fugue.h"
#include "algo/shabal/sph_shabal.h"
#include "algo/whirlpool/sph_whirlpool.h"
#include <openssl/sha.h>
#if defined(__AES__)
#include "algo/echo/aes_ni/hash_api.h"
#include "algo/groestl/aes_ni/hash-groestl.h"
#else
#include "algo/echo/sph_echo.h"
#include "algo/groestl/sph_groestl.h"
#endif
// Config
#define MINOTAUR_ALGO_COUNT 16
typedef struct TortureNode TortureNode;
typedef struct TortureGarden TortureGarden;
// Graph of hash algos plus SPH contexts
struct TortureGarden {
#if defined(__AES__)
hashState_echo echo;
hashState_groestl groestl;
#else
sph_echo512_context echo;
sph_groestl512_context groestl;
#endif
sph_blake512_context blake;
sph_bmw512_context bmw;
sph_skein512_context skein;
sph_jh512_context jh;
sph_keccak512_context keccak;
hashState_luffa luffa;
cubehashParam cube;
shavite512_context shavite;
hashState_sd simd;
sph_hamsi512_context hamsi;
sph_fugue512_context fugue;
sph_shabal512_context shabal;
sph_whirlpool_context whirlpool;
SHA512_CTX sha512;
struct TortureNode {
unsigned int algo;
TortureNode *childLeft;
TortureNode *childRight;
} nodes[22];
} __attribute__ ((aligned (64)));
// Get a 64-byte hash for given 64-byte input, using given TortureGarden contexts and given algo index
static void get_hash( void *output, const void *input, TortureGarden *garden,
unsigned int algo )
{
unsigned char hash[64] __attribute__ ((aligned (64)));
switch (algo) {
case 0:
sph_blake512_init(&garden->blake);
sph_blake512(&garden->blake, input, 64);
sph_blake512_close(&garden->blake, hash);
break;
case 1:
sph_bmw512_init(&garden->bmw);
sph_bmw512(&garden->bmw, input, 64);
sph_bmw512_close(&garden->bmw, hash);
break;
case 2:
cubehashInit( &garden->cube, 512, 16, 32 );
cubehashUpdateDigest( &garden->cube, (byte*)hash,
(const byte*)input, 64 );
break;
case 3:
#if defined(__AES__)
echo_full( &garden->echo, (BitSequence *)hash, 512,
(const BitSequence *)input, 64 );
#else
sph_echo512_init(&garden->echo);
sph_echo512(&garden->echo, input, 64);
sph_echo512_close(&garden->echo, hash);
#endif
break;
case 4:
sph_fugue512_init(&garden->fugue);
sph_fugue512(&garden->fugue, input, 64);
sph_fugue512_close(&garden->fugue, hash);
break;
case 5:
#if defined(__AES__)
groestl512_full( &garden->groestl, (char*)hash, (char*)input, 512 );
#else
sph_groestl512_init(&garden->groestl);
sph_groestl512(&garden->groestl, input, 64);
sph_groestl512_close(&garden->groestl, hash);
#endif
break;
case 6:
sph_hamsi512_init(&garden->hamsi);
sph_hamsi512(&garden->hamsi, input, 64);
sph_hamsi512_close(&garden->hamsi, hash);
break;
case 7:
SHA512_Init( &garden->sha512 );
SHA512_Update( &garden->sha512, input, 64 );
SHA512_Final( (unsigned char*)hash, &garden->sha512 );
break;
case 8:
sph_jh512_init(&garden->jh);
sph_jh512(&garden->jh, input, 64);
sph_jh512_close(&garden->jh, hash);
break;
case 9:
sph_keccak512_init(&garden->keccak);
sph_keccak512(&garden->keccak, input, 64);
sph_keccak512_close(&garden->keccak, hash);
break;
case 10:
init_luffa( &garden->luffa, 512 );
update_and_final_luffa( &garden->luffa, (BitSequence*)hash,
(const BitSequence*)input, 64 );
break;
case 11:
sph_shabal512_init(&garden->shabal);
sph_shabal512(&garden->shabal, input, 64);
sph_shabal512_close(&garden->shabal, hash);
break;
case 12:
sph_shavite512_init(&garden->shavite);
sph_shavite512(&garden->shavite, input, 64);
sph_shavite512_close(&garden->shavite, hash);
break;
case 13:
init_sd( &garden->simd, 512 );
update_final_sd( &garden->simd, (BitSequence *)hash,
(const BitSequence*)input, 512 );
break;
case 14:
sph_skein512_init(&garden->skein);
sph_skein512(&garden->skein, input, 64);
sph_skein512_close(&garden->skein, hash);
break;
case 15:
sph_whirlpool_init(&garden->whirlpool);
sph_whirlpool(&garden->whirlpool, input, 64);
sph_whirlpool_close(&garden->whirlpool, hash);
break;
}
// Output the hash
memcpy(output, hash, 64);
}
// Recursively traverse a given torture garden starting with a given hash and given node within the garden. The hash is overwritten with the final hash.
static void traverse_garden( TortureGarden *garden, void *hash,
TortureNode *node )
{
unsigned char partialHash[64] __attribute__ ((aligned (64)));
get_hash(partialHash, hash, garden, node->algo);
if ( partialHash[63] % 2 == 0 )
{ // Last byte of output hash is even
if ( node->childLeft != NULL )
traverse_garden( garden, partialHash, node->childLeft );
}
else
{ // Last byte of output hash is odd
if ( node->childRight != NULL )
traverse_garden( garden, partialHash, node->childRight );
}
memcpy( hash, partialHash, 64 );
}
// Associate child nodes with a parent node
static inline void link_nodes( TortureNode *parent, TortureNode *childLeft,
TortureNode *childRight )
{
parent->childLeft = childLeft;
parent->childRight = childRight;
}
static __thread TortureGarden garden;
bool initialize_torture_garden()
{
// Create torture garden nodes. Note that both sides of 19 and 20 lead to 21, and 21 has no children (to make traversal complete).
link_nodes(&garden.nodes[0], &garden.nodes[1], &garden.nodes[2]);
link_nodes(&garden.nodes[1], &garden.nodes[3], &garden.nodes[4]);
link_nodes(&garden.nodes[2], &garden.nodes[5], &garden.nodes[6]);
link_nodes(&garden.nodes[3], &garden.nodes[7], &garden.nodes[8]);
link_nodes(&garden.nodes[4], &garden.nodes[9], &garden.nodes[10]);
link_nodes(&garden.nodes[5], &garden.nodes[11], &garden.nodes[12]);
link_nodes(&garden.nodes[6], &garden.nodes[13], &garden.nodes[14]);
link_nodes(&garden.nodes[7], &garden.nodes[15], &garden.nodes[16]);
link_nodes(&garden.nodes[8], &garden.nodes[15], &garden.nodes[16]);
link_nodes(&garden.nodes[9], &garden.nodes[15], &garden.nodes[16]);
link_nodes(&garden.nodes[10], &garden.nodes[15], &garden.nodes[16]);
link_nodes(&garden.nodes[11], &garden.nodes[17], &garden.nodes[18]);
link_nodes(&garden.nodes[12], &garden.nodes[17], &garden.nodes[18]);
link_nodes(&garden.nodes[13], &garden.nodes[17], &garden.nodes[18]);
link_nodes(&garden.nodes[14], &garden.nodes[17], &garden.nodes[18]);
link_nodes(&garden.nodes[15], &garden.nodes[19], &garden.nodes[20]);
link_nodes(&garden.nodes[16], &garden.nodes[19], &garden.nodes[20]);
link_nodes(&garden.nodes[17], &garden.nodes[19], &garden.nodes[20]);
link_nodes(&garden.nodes[18], &garden.nodes[19], &garden.nodes[20]);
link_nodes(&garden.nodes[19], &garden.nodes[21], &garden.nodes[21]);
link_nodes(&garden.nodes[20], &garden.nodes[21], &garden.nodes[21]);
garden.nodes[21].childLeft = NULL;
garden.nodes[21].childRight = NULL;
return true;
}
// Produce a 32-byte hash from 80-byte input data
int minotaur_hash( void *output, const void *input, int thr_id )
{
unsigned char hash[64] __attribute__ ((aligned (64)));
// Find initial sha512 hash
SHA512_Init( &garden.sha512 );
SHA512_Update( &garden.sha512, input, 80 );
SHA512_Final( (unsigned char*) hash, &garden.sha512 );
// Assign algos to torture garden nodes based on initial hash
for ( int i = 0; i < 22; i++ )
garden.nodes[i].algo = hash[i] % MINOTAUR_ALGO_COUNT;
// Send the initial hash through the torture garden
traverse_garden( &garden, hash, &garden.nodes[0] );
memcpy( output, hash, 32 );
return 1;
}
bool register_minotaur_algo( algo_gate_t* gate )
{
gate->hash = (void*)&minotaur_hash;
gate->optimizations = SSE2_OPT | AES_OPT | AVX2_OPT | AVX512_OPT;
gate->miner_thread_init = (void*)&initialize_torture_garden;
return true;
};

View File

@@ -135,18 +135,16 @@ void x16rt_getAlgoString( const uint32_t *timeHash, char *output)
void veil_build_extraheader( struct work* g_work, struct stratum_ctx* sctx )
{
uint32_t merkleroothash[8];
uint32_t witmerkleroothash[8];
uint32_t denom10[8];
uint32_t denom100[8];
uint32_t denom1000[8];
uint32_t denom10000[8];
int i;
uchar merkle_tree[64] = { 0 };
size_t t;
algo_gate.gen_merkle_root( merkle_tree, sctx );
// Increment extranonce2
for ( t = 0; t < sctx->xnonce2_size && !( ++sctx->job.xnonce2[t] ); t++ );
// Assemble block header
// algo_gate.build_block_header( g_work, le32dec( sctx->job.version ),
// (uint32_t*) sctx->job.prevhash, (uint32_t*) merkle_tree,
// le32dec( sctx->job.ntime ), le32dec(sctx->job.nbits) );
int i;
memset( g_work->data, 0, sizeof(g_work->data) );
g_work->data[0] = le32dec( sctx->job.version );
@@ -164,35 +162,35 @@ void veil_build_extraheader( struct work* g_work, struct stratum_ctx* sctx )
g_work->data[31] = 0x00000280;
for ( i = 0; i < 8; i++ )
g_work->merkleroothash[7 - i] = be32dec((uint32_t *)merkle_tree + i);
merkleroothash[7 - i] = be32dec((uint32_t *)merkle_tree + i);
for ( i = 0; i < 8; i++ )
g_work->witmerkleroothash[7 - i] = be32dec((uint32_t *)merkle_tree + i);
witmerkleroothash[7 - i] = be32dec((uint32_t *)merkle_tree + i);
for ( i = 0; i < 8; i++ )
g_work->denom10[i] = le32dec((uint32_t *)sctx->job.denom10 + i);
denom10[i] = le32dec((uint32_t *)sctx->job.denom10 + i);
for ( i = 0; i < 8; i++ )
g_work->denom100[i] = le32dec((uint32_t *)sctx->job.denom100 + i);
denom100[i] = le32dec((uint32_t *)sctx->job.denom100 + i);
for ( i = 0; i < 8; i++ )
g_work->denom1000[i] = le32dec((uint32_t *)sctx->job.denom1000 + i);
denom1000[i] = le32dec((uint32_t *)sctx->job.denom1000 + i);
for ( i = 0; i < 8; i++ )
g_work->denom10000[i] = le32dec((uint32_t *)sctx->job.denom10000 + i);
denom10000[i] = le32dec((uint32_t *)sctx->job.denom10000 + i);
uint32_t pofnhash[8];
memset(pofnhash, 0x00, 32);
char denom10_str [ 2 * sizeof( g_work->denom10 ) + 1 ];
char denom100_str [ 2 * sizeof( g_work->denom100 ) + 1 ];
char denom1000_str [ 2 * sizeof( g_work->denom1000 ) + 1 ];
char denom10000_str [ 2 * sizeof( g_work->denom10000 ) + 1 ];
char merkleroot_str [ 2 * sizeof( g_work->merkleroothash ) + 1 ];
char witmerkleroot_str[ 2 * sizeof( g_work->witmerkleroothash ) + 1 ];
char denom10_str [ 2 * sizeof( denom10 ) + 1 ];
char denom100_str [ 2 * sizeof( denom100 ) + 1 ];
char denom1000_str [ 2 * sizeof( denom1000 ) + 1 ];
char denom10000_str [ 2 * sizeof( denom10000 ) + 1 ];
char merkleroot_str [ 2 * sizeof( merkleroothash ) + 1 ];
char witmerkleroot_str[ 2 * sizeof( witmerkleroothash ) + 1 ];
char pofn_str [ 2 * sizeof( pofnhash ) + 1 ];
cbin2hex( denom10_str, (char*) g_work->denom10, 32 );
cbin2hex( denom100_str, (char*) g_work->denom100, 32 );
cbin2hex( denom1000_str, (char*) g_work->denom1000, 32 );
cbin2hex( denom10000_str, (char*) g_work->denom10000, 32 );
cbin2hex( merkleroot_str, (char*) g_work->merkleroothash, 32 );
cbin2hex( witmerkleroot_str, (char*) g_work->witmerkleroothash, 32 );
cbin2hex( denom10_str, (char*) denom10, 32 );
cbin2hex( denom100_str, (char*) denom100, 32 );
cbin2hex( denom1000_str, (char*) denom1000, 32 );
cbin2hex( denom10000_str, (char*) denom10000, 32 );
cbin2hex( merkleroot_str, (char*) merkleroothash, 32 );
cbin2hex( witmerkleroot_str, (char*) witmerkleroothash, 32 );
cbin2hex( pofn_str, (char*) pofnhash, 32 );
if ( true )

View File

@@ -58,7 +58,7 @@ union _sonoa_8way_context_overlay
typedef union _sonoa_8way_context_overlay sonoa_8way_context_overlay;
int sonoa_8way_hash( void *state, const void *input, int thrid )
int sonoa_8way_hash( void *state, const void *input, int thr_id )
{
uint64_t vhash[8*8] __attribute__ ((aligned (128)));
uint64_t vhashA[8*8] __attribute__ ((aligned (64)));
@@ -186,7 +186,7 @@ int sonoa_8way_hash( void *state, const void *input, int thrid )
#endif
if ( work_restart[thrid].restart ) return 0;
if ( work_restart[thr_id].restart ) return 0;
// 2
bmw512_8way_full( &ctx.bmw, vhash, vhash, 64 );
@@ -302,7 +302,7 @@ int sonoa_8way_hash( void *state, const void *input, int thrid )
hamsi512_8way_update( &ctx.hamsi, vhash, 64 );
hamsi512_8way_close( &ctx.hamsi, vhash );
if ( work_restart[thrid].restart ) return 0;
if ( work_restart[thr_id].restart ) return 0;
// 3
bmw512_8way_full( &ctx.bmw, vhash, vhash, 64 );
@@ -432,7 +432,7 @@ int sonoa_8way_hash( void *state, const void *input, int thrid )
sph_fugue512_full( &ctx.fugue, hash6, hash6, 64 );
sph_fugue512_full( &ctx.fugue, hash7, hash7, 64 );
if ( work_restart[thrid].restart ) return 0;
if ( work_restart[thr_id].restart ) return 0;
// 4
intrlv_8x64_512( vhash, hash0, hash1, hash2, hash3, hash4, hash5, hash6,
@@ -630,7 +630,7 @@ int sonoa_8way_hash( void *state, const void *input, int thrid )
#endif
if ( work_restart[thrid].restart ) return 0;
if ( work_restart[thr_id].restart ) return 0;
// 5
bmw512_8way_full( &ctx.bmw, vhash, vhash, 64 );
@@ -783,7 +783,7 @@ int sonoa_8way_hash( void *state, const void *input, int thrid )
sph_whirlpool512_full( &ctx.whirlpool, hash6, hash6, 64 );
sph_whirlpool512_full( &ctx.whirlpool, hash7, hash7, 64 );
if ( work_restart[thrid].restart ) return 0;
if ( work_restart[thr_id].restart ) return 0;
// 6
intrlv_8x64_512( vhash, hash0, hash1, hash2, hash3, hash4, hash5, hash6,
@@ -952,7 +952,7 @@ int sonoa_8way_hash( void *state, const void *input, int thrid )
sph_whirlpool512_full( &ctx.whirlpool, hash6, hash6, 64 );
sph_whirlpool512_full( &ctx.whirlpool, hash7, hash7, 64 );
if ( work_restart[thrid].restart ) return 0;
if ( work_restart[thr_id].restart ) return 0;
// 7
intrlv_8x64_512( vhash, hash0, hash1, hash2, hash3, hash4, hash5, hash6,
@@ -1117,49 +1117,6 @@ int sonoa_8way_hash( void *state, const void *input, int thrid )
return 1;
}
int scanhash_sonoa_8way( struct work *work, uint32_t max_nonce,
uint64_t *hashes_done, struct thr_info *mythr )
{
uint32_t hash[8*16] __attribute__ ((aligned (128)));
uint32_t vdata[20*8] __attribute__ ((aligned (64)));
uint32_t lane_hash[8] __attribute__ ((aligned (64)));
uint32_t *hashd7 = &(hash[7<<3]);
uint32_t *pdata = work->data;
const uint32_t *ptarget = work->target;
const uint32_t first_nonce = pdata[19];
const uint32_t last_nonce = max_nonce - 8;
__m512i *noncev = (__m512i*)vdata + 9; // aligned
uint32_t n = first_nonce;
const int thr_id = mythr->id;
const uint32_t targ32 = ptarget[7];
mm512_bswap32_intrlv80_8x64( vdata, pdata );
*noncev = mm512_intrlv_blend_32(
_mm512_set_epi32( n+7, 0, n+6, 0, n+5, 0, n+4, 0,
n+3, 0, n+2, 0, n+1, 0, n, 0 ), *noncev );
do
{
if ( sonoa_8way_hash( hash, vdata, thr_id ) )
for ( int lane = 0; lane < 8; lane++ )
if unlikely( ( hashd7[ lane ] <= targ32 ) )
{
extr_lane_8x32( lane_hash, hash, lane, 256 );
if ( likely( valid_hash( lane_hash, ptarget ) && !opt_benchmark ) )
{
pdata[19] = bswap_32( n + lane );
submit_solution( work, lane_hash, mythr );
}
}
*noncev = _mm512_add_epi32( *noncev,
m512_const1_64( 0x0000000800000000 ) );
n += 8;
} while ( likely( ( n < last_nonce ) && !work_restart[thr_id].restart ) );
pdata[19] = n;
*hashes_done = n - first_nonce;
return 0;
}
#elif defined(SONOA_4WAY)
@@ -1186,7 +1143,7 @@ union _sonoa_4way_context_overlay
typedef union _sonoa_4way_context_overlay sonoa_4way_context_overlay;
int sonoa_4way_hash( void *state, const void *input, int thrid )
int sonoa_4way_hash( void *state, const void *input, int thr_id )
{
uint64_t hash0[8] __attribute__ ((aligned (64)));
uint64_t hash1[8] __attribute__ ((aligned (64)));
@@ -1250,7 +1207,7 @@ int sonoa_4way_hash( void *state, const void *input, int thrid )
echo_full( &ctx.echo, (BitSequence *)hash3, 512,
(const BitSequence *)hash3, 64 );
if ( work_restart[thrid].restart ) return 0;
if ( work_restart[thr_id].restart ) return 0;
// 2
intrlv_4x64_512( vhash, hash0, hash1, hash2, hash3 );
@@ -1310,7 +1267,7 @@ int sonoa_4way_hash( void *state, const void *input, int thrid )
hamsi512_4way_update( &ctx.hamsi, vhash, 64 );
hamsi512_4way_close( &ctx.hamsi, vhash );
if ( work_restart[thrid].restart ) return 0;
if ( work_restart[thr_id].restart ) return 0;
// 3
bmw512_4way_init( &ctx.bmw );
@@ -1375,7 +1332,7 @@ int sonoa_4way_hash( void *state, const void *input, int thrid )
sph_fugue512_full( &ctx.fugue, hash2, hash2, 64 );
sph_fugue512_full( &ctx.fugue, hash3, hash3, 64 );
if ( work_restart[thrid].restart ) return 0;
if ( work_restart[thr_id].restart ) return 0;
// 4
intrlv_4x64_512( vhash, hash0, hash1, hash2, hash3 );
@@ -1472,7 +1429,7 @@ int sonoa_4way_hash( void *state, const void *input, int thrid )
shavite512_2way_init( &ctx.shavite );
shavite512_2way_update_close( &ctx.shavite, vhashB, vhashB, 64 );
if ( work_restart[thrid].restart ) return 0;
if ( work_restart[thr_id].restart ) return 0;
// 5
rintrlv_2x128_4x64( vhash, vhashA, vhashB, 512 );
@@ -1557,7 +1514,7 @@ int sonoa_4way_hash( void *state, const void *input, int thrid )
sph_whirlpool512_full( &ctx.whirlpool, hash2, hash2, 64 );
sph_whirlpool512_full( &ctx.whirlpool, hash3, hash3, 64 );
if ( work_restart[thrid].restart ) return 0;
if ( work_restart[thr_id].restart ) return 0;
// 6
intrlv_4x64_512( vhash, hash0, hash1, hash2, hash3 );
@@ -1650,7 +1607,7 @@ int sonoa_4way_hash( void *state, const void *input, int thrid )
sph_whirlpool512_full( &ctx.whirlpool, hash2, hash2, 64 );
sph_whirlpool512_full( &ctx.whirlpool, hash3, hash3, 64 );
if ( work_restart[thrid].restart ) return 0;
if ( work_restart[thr_id].restart ) return 0;
// 7
intrlv_4x64_512( vhash, hash0, hash1, hash2, hash3 );
@@ -1745,46 +1702,4 @@ int sonoa_4way_hash( void *state, const void *input, int thrid )
return 1;
}
int scanhash_sonoa_4way( struct work *work, const uint32_t max_nonce,
uint64_t *hashes_done, struct thr_info *mythr )
{
uint32_t hash[4*16] __attribute__ ((aligned (64)));
uint32_t vdata[24*4] __attribute__ ((aligned (64)));
uint32_t lane_hash[8] __attribute__ ((aligned (32)));
uint32_t *hashd7 = &( hash[7<<2] );
uint32_t *pdata = work->data;
const uint32_t *ptarget = work->target;
const uint32_t first_nonce = pdata[19];
const uint32_t last_nonce = max_nonce - 4;
const uint32_t targ32 = ptarget[7];
uint32_t n = first_nonce;
__m256i *noncev = (__m256i*)vdata + 9;
const int thr_id = mythr->id;
mm256_bswap32_intrlv80_4x64( vdata, pdata );
*noncev = mm256_intrlv_blend_32(
_mm256_set_epi32( n+3, 0, n+2, 0, n+1, 0, n, 0 ), *noncev );
do
{
if ( sonoa_4way_hash( hash, vdata, thr_id ) )
for ( int lane = 0; lane < 4; lane++ )
if ( unlikely( hashd7[ lane ] <= targ32 ) )
{
extr_lane_4x32( lane_hash, hash, lane, 256 );
if ( likely( valid_hash( lane_hash, ptarget ) && !opt_benchmark ) )
{
pdata[19] = bswap_32( n + lane );
submit_solution( work, lane_hash, mythr );
}
}
*noncev = _mm256_add_epi32( *noncev,
m256_const1_64( 0x0000000400000000 ) );
n += 4;
} while ( likely( ( n < last_nonce ) && !work_restart[thr_id].restart ) );
pdata[19] = n;
*hashes_done = n - first_nonce;
return 0;
}
#endif

View File

@@ -3,15 +3,14 @@
bool register_sonoa_algo( algo_gate_t* gate )
{
#if defined (SONOA_8WAY)
gate->scanhash = (void*)&scanhash_sonoa_8way;
// gate->hash = (void*)&sonoa_8way_hash;
gate->scanhash = (void*)&scanhash_8way_64in_32out;
gate->hash = (void*)&sonoa_8way_hash;
#elif defined (SONOA_4WAY)
gate->scanhash = (void*)&scanhash_sonoa_4way;
// gate->hash = (void*)&sonoa_4way_hash;
gate->scanhash = (void*)&scanhash_4way_64in_32out;
gate->hash = (void*)&sonoa_4way_hash;
#else
init_sonoa_ctx();
gate->scanhash = (void*)&scanhash_sonoa;
// gate->hash = (void*)&sonoa_hash;
gate->hash = (void*)&sonoa_hash;
#endif
gate->optimizations = SSE2_OPT | AES_OPT | AVX2_OPT | AVX512_OPT | VAES_OPT;
return true;

View File

@@ -14,21 +14,15 @@ bool register_sonoa_algo( algo_gate_t* gate );
#if defined(SONOA_8WAY)
int sonoa_8way_hash( void *state, const void *input, int thrid );
int scanhash_sonoa_8way( struct work *work, uint32_t max_nonce,
uint64_t *hashes_done, struct thr_info *mythr );
int sonoa_8way_hash( void *state, const void *input, int thr_id );
#elif defined(SONOA_4WAY)
int sonoa_4way_hash( void *state, const void *input, int thrid );
int scanhash_sonoa_4way( struct work *work, uint32_t max_nonce,
uint64_t *hashes_done, struct thr_info *mythr );
int sonoa_4way_hash( void *state, const void *input, int thr_id );
#else
int sonoa_hash( void *state, const void *input, int thrid );
int scanhash_sonoa( struct work *work, uint32_t max_nonce,
uint64_t *hashes_done, struct thr_info *mythr );
int sonoa_hash( void *state, const void *input, int thr_id );
void init_sonoa_ctx();
#endif

View File

@@ -83,7 +83,7 @@ void init_sonoa_ctx()
sph_haval256_5_init(&sonoa_ctx.haval);
};
int sonoa_hash( void *state, const void *input, int thrid )
int sonoa_hash( void *state, const void *input, int thr_id )
{
uint8_t hash[128] __attribute__ ((aligned (64)));
sonoa_ctx_holder ctx __attribute__ ((aligned (64)));
@@ -132,7 +132,7 @@ int sonoa_hash( void *state, const void *input, int thrid )
sph_echo512_close(&ctx.echo, hash);
#endif
if ( work_restart[thrid].restart ) return 0;
if ( work_restart[thr_id].restart ) return 0;
//
sph_bmw512_init( &ctx.bmw);
@@ -190,7 +190,7 @@ int sonoa_hash( void *state, const void *input, int thrid )
sph_hamsi512(&ctx.hamsi, hash, 64);
sph_hamsi512_close(&ctx.hamsi, hash);
if ( work_restart[thrid].restart ) return 0;
if ( work_restart[thr_id].restart ) return 0;
//
sph_bmw512_init( &ctx.bmw);
@@ -252,7 +252,7 @@ int sonoa_hash( void *state, const void *input, int thrid )
sph_fugue512(&ctx.fugue, hash, 64);
sph_fugue512_close(&ctx.fugue, hash);
if ( work_restart[thrid].restart ) return 0;
if ( work_restart[thr_id].restart ) return 0;
//
sph_bmw512_init( &ctx.bmw);
@@ -336,7 +336,7 @@ int sonoa_hash( void *state, const void *input, int thrid )
sph_shavite512(&ctx.shavite, hash, 64);
sph_shavite512_close(&ctx.shavite, hash);
if ( work_restart[thrid].restart ) return 0;
if ( work_restart[thr_id].restart ) return 0;
//
sph_bmw512_init( &ctx.bmw);
@@ -410,7 +410,7 @@ int sonoa_hash( void *state, const void *input, int thrid )
sph_whirlpool(&ctx.whirlpool, hash, 64);
sph_whirlpool_close(&ctx.whirlpool, hash);
if ( work_restart[thrid].restart ) return 0;
if ( work_restart[thr_id].restart ) return 0;
//
sph_bmw512_init( &ctx.bmw);
sph_bmw512(&ctx.bmw, hash, 64);
@@ -487,7 +487,7 @@ int sonoa_hash( void *state, const void *input, int thrid )
sph_whirlpool(&ctx.whirlpool, hash, 64);
sph_whirlpool_close(&ctx.whirlpool, hash);
if ( work_restart[thrid].restart ) return 0;
if ( work_restart[thr_id].restart ) return 0;
//
sph_bmw512_init( &ctx.bmw);
@@ -569,34 +569,4 @@ int sonoa_hash( void *state, const void *input, int thrid )
return 1;
}
int scanhash_sonoa( struct work *work, uint32_t max_nonce,
uint64_t *hashes_done, struct thr_info *mythr)
{
uint32_t edata[20] __attribute__((aligned(64)));
uint32_t hash64[8] __attribute__((aligned(64)));
uint32_t *pdata = work->data;
uint32_t *ptarget = work->target;
uint32_t n = pdata[19];
const uint32_t first_nonce = pdata[19];
const int thr_id = mythr->id;
const bool bench = opt_benchmark;
mm128_bswap32_80( edata, pdata );
do
{
edata[19] = n;
if ( sonoa_hash( hash64, edata, thr_id ) )
if ( unlikely( valid_hash( hash64, ptarget ) && !bench ) )
{
pdata[19] = bswap_32( n );
submit_solution( work, hash64, mythr );
}
n++;
} while ( n < max_nonce && !work_restart[thr_id].restart );
*hashes_done = n - first_nonce;
pdata[19] = n;
return 0;
}
#endif

View File

@@ -57,7 +57,7 @@ union _x17_8way_context_overlay
} __attribute__ ((aligned (64)));
typedef union _x17_8way_context_overlay x17_8way_context_overlay;
void x17_8way_hash( void *state, const void *input )
int x17_8way_hash( void *state, const void *input, int thr_id )
{
uint64_t vhash[8*8] __attribute__ ((aligned (128)));
uint64_t vhashA[8*8] __attribute__ ((aligned (64)));
@@ -230,50 +230,8 @@ void x17_8way_hash( void *state, const void *input )
haval256_5_8way_init( &ctx.haval );
haval256_5_8way_update( &ctx.haval, vhashA, 64 );
haval256_5_8way_close( &ctx.haval, state );
}
int scanhash_x17_8way( struct work *work, uint32_t max_nonce,
uint64_t *hashes_done, struct thr_info *mythr )
{
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 *hash32_d7 = &(hash32[7*8]);
uint32_t *pdata = work->data;
const uint32_t *ptarget = work->target;
const uint32_t first_nonce = pdata[19];
const uint32_t last_nonce = max_nonce - 8;
__m512i *noncev = (__m512i*)vdata + 9;
uint32_t n = first_nonce;
const int thr_id = mythr->id;
const uint32_t targ32_d7 = ptarget[7];
const bool bench = opt_benchmark;
mm512_bswap32_intrlv80_8x64( vdata, pdata );
*noncev = mm512_intrlv_blend_32(
_mm512_set_epi32( n+7, 0, n+6, 0, n+5, 0, n+4, 0,
n+3, 0, n+2, 0, n+1, 0, n, 0 ), *noncev );
do
{
x17_8way_hash( hash32, vdata );
for ( int lane = 0; lane < 8; lane++ )
if ( unlikely( ( hash32_d7[ lane ] <= targ32_d7 ) && !bench ) )
{
extr_lane_8x32( lane_hash, hash32, lane, 256 );
if ( likely( valid_hash( lane_hash, ptarget ) ) )
{
pdata[19] = bswap_32( n + lane );
submit_solution( work, lane_hash, mythr );
}
}
*noncev = _mm512_add_epi32( *noncev,
m512_const1_64( 0x0000000800000000 ) );
n += 8;
} while ( likely( ( n < last_nonce ) && !work_restart[thr_id].restart ) );
pdata[19] = n;
*hashes_done = n - first_nonce;
return 0;
return 1;
}
#elif defined(X17_4WAY)
@@ -300,7 +258,7 @@ union _x17_4way_context_overlay
};
typedef union _x17_4way_context_overlay x17_4way_context_overlay;
void x17_4way_hash( void *state, const void *input )
int x17_4way_hash( void *state, const void *input, int thr_id )
{
uint64_t vhash[8*4] __attribute__ ((aligned (64)));
uint64_t vhashA[8*4] __attribute__ ((aligned (64)));
@@ -399,49 +357,8 @@ void x17_4way_hash( void *state, const void *input )
haval256_5_4way_init( &ctx.haval );
haval256_5_4way_update( &ctx.haval, vhashB, 64 );
haval256_5_4way_close( &ctx.haval, state );
}
int scanhash_x17_4way( struct work *work, uint32_t max_nonce,
uint64_t *hashes_done, struct thr_info *mythr )
{
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 *hash32_d7 = &(hash32[ 7*4 ]);
uint32_t *pdata = work->data;
const uint32_t *ptarget = work->target;
const uint32_t first_nonce = pdata[19];
const uint32_t last_nonce = max_nonce - 4;
__m256i *noncev = (__m256i*)vdata + 9;
uint32_t n = first_nonce;
const int thr_id = mythr->id;
const uint32_t targ32_d7 = ptarget[7];
const bool bench = opt_benchmark;
mm256_bswap32_intrlv80_4x64( vdata, pdata );
*noncev = mm256_intrlv_blend_32(
_mm256_set_epi32( n+3, 0, n+2, 0, n+1, 0, n, 0 ), *noncev );
do
{
x17_4way_hash( hash32, vdata );
for ( int lane = 0; lane < 4; lane++ )
if ( unlikely( hash32_d7[ lane ] <= targ32_d7 && !bench ) )
{
extr_lane_4x32( lane_hash, hash32, lane, 256 );
if ( valid_hash( lane_hash, ptarget ) )
{
pdata[19] = bswap_32( n + lane );
submit_solution( work, lane_hash, mythr );
}
}
*noncev = _mm256_add_epi32( *noncev,
m256_const1_64( 0x0000000400000000 ) );
n += 4;
} while ( likely( ( n <= last_nonce ) && !work_restart[thr_id].restart ) );
pdata[19] = n;
*hashes_done = n - first_nonce;
return 0;
return 1;
}
#endif

View File

@@ -3,13 +3,12 @@
bool register_x17_algo( algo_gate_t* gate )
{
#if defined (X17_8WAY)
gate->scanhash = (void*)&scanhash_x17_8way;
gate->scanhash = (void*)&scanhash_8way_64in_32out;
gate->hash = (void*)&x17_8way_hash;
#elif defined (X17_4WAY)
gate->scanhash = (void*)&scanhash_x17_4way;
gate->scanhash = (void*)&scanhash_4way_64in_32out;
gate->hash = (void*)&x17_4way_hash;
#else
gate->scanhash = (void*)&scanhash_x17;
gate->hash = (void*)&x17_hash;
#endif
gate->optimizations = SSE2_OPT | AES_OPT | AVX2_OPT | AVX512_OPT | VAES_OPT;

View File

@@ -14,20 +14,15 @@ bool register_x17_algo( algo_gate_t* gate );
#if defined(X17_8WAY)
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 );
int x17_8way_hash( void *state, const void *input, int thr_id );
#elif defined(X17_4WAY)
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 );
int x17_4way_hash( void *state, const void *input, int thr_id );
#endif
void x17_hash( void *state, const void *input );
int scanhash_x17( struct work *work, uint32_t max_nonce,
uint64_t *hashes_done, struct thr_info *mythr );
int x17_hash( void *state, const void *input, int thr_id );
#endif

View File

@@ -56,7 +56,7 @@ union _x17_context_overlay
};
typedef union _x17_context_overlay x17_context_overlay;
void x17_hash(void *output, const void *input)
int x17_hash(void *output, const void *input, int thr_id )
{
// unsigned char hash[64 * 4] __attribute__((aligned(64))) = {0};
unsigned char hash[64] __attribute__((aligned(64)));
@@ -143,36 +143,8 @@ void x17_hash(void *output, const void *input)
sph_haval256_5_init(&ctx.haval);
sph_haval256_5( &ctx.haval, (const void*)hash, 64 );
sph_haval256_5_close( &ctx.haval, output );
}
int scanhash_x17( struct work *work, uint32_t max_nonce,
uint64_t *hashes_done, struct thr_info *mythr)
{
uint32_t edata[20] __attribute__((aligned(64)));
uint32_t hash64[8] __attribute__((aligned(64)));
uint32_t *pdata = work->data;
uint32_t *ptarget = work->target;
uint32_t n = pdata[19] - 1;
const uint32_t first_nonce = pdata[19];
const int thr_id = mythr->id;
const bool bench = opt_benchmark;
mm128_bswap32_80( edata, pdata );
do
{
edata[19] = n;
x17_hash( hash64, edata );
if ( unlikely( valid_hash( hash64, ptarget ) && !bench ) )
{
pdata[19] = bswap_32( n );
submit_solution( work, hash64, mythr );
}
n++;
} while ( n < max_nonce && !work_restart[thr_id].restart );
*hashes_done = n - first_nonce;
pdata[19] = n;
return 0;
return 1;
}
#endif

View File

@@ -57,7 +57,7 @@ union _xevan_8way_context_overlay
} __attribute__ ((aligned (64)));
typedef union _xevan_8way_context_overlay xevan_8way_context_overlay;
void xevan_8way_hash( void *output, const void *input )
int xevan_8way_hash( void *output, const void *input, int thr_id )
{
uint64_t vhash[16<<3] __attribute__ ((aligned (128)));
uint64_t vhashA[16<<3] __attribute__ ((aligned (64)));
@@ -395,50 +395,8 @@ void xevan_8way_hash( void *output, const void *input )
haval256_5_8way_init( &ctx.haval );
haval256_5_8way_update( &ctx.haval, vhashA, dataLen );
haval256_5_8way_close( &ctx.haval, output );
}
int scanhash_xevan_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 vdata[20*8] __attribute__ ((aligned (64)));
uint32_t lane_hash[8] __attribute__ ((aligned (64)));
uint32_t *hashd7 = &(hash[7*8]);
uint32_t *pdata = work->data;
const uint32_t *ptarget = work->target;
const uint32_t first_nonce = pdata[19];
const uint32_t last_nonce = max_nonce - 8;
__m512i *noncev = (__m512i*)vdata + 9;
uint32_t n = first_nonce;
const int thr_id = mythr->id;
const uint32_t targ32 = ptarget[7];
const bool bench = opt_benchmark;
mm512_bswap32_intrlv80_8x64( vdata, pdata );
*noncev = mm512_intrlv_blend_32(
_mm512_set_epi32( n+7, 0, n+6, 0, n+5, 0, n+4, 0,
n+3, 0, n+2, 0, n+1, 0, n, 0 ), *noncev );
do
{
xevan_8way_hash( hash, vdata );
for ( int lane = 0; lane < 8; lane++ )
if ( unlikely( ( hashd7[ lane ] <= targ32 ) && !bench ) )
{
extr_lane_8x32( lane_hash, hash, lane, 256 );
if ( likely( valid_hash( lane_hash, ptarget ) ) )
{
pdata[19] = bswap_32( n + lane );
submit_solution( work, lane_hash, mythr );
}
}
*noncev = _mm512_add_epi32( *noncev,
m512_const1_64( 0x0000000800000000 ) );
n += 8;
} while ( likely( ( n < last_nonce ) && !work_restart[thr_id].restart ) );
pdata[19] = n;
*hashes_done = n - first_nonce;
return 0;
return 1;
}
#elif defined(XEVAN_4WAY)
@@ -465,7 +423,7 @@ union _xevan_4way_context_overlay
};
typedef union _xevan_4way_context_overlay xevan_4way_context_overlay;
void xevan_4way_hash( void *output, const void *input )
int xevan_4way_hash( void *output, const void *input, int thr_id )
{
uint64_t hash0[16] __attribute__ ((aligned (64)));
uint64_t hash1[16] __attribute__ ((aligned (64)));
@@ -540,10 +498,10 @@ void xevan_4way_hash( void *output, const void *input )
dintrlv_4x64( hash0, hash1, hash2, hash3, vhash, dataLen<<3 );
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, 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 );
// Parallel 4way 32 bit
intrlv_4x32( vhash, hash0, hash1, hash2, hash3, dataLen<<3 );
@@ -637,10 +595,10 @@ void xevan_4way_hash( void *output, const void *input )
dintrlv_4x64( hash0, hash1, hash2, hash3, vhash, dataLen<<3 );
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, 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 );
intrlv_4x32( vhash, hash0, hash1, hash2, hash3, dataLen<<3 );
@@ -666,49 +624,8 @@ void xevan_4way_hash( void *output, const void *input )
haval256_5_4way_init( &ctx.haval );
haval256_5_4way_update( &ctx.haval, vhashA, dataLen );
haval256_5_4way_close( &ctx.haval, output );
}
int scanhash_xevan_4way( struct work *work, uint32_t max_nonce,
uint64_t *hashes_done, struct thr_info *mythr )
{
uint32_t hash[16*4] __attribute__ ((aligned (128)));
uint32_t vdata[20*4] __attribute__ ((aligned (64)));
uint32_t lane_hash[8] __attribute__ ((aligned (64)));
uint32_t *hashd7 = &(hash[7<<2]);
uint32_t *pdata = work->data;
uint32_t *ptarget = work->target;
int thr_id = mythr->id;
__m256i *noncev = (__m256i*)vdata + 9;
const uint32_t targ32 = ptarget[7];
const uint32_t first_nonce = pdata[19];
const uint32_t last_nonce = max_nonce - 4;
uint32_t n = first_nonce;
const bool bench = opt_benchmark;
if ( bench ) ptarget[7] = 0x0cff;
mm256_bswap32_intrlv80_4x64( vdata, pdata );
*noncev = mm256_intrlv_blend_32(
_mm256_set_epi32( n+3, 0, n+2, 0, n+1, 0, n, 0 ), *noncev );
do {
xevan_4way_hash( hash, vdata );
for ( int lane = 0; lane < 4; lane++ )
if ( unlikely( hashd7[ lane ] <= targ32 ) && ! bench )
{
extr_lane_4x32( lane_hash, hash, lane, 256 );
if ( valid_hash( lane_hash, ptarget ) )
{
pdata[19] = bswap_32( n + lane );
submit_solution( work, lane_hash, mythr );
}
}
*noncev = _mm256_add_epi32( *noncev,
m256_const1_64( 0x0000000400000000 ) );
n += 4;
} while ( likely( ( n < last_nonce ) && !work_restart[thr_id].restart ) );
pdata[19] = n;
*hashes_done = n - first_nonce;
return 0;
return 1;
}
#endif

View File

@@ -3,14 +3,13 @@
bool register_xevan_algo( algo_gate_t* gate )
{
#if defined (XEVAN_8WAY)
gate->scanhash = (void*)&scanhash_xevan_8way;
gate->scanhash = (void*)&scanhash_8way_64in_32out;
gate->hash = (void*)&xevan_8way_hash;
#elif defined (XEVAN_4WAY)
gate->scanhash = (void*)&scanhash_xevan_4way;
gate->scanhash = (void*)&scanhash_4way_64in_32out;
gate->hash = (void*)&xevan_4way_hash;
#else
init_xevan_ctx();
gate->scanhash = (void*)&scanhash_xevan;
gate->hash = (void*)&xevan_hash;
#endif
gate->optimizations = SSE2_OPT | AES_OPT | AVX2_OPT | AVX512_OPT | VAES_OPT;

View File

@@ -14,26 +14,15 @@ bool register_xevan_algo( algo_gate_t* gate );
#if defined(XEVAN_8WAY)
void xevan_8way_hash( void *state, const void *input );
int xevan_8way_hash( void *state, const void *input, int thr_id );
int scanhash_xevan_8way( struct work *work, uint32_t max_nonce,
uint64_t *hashes_done, struct thr_info *mythr );
#elif defined(XEVAN_4WAY)
void xevan_4way_hash( void *state, const void *input );
int scanhash_xevan_4way( struct work *work, uint32_t max_nonce,
uint64_t *hashes_done, struct thr_info *mythr );
//void init_xevan_4way_ctx();
int xevan_4way_hash( void *state, const void *input, int thr_id );
#else
void xevan_hash( void *state, const void *input );
int scanhash_xevan( struct work *work, uint32_t max_nonce,
uint64_t *hashes_done, struct thr_info *mythr );
int xevan_hash( void *state, const void *input, int trh_id );
void init_xevan_ctx();
#endif

View File

@@ -83,7 +83,7 @@ void init_xevan_ctx()
#endif
};
void xevan_hash(void *output, const void *input)
int xevan_hash(void *output, const void *input, int thr_id )
{
uint32_t _ALIGN(64) hash[32]; // 128 bytes required
const int dataLen = 128;
@@ -218,36 +218,8 @@ void xevan_hash(void *output, const void *input)
sph_haval256_5_close(&ctx.haval, hash);
memcpy(output, hash, 32);
}
int scanhash_xevan( struct work *work, uint32_t max_nonce,
uint64_t *hashes_done, struct thr_info *mythr)
{
uint32_t edata[20] __attribute__((aligned(64)));
uint32_t hash64[8] __attribute__((aligned(64)));
uint32_t *pdata = work->data;
uint32_t *ptarget = work->target;
uint32_t n = pdata[19];
const uint32_t first_nonce = pdata[19];
const int thr_id = mythr->id;
const bool bench = opt_benchmark;
mm128_bswap32_80( edata, pdata );
do
{
edata[19] = n;
xevan_hash( hash64, edata );
if ( unlikely( valid_hash( hash64, ptarget ) && !bench ) )
{
pdata[19] = bswap_32( n );
submit_solution( work, hash64, mythr );
}
n++;
} while ( n < max_nonce && !work_restart[thr_id].restart );
pdata[19] = n;
*hashes_done = n - first_nonce;
return 0;
return 1;
}
#endif

View File

@@ -445,7 +445,7 @@ bool register_yescrypt_algo( algo_gate_t* gate )
YESCRYPT_P = 1;
applog( LOG_NOTICE,"Yescrypt parameters: N= %d, R= %d.", YESCRYPT_N,
applog( LOG_NOTICE,"Yescrypt parameters: N= %d, R= %d", YESCRYPT_N,
YESCRYPT_R );
if ( yescrypt_client_key )
applog( LOG_NOTICE,"Key= \"%s\"\n", yescrypt_client_key );

View File

@@ -19,12 +19,11 @@
*/
#include "cpuminer-config.h"
#include "miner.h"
#include <stdio.h>
#include <string.h>
#include <stdint.h>
#include <stdlib.h>
#include "algo-gate-api.h"
#include "yespower.h"
#include "yescrypt-r8g.h"
int scanhash_yespower_r8g( struct work *work, uint32_t max_nonce,
uint64_t *hashes_done, struct thr_info *mythr )
@@ -38,17 +37,7 @@ int scanhash_yespower_r8g( struct work *work, uint32_t max_nonce,
const uint32_t last_nonce = max_nonce;
const int thr_id = mythr->id;
static __thread int initialized = 0;
static __thread yespower_local_t local;
if ( !initialized )
{
if ( yespower_init_local( &local ) )
return -1;
initialized = 1;
}
yespower_params_t params =
yespower_params_t params =
{
.version = YESPOWER_0_5,
.N = 2048,
@@ -67,7 +56,7 @@ int scanhash_yespower_r8g( struct work *work, uint32_t max_nonce,
SHA256_Update( &sha256_prehash_ctx, endiandata, 64 );
do {
yespower_hash( &local, (unsigned char *)endiandata, params.perslen,
yespower_tls( (unsigned char *)endiandata, params.perslen,
&params, (yespower_binary_t*)hash, thr_id );
if unlikely( valid_hash( hash, ptarget ) && !opt_benchmark )
@@ -87,6 +76,7 @@ bool register_yescryptr8g_algo( algo_gate_t* gate )
{
gate->optimizations = SSE2_OPT | SHA_OPT;
gate->scanhash = (void*)&scanhash_yespower_r8g;
gate->hash = (void*)&yespower_tls;
pk_buffer_size = 26;
opt_sapling = true;
opt_target_factor = 65536.0;

View File

@@ -0,0 +1,49 @@
/*-
* Copyright 2009 Colin Percival
* Copyright 2013-2018 Alexander Peslyak
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
*
* THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*
* This file was originally written by Colin Percival as part of the Tarsnap
* online backup system.
*/
#ifndef _YESPOWERR8G_H_
#define _YESPOWERR8G_H_
#include <stdint.h>
#include <stdlib.h> /* for size_t */
#include "algo-gate-api.h"
#include "algo/yespower/yespower.h"
#ifdef __cplusplus
extern "C" {
#endif
extern int yespowerr8g_tls(const uint8_t *src, size_t srclen,
const yespower_params_t *params, yespower_binary_t *dst);
#ifdef __cplusplus
}
#endif
#endif /* !_YESPOWERR8G_H_ */

View File

@@ -1112,10 +1112,10 @@ static void smix(uint8_t *B, size_t r, uint32_t N,
*
* Return 0 on success; or -1 on error.
*/
int yespower_b2b_hash(yespower_local_t *local,
int yespower_b2b(yespower_local_t *local,
const uint8_t *src, size_t srclen,
const yespower_params_t *params,
void *dst, int thrid )
yespower_binary_t *dst, int thrid )
{
uint32_t N = params->N;
uint32_t r = params->r;
@@ -1191,4 +1191,37 @@ fail:
return 0;
}
/**
* yespower_tls(src, srclen, params, dst):
* Compute yespower(src[0 .. srclen - 1], N, r), to be checked for "< target".
* The memory allocation is maintained internally using thread-local storage.
*
* Return 0 on success; or -1 on error.
*/
int yespower_b2b_tls(const uint8_t *src, size_t srclen,
const yespower_params_t *params, yespower_binary_t *dst, int thrid )
{
static __thread int initialized = 0;
static __thread yespower_local_t local;
if (!initialized) {
init_region(&local);
initialized = 1;
}
return yespower_b2b(&local, src, srclen, params, dst, thrid);
}
/*
int yespower_init_local(yespower_local_t *local)
{
init_region(local);
return 0;
}
int yespower_free_local(yespower_local_t *local)
{
return free_region(local);
}
*/
#endif

View File

@@ -23,17 +23,26 @@
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*
* This file was originally written by Cryply team as part of the Cryply
* coin.
*/
#include "yespower.h"
#include "algo-gate-api.h"
yespower_params_t yespower_params;
// Give each thread its own copy to avoid requiring mutex.
//SHA256_CTX sha256_prehash_ctx;
__thread SHA256_CTX sha256_prehash_ctx;
// YESPOWER
int yespower_hash( const char *input, char *output, uint32_t len, int thrid )
{
return yespower_tls( input, len, &yespower_params,
(yespower_binary_t*)output, thrid );
}
int scanhash_yespower( struct work *work, uint32_t max_nonce,
uint64_t *hashes_done, struct thr_info *mythr )
{
@@ -46,16 +55,6 @@ int scanhash_yespower( struct work *work, uint32_t max_nonce,
uint32_t n = first_nonce;
const int thr_id = mythr->id;
static __thread int initialized = 0;
static __thread yespower_local_t local;
if ( !initialized )
{
if ( yespower_init_local( &local ) )
return -1;
initialized = 1;
}
for ( int k = 0; k < 19; k++ )
be32enc( &endiandata[k], pdata[k] );
endiandata[19] = n;
@@ -65,8 +64,7 @@ int scanhash_yespower( struct work *work, uint32_t max_nonce,
SHA256_Update( &sha256_prehash_ctx, endiandata, 64 );
do {
if ( yespower_hash( &local, (char*)endiandata, 80, &yespower_params,
(char*)vhash, thr_id ) )
if ( yespower_hash( (char*)endiandata, (char*)vhash, 80, thr_id ) )
if unlikely( valid_hash( vhash, ptarget ) && !opt_benchmark )
{
be32enc( pdata+19, n );
@@ -81,6 +79,11 @@ int scanhash_yespower( struct work *work, uint32_t max_nonce,
// YESPOWER-B2B
int yespower_b2b_hash( const char *input, char *output, uint32_t len, int thrid )
{
return yespower_b2b_tls( input, len, &yespower_params, (yespower_binary_t*)output, thrid );
}
int scanhash_yespower_b2b( struct work *work, uint32_t max_nonce,
uint64_t *hashes_done, struct thr_info *mythr )
{
@@ -93,16 +96,6 @@ int scanhash_yespower_b2b( struct work *work, uint32_t max_nonce,
const uint32_t last_nonce = max_nonce;
const int thr_id = mythr->id;
static __thread int initialized = 0;
static __thread yespower_local_t local;
if ( !initialized )
{
if ( yespower_init_local( &local ) )
return -1;
initialized = 1;
}
for ( int k = 0; k < 19; k++ )
be32enc( &endiandata[k], pdata[k] );
endiandata[19] = n;
@@ -112,8 +105,7 @@ int scanhash_yespower_b2b( struct work *work, uint32_t max_nonce,
SHA256_Update( &sha256_prehash_ctx, endiandata, 64 );
do {
if (yespower_b2b_hash( &local, (char*) endiandata, 80, &yespower_params,
(char*) vhash, thr_id ) )
if (yespower_b2b_hash( (char*) endiandata, (char*) vhash, 80, thr_id ) )
if unlikely( valid_hash( vhash, ptarget ) && !opt_benchmark )
{
be32enc( pdata+19, n );
@@ -147,13 +139,14 @@ bool register_yespower_algo( algo_gate_t* gate )
yespower_params.perslen = 0;
}
applog( LOG_NOTICE,"Yespower parameters: N= %d, R= %d.", yespower_params.N,
applog( LOG_NOTICE,"Yespower parameters: N= %d, R= %d", yespower_params.N,
yespower_params.r );
if ( yespower_params.pers )
applog( LOG_NOTICE,"Key= \"%s\"\n", yespower_params.pers );
gate->optimizations = SSE2_OPT | SHA_OPT;
gate->scanhash = (void*)&scanhash_yespower;
gate->hash = (void*)&yespower_hash;
opt_target_factor = 65536.0;
return true;
};
@@ -167,6 +160,7 @@ bool register_yespowerr16_algo( algo_gate_t* gate )
yespower_params.perslen = 0;
gate->optimizations = SSE2_OPT | SHA_OPT;
gate->scanhash = (void*)&scanhash_yespower;
gate->hash = (void*)&yespower_hash;
opt_target_factor = 65536.0;
return true;
};
@@ -270,13 +264,14 @@ bool register_power2b_algo( algo_gate_t* gate )
yespower_params.pers = "Now I am become Death, the destroyer of worlds";
yespower_params.perslen = 46;
applog( LOG_NOTICE,"yespower-b2b parameters: N= %d, R= %d.", yespower_params.N,
applog( LOG_NOTICE,"yespower-b2b parameters: N= %d, R= %d", yespower_params.N,
yespower_params.r );
applog( LOG_NOTICE,"Key= \"%s\"", yespower_params.pers );
applog( LOG_NOTICE,"Key length= %d\n", yespower_params.perslen );
gate->optimizations = SSE2_OPT;
gate->scanhash = (void*)&scanhash_yespower_b2b;
gate->hash = (void*)&yespower_b2b_hash;
opt_target_factor = 65536.0;
return true;
};
@@ -316,6 +311,7 @@ bool register_yespower_b2b_algo( algo_gate_t* gate )
gate->optimizations = SSE2_OPT;
gate->scanhash = (void*)&scanhash_yespower_b2b;
gate->hash = (void*)&yespower_b2b_hash;
opt_target_factor = 65536.0;
return true;
};

View File

@@ -1024,10 +1024,10 @@ static void smix(uint8_t *B, size_t r, uint32_t N,
*
* Return 0 on success; or -1 on error.
*/
int yespower_hash( yespower_local_t *local,
int yespower(yespower_local_t *local,
const uint8_t *src, size_t srclen,
const yespower_params_t *params,
void *dst, int thrid )
yespower_binary_t *dst, int thrid )
{
yespower_version_t version = params->version;
uint32_t N = params->N;
@@ -1158,6 +1158,27 @@ int yespower_hash( yespower_local_t *local,
return 1;
}
/**
* yespower_tls(src, srclen, params, dst):
* Compute yespower(src[0 .. srclen - 1], N, r), to be checked for "< target".
* The memory allocation is maintained internally using thread-local storage.
*
* Return 0 on success; or -1 on error.
*/
int yespower_tls(const uint8_t *src, size_t srclen,
const yespower_params_t *params, yespower_binary_t *dst, int thrid )
{
static __thread int initialized = 0;
static __thread yespower_local_t local;
if (!initialized) {
if (yespower_init_local(&local))
return -1;
initialized = 1;
}
return yespower( &local, src, srclen, params, dst, thrid );
}
int yespower_init_local(yespower_local_t *local)
{
@@ -1169,5 +1190,4 @@ int yespower_free_local(yespower_local_t *local)
{
return free_region(local);
}
#endif

View File

@@ -78,19 +78,66 @@ typedef struct {
extern yespower_params_t yespower_params;
//SHA256_CTX sha256_prehash_ctx;
extern __thread SHA256_CTX sha256_prehash_ctx;
/**
* yespower_init_local(local):
* Initialize the thread-local (RAM) data structure. Actual memory allocation
* is currently fully postponed until a call to yespower().
*
* Return 0 on success; or -1 on error.
*
* MT-safe as long as local is local to the thread.
*/
extern int yespower_init_local(yespower_local_t *local);
/**
* yespower_free_local(local):
* Free memory that may have been allocated for an initialized thread-local
* (RAM) data structure.
*
* Return 0 on success; or -1 on error.
*
* MT-safe as long as local is local to the thread.
*/
extern int yespower_free_local(yespower_local_t *local);
extern int yespower_hash(yespower_local_t *local,
/**
* yespower(local, src, srclen, params, dst):
* Compute yespower(src[0 .. srclen - 1], N, r), to be checked for "< target".
* local is the thread-local data structure, allowing to preserve and reuse a
* memory allocation across calls, thereby reducing processing overhead.
*
* Return 0 on success; or -1 on error.
*
* local must be initialized with yespower_init_local().
*
* MT-safe as long as local and dst are local to the thread.
*/
extern int yespower(yespower_local_t *local,
const uint8_t *src, size_t srclen,
const yespower_params_t *params, void *dst, int thrid);
const yespower_params_t *params, yespower_binary_t *dst, int thrid);
extern int yespower_b2b_hash(yespower_local_t *local,
extern int yespower_b2b(yespower_local_t *local,
const uint8_t *src, size_t srclen,
const yespower_params_t *params, void *dst, int thrid );
const yespower_params_t *params, yespower_binary_t *dst, int thrid );
/**
* yespower_tls(src, srclen, params, dst):
* Compute yespower(src[0 .. srclen - 1], N, r), to be checked for "< target".
* The memory allocation is maintained internally using thread-local storage.
*
* Return 0 on success; or -1 on error.
*
* MT-safe as long as dst is local to the thread.
*/
extern int yespower_tls(const uint8_t *src, size_t srclen,
const yespower_params_t *params, yespower_binary_t *dst, int thr_id);
extern int yespower_b2b_tls(const uint8_t *src, size_t srclen,
const yespower_params_t *params, yespower_binary_t *dst, int thr_id);
#if defined(__AVX2__)
@@ -103,6 +150,7 @@ extern int yespower_8way( yespower_local_t *local, const __m256i *src,
size_t srclen, const yespower_params_t *params,
yespower_8way_binary_t *dst, int thrid );
extern int yespower_8way_tls( const __m256i *src, size_t srclen,
const yespower_params_t *params, yespower_8way_binary_t *dst, int thr_id );

View File

@@ -4,13 +4,20 @@
# during develpment. However the information contained may provide compilation
# tips to users.
rm cpuminer-avx512 cpuminer-avx2 cpuminer-aes-avx cpuminer-aes-sse42 cpuminer-sse42 cpuminer-ssse3 cpuminer-sse2 cpuminer-zen > /dev/null
rm cpuminer-avx512-sha-vaes cpuminer-avx512 cpuminer-avx2 cpuminer-aes-avx cpuminer-aes-sse42 cpuminer-sse42 cpuminer-ssse3 cpuminer-sse2 cpuminer-zen > /dev/null
make distclean || echo clean
rm -f config.status
./autogen.sh || echo done
CFLAGS="-O3 -march=skylake-avx512 -Wall" ./configure --with-curl
make -j 16
CFLAGS="-O3 -march=icelake-client -Wall -fno-common" ./configure --with-curl
make -j 8
strip -s cpuminer.exe
mv cpuminer.exe cpuminer-avx512-sha-vaes.exe
strip -s cpuminer
mv cpuminer cpuminer-avx512-sha-vaes
CFLAGS="-O3 -march=skylake-avx512 -Wall -fno-common" ./configure --with-curl
make -j 8
strip -s cpuminer.exe
mv cpuminer.exe cpuminer-avx512.exe
strip -s cpuminer
@@ -19,8 +26,8 @@ mv cpuminer cpuminer-avx512
make clean || echo clean
rm -f config.status
# GCC 9 doesn't include AES with core-avx2
CFLAGS="-O3 -march=core-avx2 -maes -Wall" ./configure --with-curl
make -j 16
CFLAGS="-O3 -march=core-avx2 -maes -Wall -fno-common" ./configure --with-curl
make -j 8
strip -s cpuminer.exe
mv cpuminer.exe cpuminer-avx2.exe
strip -s cpuminer
@@ -28,17 +35,17 @@ mv cpuminer cpuminer-avx2
make clean || echo clean
rm -f config.status
CFLAGS="-O3 -march=corei7-avx -maes -Wall" ./configure --with-curl
make -j 16
CFLAGS="-O3 -march=corei7-avx -maes -Wall -fno-common" ./configure --with-curl
make -j 8
strip -s cpuminer.exe
mv cpuminer.exe cpuminer-avx.exe
strip -s cpuminer
mv cpuminer cpuminer-aes-avx
mv cpuminer cpuminer-avx
make clean || echo clean
rm -f config.status
CFLAGS="-O3 -maes -msse4.2 -Wall" ./configure --with-curl
make -j 16
CFLAGS="-O3 -maes -msse4.2 -Wall -fno-common" ./configure --with-curl
make -j 8
strip -s cpuminer.exe
mv cpuminer.exe cpuminer-aes-sse42.exe
strip -s cpuminer
@@ -46,8 +53,8 @@ mv cpuminer cpuminer-aes-sse42
#make clean || echo clean
#rm -f config.status
#CFLAGS="-O3 -march=corei7 -Wall" ./configure --with-curl
#make -j 16
#CFLAGS="-O3 -march=corei7 -Wall -fno-common" ./configure --with-curl
#make -j 8
#strip -s cpuminer.exe
#mv cpuminer.exe cpuminer-sse42.exe
#strip -s cpuminer
@@ -55,8 +62,8 @@ mv cpuminer cpuminer-aes-sse42
#make clean || echo clean
#rm -f config.status
#CFLAGS="-O3 -march=core2 -Wall" ./configure --with-curl
#make -j 16
#CFLAGS="-O3 -march=core2 -Wall -fno-common" ./configure --with-curl
#make -j 8
#strip -s cpuminer.exe
#mv cpuminer.exe cpuminer-ssse3.exe
#strip -s cpuminer
@@ -64,8 +71,8 @@ mv cpuminer cpuminer-aes-sse42
make clean || echo clean
rm -f config.status
CFLAGS="-O3 -msse2 -Wall" ./configure --with-curl
make -j 16
CFLAGS="-O3 -msse2 -Wall -fno-common" ./configure --with-curl
make -j 8
strip -s cpuminer.exe
mv cpuminer.exe cpuminer-sse2.exe
strip -s cpuminer
@@ -73,8 +80,8 @@ mv cpuminer cpuminer-sse2
make clean || echo done
rm -f config.status
CFLAGS="-O3 -march=znver1 -Wall" ./configure --with-curl
make -j 16
CFLAGS="-O3 -march=znver1 -Wall -fno-common" ./configure --with-curl
make -j 8
strip -s cpuminer.exe
mv cpuminer.exe cpuminer-zen.exe
strip -s cpuminer
@@ -82,8 +89,8 @@ mv cpuminer cpuminer-zen
make clean || echo done
rm -f config.status
CFLAGS="-O3 -march=native -Wall" ./configure --with-curl
make -j 16
CFLAGS="-O3 -march=native -Wall -fno-common" ./configure --with-curl
make -j 8
strip -s cpuminer.exe
strip -s cpuminer

27
build-no-common.sh Executable file
View File

@@ -0,0 +1,27 @@
#!/bin/bash
#if [ "$OS" = "Windows_NT" ]; then
# ./mingw64.sh
# exit 0
#fi
# Linux build
make distclean || echo clean
rm -f config.status
./autogen.sh || echo done
# Ubuntu 10.04 (gcc 4.4)
# extracflags="-O3 -march=native -Wall -D_REENTRANT -funroll-loops -fvariable-expansion-in-unroller -fmerge-all-constants -fbranch-target-load-optimize2 -fsched2-use-superblocks -falign-loops=16 -falign-functions=16 -falign-jumps=16 -falign-labels=16"
# Debian 7.7 / Ubuntu 14.04 (gcc 4.7+)
#extracflags="$extracflags -Ofast -flto -fuse-linker-plugin -ftree-loop-if-convert-stores"
#CFLAGS="-O3 -march=native -Wall" ./configure --with-curl --with-crypto=$HOME/usr
CFLAGS="-O3 -march=native -Wall -fno-common" ./configure --with-curl
#CFLAGS="-O3 -march=native -Wall" CXXFLAGS="$CFLAGS -std=gnu++11" ./configure --with-curl
make -j 4
strip -s cpuminer

View File

@@ -3,8 +3,8 @@
# imake clean and rm all the targetted executables.
# tips to users.
rm cpuminer-avx512 cpuminer-avx2 cpuminer-aes-avx cpuminer-aes-sse42 cpuminer-sse2 cpuminer-zen > /dev/null
rm cpuminer-avx512-sha-vaes cpuminer-avx512 cpuminer-avx2 cpuminer-avx cpuminer-aes-sse42 cpuminer-sse2 cpuminer-zen > /dev/null
rm cpuminer-avx512.exe cpuminer-avx2.exe cpuminer-aes-avx.exe cpuminer-aes-sse42.exe cpuminer-sse2.exe cpuminer-zen.exe > /dev/null
rm cpuminer-avx512-sha-vaes.exe cpuminer-avx512.exe cpuminer-avx2.exe cpuminer-avx.exe cpuminer-aes-sse42.exe cpuminer-sse2.exe cpuminer-zen.exe > /dev/null
make distclean > /dev/null

211
configure vendored
View File

@@ -1,6 +1,6 @@
#! /bin/sh
# Guess values for system-dependent variables and create Makefiles.
# Generated by GNU Autoconf 2.69 for cpuminer-opt 3.12.8.
# Generated by GNU Autoconf 2.69 for cpuminer-opt 3.14.3.
#
#
# Copyright (C) 1992-1996, 1998-2012 Free Software Foundation, Inc.
@@ -577,8 +577,8 @@ MAKEFLAGS=
# Identity of this package.
PACKAGE_NAME='cpuminer-opt'
PACKAGE_TARNAME='cpuminer-opt'
PACKAGE_VERSION='3.12.8'
PACKAGE_STRING='cpuminer-opt 3.12.8'
PACKAGE_VERSION='3.14.3'
PACKAGE_STRING='cpuminer-opt 3.14.3'
PACKAGE_BUGREPORT=''
PACKAGE_URL=''
@@ -667,7 +667,6 @@ am__nodep
AMDEPBACKSLASH
AMDEP_FALSE
AMDEP_TRUE
am__quote
am__include
DEPDIR
OBJEXT
@@ -757,7 +756,8 @@ PACKAGE_VERSION
PACKAGE_TARNAME
PACKAGE_NAME
PATH_SEPARATOR
SHELL'
SHELL
am__quote'
ac_subst_files=''
ac_user_opts='
enable_option_checking
@@ -1332,7 +1332,7 @@ 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 3.12.8 to adapt to many kinds of systems.
\`configure' configures cpuminer-opt 3.14.3 to adapt to many kinds of systems.
Usage: $0 [OPTION]... [VAR=VALUE]...
@@ -1404,7 +1404,7 @@ fi
if test -n "$ac_init_help"; then
case $ac_init_help in
short | recursive ) echo "Configuration of cpuminer-opt 3.12.8:";;
short | recursive ) echo "Configuration of cpuminer-opt 3.14.3:";;
esac
cat <<\_ACEOF
@@ -1509,7 +1509,7 @@ fi
test -n "$ac_init_help" && exit $ac_status
if $ac_init_version; then
cat <<\_ACEOF
cpuminer-opt configure 3.12.8
cpuminer-opt configure 3.14.3
generated by GNU Autoconf 2.69
Copyright (C) 2012 Free Software Foundation, Inc.
@@ -2012,7 +2012,7 @@ 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 3.12.8, which was
It was created by cpuminer-opt $as_me 3.14.3, which was
generated by GNU Autoconf 2.69. Invocation command line was
$ $0 $@
@@ -2507,7 +2507,7 @@ ac_config_headers="$ac_config_headers cpuminer-config.h"
am__api_version='1.15'
am__api_version='1.16'
# Find a good install program. We prefer a C program (faster),
# so one script is as good as another. But avoid the broken or
@@ -2993,7 +2993,7 @@ fi
# Define the identity of the package.
PACKAGE='cpuminer-opt'
VERSION='3.12.8'
VERSION='3.14.3'
cat >>confdefs.h <<_ACEOF
@@ -3023,8 +3023,8 @@ MAKEINFO=${MAKEINFO-"${am_missing_run}makeinfo"}
# For better backward compatibility. To be removed once Automake 1.9.x
# dies out for good. For more background, see:
# <http://lists.gnu.org/archive/html/automake/2012-07/msg00001.html>
# <http://lists.gnu.org/archive/html/automake/2012-07/msg00014.html>
# <https://lists.gnu.org/archive/html/automake/2012-07/msg00001.html>
# <https://lists.gnu.org/archive/html/automake/2012-07/msg00014.html>
mkdir_p='$(MKDIR_P)'
# We need awk for the "check" target (and possibly the TAP driver). The
@@ -3075,7 +3075,7 @@ END
Aborting the configuration process, to ensure you take notice of the issue.
You can download and install GNU coreutils to get an 'rm' implementation
that behaves properly: <http://www.gnu.org/software/coreutils/>.
that behaves properly: <https://www.gnu.org/software/coreutils/>.
If you want to complete the configuration process using your problematic
'rm' anyway, export the environment variable ACCEPT_INFERIOR_RM_PROGRAM
@@ -3115,45 +3115,45 @@ DEPDIR="${am__leading_dot}deps"
ac_config_commands="$ac_config_commands depfiles"
am_make=${MAKE-make}
cat > confinc << 'END'
{ $as_echo "$as_me:${as_lineno-$LINENO}: checking whether ${MAKE-make} supports the include directive" >&5
$as_echo_n "checking whether ${MAKE-make} supports the include directive... " >&6; }
cat > confinc.mk << 'END'
am__doit:
@echo this is the am__doit target
@echo this is the am__doit target >confinc.out
.PHONY: am__doit
END
# If we don't find an include directive, just comment out the code.
{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for style of include used by $am_make" >&5
$as_echo_n "checking for style of include used by $am_make... " >&6; }
am__include="#"
am__quote=
_am_result=none
# First try GNU make style include.
echo "include confinc" > confmf
# Ignore all kinds of additional output from 'make'.
case `$am_make -s -f confmf 2> /dev/null` in #(
*the\ am__doit\ target*)
am__include=include
am__quote=
_am_result=GNU
;;
esac
# Now try BSD make style include.
if test "$am__include" = "#"; then
echo '.include "confinc"' > confmf
case `$am_make -s -f confmf 2> /dev/null` in #(
*the\ am__doit\ target*)
am__include=.include
am__quote="\""
_am_result=BSD
# BSD make does it like this.
echo '.include "confinc.mk" # ignored' > confmf.BSD
# Other make implementations (GNU, Solaris 10, AIX) do it like this.
echo 'include confinc.mk # ignored' > confmf.GNU
_am_result=no
for s in GNU BSD; do
{ echo "$as_me:$LINENO: ${MAKE-make} -f confmf.$s && cat confinc.out" >&5
(${MAKE-make} -f confmf.$s && cat confinc.out) >&5 2>&5
ac_status=$?
echo "$as_me:$LINENO: \$? = $ac_status" >&5
(exit $ac_status); }
case $?:`cat confinc.out 2>/dev/null` in #(
'0:this is the am__doit target') :
case $s in #(
BSD) :
am__include='.include' am__quote='"' ;; #(
*) :
am__include='include' am__quote='' ;;
esac ;; #(
*) :
;;
esac
fi
{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $_am_result" >&5
$as_echo "$_am_result" >&6; }
rm -f confinc confmf
esac
if test "$am__include" != "#"; then
_am_result="yes ($s style)"
break
fi
done
rm -f confinc.* confmf.*
{ $as_echo "$as_me:${as_lineno-$LINENO}: result: ${_am_result}" >&5
$as_echo "${_am_result}" >&6; }
# Check whether --enable-dependency-tracking was given.
if test "${enable_dependency_tracking+set}" = set; then :
@@ -6690,7 +6690,7 @@ cat >>$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 3.12.8, which was
This file was extended by cpuminer-opt $as_me 3.14.3, which was
generated by GNU Autoconf 2.69. Invocation command line was
CONFIG_FILES = $CONFIG_FILES
@@ -6756,7 +6756,7 @@ _ACEOF
cat >>$CONFIG_STATUS <<_ACEOF || ac_write_fail=1
ac_cs_config="`$as_echo "$ac_configure_args" | sed 's/^ //; s/[\\""\`\$]/\\\\&/g'`"
ac_cs_version="\\
cpuminer-opt config.status 3.12.8
cpuminer-opt config.status 3.14.3
configured by $0, generated by GNU Autoconf 2.69,
with options \\"\$ac_cs_config\\"
@@ -6875,7 +6875,7 @@ cat >>$CONFIG_STATUS <<_ACEOF || ac_write_fail=1
#
# INIT-COMMANDS
#
AMDEP_TRUE="$AMDEP_TRUE" ac_aux_dir="$ac_aux_dir"
AMDEP_TRUE="$AMDEP_TRUE" MAKE="${MAKE-make}"
_ACEOF
@@ -7489,29 +7489,35 @@ $as_echo "$as_me: executing $ac_file commands" >&6;}
# Older Autoconf quotes --file arguments for eval, but not when files
# are listed without --file. Let's play safe and only enable the eval
# if we detect the quoting.
case $CONFIG_FILES in
*\'*) eval set x "$CONFIG_FILES" ;;
*) set x $CONFIG_FILES ;;
esac
# TODO: see whether this extra hack can be removed once we start
# requiring Autoconf 2.70 or later.
case $CONFIG_FILES in #(
*\'*) :
eval set x "$CONFIG_FILES" ;; #(
*) :
set x $CONFIG_FILES ;; #(
*) :
;;
esac
shift
for mf
# Used to flag and report bootstrapping failures.
am_rc=0
for am_mf
do
# Strip MF so we end up with the name of the file.
mf=`echo "$mf" | sed -e 's/:.*$//'`
# Check whether this is an Automake generated Makefile or not.
# We used to match only the files named 'Makefile.in', but
# some people rename them; so instead we look at the file content.
# Grep'ing the first line is not enough: some people post-process
# each Makefile.in and add a new line on top of each file to say so.
# Grep'ing the whole file is not good either: AIX grep has a line
am_mf=`$as_echo "$am_mf" | sed -e 's/:.*$//'`
# Check whether this is an Automake generated Makefile which includes
# dependency-tracking related rules and includes.
# Grep'ing the whole file directly is not great: AIX grep has a line
# limit of 2048, but all sed's we know have understand at least 4000.
if sed -n 's,^#.*generated by automake.*,X,p' "$mf" | grep X >/dev/null 2>&1; then
dirpart=`$as_dirname -- "$mf" ||
$as_expr X"$mf" : 'X\(.*[^/]\)//*[^/][^/]*/*$' \| \
X"$mf" : 'X\(//\)[^/]' \| \
X"$mf" : 'X\(//\)$' \| \
X"$mf" : 'X\(/\)' \| . 2>/dev/null ||
$as_echo X"$mf" |
sed -n 's,^am--depfiles:.*,X,p' "$am_mf" | grep X >/dev/null 2>&1 \
|| continue
am_dirpart=`$as_dirname -- "$am_mf" ||
$as_expr X"$am_mf" : 'X\(.*[^/]\)//*[^/][^/]*/*$' \| \
X"$am_mf" : 'X\(//\)[^/]' \| \
X"$am_mf" : 'X\(//\)$' \| \
X"$am_mf" : 'X\(/\)' \| . 2>/dev/null ||
$as_echo X"$am_mf" |
sed '/^X\(.*[^/]\)\/\/*[^/][^/]*\/*$/{
s//\1/
q
@@ -7529,53 +7535,48 @@ $as_echo X"$mf" |
q
}
s/.*/./; q'`
else
continue
fi
# Extract the definition of DEPDIR, am__include, and am__quote
# from the Makefile without running 'make'.
DEPDIR=`sed -n 's/^DEPDIR = //p' < "$mf"`
test -z "$DEPDIR" && continue
am__include=`sed -n 's/^am__include = //p' < "$mf"`
test -z "$am__include" && continue
am__quote=`sed -n 's/^am__quote = //p' < "$mf"`
# Find all dependency output files, they are included files with
# $(DEPDIR) in their names. We invoke sed twice because it is the
# simplest approach to changing $(DEPDIR) to its actual value in the
# expansion.
for file in `sed -n "
s/^$am__include $am__quote\(.*(DEPDIR).*\)$am__quote"'$/\1/p' <"$mf" | \
sed -e 's/\$(DEPDIR)/'"$DEPDIR"'/g'`; do
# Make sure the directory exists.
test -f "$dirpart/$file" && continue
fdir=`$as_dirname -- "$file" ||
$as_expr X"$file" : 'X\(.*[^/]\)//*[^/][^/]*/*$' \| \
X"$file" : 'X\(//\)[^/]' \| \
X"$file" : 'X\(//\)$' \| \
X"$file" : 'X\(/\)' \| . 2>/dev/null ||
$as_echo X"$file" |
sed '/^X\(.*[^/]\)\/\/*[^/][^/]*\/*$/{
am_filepart=`$as_basename -- "$am_mf" ||
$as_expr X/"$am_mf" : '.*/\([^/][^/]*\)/*$' \| \
X"$am_mf" : 'X\(//\)$' \| \
X"$am_mf" : 'X\(/\)' \| . 2>/dev/null ||
$as_echo X/"$am_mf" |
sed '/^.*\/\([^/][^/]*\)\/*$/{
s//\1/
q
}
/^X\(\/\/\)[^/].*/{
/^X\/\(\/\/\)$/{
s//\1/
q
}
/^X\(\/\/\)$/{
s//\1/
q
}
/^X\(\/\).*/{
/^X\/\(\/\).*/{
s//\1/
q
}
s/.*/./; q'`
as_dir=$dirpart/$fdir; as_fn_mkdir_p
# echo "creating $dirpart/$file"
echo '# dummy' > "$dirpart/$file"
done
{ echo "$as_me:$LINENO: cd "$am_dirpart" \
&& sed -e '/# am--include-marker/d' "$am_filepart" \
| $MAKE -f - am--depfiles" >&5
(cd "$am_dirpart" \
&& sed -e '/# am--include-marker/d' "$am_filepart" \
| $MAKE -f - am--depfiles) >&5 2>&5
ac_status=$?
echo "$as_me:$LINENO: \$? = $ac_status" >&5
(exit $ac_status); } || am_rc=$?
done
if test $am_rc -ne 0; then
{ { $as_echo "$as_me:${as_lineno-$LINENO}: error: in \`$ac_pwd':" >&5
$as_echo "$as_me: error: in \`$ac_pwd':" >&2;}
as_fn_error $? "Something went wrong bootstrapping makefile fragments
for automatic dependency tracking. Try re-running configure with the
'--disable-dependency-tracking' option to at least be able to build
the package (albeit without support for automatic dependency tracking).
See \`config.log' for more details" "$LINENO" 5; }
fi
{ am_dirpart=; unset am_dirpart;}
{ am_filepart=; unset am_filepart;}
{ am_mf=; unset am_mf;}
{ am_rc=; unset am_rc;}
rm -f conftest-deps.mk
}
;;

View File

@@ -1,4 +1,4 @@
AC_INIT([cpuminer-opt], [3.12.8])
AC_INIT([cpuminer-opt], [3.14.3])
AC_PREREQ([2.59c])
AC_CANONICAL_SYSTEM

File diff suppressed because it is too large Load Diff

57
miner.h
View File

@@ -83,6 +83,8 @@ enum {
};
#endif
extern bool is_power_of_2( int n );
static inline bool is_windows(void)
{
#ifdef WIN32
@@ -313,6 +315,10 @@ size_t address_to_script( unsigned char *out, size_t outsz, const char *addr );
int timeval_subtract( struct timeval *result, struct timeval *x,
struct timeval *y);
// Segwit BEGIN
extern void memrev(unsigned char *p, size_t len);
// Segwit END
// Bitcoin formula for converting difficulty to an equivalent
// number of hashes.
//
@@ -324,12 +330,12 @@ int timeval_subtract( struct timeval *result, struct timeval *x,
#define EXP16 65536.
#define EXP32 4294967296.
const long double exp32; // 2**32
const long double exp48; // 2**48
const long double exp64; // 2**64
const long double exp96; // 2**96
const long double exp128; // 2**128
const long double exp160; // 2**160
extern const long double exp32; // 2**32
extern const long double exp48; // 2**48
extern const long double exp64; // 2**64
extern const long double exp96; // 2**96
extern const long double exp128; // 2**128
extern const long double exp160; // 2**160
bool fulltest( const uint32_t *hash, const uint32_t *target );
bool valid_hash( const void*, const void* );
@@ -374,36 +380,25 @@ void cpu_brand_string( char* s );
float cpu_temp( int core );
*/
struct work {
struct work
{
uint32_t target[8] __attribute__ ((aligned (64)));
uint32_t data[48] __attribute__ ((aligned (64)));
uint32_t target[8] __attribute__ ((aligned (64)));
double targetdiff;
// double shareratio;
double sharediff;
double stratum_diff;
int height;
char *txs;
char *workid;
char *job_id;
size_t xnonce2_len;
unsigned char *xnonce2;
bool sapling;
bool stale;
// x16rt
uint32_t merkleroothash[8];
uint32_t witmerkleroothash[8];
uint32_t denom10[8];
uint32_t denom100[8];
uint32_t denom1000[8];
uint32_t denom10000[8];
} __attribute__ ((aligned (64)));
struct stratum_job {
struct stratum_job
{
unsigned char prevhash[32];
unsigned char final_sapling_hash[32];
char *job_id;
@@ -417,7 +412,7 @@ struct stratum_job {
unsigned char ntime[4];
double diff;
bool clean;
// for x16rt
// for x16rt-veil
unsigned char extra[64];
unsigned char denom10[32];
unsigned char denom100[32];
@@ -551,15 +546,16 @@ enum algos {
ALGO_LYRA2RE,
ALGO_LYRA2REV2,
ALGO_LYRA2REV3,
ALGO_LYRA2Z,
ALGO_LYRA2Z,
ALGO_LYRA2Z330,
ALGO_M7M,
ALGO_M7M,
ALGO_MINOTAUR,
ALGO_MYR_GR,
ALGO_NEOSCRYPT,
ALGO_NIST5,
ALGO_PENTABLAKE,
ALGO_PHI1612,
ALGO_PHI2,
ALGO_PHI2,
ALGO_POLYTIMOS,
ALGO_POWER2B,
ALGO_QUARK,
@@ -642,10 +638,11 @@ static const char* const algo_names[] = {
"lyra2re",
"lyra2rev2",
"lyra2rev3",
"lyra2z",
"lyra2z",
"lyra2z330",
"m7m",
"myr-gr",
"minotaur",
"myr-gr",
"neoscrypt",
"nist5",
"pentablake",
@@ -750,6 +747,7 @@ extern double opt_diff_factor;
extern double opt_target_factor;
extern bool opt_randomize;
extern bool allow_mininginfo;
extern pthread_rwlock_t g_work_lock;
extern time_t g_work_time;
extern bool opt_stratum_stats;
extern int num_cpus;
@@ -802,7 +800,8 @@ Options:\n\
lyra2z330 Lyra2 330 rows\n\
m7m Magi (XMG)\n\
myr-gr Myriad-Groestl\n\
neoscrypt NeoScrypt(128, 2, 1)\n\
minotaur Ringcoin (RNG)\n\
neoscrypt NeoScrypt(128, 2, 1)\n\
nist5 Nist5\n\
pentablake 5 x blake512\n\
phi1612 phi\n\

View File

@@ -375,10 +375,10 @@ static inline void memcpy_512( __m512i *dst, const __m512i *src, const int n )
// Generic for odd rotations
#define mm512_ror_x64( v, n ) _mm512_alignr_epi64( v, v, n )
#define mm512_rol_x64( v, n ) _mm512_alignr_epi64( v, v, 8-n )
#define mm512_rol_x64( v, n ) _mm512_alignr_epi64( v, v, 8-(n) )
#define mm512_ror_x32( v, n ) _mm512_alignr_epi32( v, v, n )
#define mm512_rol_x32( v, n ) _mm512_alignr_epi32( v, v, 16-n )
#define mm512_rol_x32( v, n ) _mm512_alignr_epi32( v, v, 16-(n) )
#define mm512_ror_1x16( v ) \
_mm512_permutexvar_epi16( m512_const_64( \

24
util.c
View File

@@ -81,6 +81,15 @@ struct thread_q {
pthread_cond_t cond;
};
bool is_power_of_2( int n )
{
while ( n > 1 )
{
if ( n % 2 != 0 ) return false;
n = n / 2;
}
return true;
}
void applog2( int prio, const char *fmt, ... )
{
@@ -609,6 +618,8 @@ json_t *json_rpc_call(CURL *curl, const char *url,
goto err_out;
}
// want_stratum is useless, and so is this code it seems. Nothing in
// hi appears to be set.
/* If X-Stratum was found, activate Stratum */
if (want_stratum && hi.stratum_url &&
!strncasecmp(hi.stratum_url, "stratum+tcp://", 14)) {
@@ -747,6 +758,19 @@ err_out:
return cfg;
}
// Segwit BEGIN
void memrev(unsigned char *p, size_t len)
{
unsigned char c, *q;
for (q = p + len - 1; p < q; p++, q--) {
c = *p;
*p = *q;
*q = c;
}
}
// Segwit END
void cbin2hex(char *out, const char *in, size_t len)
{
if (out) {

View File

@@ -10,13 +10,10 @@
# define some local variables
export LOCAL_LIB="$HOME/usr/lib"
export CONFIGURE_ARGS="--with-curl=$LOCAL_LIB/curl --with-crypto=$LOCAL_LIB/openssl --host=x86_64-w64-mingw32"
export MINGW_LIB="/usr/x86_64-w64-mingw32/lib"
export GCC_MINGW_LIB="/usr/lib/gcc/x86_64-w64-mingw32/7.3-win32"
# set correct gcc version
export GCC_MINGW_LIB="/usr/lib/gcc/x86_64-w64-mingw32/9.3-win32"
# used by GCC
export LDFLAGS="-L$LOCAL_LIB/curl/lib/.libs -L$LOCAL_LIB/gmp/.libs -L$LOCAL_LIB/openssl"
@@ -43,19 +40,27 @@ cp $LOCAL_LIB/curl/lib/.libs/libcurl-4.dll release/
# Start building...
make distclean || echo clean
./clean-all.sh || echo clean
rm -f config.status
./autogen.sh || echo done
CFLAGS="-O3 -march=icelake-client -Wall" ./configure $CONFIGURE_ARGS
make -j 8
strip -s cpuminer.exe
mv cpuminer.exe release/cpuminer-avx512-sha-vaes.exe
make clean || echo clean
rm -f config.status
CFLAGS="-O3 -march=znver1 -Wall" ./configure $CONFIGURE_ARGS
make -j 16
make -j 8
strip -s cpuminer.exe
mv cpuminer.exe release/cpuminer-zen.exe
# mingw won't compile avx512 without -fno-asynchronous-unwind-tables
make clean || echo clean
rm -f config.status
CFLAGS="-O3 -march=skylake-avx512 -Wall -fno-asynchronous-unwind-tables" ./configure $CONFIGURE_ARGS
make -j 16
CFLAGS="-O3 -march=skylake-avx512 -Wall" ./configure $CONFIGURE_ARGS
#CFLAGS="-O3 -march=skylake-avx512 -Wall -fno-asynchronous-unwind-tables" ./configure $CONFIGURE_ARGS
make -j 8
strip -s cpuminer.exe
mv cpuminer.exe release/cpuminer-avx512.exe
@@ -63,7 +68,7 @@ make clean || echo clean
rm -f config.status
# GCC 9 doesn't include AES in -march=core-avx2
CFLAGS="-O3 -march=core-avx2 -maes -Wall" ./configure $CONFIGURE_ARGS
make -j 16
make -j 8
strip -s cpuminer.exe
mv cpuminer.exe release/cpuminer-avx2.exe
@@ -71,7 +76,7 @@ make clean || echo clean
rm -f config.status
# -march=corei7-avx still includes aes, but just in case
CFLAGS="-O3 -march=corei7-avx -maes -Wall" ./configure $CONFIGURE_ARGS
make -j 16
make -j 8
strip -s cpuminer.exe
mv cpuminer.exe release/cpuminer-avx.exe
@@ -80,7 +85,7 @@ make clean || echo clean
rm -f config.status
CFLAGS="-O3 -march=westmere -Wall" ./configure $CONFIGURE_ARGS
#CFLAGS="-O3 -maes -msse4.2 -Wall" ./configure $CONFIGURE_ARGS
make -j 16
make -j 8
strip -s cpuminer.exe
mv cpuminer.exe release/cpuminer-aes-sse42.exe
@@ -102,7 +107,7 @@ mv cpuminer.exe release/cpuminer-aes-sse42.exe
make clean || echo clean
rm -f config.status
CFLAGS="-O3 -msse2 -Wall" ./configure $CONFIGURE_ARGS
make -j 16
make -j 8
strip -s cpuminer.exe
mv cpuminer.exe release/cpuminer-sse2.exe
make clean || echo clean