X-Git-Url: https://git.sesse.net/?p=stockfish;a=blobdiff_plain;f=src%2FMakefile;h=cab7a7e50629021f17a68a4458aee45c74989bc7;hp=6b02425e07b2ce2f160e98ed93fa2defd3e26586;hb=6d6267c378aa0aa354e203e5025361d9a4e0d449;hpb=9b4e123fbee44b0dc5d6aba497e5e70d165f576c

diff --git a/src/Makefile b/src/Makefile
index 6b02425e..cab7a7e5 100644
--- a/src/Makefile
+++ b/src/Makefile
@@ -1,6 +1,7 @@
 # Stockfish, a UCI chess playing engine derived from Glaurung 2.1
 # Copyright (C) 2004-2008 Tord Romstad (Glaurung author)
-# Copyright (C) 2008-2014 Marco Costalba, Joona Kiiski, Tord Romstad
+# Copyright (C) 2008-2015 Marco Costalba, Joona Kiiski, Tord Romstad
+# Copyright (C) 2015-2019 Marco Costalba, Joona Kiiski, Gary Linscott, Tord Romstad
 #
 # Stockfish is free software: you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by
@@ -20,46 +21,61 @@
 ### Section 1. General Configuration
 ### ==========================================================================
 
-### Establish the operating system name
-UNAME = $(shell uname)
-
 ### Executable name
+ifeq ($(COMP),mingw)
+EXE = stockfish.exe
+else
 EXE = stockfish
+endif
 
 ### Installation dir definitions
 PREFIX = /usr/local
-# Haiku has a non-standard filesystem layout
-ifeq ($(UNAME),Haiku)
-	PREFIX=/boot/system/non-packaged
-endif
 BINDIR = $(PREFIX)/bin
 
 ### Built-in benchmark for pgo-builds
-PGOBENCH = ./$(EXE) bench 16 1 1 default time
+PGOBENCH = ./$(EXE) bench
 
-### Object files
-OBJS = benchmark.o bitbase.o bitboard.o endgame.o evaluate.o main.o \
-	material.o misc.o movegen.o movepick.o pawns.o position.o \
-	search.o thread.o timeman.o tt.o uci.o ucioption.o syzygy/tbprobe.o
+### Source and object files
+SRCS = benchmark.cpp bitbase.cpp bitboard.cpp endgame.cpp evaluate.cpp main.cpp \
+	material.cpp misc.cpp movegen.cpp movepick.cpp pawns.cpp position.cpp psqt.cpp \
+	search.cpp thread.cpp timeman.cpp tt.cpp uci.cpp ucioption.cpp tune.cpp syzygy/tbprobe.cpp \
+	nnue/evaluate_nnue.cpp nnue/features/half_kp.cpp
+
+OBJS = $(notdir $(SRCS:.cpp=.o))
+
+VPATH = syzygy:nnue:nnue/features
+
+### Establish the operating system name
+KERNEL = $(shell uname -s)
+ifeq ($(KERNEL),Linux)
+	OS = $(shell uname -o)
+endif
 
 ### ==========================================================================
 ### Section 2. High-level Configuration
 ### ==========================================================================
 #
-# flag                --- Comp switch --- Description
+# flag                --- Comp switch      --- Description
 # ----------------------------------------------------------------------------
 #
 # debug = yes/no      --- -DNDEBUG         --- Enable/Disable debug mode
+# sanitize = undefined/thread/no (-fsanitize )
+#                     --- ( undefined )    --- enable undefined behavior checks
+#                     --- ( thread    )    --- enable threading error  checks
 # optimize = yes/no   --- (-O3/-fast etc.) --- Enable/Disable optimizations
 # arch = (name)       --- (-arch)          --- Target architecture
-# os = (name)         ---                  --- Target operating system
 # bits = 64/32        --- -DIS_64BIT       --- 64-/32-bit operating system
-# prefetch = yes/no   --- -DUSE_PREFETCH   --- Use prefetch x86 asm-instruction
-# bsfq = yes/no       --- -DUSE_BSFQ       --- Use bsfq x86_64 asm-instruction (only
-#                                              with GCC and ICC 64-bit)
-# popcnt = yes/no     --- -DUSE_POPCNT     --- Use popcnt x86_64 asm-instruction
+# prefetch = yes/no   --- -DUSE_PREFETCH   --- Use prefetch asm-instruction
+# popcnt = yes/no     --- -DUSE_POPCNT     --- Use popcnt asm-instruction
 # sse = yes/no        --- -msse            --- Use Intel Streaming SIMD Extensions
+# sse3 = yes/no       --- -msse3           --- Use Intel Streaming SIMD Extensions 3
+# ssse3 = yes/no      --- -mssse3          --- Use Intel Supplemental Streaming SIMD Extensions 3
+# sse41 = yes/no      --- -msse4.1         --- Use Intel Streaming SIMD Extensions 4.1
+# sse42 = yes/no      --- -msse4.2         --- Use Intel Streaming SIMD Extensions 4.2
+# avx2 = yes/no       --- -mavx2           --- Use Intel Advanced Vector Extensions 2
 # pext = yes/no       --- -DUSE_PEXT       --- Use pext x86_64 asm-instruction
+# avx512 = yes/no     --- -mavx512bw       --- Use Intel Advanced Vector Extensions 512
+# neon = yes/no       --- -DUSE_NEON       --- Use ARM SIMD architecture
 #
 # Note that Makefile is space sensitive, so when adding new architectures
 # or modifying existing flags, you have to make sure there are no extra spaces
@@ -68,85 +84,180 @@ OBJS = benchmark.o bitbase.o bitboard.o endgame.o evaluate.o main.o \
 ### 2.1. General and architecture defaults
 optimize = yes
 debug = no
-os = any
-bits = 32
+sanitize = no
+bits = 64
 prefetch = no
-bsfq = no
 popcnt = no
 sse = no
+sse3 = no
+ssse3 = no
+sse41 = no
+sse42 = no
+avx2 = no
 pext = no
+avx512 = no
+neon = no
+ARCH = x86-64-modern
 
 ### 2.2 Architecture specific
-
 ifeq ($(ARCH),general-32)
 	arch = any
+	bits = 32
 endif
 
 ifeq ($(ARCH),x86-32-old)
 	arch = i386
+	bits = 32
 endif
 
 ifeq ($(ARCH),x86-32)
 	arch = i386
+	bits = 32
 	prefetch = yes
 	sse = yes
 endif
 
 ifeq ($(ARCH),general-64)
 	arch = any
-	bits = 64
 endif
 
 ifeq ($(ARCH),x86-64)
 	arch = x86_64
-	bits = 64
 	prefetch = yes
-	bsfq = yes
 	sse = yes
 endif
 
+ifeq ($(ARCH),x86-64-sse3)
+	arch = x86_64
+	prefetch = yes
+	sse = yes
+	sse3 = yes
+endif
+
+ifeq ($(ARCH),x86-64-sse3-popcnt)
+	arch = x86_64
+	prefetch = yes
+	sse = yes
+	sse3 = yes
+	popcnt = yes
+endif
+
+ifeq ($(ARCH),x86-64-ssse3)
+	arch = x86_64
+	prefetch = yes
+	sse = yes
+	sse3 = yes
+	ssse3 = yes
+endif
+
+ifeq ($(ARCH),x86-64-sse41)
+	arch = x86_64
+	prefetch = yes
+	popcnt = yes
+	sse = yes
+	sse3 = yes
+	ssse3 = yes
+	sse41 = yes
+endif
+
 ifeq ($(ARCH),x86-64-modern)
 	arch = x86_64
-	bits = 64
 	prefetch = yes
-	bsfq = yes
 	popcnt = yes
 	sse = yes
+	sse3 = yes
+	ssse3 = yes
+	sse41 = yes
+endif
+
+ifeq ($(ARCH),x86-64-sse42)
+	arch = x86_64
+	prefetch = yes
+	popcnt = yes
+	sse = yes
+	sse3 = yes
+	ssse3 = yes
+	sse41 = yes
+	sse42 = yes
+endif
+
+ifeq ($(ARCH),x86-64-avx2)
+	arch = x86_64
+	prefetch = yes
+	popcnt = yes
+	sse = yes
+	sse3 = yes
+	ssse3 = yes
+	sse41 = yes
+	sse42 = yes
+	avx2 = yes
 endif
 
 ifeq ($(ARCH),x86-64-bmi2)
 	arch = x86_64
-	bits = 64
 	prefetch = yes
-	bsfq = yes
 	popcnt = yes
 	sse = yes
+	sse3 = yes
+	ssse3 = yes
+	sse41 = yes
+	sse42 = yes
+	avx2 = yes
 	pext = yes
 endif
 
+ifeq ($(ARCH),x86-64-avx512)
+	arch = x86_64
+	prefetch = yes
+	popcnt = yes
+	sse = yes
+	sse3 = yes
+	ssse3 = yes
+	sse41 = yes
+	sse42 = yes
+	avx2 = yes
+	pext = yes
+	avx512 = yes
+endif
+
 ifeq ($(ARCH),armv7)
 	arch = armv7
 	prefetch = yes
-	bsfq = yes
+	bits = 32
+endif
+
+ifeq ($(ARCH),armv8)
+	arch = armv8-a
+	prefetch = yes
+	popcnt = yes
+	neon = yes
+endif
+
+ifeq ($(ARCH),apple-silicon)
+	arch = arm64
+	prefetch = yes
+	popcnt = yes
+	neon = yes
 endif
 
 ifeq ($(ARCH),ppc-32)
 	arch = ppc
+	bits = 32
 endif
 
 ifeq ($(ARCH),ppc-64)
 	arch = ppc64
-	bits = 64
+	popcnt = yes
+	prefetch = yes
 endif
 
-
 ### ==========================================================================
-### Section 3. Low-level configuration
+### Section 3. Low-level Configuration
 ### ==========================================================================
 
 ### 3.1 Selecting compiler (default = gcc)
-
-CXXFLAGS += -Wall -Wcast-qual -fno-exceptions -fno-rtti $(EXTRACXXFLAGS)
+CXXFLAGS += -Wall -Wcast-qual -fno-exceptions -std=c++17 $(EXTRACXXFLAGS)
+DEPENDFLAGS += -std=c++17
 LDFLAGS += $(EXTRALDFLAGS)
 
 ifeq ($(COMP),)
@@ -156,14 +267,49 @@ endif
 ifeq ($(COMP),gcc)
 	comp=gcc
 	CXX=g++
-	CXXFLAGS += -ansi -pedantic -Wno-long-long -Wextra -Wshadow
+	CXXFLAGS += -pedantic -Wextra -Wshadow
+
+	ifeq ($(ARCH),$(filter $(ARCH),armv7 armv8))
+		ifeq ($(OS),Android)
+			CXXFLAGS += -m$(bits)
+			LDFLAGS += -m$(bits)
+		endif
+	else
+		CXXFLAGS += -m$(bits)
+		LDFLAGS += -m$(bits)
+	endif
+
+	ifneq ($(KERNEL),Darwin)
+	   LDFLAGS += -Wl,--no-as-needed
+	endif
+	
+	gccversion = $(shell $(CXX) --version)
+	gccisclang = $(findstring clang,$(gccversion))
 endif
 
 ifeq ($(COMP),mingw)
 	comp=mingw
-	CXX=g++
+
+	ifeq ($(KERNEL),Linux)
+		ifeq ($(bits),64)
+			ifeq ($(shell which x86_64-w64-mingw32-c++-posix),)
+				CXX=x86_64-w64-mingw32-c++
+			else
+				CXX=x86_64-w64-mingw32-c++-posix
+			endif
+		else
+			ifeq ($(shell which i686-w64-mingw32-c++-posix),)
+				CXX=i686-w64-mingw32-c++
+			else
+				CXX=i686-w64-mingw32-c++-posix
+			endif
+		endif
+	else
+		CXX=g++
+	endif
+
 	CXXFLAGS += -Wextra -Wshadow
-	LDFLAGS += -static-libstdc++ -static-libgcc
+	LDFLAGS += -static
 endif
 
 ifeq ($(COMP),icc)
@@ -175,100 +321,101 @@ endif
 ifeq ($(COMP),clang)
 	comp=clang
 	CXX=clang++
-	CXXFLAGS += -pedantic -Wno-long-long -Wextra -Wshadow
+	CXXFLAGS += -pedantic -Wextra -Wshadow
+
+	ifneq ($(KERNEL),Darwin)
+	ifneq ($(KERNEL),OpenBSD)
+		LDFLAGS += -latomic
+	endif
+	endif
+
+	ifeq ($(ARCH),$(filter $(ARCH),armv7 armv8))
+		ifeq ($(OS),Android)
+			CXXFLAGS += -m$(bits)
+			LDFLAGS += -m$(bits)
+		endif
+	else
+		CXXFLAGS += -m$(bits)
+		LDFLAGS += -m$(bits)
+	endif
 endif
 
 ifeq ($(comp),icc)
-	profile_prepare = icc-profile-prepare
 	profile_make = icc-profile-make
 	profile_use = icc-profile-use
-	profile_clean = icc-profile-clean
 else
-	profile_prepare = gcc-profile-prepare
+ifeq ($(comp),clang)
+	profile_make = clang-profile-make
+	profile_use = clang-profile-use
+else
 	profile_make = gcc-profile-make
 	profile_use = gcc-profile-use
-	profile_clean = gcc-profile-clean
+endif
+endif
+
+ifeq ($(KERNEL),Darwin)
+	CXXFLAGS += -arch $(arch) -mmacosx-version-min=10.15
+	LDFLAGS += -arch $(arch) -mmacosx-version-min=10.15
+endif
+
+### Travis CI script uses COMPILER to overwrite CXX
+ifdef COMPILER
+	COMPCXX=$(COMPILER)
 endif
 
-ifeq ($(UNAME),Darwin)
-	CXXFLAGS += -arch $(arch) -mmacosx-version-min=10.6
-	LDFLAGS += -arch $(arch) -mmacosx-version-min=10.6
+### Allow overwriting CXX from command line
+ifdef COMPCXX
+	CXX=$(COMPCXX)
 endif
 
 ### On mingw use Windows threads, otherwise POSIX
 ifneq ($(comp),mingw)
 	# On Android Bionic's C library comes with its own pthread implementation bundled in
-	ifneq ($(arch),armv7)
+	ifneq ($(OS),Android)
 		# Haiku has pthreads in its libroot, so only link it in on other platforms
-		ifneq ($(UNAME),Haiku)
+		ifneq ($(KERNEL),Haiku)
 			LDFLAGS += -lpthread
 		endif
 	endif
 endif
 
-### 3.4 Debugging
+### 3.2.1 Debugging
 ifeq ($(debug),no)
 	CXXFLAGS += -DNDEBUG
 else
 	CXXFLAGS += -g
 endif
 
-### 3.5 Optimization
-ifeq ($(optimize),yes)
+### 3.2.2 Debugging with undefined behavior sanitizers
+ifneq ($(sanitize),no)
+        CXXFLAGS += -g3 -fsanitize=$(sanitize)
+        LDFLAGS += -fsanitize=$(sanitize)
+endif
 
-	ifeq ($(comp),gcc)
-		CXXFLAGS += -O3
+### 3.3 Optimization
+ifeq ($(optimize),yes)
 
-		ifeq ($(UNAME),Darwin)
-			ifeq ($(arch),i386)
-				CXXFLAGS += -mdynamic-no-pic
-			endif
-			ifeq ($(arch),x86_64)
-				CXXFLAGS += -mdynamic-no-pic
-			endif
-		endif
+	CXXFLAGS += -O3
 
-		ifeq ($(arch),armv7)
+	ifeq ($(comp),gcc)
+		ifeq ($(OS), Android)
 			CXXFLAGS += -fno-gcse -mthumb -march=armv7-a -mfloat-abi=softfp
 		endif
 	endif
 
-	ifeq ($(comp),mingw)
-		CXXFLAGS += -O3
-	endif
-
-	ifeq ($(comp),icc)
-		ifeq ($(UNAME),Darwin)
-			CXXFLAGS += -fast -mdynamic-no-pic
-		else
-			CXXFLAGS += -fast
-		endif
-	endif
-
-	ifeq ($(comp),clang)
-		CXXFLAGS += -O3
-
-		ifeq ($(UNAME),Darwin)
-			ifeq ($(pext),no)
-				CXXFLAGS += -flto
-				LDFLAGS += $(CXXFLAGS)
-			endif
-			ifeq ($(arch),i386)
-				CXXFLAGS += -mdynamic-no-pic
-			endif
-			ifeq ($(arch),x86_64)
-				CXXFLAGS += -mdynamic-no-pic
-			endif
+	ifeq ($(comp),$(filter $(comp),gcc clang icc))
+		ifeq ($(KERNEL),Darwin)
+			CXXFLAGS += -mdynamic-no-pic
 		endif
 	endif
 endif
 
-### 3.6. Bits
+### 3.4 Bits
 ifeq ($(bits),64)
 	CXXFLAGS += -DIS_64BIT
 endif
 
-### 3.7 prefetch
+### 3.5 prefetch
 ifeq ($(prefetch),yes)
 	ifeq ($(sse),yes)
 		CXXFLAGS += -msse
@@ -278,72 +425,152 @@ else
 	CXXFLAGS += -DNO_PREFETCH
 endif
 
-### 3.8 bsfq
-ifeq ($(bsfq),yes)
-	CXXFLAGS += -DUSE_BSFQ
-endif
-
-### 3.9 popcnt
+### 3.6 popcnt
 ifeq ($(popcnt),yes)
-	ifeq ($(comp),icc)
+	ifeq ($(arch),$(filter $(arch),ppc64 armv8-a arm64))
+		CXXFLAGS += -DUSE_POPCNT
+	else ifeq ($(comp),icc)
 		CXXFLAGS += -msse3 -DUSE_POPCNT
 	else
 		CXXFLAGS += -msse3 -mpopcnt -DUSE_POPCNT
 	endif
 endif
 
-### 3.10 pext
+ifeq ($(avx2),yes)
+	CXXFLAGS += -DUSE_AVX2
+	ifeq ($(comp),$(filter $(comp),gcc clang mingw))
+		CXXFLAGS += -mavx2
+	endif
+endif
+
+ifeq ($(avx512),yes)
+	CXXFLAGS += -DUSE_AVX512
+	ifeq ($(comp),$(filter $(comp),gcc clang mingw))
+		CXXFLAGS += -mavx512bw
+	endif
+endif
+
+ifeq ($(sse42),yes)
+	CXXFLAGS += -DUSE_SSE42
+	ifeq ($(comp),$(filter $(comp),gcc clang mingw))
+		CXXFLAGS += -msse4.2
+	endif
+endif
+
+ifeq ($(sse41),yes)
+	CXXFLAGS += -DUSE_SSE41
+	ifeq ($(comp),$(filter $(comp),gcc clang mingw))
+		CXXFLAGS += -msse4.1
+	endif
+endif
+
+ifeq ($(ssse3),yes)
+	CXXFLAGS += -DUSE_SSSE3
+	ifeq ($(comp),$(filter $(comp),gcc clang mingw))
+		CXXFLAGS += -mssse3
+	endif
+endif
+
+ifeq ($(sse3),yes)
+	CXXFLAGS += -DUSE_SSE3
+	ifeq ($(comp),$(filter $(comp),gcc clang mingw))
+		CXXFLAGS += -msse3
+	endif
+endif
+
+ifeq ($(neon),yes)
+	CXXFLAGS += -DUSE_NEON
+endif
+
+ifeq ($(arch),x86_64)
+	CXXFLAGS += -DUSE_SSE2
+endif
+
+### 3.7 pext
 ifeq ($(pext),yes)
 	CXXFLAGS += -DUSE_PEXT
 	ifeq ($(comp),$(filter $(comp),gcc clang mingw))
-		CXXFLAGS += -mbmi -mbmi2
+		CXXFLAGS += -mbmi2
 	endif
 endif
 
-### 3.11 Link Time Optimization, it works since gcc 4.5 but not on mingw.
+### 3.8 Link Time Optimization
 ### This is a mix of compile and link time options because the lto link phase
 ### needs access to the optimization flags.
-ifeq ($(comp),gcc)
-	ifeq ($(optimize),yes)
-	ifeq ($(debug),no)
-		GCC_MAJOR := `$(CXX) -dumpversion | cut -f1 -d.`
-		GCC_MINOR := `$(CXX) -dumpversion | cut -f2 -d.`
-		ifeq (1,$(shell expr \( $(GCC_MAJOR) \> 4 \) \| \( $(GCC_MAJOR) \= 4 \& $(GCC_MINOR) \>= 5 \)))
-			CXXFLAGS += -flto
-			LDFLAGS += $(CXXFLAGS)
-		endif
+ifeq ($(optimize),yes)
+ifeq ($(debug), no)
+	ifeq ($(comp),clang)
+		CXXFLAGS += -flto=thin
+		LDFLAGS += $(CXXFLAGS)
+
+# GCC and CLANG use different methods for parallelizing LTO and CLANG pretends to be
+# GCC on some systems.
+	else ifeq ($(comp),gcc)
+	ifeq ($(gccisclang),)
+		CXXFLAGS += -flto
+		LDFLAGS += $(CXXFLAGS) -flto=jobserver
+	else
+		CXXFLAGS += -flto=thin
+		LDFLAGS += $(CXXFLAGS)
 	endif
+
+# To use LTO and static linking on windows, the tool chain requires a recent gcc:
+# gcc version 10.1 in msys2 or TDM-GCC version 9.2 are know to work, older might not.
+# So, only enable it for a cross from Linux by default.
+	else ifeq ($(comp),mingw)
+	ifeq ($(KERNEL),Linux)
+		CXXFLAGS += -flto
+		LDFLAGS += $(CXXFLAGS) -flto=jobserver
 	endif
+	endif
+endif
+endif
+
+### 3.9 Android 5 can only run position independent executables. Note that this
+### breaks Android 4.0 and earlier.
+ifeq ($(OS), Android)
+	CXXFLAGS += -fPIE
+	LDFLAGS += -fPIE -pie
 endif
 
 ### ==========================================================================
-### Section 4. Public targets
+### Section 4. Public Targets
 ### ==========================================================================
 
 help:
 	@echo ""
 	@echo "To compile stockfish, type: "
 	@echo ""
-	@echo "make target ARCH=arch [COMP=comp]"
+	@echo "make target ARCH=arch [COMP=compiler] [COMPCXX=cxx]"
 	@echo ""
 	@echo "Supported targets:"
 	@echo ""
 	@echo "build                   > Standard build"
-	@echo "profile-build           > PGO build"
+	@echo "profile-build           > Standard build with PGO"
 	@echo "strip                   > Strip executable"
 	@echo "install                 > Install executable"
 	@echo "clean                   > Clean up"
+	@echo "net                     > Download the default nnue net"
 	@echo ""
 	@echo "Supported archs:"
 	@echo ""
-	@echo "x86-64                  > x86 64-bit"
-	@echo "x86-64-modern           > x86 64-bit with popcnt support"
-	@echo "x86-64-bmi2             > x86 64-bit with pext support"
-	@echo "x86-32                  > x86 32-bit with SSE support"
+	@echo "x86-64-avx512           > x86 64-bit with avx512 support"
+	@echo "x86-64-bmi2             > x86 64-bit with bmi2 support"
+	@echo "x86-64-avx2             > x86 64-bit with avx2 support"
+	@echo "x86-64-sse42            > x86 64-bit with sse42 support"
+	@echo "x86-64-modern           > x86 64-bit with sse41 support (x86-64-sse41)"
+	@echo "x86-64-sse41            > x86 64-bit with sse41 support"
+	@echo "x86-64-ssse3            > x86 64-bit with ssse3 support"
+	@echo "x86-64-sse3-popcnt      > x86 64-bit with sse3 and popcnt support"
+	@echo "x86-64-sse3             > x86 64-bit with sse3 support"
+	@echo "x86-64                  > x86 64-bit generic"
+	@echo "x86-32                  > x86 32-bit (also enables SSE)"
 	@echo "x86-32-old              > x86 32-bit fall back for old hardware"
 	@echo "ppc-64                  > PPC 64-bit"
 	@echo "ppc-32                  > PPC 32-bit"
 	@echo "armv7                   > ARMv7 32-bit"
+	@echo "armv8                   > ARMv8 64-bit"
+	@echo "apple-silicon           > Apple silicon ARM64"
 	@echo "general-64              > unspecified 64-bit"
 	@echo "general-32              > unspecified 32-bit"
 	@echo ""
@@ -354,40 +581,42 @@ help:
 	@echo "clang                   > LLVM Clang compiler"
 	@echo "icc                     > Intel compiler"
 	@echo ""
-	@echo "Non-standard targets:"
+	@echo "Simple examples. If you don't know what to do, you likely want to run: "
+	@echo ""
+	@echo "make -j build ARCH=x86-64    (This is for 64-bit systems)"
+	@echo "make -j build ARCH=x86-32    (This is for 32-bit systems)"
 	@echo ""
-	@echo "make hpux               >  Compile for HP-UX. Compiler = aCC"
+	@echo "Advanced examples, for experienced users: "
 	@echo ""
-	@echo "Examples. If you don't know what to do, you likely want to run: "
+	@echo "make -j build ARCH=x86-64-modern COMP=clang"
+	@echo "make -j profile-build ARCH=x86-64-bmi2 COMP=gcc COMPCXX=g++-4.8"
 	@echo ""
-	@echo "make build ARCH=x86-64    (This is for 64-bit systems)"
-	@echo "make build ARCH=x86-32    (This is for 32-bit systems)"
+	@echo "The selected architecture $(ARCH) enables the following configuration: "
 	@echo ""
+	@$(MAKE) ARCH=$(ARCH) COMP=$(COMP) config-sanity
 
-.PHONY: build profile-build
-build:
-	$(MAKE) ARCH=$(ARCH) COMP=$(COMP) config-sanity
+
+.PHONY: help build profile-build strip install clean net objclean profileclean \
+        config-sanity icc-profile-use icc-profile-make gcc-profile-use gcc-profile-make \
+        clang-profile-use clang-profile-make
+
+build: config-sanity
 	$(MAKE) ARCH=$(ARCH) COMP=$(COMP) all
 
-profile-build:
-	$(MAKE) ARCH=$(ARCH) COMP=$(COMP) config-sanity
-	@echo ""
-	@echo "Step 0/4. Preparing for profile build."
-	$(MAKE) ARCH=$(ARCH) COMP=$(COMP) $(profile_prepare)
+profile-build: config-sanity objclean profileclean
 	@echo ""
-	@echo "Step 1/4. Building executable for benchmark ..."
-	@touch *.cpp *.h
+	@echo "Step 1/4. Building instrumented executable ..."
 	$(MAKE) ARCH=$(ARCH) COMP=$(COMP) $(profile_make)
 	@echo ""
 	@echo "Step 2/4. Running benchmark for pgo-build ..."
-	@$(PGOBENCH) > /dev/null
+	$(PGOBENCH) > /dev/null
 	@echo ""
-	@echo "Step 3/4. Building final executable ..."
-	@touch *.cpp
+	@echo "Step 3/4. Building optimized executable ..."
+	$(MAKE) ARCH=$(ARCH) COMP=$(COMP) objclean
 	$(MAKE) ARCH=$(ARCH) COMP=$(COMP) $(profile_use)
 	@echo ""
 	@echo "Step 4/4. Deleting profile data ..."
-	$(MAKE) ARCH=$(ARCH) COMP=$(COMP) $(profile_clean)
+	$(MAKE) ARCH=$(ARCH) COMP=$(COMP) profileclean
 
 strip:
 	strip $(EXE)
@@ -397,14 +626,32 @@ install:
 	-cp $(EXE) $(BINDIR)
 	-strip $(BINDIR)/$(EXE)
 
-clean:
-	$(RM) $(EXE) $(EXE).exe *.o .depend *~ core bench.txt *.gcda ./syzygy/*.o ./syzygy/*.gcda
+#clean all
+clean: objclean profileclean
+	@rm -f .depend *~ core
+
+net:
+	$(eval nnuenet := $(shell grep EvalFile ucioption.cpp | grep Option | sed 's/.*\(nn-[a-z0-9]\{12\}.nnue\).*/\1/'))
+	@echo "Default net: $(nnuenet)"
+	$(eval nnuedownloadurl := https://tests.stockfishchess.org/api/nn/$(nnuenet))
+	$(eval curl_or_wget := $(shell if hash curl 2>/dev/null; then echo "curl -sL"; elif hash wget 2>/dev/null; then echo "wget -qO-"; fi))
+	@if test -f "$(nnuenet)"; then echo "Already available."; else echo "Downloading $(nnuedownloadurl)"; $(curl_or_wget) $(nnuedownloadurl) > $(nnuenet); fi
+
+# clean binaries and objects
+objclean:
+	@rm -f $(EXE) *.o ./syzygy/*.o ./nnue/*.o ./nnue/features/*.o
+
+# clean auxiliary profiling files
+profileclean:
+	@rm -rf profdir
+	@rm -f bench.txt *.gcda *.gcno ./syzygy/*.gcda ./nnue/*.gcda ./nnue/features/*.gcda
+	@rm -f stockfish.profdata *.profraw
 
 default:
 	help
 
 ### ==========================================================================
-### Section 5. Private targets
+### Section 5. Private Targets
 ### ==========================================================================
 
 all: $(EXE) .depend
@@ -413,15 +660,23 @@ config-sanity:
 	@echo ""
 	@echo "Config:"
 	@echo "debug: '$(debug)'"
+	@echo "sanitize: '$(sanitize)'"
 	@echo "optimize: '$(optimize)'"
 	@echo "arch: '$(arch)'"
-	@echo "os: '$(os)'"
 	@echo "bits: '$(bits)'"
+	@echo "kernel: '$(KERNEL)'"
+	@echo "os: '$(OS)'"
 	@echo "prefetch: '$(prefetch)'"
-	@echo "bsfq: '$(bsfq)'"
 	@echo "popcnt: '$(popcnt)'"
 	@echo "sse: '$(sse)'"
+	@echo "sse3: '$(sse3)'"
+	@echo "ssse3: '$(ssse3)'"
+	@echo "sse41: '$(sse41)'"
+	@echo "sse42: '$(sse42)'"
+	@echo "avx2: '$(avx2)'"
 	@echo "pext: '$(pext)'"
+	@echo "avx512: '$(avx512)'"
+	@echo "neon: '$(neon)'"
 	@echo ""
 	@echo "Flags:"
 	@echo "CXX: $(CXX)"
@@ -431,23 +686,40 @@ config-sanity:
 	@echo "Testing config sanity. If this fails, try 'make help' ..."
 	@echo ""
 	@test "$(debug)" = "yes" || test "$(debug)" = "no"
+	@test "$(sanitize)" = "undefined" || test "$(sanitize)" = "thread" || test "$(sanitize)" = "address" || test "$(sanitize)" = "no"
 	@test "$(optimize)" = "yes" || test "$(optimize)" = "no"
 	@test "$(arch)" = "any" || test "$(arch)" = "x86_64" || test "$(arch)" = "i386" || \
-	 test "$(arch)" = "ppc64" || test "$(arch)" = "ppc" || test "$(arch)" = "armv7"
-	@test "$(os)" = "any"
+	 test "$(arch)" = "ppc64" || test "$(arch)" = "ppc" || \
+	 test "$(arch)" = "armv7" || test "$(arch)" = "armv8-a" || test "$(arch)" = "arm64"
 	@test "$(bits)" = "32" || test "$(bits)" = "64"
 	@test "$(prefetch)" = "yes" || test "$(prefetch)" = "no"
-	@test "$(bsfq)" = "yes" || test "$(bsfq)" = "no"
 	@test "$(popcnt)" = "yes" || test "$(popcnt)" = "no"
 	@test "$(sse)" = "yes" || test "$(sse)" = "no"
+	@test "$(sse3)" = "yes" || test "$(sse3)" = "no"
+	@test "$(ssse3)" = "yes" || test "$(ssse3)" = "no"
+	@test "$(sse41)" = "yes" || test "$(sse41)" = "no"
+	@test "$(sse42)" = "yes" || test "$(sse42)" = "no"
+	@test "$(avx2)" = "yes" || test "$(avx2)" = "no"
 	@test "$(pext)" = "yes" || test "$(pext)" = "no"
+	@test "$(avx512)" = "yes" || test "$(avx512)" = "no"
+	@test "$(neon)" = "yes" || test "$(neon)" = "no"
 	@test "$(comp)" = "gcc" || test "$(comp)" = "icc" || test "$(comp)" = "mingw" || test "$(comp)" = "clang"
 
 $(EXE): $(OBJS)
-	$(CXX) -o $@ $(OBJS) $(LDFLAGS)
+	+$(CXX) -o $@ $(OBJS) $(LDFLAGS)
 
-gcc-profile-prepare:
-	$(MAKE) ARCH=$(ARCH) COMP=$(COMP) gcc-profile-clean
+clang-profile-make:
+	$(MAKE) ARCH=$(ARCH) COMP=$(COMP) \
+	EXTRACXXFLAGS='-fprofile-instr-generate ' \
+	EXTRALDFLAGS=' -fprofile-instr-generate' \
+	all
+
+clang-profile-use:
+	llvm-profdata merge -output=stockfish.profdata *.profraw
+	$(MAKE) ARCH=$(ARCH) COMP=$(COMP) \
+	EXTRACXXFLAGS='-fprofile-instr-use=stockfish.profdata' \
+	EXTRALDFLAGS='-fprofile-use ' \
+	all
 
 gcc-profile-make:
 	$(MAKE) ARCH=$(ARCH) COMP=$(COMP) \
@@ -457,18 +729,12 @@ gcc-profile-make:
 
 gcc-profile-use:
 	$(MAKE) ARCH=$(ARCH) COMP=$(COMP) \
-	EXTRACXXFLAGS='-fprofile-use' \
+	EXTRACXXFLAGS='-fprofile-use -fno-peel-loops -fno-tracer' \
 	EXTRALDFLAGS='-lgcov' \
 	all
 
-gcc-profile-clean:
-	@rm -rf *.gcda *.gcno syzygy/*.gcda syzygy/*.gcno bench.txt
-
-icc-profile-prepare:
-	$(MAKE) ARCH=$(ARCH) COMP=$(COMP) icc-profile-clean
-	@mkdir profdir
-
 icc-profile-make:
+	@mkdir -p profdir
 	$(MAKE) ARCH=$(ARCH) COMP=$(COMP) \
 	EXTRACXXFLAGS='-prof-gen=srcpos -prof_dir ./profdir' \
 	all
@@ -478,23 +744,7 @@ icc-profile-use:
 	EXTRACXXFLAGS='-prof_use -prof_dir ./profdir' \
 	all
 
-icc-profile-clean:
-	@rm -rf profdir bench.txt
-
 .depend:
-	-@$(CXX) $(DEPENDFLAGS) -MM $(OBJS:.o=.cpp) > $@ 2> /dev/null
+	-@$(CXX) $(DEPENDFLAGS) -MM $(SRCS) > $@ 2> /dev/null
 
 -include .depend
-
-
-### ==========================================================================
-### Section 6. Non-standard targets
-### ==========================================================================
-
-hpux:
-	$(MAKE) \
-	CXX='/opt/aCC/bin/aCC -AA +hpxstd98 -mt +O3 -DNDEBUG -DNO_PREFETCH' \
-	CXXFLAGS="" \
-	LDFLAGS="" \
-	all
-