Merge latest changes from nodchip repo

This commit is contained in:
Dariusz Orzechowski
2020-07-20 13:19:25 +02:00
5 changed files with 187 additions and 19 deletions

View File

@@ -73,6 +73,7 @@ endif
# 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 --- -mavx512vbmi --- Use Intel Advanced Vector Extensions 512
#
# 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
@@ -86,11 +87,13 @@ bits = 64
prefetch = no
popcnt = no
sse = no
sse3 = no
ssse3 = no
sse41 = no
sse42 = no
avx2 = no
pext = no
avx512 = no
### 2.2 Architecture specific
ifeq ($(ARCH),general-32)
@@ -120,13 +123,6 @@ ifeq ($(ARCH),x86-64)
sse = yes
endif
ifeq ($(ARCH),x86-64-ssse3)
arch = x86_64
prefetch = yes
sse = yes
ssse3 = yes
endif
ifeq ($(ARCH),x86-64-modern)
arch = x86_64
prefetch = yes
@@ -134,10 +130,36 @@ ifeq ($(ARCH),x86-64-modern)
sse = yes
endif
ifeq ($(ARCH),x86-64-sse3)
arch = x86_64
prefetch = yes
sse = yes
sse3 = yes
ssse3 = yes
endif
ifeq ($(ARCH),x86-64-sse3-popcnt)
arch = x86_64
prefetch = yes
popcnt = yes
sse = yes
sse3 = yes
ssse3 = yes
endif
ifeq ($(ARCH),x86-64-ssse3)
arch = x86_64
prefetch = yes
sse = yes
sse3 = yes
ssse3 = yes
endif
ifeq ($(ARCH),x86-64-sse41)
arch = x86_64
prefetch = yes
sse = yes
sse3 = yes
ssse3 = yes
sse41 = yes
endif
@@ -147,6 +169,7 @@ ifeq ($(ARCH),x86-64-sse42)
prefetch = yes
popcnt = yes
sse = yes
sse3 = yes
ssse3 = yes
sse41 = yes
sse42 = yes
@@ -158,6 +181,7 @@ ifeq ($(ARCH),x86-64-avx2)
prefetch = yes
popcnt = yes
sse = yes
sse3 = yes
ssse3 = yes
sse41 = yes
sse42 = yes
@@ -169,6 +193,7 @@ ifeq ($(ARCH),x86-64-bmi2)
prefetch = yes
popcnt = yes
sse = yes
sse3 = yes
ssse3 = yes
sse41 = yes
sse42 = yes
@@ -176,6 +201,21 @@ ifeq ($(ARCH),x86-64-bmi2)
pext = yes
endif
ifeq ($(ARCH),x86-64-avx512)
arch = x86_64
bits = 64
prefetch = yes
popcnt = yes
sse = yes
sse3 = yes
ssse3 = yes
sse41 = yes
sse42 = yes
avx2 = yes
pext = yes
avx512 = yes
endif
ifeq ($(ARCH),armv7)
arch = armv7
prefetch = yes
@@ -394,12 +434,11 @@ endif
### 3.6 popcnt
ifeq ($(popcnt),yes)
ifeq ($(arch),$(filter $(arch),ppc64 armv8-a))
CXXFLAGS += -DUSE_POPCNT
else ifeq ($(comp),icc)
CXXFLAGS += -msse3 -DUSE_POPCNT
else
CXXFLAGS += -msse3 -mpopcnt -DUSE_POPCNT
CXXFLAGS += -DUSE_POPCNT
ifneq ($(arch),$(filter $(arch),ppc64 armv8-a))
ifeq ($(comp),$(filter $(comp),gcc clang mingw msys2))
CXXFLAGS += -mpopcnt
endif
endif
endif
@@ -410,6 +449,13 @@ ifeq ($(avx2),yes)
endif
endif
ifeq ($(avx512),yes)
CXXFLAGS += -DUSE_AVX512
ifeq ($(comp),$(filter $(comp),gcc clang mingw msys2))
CXXFLAGS += -mavx512bw
endif
endif
ifeq ($(sse42),yes)
CXXFLAGS += -DUSE_SSE42
ifeq ($(comp),$(filter $(comp),gcc clang mingw msys2))
@@ -431,6 +477,13 @@ ifeq ($(ssse3),yes)
endif
endif
ifeq ($(sse3),yes)
CXXFLAGS += -DUSE_SSE3
ifeq ($(comp),$(filter $(comp),gcc clang mingw msys2))
CXXFLAGS += -msse3
endif
endif
ifeq ($(arch),x86_64)
CXXFLAGS += -DUSE_SSE2
endif
@@ -485,18 +538,22 @@ help:
@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 ""
@echo "Supported archs:"
@echo ""
@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-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-modern > x86 64-bit with popcnt 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"
@@ -593,11 +650,13 @@ config-sanity:
@echo "prefetch: '$(prefetch)'"
@echo "popcnt: '$(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 ""
@echo "Flags:"
@echo "CXX: $(CXX)"
@@ -616,11 +675,13 @@ config-sanity:
@test "$(prefetch)" = "yes" || test "$(prefetch)" = "no"
@test "$(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 "$(avx512)" = "no"
@test "$(comp)" = "gcc" || test "$(comp)" = "icc" || test "$(comp)" = "mingw" || test "$(comp)" = "clang"
$(EXE): $(OBJS)