# 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
prefetch = no
popcnt = no
sse = no
-sse3 = no
ssse3 = no
sse41 = no
-sse42 = no
avx2 = no
pext = no
avx512 = no
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
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
prefetch = yes
popcnt = yes
sse = yes
- sse3 = yes
ssse3 = yes
sse41 = yes
endif
-ifeq ($(ARCH),x86-64-sse42)
+ifeq ($(ARCH),x86-64-sse41-popcnt)
arch = x86_64
prefetch = yes
popcnt = yes
sse = yes
- sse3 = yes
ssse3 = yes
sse41 = yes
- sse42 = yes
endif
ifeq ($(ARCH),x86-64-avx2)
prefetch = yes
popcnt = yes
sse = yes
- sse3 = yes
ssse3 = yes
sse41 = yes
- sse42 = yes
avx2 = yes
endif
prefetch = yes
popcnt = yes
sse = yes
- sse3 = yes
ssse3 = yes
sse41 = yes
- sse42 = yes
avx2 = yes
pext = yes
endif
prefetch = yes
popcnt = yes
sse = yes
- sse3 = yes
ssse3 = yes
sse41 = yes
- sse42 = yes
avx2 = yes
pext = yes
avx512 = yes
endif
endif
-ifeq ($(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 $(comp),gcc clang mingw))
endif
endif
-ifeq ($(sse3),yes)
- CXXFLAGS += -DUSE_SSE3
- ifeq ($(comp),$(filter $(comp),gcc clang mingw))
- CXXFLAGS += -msse3
- endif
-endif
-
ifeq ($(neon),yes)
CXXFLAGS += -DUSE_NEON
endif
@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-sse41-popcnt > x86 64-bit with sse41 and popcnt support"
+ @echo "x86-64-modern > the same as previous (x86-64-sse41-popcnt)"
@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 "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)'"
@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"