Add -mbmi2 flag when -mavx2 is used in Makefiles

pybind_interface/avx2/CMakeLists.txt

@@ -20,8 +20,15 @@ if(WIN32)
     # Add /O2 to any configuration that is NOT Debug.
     # This prevents a conflict with /RTC1 in DEBUG builds.
     add_compile_options($<$<NOT:$<CONFIG:Debug>>:/O2>)
-else()
+elseif(LINUX)
     add_compile_options(-mavx2 -mfma -O3 -flto=auto)
+    execute_process(
+        COMMAND bash --noprofile -c "grep -qs bmi2 /proc/cpuinfo"
+        RESULT_VARIABLE _EXIT_CODE
+    )
+    if(_EXIT_CODE EQUAL 0)
+        add_compile_options("-mbmi2")
+    endif()
 endif()
 
 if(APPLE)

tests/Makefile

@@ -13,33 +13,34 @@
 # limitations under the License.
 
 # Determine the hardware features available in this CPU.
-HAVE_SSE := $(shell grep -qs sse /proc/cpuinfo && echo "true")
 HAVE_AVX2 := $(shell grep -qs avx2 /proc/cpuinfo && echo "true")
 HAVE_AVX512 := $(shell grep -qs avx512f /proc/cpuinfo && echo "true")
+HAVE_BMI2 := $(shell grep -qs bmi2 /proc/cpuinfo && echo "true")
+HAVE_SSE := $(shell grep -qs sse /proc/cpuinfo && echo "true")
 
 # Default targets. Always built.
 BASIC_FILES := $(shell ls *.cc | egrep -v '_avx|_sse')
 
 # Additional flags and targets for non-CUDA cases.
-SSE_FILES =
-AVX2_FILES =
-AVX512_FILES =
-ifneq (,$(HAVE_SSE))
-    SSE_FLAGS ?= -msse4
-    SSE_FILES := $(wildcard *_sse_test.cc)
-endif
 ifneq (,$(HAVE_AVX2))
     AVX2_FLAGS ?= -mavx2 -mfma
     AVX2_FILES := $(wildcard *_avx_test.cc)
 endif
 ifneq (,$(HAVE_AVX512))
-    AVX512_FLAGS ?= -mavx512f -mbmi2
+    AVX512_FLAGS ?= -mavx512f
     AVX512_FILES := $(wildcard *_avx512_test.cc)
 endif
+ifneq (,$(HAVE_BMI2))
+    BMI2_FLAGS ?= -mbmi2
+endif
+ifneq (,$(HAVE_SSE))
+    SSE_FLAGS ?= -msse4
+    SSE_FILES := $(wildcard *_sse_test.cc)
+endif
 
 CXX_FILES := $(BASIC_FILES) $(SSE_FILES) $(AVX2_FILES) $(AVX512_FILES)
 CXX_TARGETS := $(CXX_FILES:%.cc=%.x)
-CXXFLAGS := $(CXXFLAGS) $(SSE_FLAGS) $(AVX2_FLAGS) $(AVX512_FLAGS)
+CXXFLAGS := $(CXXFLAGS) $(SSE_FLAGS) $(AVX2_FLAGS) $(AVX512_FLAGS) $(BMI2_FLAGS)
 
 CUDA_FILES := $(wildcard *cuda_test.cu)
 CUDA_TARGETS := $(CUDA_FILES:%cuda_test.cu=%cuda_test.x)
@@ -125,8 +126,17 @@ clean:
 	-rm -f ./*.x ./*.a ./*.so ./*.mod
 	rm -rf $(GTEST_DIR)/build
 
-LOCAL_VARS = HAVE_SSE HAVE_AVX2 HAVE_AVX512 SSE_FLAGS AVX2_FLAGS $\
-	AVX512_FLAGS CXXFLAGS CXX_TARGETS TEST_FLAGS
+LOCAL_VARS = BASIC_FILES CXX_FILES CXX_TARGETS CXXFLAGS $\
+    CUDA_FILES CUDA_TARGETS $\
+    CUSTATEVEC_FILES CUSTATEVEC_FLAGS $\
+    CUSTATEVECEX_FILES CUSTATEVECEX_FLAGS $\
+	HAVE_AVX2 AVX2_FILES AVX2_FLAGS $\
+	HAVE_AVX512 AVX512_FILES AVX512_FLAGS $\
+    HAVE_BMI2 BMI2_FLAGS $\
+    HAVE_SSE SSE_FILES SSE_FLAGS $\
+	HIP_FILES HIP_TARGETS $\
+    GMOCK_DIR GTEST_DIR $\
+    TESTFLAGS
 
 .PHONY: print-vars
 print-vars: ; @$(foreach n,$(sort $(LOCAL_VARS)),echo $n=$($n);)