Merge pull request #3051 from stan-dev/tbb-winarm64

Add support for Windows ARM64

Author: WardBrian

lib/tbb_2020.3/STAN_CHANGES

@@ -6,3 +6,10 @@ This file documents changes done for the stan-math project
 - build/windows.inc patches for RTools make:
   - L15 changed setting to use '?=', allowing override
   - L25,L113,L114 added additional '/' to each cmd flag
+
+- Support for Windows ARM64 with RTools:
+  - build/Makefile.tbb
+    - L94 Wrapped the use of `--version-script` export in conditional on non-WINARM64
+  - build/windows.gcc.ino
+    - L84 Wrapped the use of `-flifetime-dse` flag in conditional on non-WINARM64
+    

lib/tbb_2020.3/build/Makefile.tbb

@@ -91,7 +91,11 @@ ifneq (,$(TBB.DEF))
 tbb.def: $(TBB.DEF) $(TBB.LST)
 	$(CPLUS) $(PREPROC_ONLY) $< $(CPLUS_FLAGS) $(INCLUDES) > $@
 
-LIB_LINK_FLAGS += $(EXPORT_KEY)tbb.def
+# LLVM on Windows doesn't need --version-script export
+# https://reviews.llvm.org/D63743
+ifeq (, $(WINARM64))
+  LIB_LINK_FLAGS += $(EXPORT_KEY)tbb.def
+endif
 $(TBB.DLL): tbb.def
 endif
 

lib/tbb_2020.3/build/windows.gcc.inc

@@ -80,8 +80,11 @@ endif
 # gcc 6.0 and later have -flifetime-dse option that controls
 # elimination of stores done outside the object lifetime
 ifeq (ok,$(call detect_js,/minversion gcc 6.0))
-    # keep pre-contruction stores for zero initialization
-    DSE_KEY = -flifetime-dse=1
+    # Clang does not support -flifetime-dse
+    ifeq (, $(WINARM64))
+      # keep pre-contruction stores for zero initialization
+      DSE_KEY = -flifetime-dse=1
+    endif
 endif
 
 ifeq ($(cfg), release)

make/compiler_flags

@@ -17,6 +17,7 @@ endif
 
 ## Set OS specific library filename extensions
 ifeq ($(OS),Windows_NT)
+  WINARM64 := $(shell echo | $(CXX) -E -dM -  | findstr __aarch64__)
   LIBRARY_SUFFIX ?= .dll
 endif
 
@@ -271,8 +272,13 @@ CXXFLAGS_TBB ?= -I $(TBB_INC)
 else
 CXXFLAGS_TBB ?= -I $(TBB)/include
 endif
+LDFLAGS_TBB ?= -Wl,-L,"$(TBB_LIB)" -Wl,--disable-new-dtags
+
+# Windows LLVM/Clang does not support -rpath, but is not needed on Windows anyway
+ifeq ($(WINARM64),)
+  LDFLAGS_TBB += -Wl,-rpath,"$(TBB_LIB)"
+endif
 
-LDFLAGS_TBB ?= -Wl,-L,"$(TBB_LIB)" -Wl,-rpath,"$(TBB_LIB)" -Wl,--disable-new-dtags
 LDLIBS_TBB ?= -ltbb
 
 else
@@ -290,7 +296,12 @@ ifeq ($(OS),Linux)
 endif
 
 CXXFLAGS_TBB ?= -I $(TBB)/include
-LDFLAGS_TBB ?= -Wl,-L,"$(TBB_BIN_ABSOLUTE_PATH)" -Wl,-rpath,"$(TBB_BIN_ABSOLUTE_PATH)" $(LDFLAGS_FLTO_FLTO) $(LDFLAGS_OPTIM_TBB)
+LDFLAGS_TBB ?= -Wl,-L,"$(TBB_BIN_ABSOLUTE_PATH)" $(LDFLAGS_FLTO_FLTO) $(LDFLAGS_OPTIM_TBB)
+
+# Windows LLVM/Clang does not support -rpath, but is not needed on Windows anyway
+ifeq ($(WINARM64),)
+  LDFLAGS_TBB += -Wl,-rpath,"$(TBB_BIN_ABSOLUTE_PATH)"
+endif
 LDLIBS_TBB ?= -ltbb
 
 endif

make/libraries

@@ -138,6 +138,11 @@ endif
 ifeq (Windows_NT, $(OS))
   ifeq ($(IS_UCRT),true)
     TBB_CXXFLAGS += -D_UCRT
+  endif
+  # TBB does not have assembly code for Windows ARM64, so we need to use GCC builtins
+  ifneq ($(WINARM64),)
+	TBB_CXXFLAGS += -DTBB_USE_GCC_BUILTINS
+	CXXFLAGS_TBB += -DTBB_USE_GCC_BUILTINS
   endif
 	SH_CHECK := $(shell command -v sh 2>/dev/null)
 	ifdef SH_CHECK
@@ -169,11 +174,11 @@ endif
 $(TBB_BIN)/tbb.def: $(TBB_BIN)/tbb-make-check
 	@mkdir -p $(TBB_BIN)
 	touch $(TBB_BIN)/version_$(notdir $(TBB))
-	tbb_root="$(TBB_RELATIVE_PATH)" CXX="$(CXX)" CC="$(TBB_CC)" LDFLAGS='$(LDFLAGS_TBB)' '$(MAKE)' -C "$(TBB_BIN)" -r -f "$(TBB_ABSOLUTE_PATH)/build/Makefile.tbb" compiler=$(TBB_CXX_TYPE) cfg=release stdver=c++1y  CXXFLAGS="$(TBB_CXXFLAGS)"
+	tbb_root="$(TBB_RELATIVE_PATH)" WINARM64="$(WINARM64)" CXX="$(CXX)" CC="$(TBB_CC)" LDFLAGS='$(LDFLAGS_TBB)' '$(MAKE)' -C "$(TBB_BIN)" -r -f "$(TBB_ABSOLUTE_PATH)/build/Makefile.tbb" compiler=$(TBB_CXX_TYPE) cfg=release stdver=c++1y  CXXFLAGS="$(TBB_CXXFLAGS)"
 
 $(TBB_BIN)/tbbmalloc.def: $(TBB_BIN)/tbb-make-check
 	@mkdir -p $(TBB_BIN)
-	tbb_root="$(TBB_RELATIVE_PATH)" CXX="$(CXX)" CC="$(TBB_CC)" LDFLAGS='$(LDFLAGS_TBB)' '$(MAKE)' -C "$(TBB_BIN)" -r -f "$(TBB_ABSOLUTE_PATH)/build/Makefile.tbbmalloc" compiler=$(TBB_CXX_TYPE) cfg=release stdver=c++1y malloc CXXFLAGS="$(TBB_CXXFLAGS)"
+	tbb_root="$(TBB_RELATIVE_PATH)" WINARM64="$(WINARM64)" CXX="$(CXX)" CC="$(TBB_CC)" LDFLAGS='$(LDFLAGS_TBB)' '$(MAKE)' -C "$(TBB_BIN)" -r -f "$(TBB_ABSOLUTE_PATH)/build/Makefile.tbbmalloc" compiler=$(TBB_CXX_TYPE) cfg=release stdver=c++1y malloc CXXFLAGS="$(TBB_CXXFLAGS)"
 
 $(TBB_BIN)/libtbb.dylib: $(TBB_BIN)/tbb.def
 $(TBB_BIN)/libtbbmalloc.dylib: $(TBB_BIN)/tbbmalloc.def