Sylvain Jeaugey
b6475625fb
Add support for alternating rings, allow for cross-nic rings without cross-rail communication. Add support for user buffer registration for network send/recv. Optimize aggregated operations to better utilize all channels. Add flattening for BCM PCI gen5 switches. Add support for inter-node NVLink communication Add support for port fusion in NET/IB. Add support for ReduceScatter and AllGather using Collnet. Update net API to v8. Fix hang during A2A connection.
139 خطوط
4.5 KiB
Makefile
139 خطوط
4.5 KiB
Makefile
#
|
|
# Copyright (c) 2015-2022, NVIDIA CORPORATION. All rights reserved.
|
|
#
|
|
# See LICENSE.txt for license information
|
|
#
|
|
include ../makefiles/common.mk
|
|
include ../makefiles/version.mk
|
|
|
|
##### src files
|
|
INCEXPORTS := nccl.h nccl_net.h
|
|
LIBSRCFILES := \
|
|
bootstrap.cc channel.cc collectives.cc debug.cc enqueue.cc group.cc \
|
|
init.cc init_nvtx.cc net.cc proxy.cc transport.cc register.cc \
|
|
$(wildcard graph/*.cc) \
|
|
$(wildcard misc/*.cc) \
|
|
$(wildcard transport/*.cc)
|
|
|
|
##### lib files
|
|
LIBNAME := libnccl.so
|
|
STATICLIBNAME := libnccl_static.a
|
|
##### pkgconfig files
|
|
PKGCONFIGFILE := nccl.pc
|
|
##### dirs
|
|
BUILDDIR ?= $(abspath ../build)
|
|
INCDIR := $(BUILDDIR)/include
|
|
LIBDIR := $(BUILDDIR)/lib
|
|
OBJDIR := $(BUILDDIR)/obj
|
|
PKGDIR := $(BUILDDIR)/lib/pkgconfig
|
|
##### target files
|
|
CUDARTLIB ?= cudart_static
|
|
|
|
ifeq ($(CUDARTLIB), cudart_static)
|
|
# Use compatibility shim only with static cudart; see https://github.com/NVIDIA/nccl/issues/658
|
|
LIBSRCFILES += enhcompat.cc
|
|
endif
|
|
|
|
INCTARGETS := $(INCEXPORTS:%=$(INCDIR)/%)
|
|
LIBSONAME := $(LIBNAME:%=%.$(NCCL_MAJOR))
|
|
LIBTARGET := $(LIBNAME:%=%.$(NCCL_MAJOR).$(NCCL_MINOR).$(NCCL_PATCH))
|
|
STATICLIBTARGET := $(STATICLIBNAME)
|
|
PKGTARGET := $(PKGCONFIGFILE)
|
|
LIBOBJ := $(LIBSRCFILES:%.cc=$(OBJDIR)/%.o)
|
|
DEPFILES := $(LIBOBJ:%.o=%.d)
|
|
LDFLAGS += -L${CUDA_LIB} -l$(CUDARTLIB) -lpthread -lrt -ldl
|
|
|
|
DEVMANIFEST := $(BUILDDIR)/obj/device/manifest
|
|
|
|
##### rules
|
|
build : lib staticlib
|
|
|
|
lib : $(INCTARGETS) $(LIBDIR)/$(LIBTARGET) $(PKGDIR)/$(PKGTARGET)
|
|
|
|
staticlib : $(LIBDIR)/$(STATICLIBTARGET)
|
|
|
|
$(DEVMANIFEST): ALWAYS_REBUILD $(INCTARGETS)
|
|
$(MAKE) -C ./device
|
|
|
|
# Empty target to force rebuild
|
|
ALWAYS_REBUILD:
|
|
|
|
-include $(DEPFILES)
|
|
$(LIBDIR)/$(LIBTARGET) $(LIBDIR)/$(STATICLIBTARGET) : $(LIBOBJ)
|
|
|
|
$(INCDIR)/nccl.h : nccl.h.in ../makefiles/version.mk
|
|
# NCCL_VERSION(X,Y,Z) ((X) * 10000 + (Y) * 100 + (Z))
|
|
@$(eval NCCL_VERSION := $(shell printf "%d%02d%02d" $(NCCL_MAJOR) $(NCCL_MINOR) $(NCCL_PATCH)))
|
|
mkdir -p $(INCDIR)
|
|
@printf "Generating %-35s > %s\n" $< $@
|
|
sed -e "s/\$${nccl:Major}/$(NCCL_MAJOR)/g" \
|
|
-e "s/\$${nccl:Minor}/$(NCCL_MINOR)/g" \
|
|
-e "s/\$${nccl:Patch}/$(NCCL_PATCH)/g" \
|
|
-e "s/\$${nccl:Suffix}/$(NCCL_SUFFIX)/g" \
|
|
-e "s/\$${nccl:Version}/$(NCCL_VERSION)/g" \
|
|
$< > $@
|
|
|
|
$(LIBDIR)/$(LIBTARGET): $(LIBOBJ) $(DEVMANIFEST)
|
|
@printf "Linking %-35s > %s\n" $(LIBTARGET) $@
|
|
mkdir -p $(LIBDIR)
|
|
$(CXX) $(CXXFLAGS) -shared -Wl,--no-as-needed -Wl,-soname,$(LIBSONAME) -o $@ $(LIBOBJ) $$(cat $(DEVMANIFEST)) $(LDFLAGS)
|
|
ln -sf $(LIBSONAME) $(LIBDIR)/$(LIBNAME)
|
|
ln -sf $(LIBTARGET) $(LIBDIR)/$(LIBSONAME)
|
|
|
|
$(LIBDIR)/$(STATICLIBTARGET): $(LIBOBJ) $(DEVMANIFEST)
|
|
@printf "Archiving %-35s > %s\n" $(STATICLIBTARGET) $@
|
|
mkdir -p $(LIBDIR)
|
|
ar cr $@ $(LIBOBJ) $$(cat $(DEVMANIFEST))
|
|
|
|
$(PKGDIR)/nccl.pc : nccl.pc.in
|
|
mkdir -p $(PKGDIR)
|
|
@printf "Generating %-35s > %s\n" $< $@
|
|
sed -e 's|$${nccl:Prefix}|\$(PREFIX)|g' \
|
|
-e "s/\$${nccl:Major}/$(NCCL_MAJOR)/g" \
|
|
-e "s/\$${nccl:Minor}/$(NCCL_MINOR)/g" \
|
|
-e "s/\$${nccl:Patch}/$(NCCL_PATCH)/g" \
|
|
$< > $@
|
|
|
|
$(INCDIR)/%.h : %.h
|
|
@printf "Grabbing %-35s > %s\n" $< $@
|
|
mkdir -p $(INCDIR)
|
|
install -m 644 $< $@
|
|
|
|
$(INCDIR)/nccl_%.h : include/nccl_%.h
|
|
@printf "Grabbing %-35s > %s\n" $< $@
|
|
mkdir -p $(INCDIR)
|
|
install -m 644 $< $@
|
|
|
|
$(PKGDIR)/%.pc : %.pc
|
|
@printf "Grabbing %-35s > %s\n" $< $@
|
|
mkdir -p $(PKGDIR)
|
|
install -m 644 $< $@
|
|
|
|
$(OBJDIR)/%.o : %.cc $(INCTARGETS)
|
|
@printf "Compiling %-35s > %s\n" $< $@
|
|
mkdir -p `dirname $@`
|
|
$(CXX) -I. -I$(INCDIR) $(CXXFLAGS) -Iinclude -c $< -o $@
|
|
@$(CXX) -I. -I$(INCDIR) $(CXXFLAGS) -Iinclude -M $< > $(@:%.o=%.d.tmp)
|
|
@sed "0,/^.*:/s//$(subst /,\/,$@):/" $(@:%.o=%.d.tmp) > $(@:%.o=%.d)
|
|
@sed -e 's/.*://' -e 's/\\$$//' < $(@:%.o=%.d.tmp) | fmt -1 | \
|
|
sed -e 's/^ *//' -e 's/$$/:/' >> $(@:%.o=%.d)
|
|
@rm -f $(@:%.o=%.d.tmp)
|
|
|
|
clean :
|
|
$(MAKE) -C device clean
|
|
rm -rf ${INCDIR} ${LIBDIR} ${PKGDIR} ${OBJDIR}
|
|
|
|
install : build
|
|
mkdir -p $(PREFIX)/lib
|
|
mkdir -p $(PREFIX)/lib/pkgconfig
|
|
mkdir -p $(PREFIX)/include
|
|
cp -P -v $(BUILDDIR)/lib/lib* $(PREFIX)/lib/
|
|
cp -P -v $(BUILDDIR)/lib/pkgconfig/* $(PREFIX)/lib/pkgconfig/
|
|
cp -v $(BUILDDIR)/include/* $(PREFIX)/include/
|
|
|
|
FILESTOFORMAT := $(shell find . -name ".\#*" -prune -o \( -name "*.cc" -o -name "*.h" \) -print | grep -v -E 'ibvwrap.h|nvmlwrap.h|gdrwrap.h|nccl.h')
|
|
# Note that formatting.mk defines a new target so in order to not overwrite the default target,
|
|
# it shouldn't be included at the top. Also, it uses the above definition of FILESTOFORMAT as well
|
|
# as the BUILDDIR variable.
|
|
include ../makefiles/formatting.mk
|