Files
rocm-systems/projects/rccl/src/Makefile
T
Sylvain Jeaugey db3bfd118f 2.24.3-1
Network user buffer support for collectives
 * Leverage user buffer registration to achieve zero-copy
   inter-node communications for Ring, NVLS and Collnet

Add RAS subsystem
 * Create a RAS thread keeping track of all NCCL communicators.
 * Add a ncclras tool contacting the RAS thread and getting a
   report.

Add fp8 support
 * Add support for e5m2 and e4m3 8-bit floating point operations.
 * Use Tree/PAT algorithms when possible for better numerical
   stability.

Add NIC fusion
 * Add a NET API to ask the network plugin to fuse a set of
   interfaces together.
 * Fuse multiple NICs under the same PCI switch as a single,
   larger NIC.

Socket connection failure retry
 * Retry in case of socket connection failure (unreachable host)
 * Avoid "Software caused connection abort" errors on retries

QP connection failure retry
 * Retry in case of IB QP connection failure during ibv_modify_qp.

NET API improvements
 * Allow plugins to force a flush in case data and completion
   ordering is not guaranteed.
 * Indicate when completion is not needed (e.g. for the LL128
   protocol), allowing plugins to skip generating a completion.
 * Allow for full offload of allgather operations when using one
   GPU per node.

NCCL_ALGO/NCCL_PROTO strict enforcement
 * Extend NCCL_ALGO/NCCL_PROTO syntax to be able to specify
   ALGO/PROTO filters for each collective operation.
 * Strictly enforce the ALGO/PROTO filters, no longer fall back
   on the ring algorithm when the filtering leaves no option and
   error out instead.

Enable CUMEM host allocations
 * Use cumem functions for host memory allocation by default.

Improved profiler plugin API
 * Avoid dependencies with NCCL includes.
 * Add information on whether the buffer is registered or not

Adjust PAT tuning
 * Improve transition between PAT and ring at scale.

Fix hangs when running with different CPU architectures
 * Detect when we use a mix of GPU architectures
 * Ensure Algo/Proto decisions are made based on that unified
   state.

Fix FD leak in UDS
 * Fix a leak when mapping buffers intra-node with cumem IPCs.

Fix crash when mixing buffer registration and graph buffer registration.
 * Separate local and graph registration to avoid crashes when we free
   buffers.

Fix user buffer registration with dmabuf
 * Make ncclSend/ncclRecv communication with buffer registration functional
   on network plugins relying on dmabuf for buffer registration.

Fix crash in IB code caused by uninitialized fields.

Fix non-blocking ncclSend/ncclRecv
 * Fix case where ncclSend/ncclRecv would return ncclSuccess in non-blocking
   mode even though the operation was not enqueued onto the stream.
 * Issue #1495

Various compiler tweaks and fixes
 * PR #758

Fix typo in ncclTopoPrintGraph
 * Issue #1468


[ROCm/rccl commit: 6aae379278]
2025-01-07 02:01:15 -08:00

155 líneas
4.9 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
LIBSRCFILES := \
bootstrap.cc channel.cc collectives.cc debug.cc enqueue.cc group.cc \
init.cc init_nvtx.cc net.cc proxy.cc transport.cc \
$(wildcard graph/*.cc) \
$(wildcard misc/*.cc) \
$(wildcard transport/*.cc) \
$(wildcard register/*.cc) \
$(filter-out ras/client.cc,$(wildcard ras/*.cc))
BINSRCFILES := ras/client.cc
##### lib files
LIBNAME := libnccl.so
STATICLIBNAME := libnccl_static.a
##### binaries
BINNAME := ncclras
##### pkgconfig files
PKGCONFIGFILE := nccl.pc
##### dirs
BUILDDIR ?= $(abspath ../build)
INCDIR := $(BUILDDIR)/include
LIBDIR := $(BUILDDIR)/lib
OBJDIR := $(BUILDDIR)/obj
PKGDIR := $(BUILDDIR)/lib/pkgconfig
BINDIR := $(BUILDDIR)/bin
##### target files
CUDARTLIB ?= cudart_static
# Use compatibility shim only with static cudart; see https://github.com/NVIDIA/nccl/issues/658
ifeq ($(CUDARTLIB), cudart_static)
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)
BINOBJ := $(BINSRCFILES:%.cc=$(OBJDIR)/%.o)
DEPFILES := $(LIBOBJ:%.o=%.d) $(BINOBJ:%.o=%.d)
LDFLAGS += -L${CUDA_LIB} -l$(CUDARTLIB) -lpthread -lrt -ldl
DEVMANIFEST := $(BUILDDIR)/obj/device/manifest
##### rules
build : lib staticlib binary
lib : $(INCTARGETS) $(LIBDIR)/$(LIBTARGET) $(PKGDIR)/$(PKGTARGET)
staticlib : $(LIBDIR)/$(STATICLIBTARGET)
binary : $(BINDIR)/$(BINNAME)
$(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))
$(BINDIR)/$(BINNAME): $(BINOBJ)
@printf "Linking %-35s > %s\n" $(BINNAME) $@
mkdir -p $(BINDIR)
$(CXX) $(CXXFLAGS) $^ -o $@
$(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 ${BINDIR} ${INCDIR} ${LIBDIR} ${PKGDIR} ${OBJDIR}
install : build
mkdir -p $(PREFIX)/lib
mkdir -p $(PREFIX)/lib/pkgconfig
mkdir -p $(PREFIX)/include
mkdir -p $(PREFIX)/bin
cp -P -v $(BUILDDIR)/lib/lib* $(PREFIX)/lib/
cp -P -v $(BUILDDIR)/lib/pkgconfig/* $(PREFIX)/lib/pkgconfig/
cp -v $(BUILDDIR)/include/* $(PREFIX)/include/
cp -v $(BUILDDIR)/bin/ncclras $(PREFIX)/bin/
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