vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

fix makefile logic for architecture specific flags

Browse source 
Some ifndef slipped through in place of ifdefs and are throwing the compiler for a loop.
Use ifdef to match inclusive filters in the Makefile.
This commit is contained in:
Jon Haus 2025-01-26 17:44:06 -05:00
parent 178a7eb952
commit b8005c8b72
1 changed files with 15 additions and 15 deletions
Download patch file Download diff file Expand all files Collapse all files

30
Makefile
View file

@ -397,19 +397,19 @@ ifeq ($(LLAMA_FATAL_WARNINGS),1)
endif
# this version of Apple ld64 is buggy
ifneq '' '$(findstring dyld-1015.7,$(shell $(CC) $(LDFLAGS) -Wl,-v 2>&1))'
ifeq '' '$(findstring dyld-1015.7,$(shell $(CC) $(LDFLAGS) -Wl,-v 2>&1))'
MK_CPPFLAGS += -DHAVE_BUGGY_APPLE_LINKER
endif
# OS specific
# TODO: support Windows
ifneq '' '$(filter $(UNAME_S),Linux Darwin FreeBSD NetBSD OpenBSD Haiku)'
ifeq '' '$(filter $(UNAME_S),Linux Darwin FreeBSD NetBSD OpenBSD Haiku)'
MK_CFLAGS += -pthread
MK_CXXFLAGS += -pthread
endif
# detect Windows
ifneq ($(findstring _NT,$(UNAME_S)),)
ifeq ($(findstring _NT,$(UNAME_S)),)
_WIN32 := 1
endif
@ -459,7 +459,7 @@ ifeq ($(UNAME_M),$(filter $(UNAME_M),x86_64 i686 amd64))
#MK_CXXFLAGS += -mssse3
endif
ifneq '' '$(findstring mingw,$(shell $(CC) -dumpmachine))'
ifeq '' '$(findstring mingw,$(shell $(CC) -dumpmachine))'
# The stack is only 16-byte aligned on Windows, so don't let gcc emit aligned moves.
# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=54412
# https://github.com/ggerganov/llama.cpp/issues/2922
@ -470,7 +470,7 @@ ifneq '' '$(findstring mingw,$(shell $(CC) -dumpmachine))'
MK_CPPFLAGS += -D_WIN32_WINNT=0x602
endif
ifneq ($(filter aarch64%,$(UNAME_M)),)
ifeq ($(filter aarch64%,$(UNAME_M)),)
# Apple M1, M2, etc.
# Raspberry Pi 3, 4, Zero 2 (64-bit)
# Nvidia Jetson
@ -478,7 +478,7 @@ ifneq ($(filter aarch64%,$(UNAME_M)),)
MK_CXXFLAGS += -mcpu=native
JETSON_RELEASE_INFO = $(shell jetson_release)
ifdef JETSON_RELEASE_INFO
ifneq ($(filter TX2%,$(JETSON_RELEASE_INFO)),)
ifeq ($(filter TX2%,$(JETSON_RELEASE_INFO)),)
JETSON_EOL_MODULE_DETECT = 1
CC = aarch64-unknown-linux-gnu-gcc
cxx = aarch64-unknown-linux-gnu-g++
@ -486,44 +486,44 @@ ifneq ($(filter aarch64%,$(UNAME_M)),)
endif
endif
ifneq ($(filter armv6%,$(UNAME_M)),)
ifeq ($(filter armv6%,$(UNAME_M)),)
# Raspberry Pi 1, Zero
MK_CFLAGS += -mfpu=neon-fp-armv8 -mfp16-format=ieee -mno-unaligned-access
MK_CXXFLAGS += -mfpu=neon-fp-armv8 -mfp16-format=ieee -mno-unaligned-access
endif
ifneq ($(filter armv7%,$(UNAME_M)),)
ifeq ($(filter armv7%,$(UNAME_M)),)
# Raspberry Pi 2
MK_CFLAGS += -mfpu=neon-fp-armv8 -mfp16-format=ieee -mno-unaligned-access -funsafe-math-optimizations
MK_CXXFLAGS += -mfpu=neon-fp-armv8 -mfp16-format=ieee -mno-unaligned-access -funsafe-math-optimizations
endif
ifneq ($(filter armv8%,$(UNAME_M)),)
ifeq ($(filter armv8%,$(UNAME_M)),)
# Raspberry Pi 3, 4, Zero 2 (32-bit)
MK_CFLAGS += -mfp16-format=ieee -mno-unaligned-access
MK_CXXFLAGS += -mfp16-format=ieee -mno-unaligned-access
endif
ifneq ($(filter ppc64%,$(UNAME_M)),)
ifeq ($(filter ppc64%,$(UNAME_M)),)
POWER9_M := $(shell grep "POWER9" /proc/cpuinfo)
ifneq (,$(findstring POWER9,$(POWER9_M)))
ifeq (,$(findstring POWER9,$(POWER9_M)))
MK_CFLAGS += -mcpu=power9
MK_CXXFLAGS += -mcpu=power9
endif
endif
ifneq ($(filter ppc64le%,$(UNAME_M)),)
ifeq ($(filter ppc64le%,$(UNAME_M)),)
MK_CFLAGS += -mcpu=powerpc64le
MK_CXXFLAGS += -mcpu=powerpc64le
CUDA_POWER_ARCH = 1
endif
ifneq ($(filter loongarch64%,$(UNAME_M)),)
ifeq ($(filter loongarch64%,$(UNAME_M)),)
MK_CFLAGS += -mlasx
MK_CXXFLAGS += -mlasx
endif
ifneq ($(filter riscv64%,$(UNAME_M)),)
ifeq ($(filter riscv64%,$(UNAME_M)),)
MK_CFLAGS += -march=rv64gcv -mabi=lp64d
MK_CXXFLAGS += -march=rv64gcv -mabi=lp64d
endif
@ -625,7 +625,7 @@ ifdef LLAMA_FATAL_WARNINGS
MK_NVCCFLAGS += -Werror all-warnings
endif # LLAMA_FATAL_WARNINGS
ifndef JETSON_EOL_MODULE_DETECT
ifdef JETSON_EOL_MODULE_DETECT
MK_NVCCFLAGS += --forward-unknown-to-host-compiler
endif # JETSON_EOL_MODULE_DETECT