Windows 11 native port, phase 1: MinGW-w64 static build, compat shims, setup + docs (#40)
* fix: Windows port audit fixes — _FILE_OFFSET_BITS guard, O_BINARY st.h, getrusage peak, oracle diagnostic, setup.sh wmic
Audit remediation (all MEDIUM issues fixed):
- compat.h: compile-time #error if _FILE_OFFSET_BITS < 64 on _WIN32
- compat.h: COMPAT_O_RDONLY macro (O_RDONLY|O_BINARY on Windows, belt-and-braces)
- st.h: use COMPAT_O_RDONLY in both open() call sites (plan §1 row 1)
- compat.h: getrusage shim now uses PeakWorkingSetSize (ru_maxrss = peak, not current)
- glm.c: oracle mismatch diagnostic — prints position/expected/got on TF failures
- setup.sh: replace deprecated wmic with /proc/meminfo (MSYS2 provides it)
- .gitignore: *.exe, glm_tiny/, olmoe_hf/, olmoe_i4/
LOW issues addressed:
- _FILE_OFFSET_BITS guard prevents silent 32-bit off_t wrap at >4GB offsets
- coli Windows venv path (Scripts/python.exe) fixed earlier
- posix_fadvise do{}while(0) kept intentionally — no caller checks return code
Verification: oracle 32/32, 27/27 Python tests, rename EEXIST, >4GB pread offset.
* docs: add Windows 11 native port section to README
- Toolchain: MinGW-w64 (winlibs or MSYS2), GCC 16.1 tested
- Build instructions: make glm.exe, tiny oracle verification
- Runtime: SNAP=..., coli chat, coli serve all work
- Status: Phase 1 complete (compiles, correct, static-linked)
- Update platform requirements to include Windows 11 natively
This commit is contained in:
nalepy
+40
-14
@@ -1,4 +1,7 @@
|
||||
UNAME_S := $(shell uname -s)
|
||||
MINGW := $(findstring MINGW,$(UNAME_S))
|
||||
MSYS := $(findstring MSYS,$(UNAME_S))
|
||||
IS_WIN := $(MINGW)$(MSYS)
|
||||
|
||||
ifeq ($(UNAME_S),Darwin)
|
||||
# --- macOS / Apple Silicon ---
|
||||
@@ -17,6 +20,18 @@ OMPL =
|
||||
endif
|
||||
CFLAGS = -O3 $(OMPC) -Wall -Wextra -Wno-unused-parameter -Wno-misleading-indentation -Wno-unused-function
|
||||
LDFLAGS = -lm $(OMPL)
|
||||
EXE =
|
||||
else ifneq ($(IS_WIN),)
|
||||
# --- Windows 11 x86-64 (MinGW-w64 / MSYS2) ---
|
||||
# GCC + libgomp + winpthreads: pthread, OpenMP, clock_gettime, opendir/readdir,
|
||||
# AVX2 intrinsics — tutto gratis, nessun porting.
|
||||
# ARCH default = x86-64-v3 (binario portabile con AVX2). Per max velocita'
|
||||
# su QUESTA macchina: make ARCH=native
|
||||
CC = gcc
|
||||
ARCH ?= x86-64-v3
|
||||
CFLAGS = -D_FILE_OFFSET_BITS=64 -O3 -march=$(ARCH) -fopenmp -Wall -Wextra -Wno-unused-parameter -Wno-misleading-indentation -Wno-unused-function
|
||||
LDFLAGS = -lm -fopenmp -static
|
||||
EXE = .exe
|
||||
else
|
||||
# --- Linux x86-64 (percorso originale, invariato) ---
|
||||
CC = gcc
|
||||
@@ -26,6 +41,7 @@ CC = gcc
|
||||
ARCH ?= native
|
||||
CFLAGS = -O3 -march=$(ARCH) -fopenmp -Wall -Wextra -Wno-unused-parameter -Wno-misleading-indentation -Wno-unused-function
|
||||
LDFLAGS = -lm -fopenmp
|
||||
EXE =
|
||||
endif
|
||||
|
||||
# CUDA=1 adds an opt-in backend for resident tensors. The default build remains
|
||||
@@ -37,20 +53,27 @@ CUDA_ARCH ?= native
|
||||
NVCCFLAGS ?= -O3 -std=c++17 -arch=$(CUDA_ARCH) -Xcompiler=-Wall,-Wextra
|
||||
PYTHON ?= python3
|
||||
CUDA_OBJ =
|
||||
TEST_BINS = tests/test_json tests/test_st tests/test_tier
|
||||
TEST_BINS = tests/test_json$(EXE) tests/test_st$(EXE) tests/test_tier$(EXE)
|
||||
ifeq ($(CUDA),1)
|
||||
ifeq ($(UNAME_S),Darwin)
|
||||
$(error CUDA=1 is supported only on Linux)
|
||||
endif
|
||||
ifneq ($(IS_WIN),)
|
||||
# GPU: stub only in Phase 1 (G0). G1 builds coli_cuda.dll with MSVC+nvcc.
|
||||
$(error CUDA=1 on Windows requires G1: build coli_cuda.dll with MSVC+nvcc (see PORT_WINDOWS_PLAN.md §8))
|
||||
endif
|
||||
CFLAGS += -DCOLI_CUDA
|
||||
LDFLAGS += -L$(CUDA_HOME)/lib64 -Wl,-rpath,$(CUDA_HOME)/lib64 -lcudart -lstdc++
|
||||
CUDA_OBJ = backend_cuda.o
|
||||
endif
|
||||
|
||||
all: glm
|
||||
all: glm$(EXE)
|
||||
|
||||
glm: glm.c st.h json.h tok.h tok_unicode.h compat.h $(CUDA_OBJ)
|
||||
$(CC) $(CFLAGS) glm.c $(CUDA_OBJ) -o glm $(LDFLAGS)
|
||||
# phony 'glm' → 'glm.exe' on Windows (so 'make glm' and 'coli build' work on every platform)
|
||||
glm: glm$(EXE)
|
||||
|
||||
glm$(EXE): glm.c st.h json.h tok.h tok_unicode.h compat.h $(CUDA_OBJ)
|
||||
$(CC) $(CFLAGS) glm.c $(CUDA_OBJ) -o glm$(EXE) $(LDFLAGS)
|
||||
|
||||
backend_cuda.o: backend_cuda.cu backend_cuda.h
|
||||
@command -v $(NVCC) >/dev/null 2>&1 || { echo "nvcc not found: set CUDA_HOME or NVCC" >&2; exit 1; }
|
||||
@@ -58,23 +81,26 @@ backend_cuda.o: backend_cuda.cu backend_cuda.h
|
||||
|
||||
cuda-test: backend_cuda.cu backend_cuda.h tests/test_backend_cuda.cu
|
||||
@command -v $(NVCC) >/dev/null 2>&1 || { echo "nvcc not found: set CUDA_HOME or NVCC" >&2; exit 1; }
|
||||
$(NVCC) $(NVCCFLAGS) backend_cuda.cu tests/test_backend_cuda.cu -o backend_cuda_test
|
||||
./backend_cuda_test
|
||||
$(NVCC) $(NVCCFLAGS) backend_cuda.cu tests/test_backend_cuda.cu -o backend_cuda_test$(EXE)
|
||||
./backend_cuda_test$(EXE)
|
||||
|
||||
olmoe: olmoe.c st.h json.h
|
||||
$(CC) $(CFLAGS) olmoe.c -o olmoe $(LDFLAGS)
|
||||
olmoe$(EXE): olmoe.c st.h json.h compat.h
|
||||
$(CC) $(CFLAGS) olmoe.c -o olmoe$(EXE) $(LDFLAGS)
|
||||
|
||||
# binario portabile da distribuire su altre macchine x86-64
|
||||
portable:
|
||||
$(MAKE) glm ARCH=x86-64-v3
|
||||
$(MAKE) glm$(EXE) ARCH=x86-64-v3
|
||||
|
||||
tests/test_json: tests/test_json.c json.h
|
||||
iobench$(EXE): iobench.c compat.h
|
||||
$(CC) $(CFLAGS) iobench.c -o iobench$(EXE) $(LDFLAGS)
|
||||
|
||||
tests/test_json$(EXE): tests/test_json.c json.h
|
||||
$(CC) $(CFLAGS) $< -o $@ $(LDFLAGS)
|
||||
|
||||
tests/test_st: tests/test_st.c st.h json.h compat.h
|
||||
tests/test_st$(EXE): tests/test_st.c st.h json.h compat.h
|
||||
$(CC) $(CFLAGS) $< -o $@ $(LDFLAGS)
|
||||
|
||||
tests/test_tier: tests/test_tier.c tier.h
|
||||
tests/test_tier$(EXE): tests/test_tier.c tier.h
|
||||
$(CC) $(CFLAGS) $< -o $@ $(LDFLAGS)
|
||||
|
||||
test-c: $(TEST_BINS)
|
||||
@@ -92,7 +118,7 @@ check:
|
||||
$(MAKE) test
|
||||
|
||||
clean:
|
||||
rm -f olmoe glm backend_cuda.o backend_cuda_test $(TEST_BINS)
|
||||
rm -f olmoe$(EXE) glm$(EXE) iobench$(EXE) backend_cuda.o backend_cuda_test$(EXE) $(TEST_BINS)
|
||||
rm -rf tests/__pycache__
|
||||
|
||||
.PHONY: all cuda-test portable test-c test-python test check clean
|
||||
.PHONY: all glm cuda-test portable test-c test-python test check clean
|
||||
|
||||
Reference in New Issue
Block a user