mirror of
https://github.com/asg017/sqlite-vec.git
synced 2026-04-25 16:56:27 +02:00
Add DiskANN graph-based index: builds a Vamana graph with configurable R (max degree) and L (search list size, separate for insert/query), supports int8 quantization with rescore, lazy reverse-edge replacement, pre-quantized query optimization, and insert buffer reuse. Includes shadow table management, delete support, KNN integration, compile flag (SQLITE_VEC_ENABLE_DISKANN), release-demo workflow, fuzz targets, and tests. Fixes rescore int8 quantization bug.
169 lines
7.1 KiB
Makefile
169 lines
7.1 KiB
Makefile
# Auto-detect clang with libFuzzer support.
|
|
# Priority: Homebrew LLVM (macOS ARM) → Homebrew LLVM (macOS Intel) →
|
|
# versioned clang (Linux) → system clang
|
|
FUZZ_CC ?= $(shell \
|
|
if [ -x /opt/homebrew/opt/llvm/bin/clang ]; then \
|
|
echo "/opt/homebrew/opt/llvm/bin/clang"; \
|
|
elif [ -x /usr/local/opt/llvm/bin/clang ]; then \
|
|
echo "/usr/local/opt/llvm/bin/clang"; \
|
|
elif command -v clang-18 >/dev/null 2>&1; then \
|
|
echo "clang-18"; \
|
|
elif command -v clang-17 >/dev/null 2>&1; then \
|
|
echo "clang-17"; \
|
|
elif command -v clang >/dev/null 2>&1; then \
|
|
echo "clang"; \
|
|
else \
|
|
echo "FUZZ_CC_NOT_FOUND"; \
|
|
fi)
|
|
|
|
# AddressSanitizer + UndefinedBehaviorSanitizer + libFuzzer.
|
|
# Override FUZZ_SANITIZERS to change (e.g., drop ubsan on Windows).
|
|
FUZZ_SANITIZERS ?= -fsanitize=address,undefined,fuzzer
|
|
|
|
# On macOS, Homebrew LLVM may need -Wl,-ld_classic to work with the system linker.
|
|
FUZZ_LDFLAGS ?= $(shell \
|
|
if [ "$$(uname -s)" = "Darwin" ]; then \
|
|
echo "-Wl,-ld_classic"; \
|
|
fi)
|
|
|
|
FUZZ_CFLAGS = $(FUZZ_SANITIZERS) -I ../../ -I ../../vendor -DSQLITE_CORE -DSQLITE_VEC_ENABLE_DISKANN=1 -g $(FUZZ_LDFLAGS)
|
|
FUZZ_SRCS = ../../vendor/sqlite3.c ../../sqlite-vec.c
|
|
|
|
TARGET_DIR = ./targets
|
|
|
|
$(TARGET_DIR):
|
|
mkdir -p $@
|
|
|
|
# Existing targets (filename uses -, Makefile target uses _)
|
|
$(TARGET_DIR)/vec0_create: vec0-create.c $(FUZZ_SRCS) | $(TARGET_DIR)
|
|
$(FUZZ_CC) $(FUZZ_CFLAGS) $(FUZZ_SRCS) $< -o $@
|
|
|
|
$(TARGET_DIR)/exec: exec.c $(FUZZ_SRCS) | $(TARGET_DIR)
|
|
$(FUZZ_CC) $(FUZZ_CFLAGS) $(FUZZ_SRCS) $< -o $@
|
|
|
|
$(TARGET_DIR)/json: json.c $(FUZZ_SRCS) | $(TARGET_DIR)
|
|
$(FUZZ_CC) $(FUZZ_CFLAGS) $(FUZZ_SRCS) $< -o $@
|
|
|
|
$(TARGET_DIR)/numpy: numpy.c $(FUZZ_SRCS) | $(TARGET_DIR)
|
|
$(FUZZ_CC) $(FUZZ_CFLAGS) $(FUZZ_SRCS) $< -o $@
|
|
|
|
# New targets
|
|
$(TARGET_DIR)/shadow_corrupt: shadow-corrupt.c $(FUZZ_SRCS) | $(TARGET_DIR)
|
|
$(FUZZ_CC) $(FUZZ_CFLAGS) $(FUZZ_SRCS) $< -o $@
|
|
|
|
$(TARGET_DIR)/vec0_operations: vec0-operations.c $(FUZZ_SRCS) | $(TARGET_DIR)
|
|
$(FUZZ_CC) $(FUZZ_CFLAGS) $(FUZZ_SRCS) $< -o $@
|
|
|
|
$(TARGET_DIR)/scalar_functions: scalar-functions.c $(FUZZ_SRCS) | $(TARGET_DIR)
|
|
$(FUZZ_CC) $(FUZZ_CFLAGS) $(FUZZ_SRCS) $< -o $@
|
|
|
|
$(TARGET_DIR)/vec0_create_full: vec0-create-full.c $(FUZZ_SRCS) | $(TARGET_DIR)
|
|
$(FUZZ_CC) $(FUZZ_CFLAGS) $(FUZZ_SRCS) $< -o $@
|
|
|
|
$(TARGET_DIR)/metadata_columns: metadata-columns.c $(FUZZ_SRCS) | $(TARGET_DIR)
|
|
$(FUZZ_CC) $(FUZZ_CFLAGS) $(FUZZ_SRCS) $< -o $@
|
|
|
|
$(TARGET_DIR)/vec_each: vec-each.c $(FUZZ_SRCS) | $(TARGET_DIR)
|
|
$(FUZZ_CC) $(FUZZ_CFLAGS) $(FUZZ_SRCS) $< -o $@
|
|
|
|
$(TARGET_DIR)/vec_mismatch: vec-mismatch.c $(FUZZ_SRCS) | $(TARGET_DIR)
|
|
$(FUZZ_CC) $(FUZZ_CFLAGS) $(FUZZ_SRCS) $< -o $@
|
|
|
|
$(TARGET_DIR)/vec0_delete_completeness: vec0-delete-completeness.c $(FUZZ_SRCS) | $(TARGET_DIR)
|
|
$(FUZZ_CC) $(FUZZ_CFLAGS) $(FUZZ_SRCS) $< -o $@
|
|
|
|
$(TARGET_DIR)/rescore_operations: rescore-operations.c $(FUZZ_SRCS) | $(TARGET_DIR)
|
|
$(FUZZ_CC) $(FUZZ_CFLAGS) -DSQLITE_VEC_ENABLE_RESCORE $(FUZZ_SRCS) $< -o $@
|
|
|
|
$(TARGET_DIR)/rescore_create: rescore-create.c $(FUZZ_SRCS) | $(TARGET_DIR)
|
|
$(FUZZ_CC) $(FUZZ_CFLAGS) -DSQLITE_VEC_ENABLE_RESCORE $(FUZZ_SRCS) $< -o $@
|
|
|
|
$(TARGET_DIR)/rescore_quantize: rescore-quantize.c $(FUZZ_SRCS) | $(TARGET_DIR)
|
|
$(FUZZ_CC) $(FUZZ_CFLAGS) -DSQLITE_VEC_ENABLE_RESCORE -DSQLITE_VEC_TEST $(FUZZ_SRCS) $< -o $@
|
|
|
|
$(TARGET_DIR)/rescore_shadow_corrupt: rescore-shadow-corrupt.c $(FUZZ_SRCS) | $(TARGET_DIR)
|
|
$(FUZZ_CC) $(FUZZ_CFLAGS) -DSQLITE_VEC_ENABLE_RESCORE $(FUZZ_SRCS) $< -o $@
|
|
|
|
$(TARGET_DIR)/rescore_knn_deep: rescore-knn-deep.c $(FUZZ_SRCS) | $(TARGET_DIR)
|
|
$(FUZZ_CC) $(FUZZ_CFLAGS) -DSQLITE_VEC_ENABLE_RESCORE $(FUZZ_SRCS) $< -o $@
|
|
|
|
$(TARGET_DIR)/rescore_quantize_edge: rescore-quantize-edge.c $(FUZZ_SRCS) | $(TARGET_DIR)
|
|
$(FUZZ_CC) $(FUZZ_CFLAGS) -DSQLITE_VEC_ENABLE_RESCORE -DSQLITE_VEC_TEST $(FUZZ_SRCS) $< -o $@
|
|
|
|
$(TARGET_DIR)/rescore_interleave: rescore-interleave.c $(FUZZ_SRCS) | $(TARGET_DIR)
|
|
$(FUZZ_CC) $(FUZZ_CFLAGS) -DSQLITE_VEC_ENABLE_RESCORE $(FUZZ_SRCS) $< -o $@
|
|
|
|
$(TARGET_DIR)/ivf_create: ivf-create.c $(FUZZ_SRCS) | $(TARGET_DIR)
|
|
$(FUZZ_CC) $(FUZZ_CFLAGS) $(FUZZ_SRCS) $< -o $@
|
|
|
|
$(TARGET_DIR)/ivf_operations: ivf-operations.c $(FUZZ_SRCS) | $(TARGET_DIR)
|
|
$(FUZZ_CC) $(FUZZ_CFLAGS) $(FUZZ_SRCS) $< -o $@
|
|
|
|
$(TARGET_DIR)/ivf_quantize: ivf-quantize.c $(FUZZ_SRCS) | $(TARGET_DIR)
|
|
$(FUZZ_CC) $(FUZZ_CFLAGS) $(FUZZ_SRCS) $< -o $@
|
|
|
|
$(TARGET_DIR)/ivf_kmeans: ivf-kmeans.c $(FUZZ_SRCS) | $(TARGET_DIR)
|
|
$(FUZZ_CC) $(FUZZ_CFLAGS) $(FUZZ_SRCS) $< -o $@
|
|
|
|
$(TARGET_DIR)/ivf_shadow_corrupt: ivf-shadow-corrupt.c $(FUZZ_SRCS) | $(TARGET_DIR)
|
|
$(FUZZ_CC) $(FUZZ_CFLAGS) $(FUZZ_SRCS) $< -o $@
|
|
|
|
$(TARGET_DIR)/ivf_knn_deep: ivf-knn-deep.c $(FUZZ_SRCS) | $(TARGET_DIR)
|
|
$(FUZZ_CC) $(FUZZ_CFLAGS) $(FUZZ_SRCS) $< -o $@
|
|
|
|
$(TARGET_DIR)/ivf_cell_overflow: ivf-cell-overflow.c $(FUZZ_SRCS) | $(TARGET_DIR)
|
|
$(FUZZ_CC) $(FUZZ_CFLAGS) $(FUZZ_SRCS) $< -o $@
|
|
|
|
$(TARGET_DIR)/ivf_rescore: ivf-rescore.c $(FUZZ_SRCS) | $(TARGET_DIR)
|
|
$(TARGET_DIR)/diskann_operations: diskann-operations.c $(FUZZ_SRCS) | $(TARGET_DIR)
|
|
$(FUZZ_CC) $(FUZZ_CFLAGS) $(FUZZ_SRCS) $< -o $@
|
|
|
|
$(TARGET_DIR)/diskann_create: diskann-create.c $(FUZZ_SRCS) | $(TARGET_DIR)
|
|
$(FUZZ_CC) $(FUZZ_CFLAGS) $(FUZZ_SRCS) $< -o $@
|
|
|
|
$(TARGET_DIR)/diskann_graph_corrupt: diskann-graph-corrupt.c $(FUZZ_SRCS) | $(TARGET_DIR)
|
|
$(FUZZ_CC) $(FUZZ_CFLAGS) $(FUZZ_SRCS) $< -o $@
|
|
|
|
$(TARGET_DIR)/diskann_deep_search: diskann-deep-search.c $(FUZZ_SRCS) | $(TARGET_DIR)
|
|
$(FUZZ_CC) $(FUZZ_CFLAGS) $(FUZZ_SRCS) $< -o $@
|
|
|
|
$(TARGET_DIR)/diskann_blob_truncate: diskann-blob-truncate.c $(FUZZ_SRCS) | $(TARGET_DIR)
|
|
$(FUZZ_CC) $(FUZZ_CFLAGS) $(FUZZ_SRCS) $< -o $@
|
|
|
|
$(TARGET_DIR)/diskann_delete_stress: diskann-delete-stress.c $(FUZZ_SRCS) | $(TARGET_DIR)
|
|
$(FUZZ_CC) $(FUZZ_CFLAGS) $(FUZZ_SRCS) $< -o $@
|
|
|
|
$(TARGET_DIR)/diskann_buffer_flush: diskann-buffer-flush.c $(FUZZ_SRCS) | $(TARGET_DIR)
|
|
$(FUZZ_CC) $(FUZZ_CFLAGS) $(FUZZ_SRCS) $< -o $@
|
|
|
|
$(TARGET_DIR)/diskann_int8_quant: diskann-int8-quant.c $(FUZZ_SRCS) | $(TARGET_DIR)
|
|
$(FUZZ_CC) $(FUZZ_CFLAGS) $(FUZZ_SRCS) $< -o $@
|
|
|
|
$(TARGET_DIR)/diskann_prune_direct: diskann-prune-direct.c $(FUZZ_SRCS) | $(TARGET_DIR)
|
|
$(FUZZ_CC) $(FUZZ_CFLAGS) $(FUZZ_SRCS) $< -o $@
|
|
|
|
$(TARGET_DIR)/diskann_command_inject: diskann-command-inject.c $(FUZZ_SRCS) | $(TARGET_DIR)
|
|
$(FUZZ_CC) $(FUZZ_CFLAGS) $(FUZZ_SRCS) $< -o $@
|
|
|
|
FUZZ_TARGETS = vec0_create exec json numpy \
|
|
shadow_corrupt vec0_operations scalar_functions \
|
|
vec0_create_full metadata_columns vec_each vec_mismatch \
|
|
vec0_delete_completeness \
|
|
rescore_operations rescore_create rescore_quantize \
|
|
rescore_shadow_corrupt rescore_knn_deep \
|
|
rescore_quantize_edge rescore_interleave \
|
|
ivf_create ivf_operations \
|
|
ivf_quantize ivf_kmeans ivf_shadow_corrupt \
|
|
ivf_knn_deep ivf_cell_overflow ivf_rescore
|
|
diskann_operations diskann_create diskann_graph_corrupt \
|
|
diskann_deep_search diskann_blob_truncate \
|
|
diskann_delete_stress diskann_buffer_flush \
|
|
diskann_int8_quant diskann_prune_direct \
|
|
diskann_command_inject
|
|
|
|
all: $(addprefix $(TARGET_DIR)/,$(FUZZ_TARGETS))
|
|
|
|
clean:
|
|
rm -rf $(TARGET_DIR)/*
|
|
|
|
.PHONY: all clean
|