Merge dev into dual-ssd-mirror: resolve #298/#192-era conflicts
Combined resolution: mir_pread/st_prefetch_rep (this PR) now carry dev's DISK-CLASS accounting unwind (dc_wall_exit) and O_DIRECT prefetch skip (g_direct); direct-path keeps dc_direct=1 plus the mirror read counters. Verified: clean build, token-exact tiny models unchanged, test_st_mirror and test_st_pread pass. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
JustVugg
+47
-2
@@ -58,9 +58,14 @@ CFLAGS = -O3 $(OMPC) -Wall -Wextra -Wno-unused-parameter -Wno-misleading-indent
|
||||
# Opt-in: ARCH=native appends -mcpu=native (arm64 clang uses -mcpu, not -march),
|
||||
# which unlocks the i8mm SMMLA int8/int4 dot kernels in colibri.c. ARCH unset ->
|
||||
# no -mcpu, default build byte-identical. Apple clang knows apple-m4 / native.
|
||||
# For older X86_64 Macs (for example, Mac Pro 2019) we need to use -march
|
||||
ifneq ($(ARCH),)
|
||||
ifneq (,$(X86_64))
|
||||
CFLAGS += -march=$(ARCH)
|
||||
else
|
||||
CFLAGS += -mcpu=$(ARCH)
|
||||
endif
|
||||
endif
|
||||
LDFLAGS = -lm $(OMPL)
|
||||
EXE =
|
||||
else ifneq ($(IS_WIN),)
|
||||
@@ -166,7 +171,7 @@ else
|
||||
PYTHON ?= python3
|
||||
endif
|
||||
CUDA_OBJ =
|
||||
TEST_BINS = tests/test_json$(EXE) tests/test_st$(EXE) tests/test_st_mirror$(EXE) tests/test_st_pread$(EXE) tests/test_tier$(EXE) tests/test_grammar$(EXE) tests/test_schema_gbnf$(EXE) tests/test_decode_batch$(EXE) tests/test_idot$(EXE) tests/test_i4_grouped$(EXE) tests/test_stops$(EXE) tests/test_topp$(EXE) tests/test_sample_nan$(EXE) tests/test_kv_alloc$(EXE) tests/test_i4_acc512$(EXE) tests/test_compat_direct$(EXE) tests/test_dsa_select$(EXE) tests/test_logit_nan$(EXE)
|
||||
TEST_BINS = tests/test_json$(EXE) tests/test_st$(EXE) tests/test_st_mirror$(EXE) tests/test_st_pread$(EXE) tests/test_tier$(EXE) tests/test_grammar$(EXE) tests/test_schema_gbnf$(EXE) tests/test_decode_batch$(EXE) tests/test_idot$(EXE) tests/test_i4_grouped$(EXE) tests/test_stops$(EXE) tests/test_topp$(EXE) tests/test_sample_nan$(EXE) tests/test_tok_o200k$(EXE) tests/test_kv_alloc$(EXE) tests/test_int3$(EXE) tests/test_int3_load$(EXE) tests/test_i4_acc512$(EXE) tests/test_compat_direct$(EXE) tests/test_dsa_select$(EXE) tests/test_logit_nan$(EXE) tests/test_pipe_block$(EXE)
|
||||
ifneq (,$(LINUX))
|
||||
TEST_BINS += tests/test_uring$(EXE)
|
||||
endif
|
||||
@@ -273,8 +278,9 @@ olmoe$(EXE): olmoe.c st.h json.h compat.h
|
||||
# Use a baseline that matches the compiler target. macOS already targets a
|
||||
# portable baseline when ARCH is empty; forcing the x86 value there breaks
|
||||
# Apple Silicon. Unknown targets use native rather than an invalid x86 flag.
|
||||
# Intel Macs need -march for vector instructions
|
||||
ifneq (,$(DARWIN))
|
||||
PORTABLE_ARCH =
|
||||
PORTABLE_ARCH = $(if $(X86_64),x86-64-v3,)
|
||||
else ifneq (,$(AARCH64))
|
||||
PORTABLE_ARCH = armv8-a
|
||||
else ifneq (,$(PPC64))
|
||||
@@ -294,6 +300,8 @@ iobench$(EXE): iobench.c compat.h
|
||||
tests/test_json$(EXE): tests/test_json.c json.h
|
||||
$(CC) $(CFLAGS) $< -o $@ $(LDFLAGS)
|
||||
|
||||
tests/test_tok_o200k$(EXE): tests/test_tok_o200k.c tok.h tok_unicode.h tok_unicode_o200k.h json.h
|
||||
$(CC) $(CFLAGS) $< -o $@ $(LDFLAGS)
|
||||
tests/test_st_pread$(EXE): tests/test_st_pread.c st.h json.h compat.h
|
||||
$(CC) $(CFLAGS) -DST_PREAD_CHUNK=7 $< -o $@ $(LDFLAGS)
|
||||
|
||||
@@ -338,6 +346,12 @@ tests/test_sample_nan$(EXE): tests/test_sample_nan.c colibri.c st.h uring.h json
|
||||
tests/test_kv_alloc$(EXE): tests/test_kv_alloc.c colibri.c st.h json.h tok.h tok_unicode.h compat.h grammar.h tier.h quant.h sample.h kv_persist.h telemetry.h
|
||||
$(CC) $(CFLAGS) $< -o $@ $(LDFLAGS)
|
||||
|
||||
tests/test_int3$(EXE): tests/test_int3.c colibri.c st.h uring.h json.h tok.h tok_unicode.h compat.h grammar.h tier.h quant.h sample.h kv_persist.h telemetry.h
|
||||
$(CC) $(CFLAGS) $< -o $@ $(LDFLAGS)
|
||||
|
||||
tests/test_int3_load$(EXE): tests/test_int3_load.c colibri.c st.h uring.h json.h tok.h tok_unicode.h compat.h grammar.h tier.h quant.h sample.h kv_persist.h telemetry.h
|
||||
$(CC) $(CFLAGS) $< -o $@ $(LDFLAGS)
|
||||
|
||||
tests/test_logit_nan$(EXE): tests/test_logit_nan.c colibri.c st.h uring.h json.h tok.h tok_unicode.h compat.h grammar.h tier.h
|
||||
$(CC) $(CFLAGS) $< -o $@ $(LDFLAGS)
|
||||
|
||||
@@ -355,9 +369,17 @@ tests/test_dsa_select$(EXE): tests/test_dsa_select.c colibri.c st.h uring.h json
|
||||
tests/bench_dsa_select$(EXE): tests/bench_dsa_select.c colibri.c st.h uring.h json.h tok.h tok_unicode.h compat.h grammar.h tier.h quant.h sample.h kv_persist.h telemetry.h
|
||||
$(CC) $(CFLAGS) $< -o $@ $(LDFLAGS)
|
||||
|
||||
# bench_idot: microbenchmark (single-acc vs independent-acc AVX-VNNI idot), NOT a test gate.
|
||||
# Build on demand on an AVX-VNNI CPU: make tests/bench_idot ARCH=native
|
||||
tests/bench_idot$(EXE): tests/bench_idot.c colibri.c st.h uring.h json.h tok.h tok_unicode.h compat.h grammar.h tier.h quant.h sample.h kv_persist.h telemetry.h
|
||||
$(CC) $(CFLAGS) $< -o $@ $(LDFLAGS)
|
||||
|
||||
tests/test_uring$(EXE): tests/test_uring.c colibri.c st.h uring.h json.h tok.h tok_unicode.h compat.h grammar.h tier.h quant.h sample.h kv_persist.h telemetry.h
|
||||
$(CC) $(CFLAGS) $< -o $@ $(LDFLAGS)
|
||||
|
||||
tests/test_pipe_block$(EXE): tests/test_pipe_block.c colibri.c st.h uring.h json.h tok.h tok_unicode.h compat.h grammar.h tier.h
|
||||
$(CC) $(CFLAGS) $< -o $@ $(LDFLAGS)
|
||||
|
||||
test-c: $(TEST_BINS)
|
||||
$(PYTHON) tools/run_tests.py $(TEST_BINS)
|
||||
|
||||
@@ -366,6 +388,29 @@ test-python:
|
||||
|
||||
test: test-c test-python
|
||||
|
||||
# --- Efficiency / regression suite (issue: "test the program for inefficiencies") ---
|
||||
# The tiny-model assertions live in test_inefficiency.py and run as part of
|
||||
# test-python (they're discovered by the test_*.py glob). These targets are
|
||||
# convenience entry points; the opt-in full-model report is NEVER in `make test`.
|
||||
#
|
||||
# make efficiency tiny-model asserted regression tests (CPU; part of test-python)
|
||||
# make efficiency-cuda the CUDA-path tests (requires a CUDA build — see below)
|
||||
# make efficiency-report opt-in full-model 🟢/🔴 diagnostic, never fails CI
|
||||
#
|
||||
# CUDA build (Windows): the CUDA tests need a host built with -DCOLI_CUDA plus
|
||||
# the runtime DLL. Do this FIRST — note CUDA_DLL=1 on BOTH the host and the
|
||||
# rule below, or `make glm.exe` will rebuild a CPU-only host and overwrite it:
|
||||
# make clean && make glm.exe CUDA_DLL=1 && make cuda-dll
|
||||
# The tests auto-skip with a clear message if the host is CPU-only.
|
||||
efficiency: test-python
|
||||
$(PYTHON) -m unittest tests.test_inefficiency -v
|
||||
|
||||
efficiency-cuda:
|
||||
$(PYTHON) -m unittest tests.test_inefficiency.TinyCudaEfficiencyTest -v
|
||||
|
||||
efficiency-report:
|
||||
$(PYTHON) tests/test_efficiency_report.py
|
||||
|
||||
# Local validation: one portable CPU build and dependency-free tests.
|
||||
check:
|
||||
$(MAKE) clean
|
||||
|
||||
Reference in New Issue
Block a user