forked from karpathy/llama2.c
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Makefile
76 lines (65 loc) · 2.34 KB
/
Makefile
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
# choose your compiler, e.g. gcc/clang
# example override to clang: make run CC=clang
CC = gcc
# the most basic way of building that is most likely to work on most systems
.PHONY: run
run: run.c
$(CC) -O3 -o run run.c -lm -lpcre
$(CC) -O3 -o runq runq.c -lm -lpcre
# useful for a debug build, can then e.g. analyze with valgrind, example:
# $ valgrind --leak-check=full ./run out/model.bin -n 3
rundebug: run.c
$(CC) -g -o run run.c -lm -lpcre
$(CC) -g -o runq runq.c -lm -lpcre
# https://gcc.gnu.org/onlinedocs/gcc/Optimize-Options.html
# https://simonbyrne.github.io/notes/fastmath/
# -Ofast enables all -O3 optimizations.
# Disregards strict standards compliance.
# It also enables optimizations that are not valid for all standard-compliant programs.
# It turns on -ffast-math, -fallow-store-data-races and the Fortran-specific
# -fstack-arrays, unless -fmax-stack-var-size is specified, and -fno-protect-parens.
# It turns off -fsemantic-interposition.
# In our specific application this is *probably* okay to use
.PHONY: runfast
runfast: run.c
$(CC) -Ofast -o run run.c -lm -lpcre
$(CC) -Ofast -o runq runq.c -lm -lpcre
# additionally compiles with OpenMP, allowing multithreaded runs
# make sure to also enable multiple threads when running, e.g.:
# OMP_NUM_THREADS=4 ./run out/model.bin
.PHONY: runomp
runomp: run.c
$(CC) -Ofast -fopenmp -march=native run.c -lpcre -lm -o run
$(CC) -Ofast -fopenmp -march=native runq.c -lpcre -lm -o runq
.PHONY: win64
win64:
x86_64-w64-mingw32-gcc -Ofast -D_WIN32 -o run.exe -I. run.c win.c
x86_64-w64-mingw32-gcc -Ofast -D_WIN32 -o runq.exe -I. runq.c win.c
# compiles with gnu99 standard flags for amazon linux, coreos, etc. compatibility
.PHONY: rungnu
rungnu:
$(CC) -Ofast -std=gnu11 -o run run.c -lm
$(CC) -Ofast -std=gnu11 -o runq runq.c -lm
.PHONY: runompgnu
runompgnu:
$(CC) -Ofast -fopenmp -std=gnu11 run.c -lm -o run
$(CC) -Ofast -fopenmp -std=gnu11 runq.c -lm -o runq
# run all tests
.PHONY: test
test:
pytest
# run only tests for run.c C implementation (is a bit faster if only C code changed)
.PHONY: testc
testc:
pytest -k runc
# run the C tests, without touching pytest / python
# to increase verbosity level run e.g. as `make testcc VERBOSITY=1`
VERBOSITY ?= 0
.PHONY: testcc
testcc:
$(CC) -DVERBOSITY=$(VERBOSITY) -O3 -o testc test.c -lm -lpcre
./testc
.PHONY: clean
clean:
rm -f run
rm -f runq