before:
$ time CC=clang make -j16
CC=clang make -j16 6,04s user 0,86s system 468% cpu 1,471 total
CC=clang make -j16 6,05s user 0,87s system 468% cpu 1,477 total
CC=clang make -j16 6,15s user 0,86s system 464% cpu 1,510 total
CC=clang make -j16 6,05s user 0,93s system 467% cpu 1,493 total
CC=clang make -j16 6,10s user 0,84s system 461% cpu 1,507 total
$ time CC=gcc make -j16
CC=gcc make -j16 9,91s user 1,43s system 508% cpu 2,231 total
CC=gcc make -j16 10,02s user 1,37s system 500% cpu 2,275 total
CC=gcc make -j16 9,80s user 1,60s system 507% cpu 2,245 total
CC=gcc make -j16 10,02s user 1,44s system 506% cpu 2,264 total
CC=gcc make -j16 9,99s user 1,45s system 505% cpu 2,261 total
after:
$ time CC=clang make -j16
CC=clang make -j16 3,41s user 0,83s system 375% cpu 1,131 total
CC=clang make -j16 3,29s user 0,90s system 373% cpu 1,122 total
CC=clang make -j16 3,35s user 0,77s system 369% cpu 1,116 total
CC=clang make -j16 3,36s user 0,78s system 374% cpu 1,105 total
CC=clang make -j16 3,46s user 0,75s system 373% cpu 1,126 total
$ time CC=gcc make -j16
CC=gcc make -j16 10,74s user 1,44s system 494% cpu 2,462 total
CC=gcc make -j16 10,68s user 1,54s system 497% cpu 2,453 total
CC=gcc make -j16 10,60s user 1,60s system 488% cpu 2,499 total
CC=gcc make -j16 10,63s user 1,51s system 485% cpu 2,502 total
CC=gcc make -j16 10,70s user 1,51s system 497% cpu 2,453 total
Therefore, we enable pre-compiled headers only when CC=clang.
i3_CFLAGS = $(XCB_CFLAGS) $(XCB_KBD_CFLAGS) $(XCB_WM_CFLAGS) $(X11_CFLAGS) $(XCURSOR_CFLAGS) $(YAJL_CFLAGS) $(LIBEV_CFLAGS) $(PCRE_CFLAGS) $(LIBSN_CFLAGS)
i3_LIBS = $(XCB_LIBS) $(XCB_KBD_LIBS) $(XCB_WM_LIBS) $(X11_LIBS) $(XCURSOR_LIBS) $(YAJL_LIBS) $(LIBEV_LIBS) $(PCRE_LIBS) $(LIBSN_LIBS) -lm
+# When using clang, we use pre-compiled headers to speed up the build. With
+# gcc, this actually makes the build slower.
+ifeq ($(CC),clang)
+i3_HEADERS_DEP := $(i3_HEADERS) include/all.h.pch
+PCH_FLAGS := -include include/all.h
+else
+i3_HEADERS_DEP := $(i3_HEADERS)
+PCH_FLAGS :=
+endif
+
i3_OBJECTS := $(i3_SOURCES_GENERATED:.c=.o) $(i3_SOURCES:.c=.o)
-src/%.o: src/%.c $(i3_HEADERS)
+include/all.h.pch: $(i3_HEADERS)
+ echo "[i3] PCH all.h"
+ $(CC) $(I3_CPPFLAGS) $(CPPFLAGS) $(i3_CFLAGS) $(I3_CFLAGS) $(CFLAGS) -x c-header include/all.h -o include/all.h.pch
+
+src/%.o: src/%.c $(i3_HEADERS_DEP)
echo "[i3] CC $<"
- $(CC) $(I3_CPPFLAGS) $(CPPFLAGS) $(i3_CFLAGS) $(I3_CFLAGS) $(CFLAGS) -c -o $@ $<
+ $(CC) $(I3_CPPFLAGS) $(CPPFLAGS) $(i3_CFLAGS) $(I3_CFLAGS) $(CFLAGS) $(PCH_FLAGS) -c -o $@ $<
-src/cfgparse.yy.c: src/cfgparse.l src/cfgparse.tab.o $(i3_HEADERS)
+src/cfgparse.yy.c: src/cfgparse.l src/cfgparse.tab.o $(i3_HEADERS_DEP)
echo "[i3] LEX $<"
$(FLEX) -i -o $@ $<
-src/cfgparse.tab.c: src/cfgparse.y $(i3_HEADERS)
+src/cfgparse.tab.c: src/cfgparse.y $(i3_HEADERS_DEP)
echo "[i3] YACC $<"
$(BISON) --debug --verbose -b $(basename $< .y) -d $<
# This target compiles the command parser twice:
# Once with -DTEST_PARSER, creating a stand-alone executable used for tests,
# and once as an object file for i3.
-src/commands_parser.o: src/commands_parser.c $(i3_HEADERS) i3-command-parser.stamp
+src/commands_parser.o: src/commands_parser.c $(i3_HEADERS_DEP) i3-command-parser.stamp
echo "[i3] CC $<"
$(CC) $(I3_CPPFLAGS) $(CPPFLAGS) $(i3_CFLAGS) $(I3_CFLAGS) $(CFLAGS) $(I3_LDFLAGS) $(LDFLAGS) -DTEST_PARSER -o test.commands_parser $< $(i3_LIBS) $(LIBS)
$(CC) $(I3_CPPFLAGS) $(CPPFLAGS) $(i3_CFLAGS) $(I3_CFLAGS) $(CFLAGS) -c -o $@ $<
clean-i3:
echo "[i3] Clean"
- rm -f $(i3_OBJECTS) $(i3_SOURCES_GENERATED) $(i3_HEADERS_CMDPARSER) i3-command-parser.stamp i3 src/*.gcno src/cfgparse.{output,dot}
+ rm -f $(i3_OBJECTS) $(i3_SOURCES_GENERATED) $(i3_HEADERS_CMDPARSER) include/all.h.pch i3-command-parser.stamp i3 src/*.gcno src/cfgparse.{output,dot}