Patch to use GCC kung foo to make bzip2 go faster!

bzip2-shared, and libbz2.so, will go about 4.5% faster.
bzip2 (not linked to libbz2.so) will go about 7% faster (install this one).

These numbers don't account for -fomit-frame-pointer, so you should actually
get better performance than this.

robert

diff -Naur bzip2-1.0.5.orig/Makefile bzip2-1.0.5/Makefile
--- bzip2-1.0.5.orig/Makefile	2008-02-14 12:39:18.000000000 +0000
+++ bzip2-1.0.5/Makefile	2010-03-01 09:07:36.000000000 +0000
@@ -21,7 +21,7 @@
 LDFLAGS=
 
 BIGFILES=-D_FILE_OFFSET_BITS=64
-CFLAGS=-Wall -Winline -O2 -g $(BIGFILES)
+CFLAGS=-Wall -Winline -O2 -fomit-frame-pointer $(BIGFILES)
 
 # Where you want it installed when you do 'make install'
 PREFIX=/usr/local
@@ -37,8 +37,19 @@
 
 all: libbz2.a bzip2 bzip2recover test
 
-bzip2: libbz2.a bzip2.o
-	$(CC) $(CFLAGS) $(LDFLAGS) -o bzip2 bzip2.o -L. -lbz2
+bzip2:
+	$(CC) $(CFLAGS) $(LDFLAGS) -o bzip2 --combine -fprofile-generate \
+	 blocksort.c huffman.c crctable.c randtable.c compress.c \
+	 decompress.c bzlib.c bzip2.c
+	 ./bzip2 -1  < sample1.ref > sample1.rb2
+	 ./bzip2 -2  < sample2.ref > sample2.rb2
+	 ./bzip2 -3  < sample3.ref > sample3.rb2
+	 ./bzip2 -d  < sample1.bz2 > sample1.tst
+	 ./bzip2 -d  < sample2.bz2 > sample2.tst
+	 ./bzip2 -ds < sample3.bz2 > sample3.tst
+	$(CC) $(CFLAGS) $(LDFLAGS) -o bzip2 --combine -fprofile-use \
+	 blocksort.c huffman.c crctable.c randtable.c compress.c \
+	 decompress.c bzlib.c bzip2.c
 
 bzip2recover: bzip2recover.o
 	$(CC) $(CFLAGS) $(LDFLAGS) -o bzip2recover bzip2recover.o
diff -Naur bzip2-1.0.5.orig/Makefile-libbz2_so bzip2-1.0.5/Makefile-libbz2_so
--- bzip2-1.0.5.orig/Makefile-libbz2_so	2007-12-09 13:00:50.000000000 +0000
+++ bzip2-1.0.5/Makefile-libbz2_so	2010-03-01 09:05:56.000000000 +0000
@@ -24,36 +24,42 @@
 SHELL=/bin/sh
 CC=gcc
 BIGFILES=-D_FILE_OFFSET_BITS=64
-CFLAGS=-fpic -fPIC -Wall -Winline -O2 -g $(BIGFILES)
+CFLAGS=-Wall -Winline -O2 -fomit-frame-pointer $(BIGFILES)
+BZIP2_SHARED=LD_PRELOAD=./libbz2.so.1.0.4 ./bzip2-shared
 
-OBJS= blocksort.o  \
-      huffman.o    \
-      crctable.o   \
-      randtable.o  \
-      compress.o   \
-      decompress.o \
-      bzlib.o
-
-all: $(OBJS)
-	$(CC) -shared -Wl,-soname -Wl,libbz2.so.1.0 -o libbz2.so.1.0.4 $(OBJS)
-	$(CC) $(CFLAGS) -o bzip2-shared bzip2.c libbz2.so.1.0.4
+all:
+	$(CC) -shared -Wl,-soname -Wl,libbz2.so.1.0 -o libbz2.so.1.0.4 \
+	 blocksort.c huffman.c crctable.c randtable.c compress.c \
+	 decompress.c bzlib.c $(CFLAGS) -fPIC --combine -fprofile-generate
+	$(CC) $(CFLAGS) --combine -fprofile-generate \
+	 -o bzip2-shared bzip2.c libbz2.so.1.0.4
+	$(BZIP2_SHARED) -1  < sample1.ref > sample1.rb2
+	$(BZIP2_SHARED) -2  < sample2.ref > sample2.rb2
+	$(BZIP2_SHARED) -3  < sample3.ref > sample3.rb2
+	$(BZIP2_SHARED) -d  < sample1.bz2 > sample1.tst
+	$(BZIP2_SHARED) -d  < sample2.bz2 > sample2.tst
+	$(BZIP2_SHARED) -ds < sample3.bz2 > sample3.tst
+	$(CC) -shared -Wl,-soname -Wl,libbz2.so.1 -o libbz2.so.1.0.4 \
+	 blocksort.c huffman.c crctable.c randtable.c compress.c \
+	 decompress.c bzlib.c $(CFLAGS) -fPIC --combine -fprofile-use
+	$(CC) $(CFLAGS) --combine -fprofile-use \
+	 -o bzip2-shared bzip2.c libbz2.so.1.0.4
+	@cat words1
+	$(BZIP2_SHARED) -1  < sample1.ref > sample1.rb2
+	$(BZIP2_SHARED) -2  < sample2.ref > sample2.rb2
+	$(BZIP2_SHARED) -3  < sample3.ref > sample3.rb2
+	$(BZIP2_SHARED) -d  < sample1.bz2 > sample1.tst
+	$(BZIP2_SHARED) -d  < sample2.bz2 > sample2.tst
+	$(BZIP2_SHARED) -ds < sample3.bz2 > sample3.tst
+	cmp sample1.bz2 sample1.rb2
+	cmp sample2.bz2 sample2.rb2
+	cmp sample3.bz2 sample3.rb2
+	cmp sample1.tst sample1.ref
+	cmp sample2.tst sample2.ref
+	cmp sample3.tst sample3.ref
+	@cat words3
 	rm -f libbz2.so.1.0
 	ln -s libbz2.so.1.0.4 libbz2.so.1.0
 
 clean: 
-	rm -f $(OBJS) bzip2.o libbz2.so.1.0.4 libbz2.so.1.0 bzip2-shared
-
-blocksort.o: blocksort.c
-	$(CC) $(CFLAGS) -c blocksort.c
-huffman.o: huffman.c
-	$(CC) $(CFLAGS) -c huffman.c
-crctable.o: crctable.c
-	$(CC) $(CFLAGS) -c crctable.c
-randtable.o: randtable.c
-	$(CC) $(CFLAGS) -c randtable.c
-compress.o: compress.c
-	$(CC) $(CFLAGS) -c compress.c
-decompress.o: decompress.c
-	$(CC) $(CFLAGS) -c decompress.c
-bzlib.o: bzlib.c
-	$(CC) $(CFLAGS) -c bzlib.c
+	rm -f libbz2.so.1.0.4 libbz2.so.1.0 bzip2-shared