deflate: add new deflate_quick strategy for level 1

The deflate_quick strategy is designed to provide maximum
deflate performance.

deflate_quick achieves this through:
    - only checking the first hash match
    - using a small inline SSE4.2-optimized longest_match
    - forcing a window size of 8K, and using a precomputed dist/len
      table
    - forcing the static Huffman tree and emitting codes immediately
      instead of tallying

This patch changes the scope of flush_pending, bi_windup, and
static_ltree to ZLIB_INTERNAL and moves END_BLOCK, send_code,
put_short, and send_bits to deflate.h.

Updates the configure script to enable by default for x86. On systems
without SSE4.2, fallback is to deflate_fast strategy.

Fixes #6
Fixes #8

1 files changed, 19 insertions, 0 deletions

diff --git a/configure b/configure
index ab4e06482d..a42da63d59 100755
--- a/configure
+++ b/configure
@@ -796,6 +796,9 @@ else
     HAVE_PCLMULQDQ_INTRIN=0
 fi
 
+DEFLATE_QUICK_o=""
+DEFLATE_QUICK_lo=""
+
 # Set ARCH specific FLAGS
 case "${ARCH}" in
     x86_64)
@@ -837,6 +840,12 @@ case "${ARCH}" in
             CRC_FOLDING_o=""
             CRC_FOLDING_lo=""
         fi
+
+        CFLAGS="${CFLAGS} -DUSE_QUICK"
+        SFLAGS="${SFLAGS} -DUSE_QUICK"
+
+        DEFLATE_QUICK_o="deflate_quick.o"
+        DEFLATE_QUICK_lo="deflate_quick.lo"
     ;;
     i386 | i486 | i586 | i686)
         OBJC="${OBJC} x86.o"
@@ -877,6 +886,12 @@ case "${ARCH}" in
             CRC_FOLDING_o=""
             CRC_FOLDING_lo=""
         fi
+
+        CFLAGS="${CFLAGS} -DUSE_QUICK"
+        SFLAGS="${SFLAGS} -DUSE_QUICK"
+
+        DEFLATE_QUICK_o="deflate_quick.o"
+        DEFLATE_QUICK_lo="deflate_quick.lo"
     ;;
 esac
 
@@ -915,6 +930,8 @@ echo FILL_WINDOW_SSE_o = ${FILL_WINDOW_SSE_o} >> configure.log
 echo FILL_WINDOW_SSE_lo= ${FILL_WINDOW_SSE_lo} >> configure.log
 echo CRC_FOLDING_o = ${CRC_FOLDING_o} >> configure.log
 echo CRC_FOLDING_lo= ${CRC_FOLDING_lo} >> configure.log
+echo DEFLATE_QUICK_o=${DEFLATE_QUICK_o} >> configure.log
+echo DEFLATE_QUICK_lo=${DEFLATE_QUICK_lo} >> configure.log
 
 # udpate Makefile with the configure results
 sed < Makefile.in "
@@ -948,6 +965,8 @@ sed < Makefile.in "
 /^FILL_WINDOW_SSE_lo *=/s#=.*#=$FILL_WINDOW_SSE_lo#
 /^CRC_FOLDING_o *=/s#=.*#=$CRC_FOLDING_o#
 /^CRC_FOLDING_lo *=/s#=.*#=$CRC_FOLDING_lo#
+/^DEFLATE_QUICK_o *=/s#=.*#=$DEFLATE_QUICK_o#
+/^DEFLATE_QUICK_lo *=/s#=.*#=$DEFLATE_QUICK_lo#
 " > Makefile
 
 # create zlib.pc with the configure results