diff --git a/README b/README
index 7bc588f..da0c488 100644
--- a/README
+++ b/README
@@ -1,8 +1,8 @@
 The Independent JPEG Group's JPEG software
 ==========================================
 
-README for release 8 of 10-Jan-2010
-===================================
+README for release 8a of 28-Feb-2010
+====================================
 
 This distribution contains the eighth public release of the Independent JPEG
 Group's free JPEG software.  You are welcome to redistribute this software and
@@ -254,8 +254,8 @@
 The "official" archive site for this software is www.ijg.org.
 The most recent released version can always be found there in
 directory "files".  This particular version will be archived as
-http://www.ijg.org/files/jpegsrc.v8.tar.gz, and in Windows-compatible
-"zip" archive format as http://www.ijg.org/files/jpegsr8.zip.
+http://www.ijg.org/files/jpegsrc.v8a.tar.gz, and in Windows-compatible
+"zip" archive format as http://www.ijg.org/files/jpegsr8a.zip.
 
 The JPEG FAQ (Frequently Asked Questions) article is a source of some
 general information about JPEG.
@@ -318,7 +318,7 @@
 TO DO
 =====
 
-Version 8.0 is the first release of a new generation JPEG standard
+Version 8 is the first release of a new generation JPEG standard
 to overcome the limitations of the original JPEG specification.
 More features are being prepared for coming releases...
 
diff --git a/change.log b/change.log
index 58ea3eb..56d096f 100644
--- a/change.log
+++ b/change.log
@@ -1,6 +1,18 @@
 CHANGE LOG for Independent JPEG Group's JPEG software
 
 
+Version 8a  28-Feb-2010
+-----------------------
+
+Writing tables-only datastreams via jpeg_write_tables works again.
+
+Support 32-bit BMPs (RGB image with Alpha channel) for read in cjpeg.
+Thank to Brett Blackham for the suggestion.
+
+Improve accuracy in floating point IDCT calculation.
+Thank to Robert Hooke for the hint.
+
+
 Version 8  10-Jan-2010
 ----------------------
 
diff --git a/configure b/configure
index df3506c..9916d47 100755
--- a/configure
+++ b/configure
@@ -1,6 +1,6 @@
 #! /bin/sh
 # Guess values for system-dependent variables and create Makefiles.
-# Generated by GNU Autoconf 2.65 for libjpeg 8.0.
+# Generated by GNU Autoconf 2.65 for libjpeg 8.0.1.
 #
 #
 # Copyright (C) 1992, 1993, 1994, 1995, 1996, 1998, 1999, 2000, 2001,
@@ -698,8 +698,8 @@
 # Identity of this package.
 PACKAGE_NAME='libjpeg'
 PACKAGE_TARNAME='libjpeg'
-PACKAGE_VERSION='8.0'
-PACKAGE_STRING='libjpeg 8.0'
+PACKAGE_VERSION='8.0.1'
+PACKAGE_STRING='libjpeg 8.0.1'
 PACKAGE_BUGREPORT=''
 PACKAGE_URL=''
 
@@ -1430,7 +1430,7 @@
   # Omit some internal or obsolete options to make the list less imposing.
   # This message is too long to be a string in the A/UX 3.1 sh.
   cat <<_ACEOF
-\`configure' configures libjpeg 8.0 to adapt to many kinds of systems.
+\`configure' configures libjpeg 8.0.1 to adapt to many kinds of systems.
 
 Usage: $0 [OPTION]... [VAR=VALUE]...
 
@@ -1501,7 +1501,7 @@
 
 if test -n "$ac_init_help"; then
   case $ac_init_help in
-     short | recursive ) echo "Configuration of libjpeg 8.0:";;
+     short | recursive ) echo "Configuration of libjpeg 8.0.1:";;
    esac
   cat <<\_ACEOF
 
@@ -1608,7 +1608,7 @@
 test -n "$ac_init_help" && exit $ac_status
 if $ac_init_version; then
   cat <<\_ACEOF
-libjpeg configure 8.0
+libjpeg configure 8.0.1
 generated by GNU Autoconf 2.65
 
 Copyright (C) 2009 Free Software Foundation, Inc.
@@ -1973,7 +1973,7 @@
 This file contains any messages produced by compilers while
 running configure, to aid debugging if configure makes a mistake.
 
-It was created by libjpeg $as_me 8.0, which was
+It was created by libjpeg $as_me 8.0.1, which was
 generated by GNU Autoconf 2.65.  Invocation command line was
 
   $ $0 $@
@@ -2905,7 +2905,7 @@
 
 # Define the identity of the package.
  PACKAGE='libjpeg'
- VERSION='8.0'
+ VERSION='8.0.1'
 
 
 cat >>confdefs.h <<_ACEOF
@@ -12675,7 +12675,7 @@
 { $as_echo "$as_me:${as_lineno-$LINENO}: checking libjpeg version number" >&5
 $as_echo_n "checking libjpeg version number... " >&6; }
 JPEG_LIB_VERSION=`sed -e '/^#define JPEG_LIB_VERSION/!d' -e 's/^[^0-9]*\([0-9][0-9]*\).*$/\1/' $srcdir/jpeglib.h`
-JPEG_LIB_VERSION="`expr $JPEG_LIB_VERSION / 10`:`expr $JPEG_LIB_VERSION % 10`"
+JPEG_LIB_VERSION="`expr $JPEG_LIB_VERSION / 10`:1"
 { $as_echo "$as_me:${as_lineno-$LINENO}: result: $JPEG_LIB_VERSION" >&5
 $as_echo "$JPEG_LIB_VERSION" >&6; }
 
@@ -13215,7 +13215,7 @@
 # report actual input values of CONFIG_FILES etc. instead of their
 # values after options handling.
 ac_log="
-This file was extended by libjpeg $as_me 8.0, which was
+This file was extended by libjpeg $as_me 8.0.1, which was
 generated by GNU Autoconf 2.65.  Invocation command line was
 
   CONFIG_FILES    = $CONFIG_FILES
@@ -13281,7 +13281,7 @@
 cat >>$CONFIG_STATUS <<_ACEOF || ac_write_fail=1
 ac_cs_config="`$as_echo "$ac_configure_args" | sed 's/^ //; s/[\\""\`\$]/\\\\&/g'`"
 ac_cs_version="\\
-libjpeg config.status 8.0
+libjpeg config.status 8.0.1
 configured by $0, generated by GNU Autoconf 2.65,
   with options \\"\$ac_cs_config\\"
 
diff --git a/configure.ac b/configure.ac
index c83e671..af8bfa1 100644
--- a/configure.ac
+++ b/configure.ac
@@ -5,7 +5,7 @@
 # Configure script for IJG libjpeg
 #
 
-AC_INIT([libjpeg], [8.0])
+AC_INIT([libjpeg], [8.0.1])
 
 # Directory where autotools helper scripts lives.
 AC_CONFIG_AUX_DIR([.])
@@ -309,7 +309,7 @@
 # Extract the library version ID from jpeglib.h.
 AC_MSG_CHECKING([libjpeg version number])
 [JPEG_LIB_VERSION=`sed -e '/^#define JPEG_LIB_VERSION/!d' -e 's/^[^0-9]*\([0-9][0-9]*\).*$/\1/' $srcdir/jpeglib.h`]
-[JPEG_LIB_VERSION="`expr $JPEG_LIB_VERSION / 10`:`expr $JPEG_LIB_VERSION % 10`"]
+[JPEG_LIB_VERSION="`expr $JPEG_LIB_VERSION / 10`:1"]
 AC_MSG_RESULT([$JPEG_LIB_VERSION])
 AC_SUBST([JPEG_LIB_VERSION])
 
diff --git a/jcapimin.c b/jcapimin.c
index 563ab42..639ce86 100644
--- a/jcapimin.c
+++ b/jcapimin.c
@@ -2,6 +2,7 @@
  * jcapimin.c
  *
  * Copyright (C) 1994-1998, Thomas G. Lane.
+ * Modified 2003-2010 by Guido Vollbeding.
  * This file is part of the Independent JPEG Group's software.
  * For conditions of distribution and use, see the accompanying README file.
  *
@@ -73,6 +74,11 @@
     cinfo->ac_huff_tbl_ptrs[i] = NULL;
   }
 
+  /* Must do it here for emit_dqt in case jpeg_write_tables is used */
+  cinfo->block_size = DCTSIZE;
+  cinfo->natural_order = jpeg_natural_order;
+  cinfo->lim_Se = DCTSIZE2-1;
+
   cinfo->script_space = NULL;
 
   cinfo->input_gamma = 1.0;	/* in case application forgets */
diff --git a/jcmaster.c b/jcmaster.c
index 5284e58..660883f 100644
--- a/jcmaster.c
+++ b/jcmaster.c
@@ -187,10 +187,6 @@
   cinfo->min_DCT_v_scaled_size = DCTSIZE;
 
 #endif /* DCT_SCALING_SUPPORTED */
-
-  cinfo->block_size = DCTSIZE;
-  cinfo->natural_order = jpeg_natural_order;
-  cinfo->lim_Se = DCTSIZE2-1;
 }
 
 
diff --git a/jddctmgr.c b/jddctmgr.c
index bdbde34..0ded9d5 100644
--- a/jddctmgr.c
+++ b/jddctmgr.c
@@ -2,6 +2,7 @@
  * jddctmgr.c
  *
  * Copyright (C) 1994-1996, Thomas G. Lane.
+ * Modified 2002-2010 by Guido Vollbeding.
  * This file is part of the Independent JPEG Group's software.
  * For conditions of distribution and use, see the accompanying README file.
  *
@@ -324,6 +325,7 @@
 	 * coefficients scaled by scalefactor[row]*scalefactor[col], where
 	 *   scalefactor[0] = 1
 	 *   scalefactor[k] = cos(k*PI/16) * sqrt(2)    for k=1..7
+	 * We apply a further scale factor of 1/8.
 	 */
 	FLOAT_MULT_TYPE * fmtbl = (FLOAT_MULT_TYPE *) compptr->dct_table;
 	int row, col;
@@ -337,7 +339,7 @@
 	  for (col = 0; col < DCTSIZE; col++) {
 	    fmtbl[i] = (FLOAT_MULT_TYPE)
 	      ((double) qtbl->quantval[i] *
-	       aanscalefactor[row] * aanscalefactor[col]);
+	       aanscalefactor[row] * aanscalefactor[col] * 0.125);
 	    i++;
 	  }
 	}
diff --git a/jidctflt.c b/jidctflt.c
index 0188ce3..23ae9d3 100644
--- a/jidctflt.c
+++ b/jidctflt.c
@@ -2,6 +2,7 @@
  * jidctflt.c
  *
  * Copyright (C) 1994-1998, Thomas G. Lane.
+ * Modified 2010 by Guido Vollbeding.
  * This file is part of the Independent JPEG Group's software.
  * For conditions of distribution and use, see the accompanying README file.
  *
@@ -76,10 +77,9 @@
   FLOAT_MULT_TYPE * quantptr;
   FAST_FLOAT * wsptr;
   JSAMPROW outptr;
-  JSAMPLE *range_limit = IDCT_range_limit(cinfo);
+  JSAMPLE *range_limit = cinfo->sample_range_limit;
   int ctr;
   FAST_FLOAT workspace[DCTSIZE2]; /* buffers data between passes */
-  SHIFT_TEMPS
 
   /* Pass 1: process columns from input, store into work array. */
 
@@ -152,12 +152,12 @@
     tmp11 = (z11 - z13) * ((FAST_FLOAT) 1.414213562); /* 2*c4 */
 
     z5 = (z10 + z12) * ((FAST_FLOAT) 1.847759065); /* 2*c2 */
-    tmp10 = ((FAST_FLOAT) 1.082392200) * z12 - z5; /* 2*(c2-c6) */
-    tmp12 = ((FAST_FLOAT) -2.613125930) * z10 + z5; /* -2*(c2+c6) */
+    tmp10 = z5 - z12 * ((FAST_FLOAT) 1.082392200); /* 2*(c2-c6) */
+    tmp12 = z5 - z10 * ((FAST_FLOAT) 2.613125930); /* 2*(c2+c6) */
 
     tmp6 = tmp12 - tmp7;	/* phase 2 */
     tmp5 = tmp11 - tmp6;
-    tmp4 = tmp10 + tmp5;
+    tmp4 = tmp10 - tmp5;
 
     wsptr[DCTSIZE*0] = tmp0 + tmp7;
     wsptr[DCTSIZE*7] = tmp0 - tmp7;
@@ -165,8 +165,8 @@
     wsptr[DCTSIZE*6] = tmp1 - tmp6;
     wsptr[DCTSIZE*2] = tmp2 + tmp5;
     wsptr[DCTSIZE*5] = tmp2 - tmp5;
-    wsptr[DCTSIZE*4] = tmp3 + tmp4;
-    wsptr[DCTSIZE*3] = tmp3 - tmp4;
+    wsptr[DCTSIZE*3] = tmp3 + tmp4;
+    wsptr[DCTSIZE*4] = tmp3 - tmp4;
 
     inptr++;			/* advance pointers to next column */
     quantptr++;
@@ -174,7 +174,6 @@
   }
   
   /* Pass 2: process rows from work array, store into output array. */
-  /* Note that we must descale the results by a factor of 8 == 2**3. */
 
   wsptr = workspace;
   for (ctr = 0; ctr < DCTSIZE; ctr++) {
@@ -187,8 +186,10 @@
     
     /* Even part */
 
-    tmp10 = wsptr[0] + wsptr[4];
-    tmp11 = wsptr[0] - wsptr[4];
+    /* Apply signed->unsigned and prepare float->int conversion */
+    z5 = wsptr[0] + ((FAST_FLOAT) CENTERJSAMPLE + (FAST_FLOAT) 0.5);
+    tmp10 = z5 + wsptr[4];
+    tmp11 = z5 - wsptr[4];
 
     tmp13 = wsptr[2] + wsptr[6];
     tmp12 = (wsptr[2] - wsptr[6]) * ((FAST_FLOAT) 1.414213562) - tmp13;
@@ -209,31 +210,23 @@
     tmp11 = (z11 - z13) * ((FAST_FLOAT) 1.414213562);
 
     z5 = (z10 + z12) * ((FAST_FLOAT) 1.847759065); /* 2*c2 */
-    tmp10 = ((FAST_FLOAT) 1.082392200) * z12 - z5; /* 2*(c2-c6) */
-    tmp12 = ((FAST_FLOAT) -2.613125930) * z10 + z5; /* -2*(c2+c6) */
+    tmp10 = z5 - z12 * ((FAST_FLOAT) 1.082392200); /* 2*(c2-c6) */
+    tmp12 = z5 - z10 * ((FAST_FLOAT) 2.613125930); /* 2*(c2+c6) */
 
     tmp6 = tmp12 - tmp7;
     tmp5 = tmp11 - tmp6;
-    tmp4 = tmp10 + tmp5;
+    tmp4 = tmp10 - tmp5;
 
-    /* Final output stage: scale down by a factor of 8 and range-limit */
+    /* Final output stage: float->int conversion and range-limit */
 
-    outptr[0] = range_limit[(int) DESCALE((INT32) (tmp0 + tmp7), 3)
-			    & RANGE_MASK];
-    outptr[7] = range_limit[(int) DESCALE((INT32) (tmp0 - tmp7), 3)
-			    & RANGE_MASK];
-    outptr[1] = range_limit[(int) DESCALE((INT32) (tmp1 + tmp6), 3)
-			    & RANGE_MASK];
-    outptr[6] = range_limit[(int) DESCALE((INT32) (tmp1 - tmp6), 3)
-			    & RANGE_MASK];
-    outptr[2] = range_limit[(int) DESCALE((INT32) (tmp2 + tmp5), 3)
-			    & RANGE_MASK];
-    outptr[5] = range_limit[(int) DESCALE((INT32) (tmp2 - tmp5), 3)
-			    & RANGE_MASK];
-    outptr[4] = range_limit[(int) DESCALE((INT32) (tmp3 + tmp4), 3)
-			    & RANGE_MASK];
-    outptr[3] = range_limit[(int) DESCALE((INT32) (tmp3 - tmp4), 3)
-			    & RANGE_MASK];
+    outptr[0] = range_limit[((int) (tmp0 + tmp7)) & RANGE_MASK];
+    outptr[7] = range_limit[((int) (tmp0 - tmp7)) & RANGE_MASK];
+    outptr[1] = range_limit[((int) (tmp1 + tmp6)) & RANGE_MASK];
+    outptr[6] = range_limit[((int) (tmp1 - tmp6)) & RANGE_MASK];
+    outptr[2] = range_limit[((int) (tmp2 + tmp5)) & RANGE_MASK];
+    outptr[5] = range_limit[((int) (tmp2 - tmp5)) & RANGE_MASK];
+    outptr[3] = range_limit[((int) (tmp3 + tmp4)) & RANGE_MASK];
+    outptr[4] = range_limit[((int) (tmp3 - tmp4)) & RANGE_MASK];
     
     wsptr += DCTSIZE;		/* advance pointer to next row */
   }
diff --git a/jpegtran.c b/jpegtran.c
index 4f76ae7..8cb3d80 100644
--- a/jpegtran.c
+++ b/jpegtran.c
@@ -1,7 +1,7 @@
 /*
  * jpegtran.c
  *
- * Copyright (C) 1995-2009, Thomas G. Lane, Guido Vollbeding.
+ * Copyright (C) 1995-2010, Thomas G. Lane, Guido Vollbeding.
  * This file is part of the Independent JPEG Group's software.
  * For conditions of distribution and use, see the accompanying README file.
  *
@@ -63,18 +63,20 @@
 #ifdef C_PROGRESSIVE_SUPPORTED
   fprintf(stderr, "  -progressive   Create progressive JPEG file\n");
 #endif
-#if TRANSFORMS_SUPPORTED
   fprintf(stderr, "Switches for modifying the image:\n");
+#if TRANSFORMS_SUPPORTED
   fprintf(stderr, "  -crop WxH+X+Y  Crop to a rectangular subarea\n");
   fprintf(stderr, "  -grayscale     Reduce to grayscale (omit color data)\n");
   fprintf(stderr, "  -flip [horizontal|vertical]  Mirror image (left-right or top-bottom)\n");
   fprintf(stderr, "  -perfect       Fail if there is non-transformable edge blocks\n");
   fprintf(stderr, "  -rotate [90|180|270]         Rotate image (degrees clockwise)\n");
+#endif
   fprintf(stderr, "  -scale M/N     Scale output image by fraction M/N, eg, 1/8\n");
+#if TRANSFORMS_SUPPORTED
   fprintf(stderr, "  -transpose     Transpose image\n");
   fprintf(stderr, "  -transverse    Transverse transpose image\n");
   fprintf(stderr, "  -trim          Drop non-transformable edge blocks\n");
-#endif /* TRANSFORMS_SUPPORTED */
+#endif
   fprintf(stderr, "Switches for advanced users:\n");
   fprintf(stderr, "  -restart N     Set restart interval in rows, or in blocks with B\n");
   fprintf(stderr, "  -maxmemory N   Maximum memory to use (in kbytes)\n");
diff --git a/jversion.h b/jversion.h
index 0c4e6ea..e7d1814 100644
--- a/jversion.h
+++ b/jversion.h
@@ -9,6 +9,6 @@
  */
 
 
-#define JVERSION	"8  10-Jan-2010"
+#define JVERSION	"8a  28-Feb-2010"
 
 #define JCOPYRIGHT	"Copyright (C) 2010, Thomas G. Lane, Guido Vollbeding"
diff --git a/rdbmp.c b/rdbmp.c
index f971180..fd773d4 100644
--- a/rdbmp.c
+++ b/rdbmp.c
@@ -2,7 +2,7 @@
  * rdbmp.c
  *
  * Copyright (C) 1994-1996, Thomas G. Lane.
- * Modified 2009 by Guido Vollbeding.
+ * Modified 2009-2010 by Guido Vollbeding.
  * This file is part of the Independent JPEG Group's software.
  * For conditions of distribution and use, see the accompanying README file.
  *
@@ -178,10 +178,41 @@
 }
 
 
+METHODDEF(JDIMENSION)
+get_32bit_row (j_compress_ptr cinfo, cjpeg_source_ptr sinfo)
+/* This version is for reading 32-bit pixels */
+{
+  bmp_source_ptr source = (bmp_source_ptr) sinfo;
+  JSAMPARRAY image_ptr;
+  register JSAMPROW inptr, outptr;
+  register JDIMENSION col;
+
+  /* Fetch next row from virtual array */
+  source->source_row--;
+  image_ptr = (*cinfo->mem->access_virt_sarray)
+    ((j_common_ptr) cinfo, source->whole_image,
+     source->source_row, (JDIMENSION) 1, FALSE);
+  /* Transfer data.  Note source values are in BGR order
+   * (even though Microsoft's own documents say the opposite).
+   */
+  inptr = image_ptr[0];
+  outptr = source->pub.buffer[0];
+  for (col = cinfo->image_width; col > 0; col--) {
+    outptr[2] = *inptr++;	/* can omit GETJSAMPLE() safely */
+    outptr[1] = *inptr++;
+    outptr[0] = *inptr++;
+    inptr++;			/* skip the 4th byte (Alpha channel) */
+    outptr += 3;
+  }
+
+  return 1;
+}
+
+
 /*
  * This method loads the image into whole_image during the first call on
  * get_pixel_rows.  The get_pixel_rows pointer is then adjusted to call
- * get_8bit_row or get_24bit_row on subsequent calls.
+ * get_8bit_row, get_24bit_row, or get_32bit_row on subsequent calls.
  */
 
 METHODDEF(JDIMENSION)
@@ -224,6 +255,9 @@
   case 24:
     source->pub.get_pixel_rows = get_24bit_row;
     break;
+  case 32:
+    source->pub.get_pixel_rows = get_32bit_row;
+    break;
   default:
     ERREXIT(cinfo, JERR_BMP_BADDEPTH);
   }
@@ -324,6 +358,9 @@
     case 24:			/* RGB image */
       TRACEMS2(cinfo, 1, JTRC_BMP, (int) biWidth, (int) biHeight);
       break;
+    case 32:			/* RGB image + Alpha channel */
+      TRACEMS2(cinfo, 1, JTRC_BMP, (int) biWidth, (int) biHeight);
+      break;
     default:
       ERREXIT(cinfo, JERR_BMP_BADDEPTH);
       break;
@@ -377,6 +414,8 @@
   /* Compute row width in file, including padding to 4-byte boundary */
   if (source->bits_per_pixel == 24)
     row_width = (JDIMENSION) (biWidth * 3);
+  else if (source->bits_per_pixel == 32)
+    row_width = (JDIMENSION) (biWidth * 4);
   else
     row_width = (JDIMENSION) biWidth;
   while ((row_width & 3) != 0) row_width++;