Update libjpeg_turbo to 1.4.90 from https://github.com/libjpeg-turbo/

jidctflt.c

Index: jidctflt.c
diff --git a/jidctflt.c b/jidctflt.c
index 0188ce3dfcd2ce2ebaa57c17da22101de01b6f2a..68c521ed7eebe5aa3b65b6216705b12942be341d 100644
--- a/jidctflt.c
+++ b/jidctflt.c
@@ -1,9 +1,13 @@
 /*
  * jidctflt.c
  *
+ * This file was part of the Independent JPEG Group's software:
  * Copyright (C) 1994-1998, Thomas G. Lane.
- * This file is part of the Independent JPEG Group's software.
- * For conditions of distribution and use, see the accompanying README file.
+ * Modified 2010 by Guido Vollbeding.
+ * libjpeg-turbo Modifications:
+ * Copyright (C) 2014, D. R. Commander.
+ * For conditions of distribution and use, see the accompanying README.ijg
+ * file.
  *
  * This file contains a floating-point implementation of the
  * inverse DCT (Discrete Cosine Transform).  In the IJG code, this routine
@@ -22,8 +26,8 @@
  * This implementation is based on Arai, Agui, and Nakajima's algorithm for
  * scaled DCT.  Their original paper (Trans. IEICE E-71(11):1095) is in
  * Japanese, but the algorithm is described in the Pennebaker & Mitchell
- * JPEG textbook (see REFERENCES section in file README).  The following code
- * is based directly on figure 4-8 in P&M.
+ * JPEG textbook (see REFERENCES section in file README.ijg).  The following
+ * code is based directly on figure 4-8 in P&M.
  * While an 8-point DCT cannot be done in less than 11 multiplies, it is
  * possible to arrange the computation so that many of the multiplies are
  * simple scalings of the final outputs.  These multiplies can then be
@@ -39,7 +43,7 @@
 #define JPEG_INTERNALS
 #include "jinclude.h"
 #include "jpeglib.h"
-#include "jdct.h"		/* Private declarations for DCT subsystem */
+#include "jdct.h"               /* Private declarations for DCT subsystem */
 
 #ifdef DCT_FLOAT_SUPPORTED
 
@@ -65,21 +69,21 @@
  */
 
 GLOBAL(void)
-jpeg_idct_float (j_decompress_ptr cinfo, jpeg_component_info * compptr,
-		 JCOEFPTR coef_block,
-		 JSAMPARRAY output_buf, JDIMENSION output_col)
+jpeg_idct_float (j_decompress_ptr cinfo, jpeg_component_info *compptr,
+                 JCOEFPTR coef_block,
+                 JSAMPARRAY output_buf, JDIMENSION output_col)
 {
   FAST_FLOAT tmp0, tmp1, tmp2, tmp3, tmp4, tmp5, tmp6, tmp7;
   FAST_FLOAT tmp10, tmp11, tmp12, tmp13;
   FAST_FLOAT z5, z10, z11, z12, z13;
   JCOEFPTR inptr;
-  FLOAT_MULT_TYPE * quantptr;
-  FAST_FLOAT * wsptr;
+  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
+  #define _0_125 ((FLOAT_MULT_TYPE)0.125)
 
   /* Pass 1: process columns from input, store into work array. */
 
@@ -95,14 +99,15 @@ jpeg_idct_float (j_decompress_ptr cinfo, jpeg_component_info * compptr,
      * With typical images and quantization tables, half or more of the
      * column DCT calculations can be simplified this way.
      */
-    
+
     if (inptr[DCTSIZE*1] == 0 && inptr[DCTSIZE*2] == 0 &&
-	inptr[DCTSIZE*3] == 0 && inptr[DCTSIZE*4] == 0 &&
-	inptr[DCTSIZE*5] == 0 && inptr[DCTSIZE*6] == 0 &&
-	inptr[DCTSIZE*7] == 0) {
+        inptr[DCTSIZE*3] == 0 && inptr[DCTSIZE*4] == 0 &&
+        inptr[DCTSIZE*5] == 0 && inptr[DCTSIZE*6] == 0 &&
+        inptr[DCTSIZE*7] == 0) {
       /* AC terms all zero */
-      FAST_FLOAT dcval = DEQUANTIZE(inptr[DCTSIZE*0], quantptr[DCTSIZE*0]);
-      
+      FAST_FLOAT dcval = DEQUANTIZE(inptr[DCTSIZE*0],
+                                    quantptr[DCTSIZE*0] * _0_125);
+
       wsptr[DCTSIZE*0] = dcval;
       wsptr[DCTSIZE*1] = dcval;
       wsptr[DCTSIZE*2] = dcval;
@@ -111,53 +116,53 @@ jpeg_idct_float (j_decompress_ptr cinfo, jpeg_component_info * compptr,
       wsptr[DCTSIZE*5] = dcval;
       wsptr[DCTSIZE*6] = dcval;
       wsptr[DCTSIZE*7] = dcval;
-      
-      inptr++;			/* advance pointers to next column */
+
+      inptr++;                  /* advance pointers to next column */
       quantptr++;
       wsptr++;
       continue;
     }
-    
+
     /* Even part */
 
-    tmp0 = DEQUANTIZE(inptr[DCTSIZE*0], quantptr[DCTSIZE*0]);
-    tmp1 = DEQUANTIZE(inptr[DCTSIZE*2], quantptr[DCTSIZE*2]);
-    tmp2 = DEQUANTIZE(inptr[DCTSIZE*4], quantptr[DCTSIZE*4]);
-    tmp3 = DEQUANTIZE(inptr[DCTSIZE*6], quantptr[DCTSIZE*6]);
+    tmp0 = DEQUANTIZE(inptr[DCTSIZE*0], quantptr[DCTSIZE*0] * _0_125);
+    tmp1 = DEQUANTIZE(inptr[DCTSIZE*2], quantptr[DCTSIZE*2] * _0_125);
+    tmp2 = DEQUANTIZE(inptr[DCTSIZE*4], quantptr[DCTSIZE*4] * _0_125);
+    tmp3 = DEQUANTIZE(inptr[DCTSIZE*6], quantptr[DCTSIZE*6] * _0_125);
 
-    tmp10 = tmp0 + tmp2;	/* phase 3 */
+    tmp10 = tmp0 + tmp2;        /* phase 3 */
     tmp11 = tmp0 - tmp2;
 
-    tmp13 = tmp1 + tmp3;	/* phases 5-3 */
+    tmp13 = tmp1 + tmp3;        /* phases 5-3 */
     tmp12 = (tmp1 - tmp3) * ((FAST_FLOAT) 1.414213562) - tmp13; /* 2*c4 */
 
-    tmp0 = tmp10 + tmp13;	/* phase 2 */
+    tmp0 = tmp10 + tmp13;       /* phase 2 */
     tmp3 = tmp10 - tmp13;
     tmp1 = tmp11 + tmp12;
     tmp2 = tmp11 - tmp12;
-    
+
     /* Odd part */
 
-    tmp4 = DEQUANTIZE(inptr[DCTSIZE*1], quantptr[DCTSIZE*1]);
-    tmp5 = DEQUANTIZE(inptr[DCTSIZE*3], quantptr[DCTSIZE*3]);
-    tmp6 = DEQUANTIZE(inptr[DCTSIZE*5], quantptr[DCTSIZE*5]);
-    tmp7 = DEQUANTIZE(inptr[DCTSIZE*7], quantptr[DCTSIZE*7]);
+    tmp4 = DEQUANTIZE(inptr[DCTSIZE*1], quantptr[DCTSIZE*1] * _0_125);
+    tmp5 = DEQUANTIZE(inptr[DCTSIZE*3], quantptr[DCTSIZE*3] * _0_125);
+    tmp6 = DEQUANTIZE(inptr[DCTSIZE*5], quantptr[DCTSIZE*5] * _0_125);
+    tmp7 = DEQUANTIZE(inptr[DCTSIZE*7], quantptr[DCTSIZE*7] * _0_125);
 
-    z13 = tmp6 + tmp5;		/* phase 6 */
+    z13 = tmp6 + tmp5;          /* phase 6 */
     z10 = tmp6 - tmp5;
     z11 = tmp4 + tmp7;
     z12 = tmp4 - tmp7;
 
-    tmp7 = z11 + z13;		/* phase 5 */
+    tmp7 = z11 + z13;           /* phase 5 */
     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 */
+    tmp6 = tmp12 - tmp7;        /* phase 2 */
     tmp5 = tmp11 - tmp6;
-    tmp4 = tmp10 + tmp5;
+    tmp4 = tmp10 - tmp5;
 
     wsptr[DCTSIZE*0] = tmp0 + tmp7;
     wsptr[DCTSIZE*7] = tmp0 - tmp7;
@@ -165,16 +170,15 @@ jpeg_idct_float (j_decompress_ptr cinfo, jpeg_component_info * compptr,
     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 */
+    inptr++;                    /* advance pointers to next column */
     quantptr++;
     wsptr++;
   }
-  
+
   /* 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++) {
@@ -184,11 +188,13 @@ jpeg_idct_float (j_decompress_ptr cinfo, jpeg_component_info * compptr,
      * the simplification applies less often (typically 5% to 10% of the time).
      * And testing floats for zero is relatively expensive, so we don't bother.
      */
-    
+
     /* 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;
@@ -209,33 +215,25 @@ jpeg_idct_float (j_decompress_ptr cinfo, jpeg_component_info * compptr,
     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;
-
-    /* Final output stage: scale down by a factor of 8 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];
-    
-    wsptr += DCTSIZE;		/* advance pointer to next row */
+    tmp4 = tmp10 - tmp5;
+
+    /* Final output stage: float->int conversion and range-limit */
+
+    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 */
   }
 }