/*****************************************************************************
* Common declarations
*****************************************************************************/
-#define elem_t short
+
+#ifndef VDEC_DFT
+typedef short elem_t;
+#else
+typedef int elem_t;
+#endif
+
+struct vdec_thread_s;
+
+#define SPARSE_SCALE_FACTOR 8
+#define DCTSIZE 8 /* 8*8 DCT */
+
+/*****************************************************************************
+ * Macros
+ *****************************************************************************/
+
+/* We assume that right shift corresponds to signed division by 2 with
+ * rounding towards minus infinity. This is correct for typical "arithmetic
+ * shift" instructions that shift in copies of the sign bit. But some
+ * C compilers implement >> with an unsigned shift. For these machines you
+ * must define RIGHT_SHIFT_IS_UNSIGNED.
+ * RIGHT_SHIFT provides a proper signed right shift of an INT32 quantity.
+ * It is only applied with constant shift counts. SHIFT_TEMPS must be
+ * included in the variables of any routine using RIGHT_SHIFT.
+ */
+
+#ifdef RIGHT_SHIFT_IS_UNSIGNED
+#define SHIFT_TEMPS INT32 shift_temp;
+#define RIGHT_SHIFT(x,shft) \
+ ((shift_temp = (x)) < 0 ? \
+ (shift_temp >> (shft)) | ((~((INT32) 0)) << (32-(shft))) : \
+ (shift_temp >> (shft)))
+#else
+#define SHIFT_TEMPS
+#define RIGHT_SHIFT(x,shft) ((x) >> (shft))
+#endif
+
+/*
+ * A 2-D IDCT can be done by 1-D IDCT on each row followed by 1-D IDCT
+ * on each column. Direct algorithms are also available, but they are
+ * much more complex and seem not to be any faster when reduced to code.
+ *
+ * The poop on this scaling stuff is as follows:
+ *
+ * Each 1-D IDCT step produces outputs which are a factor of sqrt(N)
+ * larger than the true IDCT outputs. The final outputs are therefore
+ * a factor of N larger than desired; since N=8 this can be cured by
+ * a simple right shift at the end of the algorithm. The advantage of
+ * this arrangement is that we save two multiplications per 1-D IDCT,
+ * because the y0 and y4 inputs need not be divided by sqrt(N).
+ *
+ * We have to do addition and subtraction of the integer inputs, which
+ * is no problem, and multiplication by fractional constants, which is
+ * a problem to do in integer arithmetic. We multiply all the constants
+ * by CONST_SCALE and convert them to integer constants (thus retaining
+ * CONST_BITS bits of precision in the constants). After doing a
+ * multiplication we have to divide the product by CONST_SCALE, with proper
+ * rounding, to produce the correct output. This division can be done
+ * cheaply as a right shift of CONST_BITS bits. We postpone shifting
+ * as long as possible so that partial sums can be added together with
+ * full fractional precision.
+ *
+ * The outputs of the first pass are scaled up by PASS1_BITS bits so that
+ * they are represented to better-than-integral precision. These outputs
+ * require BITS_IN_JSAMPLE + PASS1_BITS + 3 bits; this fits in a 16-bit word
+ * with the recommended scaling. (To scale up 12-bit sample data further, an
+ * intermediate INT32 array would be needed.)
+ *
+ * To avoid overflow of the 32-bit intermediate results in pass 2, we must
+ * have BITS_IN_JSAMPLE + CONST_BITS + PASS1_BITS <= 26. Error analysis
+ * shows that the values given below are the most effective.
+ */
+
+#ifdef EIGHT_BIT_SAMPLES
+#define PASS1_BITS 2
+#else
+#define PASS1_BITS 1 /* lose a little precision to avoid overflow */
+#endif
+
+#define ONE ((INT32) 1)
+
+#define CONST_SCALE (ONE << CONST_BITS)
+
+/* Convert a positive real constant to an integer scaled by CONST_SCALE.
+ * IMPORTANT: if your compiler doesn't do this arithmetic at compile time,
+ * you will pay a significant penalty in run time. In that case, figure
+ * the correct integer constant values and insert them by hand.
+ */
+
+#define FIX(x) ((INT32) ((x) * CONST_SCALE + 0.5))
+
+/* When adding two opposite-signed fixes, the 0.5 cancels */
+#define FIX2(x) ((INT32) ((x) * CONST_SCALE))
+
+/* Descale and correctly round an INT32 value that's scaled by N bits.
+ * We assume RIGHT_SHIFT rounds towards minus infinity, so adding
+ * the fudge factor is correct for either sign of X.
+ */
+
+#define DESCALE(x,n) RIGHT_SHIFT((x) + (ONE << ((n)-1)), n)
+
+/* Multiply an INT32 variable by an INT32 constant to yield an INT32 result.
+ * For 8-bit samples with the recommended scaling, all the variable
+ * and constant values involved are no more than 16 bits wide, so a
+ * 16x16->32 bit multiply can be used instead of a full 32x32 multiply;
+ * this provides a useful speedup on many machines.
+ * There is no way to specify a 16x16->32 multiply in portable C, but
+ * some C compilers will do the right thing if you provide the correct
+ * combination of casts.
+ * NB: for 12-bit samples, a full 32-bit multiplication will be needed.
+ */
+
+#ifdef EIGHT_BIT_SAMPLES
+#ifdef SHORTxSHORT_32 /* may work if 'int' is 32 bits */
+#define MULTIPLY(var,const) (((INT16) (var)) * ((INT16) (const)))
+#endif
+#ifdef SHORTxLCONST_32 /* known to work with Microsoft C 6.0 */
+#define MULTIPLY(var,const) (((INT16) (var)) * ((INT32) (const)))
+#endif
+#endif
+
+#ifndef MULTIPLY /* default definition */
+#define MULTIPLY(var,const) ((var) * (const))
+#endif
/*****************************************************************************
* Function pointers
*****************************************************************************/
-typedef void (*f_idct_t)( elem_t*, int );
+typedef void (*f_idct_t)( struct vdec_thread_s *, elem_t*, int );
/*****************************************************************************
* Prototypes
*****************************************************************************/
-void vdec_DummyIDCT( elem_t*, int );
-void vdec_SparseIDCT( elem_t*, int );
-void vdec_IDCT( elem_t*, int );
+void vdec_DummyIDCT( struct vdec_thread_s *, elem_t*, int );
+void vdec_InitIDCT (struct vdec_thread_s * p_vdec);
+void vdec_SparseIDCT( struct vdec_thread_s *, elem_t*, int );
+void vdec_IDCT( struct vdec_thread_s *, elem_t*, int );