a910049aea
This is a proof of concept RTCD implementation to replace the current
system of nested includes, prototypes, INVOKE macros, etc. Currently
only the decoder specific functions are implemented in the new system.
Additional functions will be added in subsequent commits.
Overview:
RTCD "functions" are implemented as either a global function pointer
or a macro (when only one eligible specialization available).
Functions which have RTCD specializations are listed using a simple
DSL identifying the function's base name, its prototype, and the
architecture extensions that specializations are available for.
Advantages over the old system:
- No INVOKE macros. A call to an RTCD function looks like an ordinary
function call.
- No need to pass vtables around.
- If there is only one eligible function to call, the function is
called directly, rather than indirecting through a function pointer.
- Supports the notion of "required" extensions, so in combination with
the above, on x86_64 if the best function available is sse2 or lower
it will be called directly, since all x86_64 platforms implement
sse2.
- Elides all references to functions which will never be called, which
could reduce binary size. For example if sse2 is required and there
are both mmx and sse2 implementations of a certain function, the
code will have no link time references to the mmx code.
- Significantly easier to add a new function, just one file to edit.
Disadvantages:
- Requires global writable data (though this is not a new requirement)
- 1 new generated source file.
Change-Id: Iae6edab65315f79c168485c96872641c5aa09d55
129 lines
3.5 KiB
C
129 lines
3.5 KiB
C
/*
|
|
* Copyright (c) 2010 The WebM project authors. All Rights Reserved.
|
|
*
|
|
* Use of this source code is governed by a BSD-style license
|
|
* that can be found in the LICENSE file in the root of the source
|
|
* tree. An additional intellectual property rights grant can be found
|
|
* in the file PATENTS. All contributing project authors may
|
|
* be found in the AUTHORS file in the root of the source tree.
|
|
*/
|
|
|
|
#include "vpx_config.h"
|
|
#include "vpx_rtcd.h"
|
|
#include "vp8/common/idct.h"
|
|
#include "vp8/common/blockd.h"
|
|
|
|
extern void vp8_dequantize_b_impl_mmx(short *sq, short *dq, short *q);
|
|
|
|
void vp8_dequantize_b_mmx(BLOCKD *d, short *DQC)
|
|
{
|
|
short *sq = (short *) d->qcoeff;
|
|
short *dq = (short *) d->dqcoeff;
|
|
|
|
vp8_dequantize_b_impl_mmx(sq, dq, DQC);
|
|
}
|
|
|
|
void vp8_dequant_idct_add_y_block_mmx
|
|
(short *q, short *dq,
|
|
unsigned char *dst, int stride, char *eobs)
|
|
{
|
|
int i;
|
|
|
|
for (i = 0; i < 4; i++)
|
|
{
|
|
if (eobs[0] > 1)
|
|
vp8_dequant_idct_add_mmx (q, dq, dst, stride);
|
|
else if (eobs[0] == 1)
|
|
{
|
|
vp8_dc_only_idct_add_mmx (q[0]*dq[0], dst, stride, dst, stride);
|
|
((int *)q)[0] = 0;
|
|
}
|
|
|
|
if (eobs[1] > 1)
|
|
vp8_dequant_idct_add_mmx (q+16, dq, dst+4, stride);
|
|
else if (eobs[1] == 1)
|
|
{
|
|
vp8_dc_only_idct_add_mmx (q[16]*dq[0], dst+4, stride,
|
|
dst+4, stride);
|
|
((int *)(q+16))[0] = 0;
|
|
}
|
|
|
|
if (eobs[2] > 1)
|
|
vp8_dequant_idct_add_mmx (q+32, dq, dst+8, stride);
|
|
else if (eobs[2] == 1)
|
|
{
|
|
vp8_dc_only_idct_add_mmx (q[32]*dq[0], dst+8, stride,
|
|
dst+8, stride);
|
|
((int *)(q+32))[0] = 0;
|
|
}
|
|
|
|
if (eobs[3] > 1)
|
|
vp8_dequant_idct_add_mmx (q+48, dq, dst+12, stride);
|
|
else if (eobs[3] == 1)
|
|
{
|
|
vp8_dc_only_idct_add_mmx (q[48]*dq[0], dst+12, stride,
|
|
dst+12, stride);
|
|
((int *)(q+48))[0] = 0;
|
|
}
|
|
|
|
q += 64;
|
|
dst += 4*stride;
|
|
eobs += 4;
|
|
}
|
|
}
|
|
|
|
void vp8_dequant_idct_add_uv_block_mmx
|
|
(short *q, short *dq,
|
|
unsigned char *dstu, unsigned char *dstv, int stride, char *eobs)
|
|
{
|
|
int i;
|
|
|
|
for (i = 0; i < 2; i++)
|
|
{
|
|
if (eobs[0] > 1)
|
|
vp8_dequant_idct_add_mmx (q, dq, dstu, stride);
|
|
else if (eobs[0] == 1)
|
|
{
|
|
vp8_dc_only_idct_add_mmx (q[0]*dq[0], dstu, stride, dstu, stride);
|
|
((int *)q)[0] = 0;
|
|
}
|
|
|
|
if (eobs[1] > 1)
|
|
vp8_dequant_idct_add_mmx (q+16, dq, dstu+4, stride);
|
|
else if (eobs[1] == 1)
|
|
{
|
|
vp8_dc_only_idct_add_mmx (q[16]*dq[0], dstu+4, stride,
|
|
dstu+4, stride);
|
|
((int *)(q+16))[0] = 0;
|
|
}
|
|
|
|
q += 32;
|
|
dstu += 4*stride;
|
|
eobs += 2;
|
|
}
|
|
|
|
for (i = 0; i < 2; i++)
|
|
{
|
|
if (eobs[0] > 1)
|
|
vp8_dequant_idct_add_mmx (q, dq, dstv, stride);
|
|
else if (eobs[0] == 1)
|
|
{
|
|
vp8_dc_only_idct_add_mmx (q[0]*dq[0], dstv, stride, dstv, stride);
|
|
((int *)q)[0] = 0;
|
|
}
|
|
|
|
if (eobs[1] > 1)
|
|
vp8_dequant_idct_add_mmx (q+16, dq, dstv+4, stride);
|
|
else if (eobs[1] == 1)
|
|
{
|
|
vp8_dc_only_idct_add_mmx (q[16]*dq[0], dstv+4, stride,
|
|
dstv+4, stride);
|
|
((int *)(q+16))[0] = 0;
|
|
}
|
|
|
|
q += 32;
|
|
dstv += 4*stride;
|
|
eobs += 2;
|
|
}
|
|
}
|