580b307fd7
Sync opus codec to upstream commit
02fed471a4568852d6618e041c4f2af0d7730ee2 (August 30 2013)
This brings in a lot of optimizations but also makes the diff
between our codec and the upstream much smaller as most of our
optimizations have been upstreamed or supeceded.
Speedups across the board for CELT mode files:
64kbps 128kbps
H300 9.82MHz 15.48MHz
c200 4.86MHz 9.63MHz
fuze v1 10.32MHz 15.92MHz
For the silk mode test file (16kbps) arm targets get a speedup
of about 2MHz while the H300 is 7.8MHz slower, likely because it's
now using the pseudostack more rather than the real stack which
is in iram. Patches to get around that are upcomming.
Change-Id: Ifecf963e461c51ac42e09dac1e91bc4bc3b12fa3
76 lines
2.7 KiB
C
76 lines
2.7 KiB
C
/* Copyright (C) 2013 Xiph.Org Foundation and contributors */
|
|
/*
|
|
Redistribution and use in source and binary forms, with or without
|
|
modification, are permitted provided that the following conditions
|
|
are met:
|
|
|
|
- Redistributions of source code must retain the above copyright
|
|
notice, this list of conditions and the following disclaimer.
|
|
|
|
- Redistributions in binary form must reproduce the above copyright
|
|
notice, this list of conditions and the following disclaimer in the
|
|
documentation and/or other materials provided with the distribution.
|
|
|
|
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
|
``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
|
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
|
A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER
|
|
OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
|
|
EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
|
|
PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
|
|
PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
|
|
LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
|
|
NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
|
|
SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
|
*/
|
|
|
|
#ifndef FIXED_ARMv4_H
|
|
#define FIXED_ARMv4_H
|
|
|
|
/** 16x32 multiplication, followed by a 16-bit shift right. Results fits in 32 bits */
|
|
#undef MULT16_32_Q16
|
|
static inline opus_val32 MULT16_32_Q16_armv4(opus_val16 a, opus_val32 b)
|
|
{
|
|
unsigned rd_lo;
|
|
int rd_hi;
|
|
__asm__(
|
|
"#MULT16_32_Q16\n\t"
|
|
"smull %0, %1, %2, %3\n\t"
|
|
: "=&r"(rd_lo), "=&r"(rd_hi)
|
|
: "%r"(b),"r"(a<<16)
|
|
);
|
|
return rd_hi;
|
|
}
|
|
#define MULT16_32_Q16(a, b) (MULT16_32_Q16_armv4(a, b))
|
|
|
|
|
|
/** 16x32 multiplication, followed by a 15-bit shift right. Results fits in 32 bits */
|
|
#undef MULT16_32_Q15
|
|
static inline opus_val32 MULT16_32_Q15_armv4(opus_val16 a, opus_val32 b)
|
|
{
|
|
unsigned rd_lo;
|
|
int rd_hi;
|
|
__asm__(
|
|
"#MULT16_32_Q15\n\t"
|
|
"smull %0, %1, %2, %3\n\t"
|
|
: "=&r"(rd_lo), "=&r"(rd_hi)
|
|
: "%r"(b), "r"(a<<16)
|
|
);
|
|
/*We intentionally don't OR in the high bit of rd_lo for speed.*/
|
|
return rd_hi<<1;
|
|
}
|
|
#define MULT16_32_Q15(a, b) (MULT16_32_Q15_armv4(a, b))
|
|
|
|
|
|
/** 16x32 multiply, followed by a 15-bit shift right and 32-bit add.
|
|
b must fit in 31 bits.
|
|
Result fits in 32 bits. */
|
|
#undef MAC16_32_Q15
|
|
#define MAC16_32_Q15(c, a, b) ADD32(c, MULT16_32_Q15(a, b))
|
|
|
|
|
|
/** 32x32 multiplication, followed by a 31-bit shift right. Results fits in 32 bits */
|
|
#undef MULT32_32_Q31
|
|
#define MULT32_32_Q31(a,b) (opus_val32)((((opus_int64)(a)) * ((opus_int64)(b)))>>31)
|
|
|
|
#endif
|