Unrolling the main loop to process, instead of 4 elements:
- 8: minor gain of 2 cycles (not worth the extra object size)
- 2: loss of 8 cycles.
Assigning STEP to a register is a loss. Output address (Y) is almost always
unaligned.
Timings:
- C (32/64 bits): 117/109 cycles
- SSE: 57 cycles
Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>
The 32bits targets have been compiled with -mfpmath=sse for proper reference.
sbr_sum_square C /32bits: 82c (unrolled)/102c
C /64bits: 69c (unrolled)/82c
SSE/32bits: 42c
SSE/64bits: 31c
Use of SSE4.1 dpps to perform the final sum is slower.
Not unrolling to perform 8 operations in a loop yields 10 more cycles.
Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>
This prevents having to sign-extend on 64-bit systems with 32-bit ints,
such as x86-64. Also fixes crashes on systems where we don't do it and
arguments are not in registers, such as Win64 for all weight functions.
By replacing memcpy with an unrolled loop using the alignment knowledge
it has, some speedup can be obtained.
Before (gcc 4.6.1): ~400 cycles
After: ~370 cycles
Overall, around 2% speed increase when decoding a 2400s mp3 to f32le.
Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>
We need to do unsigned saturation in order to cover the corner case when the
absolute coefficient value is 16777215 (the maximum value).
Fixes Bug #216
This will be useful to test more aggressively for failures to mark XMM
registers as clobbered in Win64 builds, and prevent regressions thereof.
Based on a patch by Ramiro Polla <ramiro.polla@gmail.com>
Provide MMX, SSE2 and SSSE3 versions, with a fast-path when the weights are
multiples of 512 (which is often the case when the values round up nicely).
*_TIMER report for the 16x16 and 8x8 cases:
C:
9015 decicycles in 16, 524257 runs, 31 skips
2656 decicycles in 8, 524271 runs, 17 skips
MMX:
4156 decicycles in 16, 262090 runs, 54 skips
1206 decicycles in 8, 262131 runs, 13 skips
MMX on fast-path:
2760 decicycles in 16, 524222 runs, 66 skips
995 decicycles in 8, 524252 runs, 36 skips
SSE2:
2163 decicycles in 16, 262131 runs, 13 skips
832 decicycles in 8, 262137 runs, 7 skips
SSE2 with fast path:
1783 decicycles in 16, 524276 runs, 12 skips
711 decicycles in 8, 524283 runs, 5 skips
SSSE3:
2117 decicycles in 16, 262136 runs, 8 skips
814 decicycles in 8, 262143 runs, 1 skips
SSSE3 with fast path:
1315 decicycles in 16, 524285 runs, 3 skips
578 decicycles in 8, 524286 runs, 2 skips
This means around a 4% speedup for some sequences.
Signed-off-by: Diego Biurrun <diego@biurrun.de>
While pshufb allows emulating bswap on XMM registers for SSSE3, more
shuffling is needed for SSE2. Alignment is critical, so specific codepaths
are provided for this case.
For the huffyuv sequence "angels_480-huffyuvcompress.avi":
C (using bswap instruction): ~ 55k cycles
SSE2: ~ 40k cycles
SSSE3 using unaligned loads: ~ 35k cycles
SSSE3 using aligned loads: ~ 30k cycles
Signed-off-by: Diego Biurrun <diego@biurrun.de>
On x86-64, it indeed uses all 16 registers (and on x86-32, this gets
clipped to 8). Not marking it properly causes callers of this function
to fail randomly because of XMM register clobbering.
Extract processing of intra 16x16 blocks from intra macroblock
processing.
Also implement a function performing inverse transform and block
reconstruction for DC-only blocks in 1 pass instead of 2.
When decoding coefficients, detect whether the block is DC-only, and take
advantage of this knowledge to perform DC-only inverse transform.
This is achieved by:
- first, changing the 108x4 element modulo_three_table into a 108 element
table (kind of base4), and accessing each value using mask and shifts.
- then, checking low bits for 0 (as they represent the presence of higher
frequency coefficients)
Also provide x86 SIMD code for the DC-only inverse transform.
Signed-off-by: Kostya Shishkov <kostya.shishkov@gmail.com>
This is required to handle clobbering of XMM registers on Win64
correctly. Fixes FFT and all tests depending on FFT on Win64.
Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>
Signed-off-by: Janne Grunau <janne-libav@jannau.net>
Originally, prior to 8742a4ff8, the caller code was compiled
within this condition:
ARCH_X86 && HAVE_7REGS && HAVE_EBX_AVAILABLE && !defined(BROKEN_RELOCATIONS)
Since HAVE_7REGS is defined as
(ARCH_X86_64 || (HAVE_EBX_AVAILABLE && HAVE_EBP_AVAILABLE))
the subcondition HAVE_7REGS && HAVE_EBX_AVAILABLE is equal
to HAVE_7REGS (for 32 bit at least). The correct simplification
of the original condition thus is HAVE_7REGS, not
HAVE_EBX_AVAILABLE.
This fixes compilation in some cases where HAVE_EBP_AVAILABLE = 0
and HAVE_EBX_AVAILABLE = 1.
Signed-off-by: Martin Storsjö <martin@martin.st>
On 32-bit OS X with gcc 4.0/4.2 and shared libraries enabled, the ebx register
is not available, but required to assemble the functions.
This reverts commit 8742a4f to a simplified version of the original constraints.
The change in 599b4c6ef didn't turn out to work properly on
i386 on OS X, where it broke building with PIC enabled.
Signed-off-by: Martin Storsjö <martin@martin.st>
This replaces the explicit offset(reg) memory references with
"m" operands for the same locations. As a result, one fewer
register operand is needed for these inline asm statements.
Signed-off-by: Mans Rullgard <mans@mansr.com>
Inspection of compiled code shows gcc handles these fine on its own.
Benchmarking also shows no measurable speed difference.
Removing the remaining cases in get_cabac_bypass_sign_x86() does
cause more substantial changes to the compiled code with uncertain
impact.
Signed-off-by: Mans Rullgard <mans@mansr.com>
The upcoming gcc 4.7 has more advanced constant propagation
resulting some inline asm operands becoming constants and thus
emitted as literals, sometimes in contexts where this results
in invalid instructions.
This patch changes the constraints of the relevant operands
to "rm" thus forcing a valid type. While obviously suboptimal,
this is what older gcc versions already did, and there is no
change to the code generated with these.
Signed-off-by: Mans Rullgard <mans@mansr.com>
This macro can cause problems in conjunction with the bitdepth
template expansion. It was presumably added to keep source
compatibility when high bitdepth support was added. However,
emulated_edge_mc is a dsputil pointer and should not be called
directly, so there is little reason to keep such a macro.
Signed-off-by: Mans Rullgard <mans@mansr.com>
Some operands need to be accessed in byte mode, which restricts the
available registers in 32-bit mode. Using the 'q' constraint selects
a suitable register.
Signed-off-by: Mans Rullgard <mans@mansr.com>
Parts are inspired from the 8-bit H.264 predict code in Libav.
Other parts ported from x264 with relicensing permission from author.
Signed-off-by: Diego Biurrun <diego@biurrun.de>
Fixes regression in 836f47d34b in ICC-10.x,
since ICC<=11.0 doesn't align stack upon function calls.
Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>
Ports the majority of IDCT functions for 10-bit H.264.
Parts are inspired from 8-bit IDCT code in Libav; other parts ported from x264 with relicensing permission from author.
Signed-off-by: Ronald S. Bultje <rbultje@google.com>
This separation allows these functions to be used in a cleaner
fashion from other codecs (e.g. qdm2) and simplifies creating
optimised versions of them.
Signed-off-by: Mans Rullgard <mans@mansr.com>
Arguments for variable size instructions are added to many macros, along
with other various changes. The x86util.asm code was ported from x264.
Signed-off-by: Diego Biurrun <diego@biurrun.de>
This patch lets e.g. dsputil_init chose dsp functions with respect to
the bit depth to decode. The naming scheme of bit depth dependent
functions is <base name>_<bit depth>[_<prefix>] (i.e. the old
clear_blocks_c is now named clear_blocks_8_c).
Note: Some of the functions for high bit depth is not dependent on the
bit depth, but only on the pixel size. This leaves some room for
optimizing binary size.
Preparatory patch for high bit depth h264 decoding support.
Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>
