1. 17 Jul, 2014 7 commits
    • Ben Avison's avatar
      armv6: Accelerate ff_fft_calc for general case (nbits != 4) · 87552d54
      Ben Avison authored
      The previous implementation targeted DTS Coherent Acoustics, which only
      requires nbits == 4 (fft16()). This case was (and still is) linked directly
      rather than being indirected through ff_fft_calc_vfp(), but now the full
      range from radix-4 up to radix-65536 is available. This benefits other codecs
      such as AAC and AC3.
      
      The implementaion is based upon the C version, with each routine larger than
      radix-16 calling a hierarchy of smaller FFT functions, then performing a
      post-processing pass. This pass benefits a lot from loop unrolling to
      counter the long pipelines in the VFP. A relaxed calling standard also
      reduces the overhead of the call hierarchy, and avoiding the excessive
      inlining performed by GCC probably helps with I-cache utilisation too.
      
      I benchmarked the result by measuring the number of gperftools samples that
      hit anywhere in the AAC decoder (starting from aac_decode_frame()) or
      specifically in the FFT routines (fft4() to fft512() and pass()) for the
      same sample AAC stream:
      
                    Before          After
                    Mean   StdDev   Mean   StdDev  Confidence  Change
      Audio decode  2245.5 53.1     1599.6 43.8    100.0%      +40.4%
      FFT routines  940.6  22.0     348.1  20.8    100.0%      +170.2%
      Signed-off-by: 's avatarMartin Storsjö <martin@martin.st>
      87552d54
    • Ben Avison's avatar
      armv6: Accelerate ff_imdct_half for general case (mdct_bits != 6) · 5c22e8e4
      Ben Avison authored
      The previous implementation targeted DTS Coherent Acoustics, which only
      requires mdct_bits == 6. This relatively small size lent itself to
      unrolling the loops a small number of times, and encoding offsets
      calculated at assembly time within the load/store instructions of each
      iteration.
      
      In the more general case (codecs such as AAC and AC3) much larger arrays
      are used - mdct_bits == [8, 9, 11]. The old method does not scale for
      these cases, so more integer registers are used with non-unrolled versions
      of the loops (and with some stack spillage). The postrotation filter loop
      is still unrolled by a factor of 2 to permit the double-buffering of some
      VFP registers to facilitate overlap of neighbouring iterations.
      
      I benchmarked the result by measuring the number of gperftools samples
      that hit anywhere in the AAC decoder (starting from aac_decode_frame())
      or specifically in ff_imdct_half_c / ff_imdct_half_vfp, for the same
      example AAC stream:
      
                        Before          After
                        Mean   StdDev   Mean   StdDev  Confidence  Change
      aac_decode_frame  2368.1 35.8     2117.2 35.3    100.0%      +11.8%
      ff_imdct_half_*   457.5  22.4     251.2  16.2    100.0%      +82.1%
      Signed-off-by: 's avatarMartin Storsjö <martin@martin.st>
      5c22e8e4
    • Diego Biurrun's avatar
    • Martin Storsjö's avatar
    • Diego Biurrun's avatar
      x86: dsputil: Coalesce all init files · c23ce454
      Diego Biurrun authored
      This makes the init files match the structure of the dsputil split.
      c23ce454
    • Nidhi Makhijani's avatar
    • Luca Barbato's avatar
      2db953f8
  2. 16 Jul, 2014 3 commits
  3. 14 Jul, 2014 1 commit
  4. 13 Jul, 2014 2 commits
  5. 11 Jul, 2014 8 commits
  6. 10 Jul, 2014 2 commits
  7. 09 Jul, 2014 16 commits
  8. 08 Jul, 2014 1 commit