RepoMirrors
/
ffmpeg
mirror of https://git.ffmpeg.org/ffmpeg.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

lavc/audiodsp: properly unroll vector_clipf 

Given that source and destination can alias, the compiler was forced to
perform each read-modify-write sequentially. We cannot use the `restrict`
qualifier to avoid this here because the AC-3 encoder uses the function
in-place. Instead this commit provides an explicit guarantee to the
compiler that batches of 8 elements will not overlap, so that it can
interleave calculations.

In practice contemporary optimising compilers are able to unroll and keep
the temporary array in FPU registers (without spilling).

On SiFive-U74, this speeds the same signs branch by 4x, and the
opposite signs branch 1.5x.
This commit is contained in:
Rémi Denis-Courmont 2024-07-25 22:40:25 +03:00
parent d527d23872
commit d86b6767ce
1 changed files with 17 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

40
libavcodec/audiodsp.c
View File

@ -38,41 +38,35 @@ static inline float clipf_c_one(float a, uint32_t mini,
static void vector_clipf_c_opposite_sign(float *dst, const float *src, static void vector_clipf_c_opposite_sign(float *dst, const float *src,
float min, float max, int len) float min, float max, int len)
{ {
int i;
uint32_t mini = av_float2int(min); uint32_t mini = av_float2int(min);
uint32_t maxi = av_float2int(max); uint32_t maxi = av_float2int(max);
uint32_t maxisign = maxi ^ (1U << 31); uint32_t maxisign = maxi ^ (1U << 31);
for (i = 0; i < len; i += 8) { for (int i = 0; i < len; i += 8) {
dst[i + 0] = clipf_c_one(src[i + 0], mini, maxi, maxisign); float tmp[8];
dst[i + 1] = clipf_c_one(src[i + 1], mini, maxi, maxisign);
dst[i + 2] = clipf_c_one(src[i + 2], mini, maxi, maxisign); for (int j = 0; j < 8; j++)
dst[i + 3] = clipf_c_one(src[i + 3], mini, maxi, maxisign); tmp[j]= clipf_c_one(src[i + j], mini, maxi, maxisign);
dst[i + 4] = clipf_c_one(src[i + 4], mini, maxi, maxisign); for (int j = 0; j < 8; j++)
dst[i + 5] = clipf_c_one(src[i + 5], mini, maxi, maxisign); dst[i + j] = tmp[j];
dst[i + 6] = clipf_c_one(src[i + 6], mini, maxi, maxisign);
dst[i + 7] = clipf_c_one(src[i + 7], mini, maxi, maxisign);
} }
} }
static void vector_clipf_c(float *dst, const float *src, int len, static void vector_clipf_c(float *dst, const float *src, int len,
float min, float max) float min, float max)
{ {
int i;
if (min < 0 && max > 0) { if (min < 0 && max > 0) {
vector_clipf_c_opposite_sign(dst, src, min, max, len); vector_clipf_c_opposite_sign(dst, src, min, max, len);
} else { return;
for (i = 0; i < len; i += 8) { }
dst[i] = av_clipf(src[i], min, max);
dst[i + 1] = av_clipf(src[i + 1], min, max); for (int i = 0; i < len; i += 8) {
dst[i + 2] = av_clipf(src[i + 2], min, max); float tmp[8];
dst[i + 3] = av_clipf(src[i + 3], min, max);
dst[i + 4] = av_clipf(src[i + 4], min, max); for (int j = 0; j < 8; j++)
dst[i + 5] = av_clipf(src[i + 5], min, max); tmp[j]= av_clipf(src[i + j], min, max);
dst[i + 6] = av_clipf(src[i + 6], min, max); for (int j = 0; j < 8; j++)
dst[i + 7] = av_clipf(src[i + 7], min, max); dst[i + j] = tmp[j];
}
} }
} }