summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--libavcodec/ppc/fft_altivec.c10
-rw-r--r--libavcodec/ppc/h264dsp.c69
-rw-r--r--libswscale/ppc/yuv2rgb_altivec.c32
3 files changed, 63 insertions, 48 deletions
diff --git a/libavcodec/ppc/fft_altivec.c b/libavcodec/ppc/fft_altivec.c
index e3c848213d..b9dd4a2445 100644
--- a/libavcodec/ppc/fft_altivec.c
+++ b/libavcodec/ppc/fft_altivec.c
@@ -38,7 +38,7 @@ void ff_fft_calc_altivec(FFTContext *s, FFTComplex *z);
void ff_fft_calc_interleave_altivec(FFTContext *s, FFTComplex *z);
#if HAVE_GNU_AS && HAVE_ALTIVEC
-static void ff_imdct_half_altivec(FFTContext *s, FFTSample *output, const FFTSample *input)
+static void imdct_half_altivec(FFTContext *s, FFTSample *output, const FFTSample *input)
{
int j, k;
int n = 1 << s->mdct_bits;
@@ -118,7 +118,7 @@ static void ff_imdct_half_altivec(FFTContext *s, FFTSample *output, const FFTSam
} while(k >= 0);
}
-static void ff_imdct_calc_altivec(FFTContext *s, FFTSample *output, const FFTSample *input)
+static void imdct_calc_altivec(FFTContext *s, FFTSample *output, const FFTSample *input)
{
int k;
int n = 1 << s->mdct_bits;
@@ -128,7 +128,7 @@ static void ff_imdct_calc_altivec(FFTContext *s, FFTSample *output, const FFTSam
vec_u32 *p0 = (vec_u32*)(output+n4);
vec_u32 *p1 = (vec_u32*)(output+n4*3);
- ff_imdct_half_altivec(s, output+n4, input);
+ imdct_half_altivec(s, output + n4, input);
for (k = 0; k < n16; k++) {
vec_u32 a = p0[k] ^ sign;
@@ -144,8 +144,8 @@ av_cold void ff_fft_init_ppc(FFTContext *s)
#if HAVE_GNU_AS && HAVE_ALTIVEC
s->fft_calc = ff_fft_calc_interleave_altivec;
if (s->mdct_bits >= 5) {
- s->imdct_calc = ff_imdct_calc_altivec;
- s->imdct_half = ff_imdct_half_altivec;
+ s->imdct_calc = imdct_calc_altivec;
+ s->imdct_half = imdct_half_altivec;
}
#endif /* HAVE_GNU_AS && HAVE_ALTIVEC */
}
diff --git a/libavcodec/ppc/h264dsp.c b/libavcodec/ppc/h264dsp.c
index 49ca03ee4e..a46327f8be 100644
--- a/libavcodec/ppc/h264dsp.c
+++ b/libavcodec/ppc/h264dsp.c
@@ -70,7 +70,7 @@
va_u32 = vec_splat((vec_u32)va_u8, 0); \
vec_ste(va_u32, element, (uint32_t*)dst);
-static void ff_h264_idct_add_altivec(uint8_t *dst, int16_t *block, int stride)
+static void h264_idct_add_altivec(uint8_t *dst, int16_t *block, int stride)
{
vec_s16 va0, va1, va2, va3;
vec_s16 vz0, vz1, vz2, vz3;
@@ -185,7 +185,8 @@ static void ff_h264_idct_add_altivec(uint8_t *dst, int16_t *block, int stride)
vec_st( hv, 0, dest ); \
}
-static void ff_h264_idct8_add_altivec( uint8_t *dst, int16_t *dct, int stride ) {
+static void h264_idct8_add_altivec(uint8_t *dst, int16_t *dct, int stride)
+{
vec_s16 s0, s1, s2, s3, s4, s5, s6, s7;
vec_s16 d0, d1, d2, d3, d4, d5, d6, d7;
vec_s16 idct0, idct1, idct2, idct3, idct4, idct5, idct6, idct7;
@@ -281,47 +282,59 @@ static void h264_idct_dc_add_altivec(uint8_t *dst, int16_t *block, int stride)
h264_idct_dc_add_internal(dst, block, stride, 4);
}
-static void ff_h264_idct8_dc_add_altivec(uint8_t *dst, int16_t *block, int stride)
+static void h264_idct8_dc_add_altivec(uint8_t *dst, int16_t *block, int stride)
{
h264_idct_dc_add_internal(dst, block, stride, 8);
}
-static void ff_h264_idct_add16_altivec(uint8_t *dst, const int *block_offset, int16_t *block, int stride, const uint8_t nnzc[15*8]){
+static void h264_idct_add16_altivec(uint8_t *dst, const int *block_offset,
+ int16_t *block, int stride,
+ const uint8_t nnzc[15 * 8])
+{
int i;
for(i=0; i<16; i++){
int nnz = nnzc[ scan8[i] ];
if(nnz){
if(nnz==1 && block[i*16]) h264_idct_dc_add_altivec(dst + block_offset[i], block + i*16, stride);
- else ff_h264_idct_add_altivec(dst + block_offset[i], block + i*16, stride);
+ else h264_idct_add_altivec(dst + block_offset[i], block + i*16, stride);
}
}
}
-static void ff_h264_idct_add16intra_altivec(uint8_t *dst, const int *block_offset, int16_t *block, int stride, const uint8_t nnzc[15*8]){
+static void h264_idct_add16intra_altivec(uint8_t *dst, const int *block_offset,
+ int16_t *block, int stride,
+ const uint8_t nnzc[15 * 8])
+{
int i;
for(i=0; i<16; i++){
- if(nnzc[ scan8[i] ]) ff_h264_idct_add_altivec(dst + block_offset[i], block + i*16, stride);
+ if(nnzc[ scan8[i] ]) h264_idct_add_altivec(dst + block_offset[i], block + i*16, stride);
else if(block[i*16]) h264_idct_dc_add_altivec(dst + block_offset[i], block + i*16, stride);
}
}
-static void ff_h264_idct8_add4_altivec(uint8_t *dst, const int *block_offset, int16_t *block, int stride, const uint8_t nnzc[15*8]){
+static void h264_idct8_add4_altivec(uint8_t *dst, const int *block_offset,
+ int16_t *block, int stride,
+ const uint8_t nnzc[15 * 8])
+{
int i;
for(i=0; i<16; i+=4){
int nnz = nnzc[ scan8[i] ];
if(nnz){
- if(nnz==1 && block[i*16]) ff_h264_idct8_dc_add_altivec(dst + block_offset[i], block + i*16, stride);
- else ff_h264_idct8_add_altivec (dst + block_offset[i], block + i*16, stride);
+ if(nnz==1 && block[i*16]) h264_idct8_dc_add_altivec(dst + block_offset[i], block + i*16, stride);
+ else h264_idct8_add_altivec(dst + block_offset[i], block + i*16, stride);
}
}
}
-static void ff_h264_idct_add8_altivec(uint8_t **dest, const int *block_offset, int16_t *block, int stride, const uint8_t nnzc[15*8]){
+static void h264_idct_add8_altivec(uint8_t **dest, const int *block_offset,
+ int16_t *block, int stride,
+ const uint8_t nnzc[15 * 8])
+{
int i, j;
for (j = 1; j < 3; j++) {
for(i = j * 16; i < j * 16 + 4; i++){
if(nnzc[ scan8[i] ])
- ff_h264_idct_add_altivec(dest[j-1] + block_offset[i], block + i*16, stride);
+ h264_idct_add_altivec(dest[j-1] + block_offset[i], block + i*16, stride);
else if(block[i*16])
h264_idct_dc_add_altivec(dest[j-1] + block_offset[i], block + i*16, stride);
}
@@ -713,12 +726,14 @@ void biweight_h264_W_altivec(uint8_t *dst, uint8_t *src, int stride, int height,
}
#define H264_WEIGHT(W) \
-static void ff_weight_h264_pixels ## W ## _altivec(uint8_t *block, int stride, int height, \
- int log2_denom, int weight, int offset){ \
+static void weight_h264_pixels ## W ## _altivec(uint8_t *block, int stride, int height, \
+ int log2_denom, int weight, int offset) \
+{ \
weight_h264_W_altivec(block, stride, height, log2_denom, weight, offset, W); \
}\
-static void ff_biweight_h264_pixels ## W ## _altivec(uint8_t *dst, uint8_t *src, int stride, int height, \
- int log2_denom, int weightd, int weights, int offset){ \
+static void biweight_h264_pixels ## W ## _altivec(uint8_t *dst, uint8_t *src, int stride, int height, \
+ int log2_denom, int weightd, int weights, int offset) \
+{ \
biweight_h264_W_altivec(dst, src, stride, height, log2_denom, weightd, weights, offset, W); \
}
@@ -732,22 +747,22 @@ av_cold void ff_h264dsp_init_ppc(H264DSPContext *c, const int bit_depth,
#if HAVE_ALTIVEC
if (av_get_cpu_flags() & AV_CPU_FLAG_ALTIVEC) {
if (bit_depth == 8) {
- c->h264_idct_add = ff_h264_idct_add_altivec;
+ c->h264_idct_add = h264_idct_add_altivec;
if (chroma_format_idc == 1)
- c->h264_idct_add8 = ff_h264_idct_add8_altivec;
- c->h264_idct_add16 = ff_h264_idct_add16_altivec;
- c->h264_idct_add16intra = ff_h264_idct_add16intra_altivec;
+ c->h264_idct_add8 = h264_idct_add8_altivec;
+ c->h264_idct_add16 = h264_idct_add16_altivec;
+ c->h264_idct_add16intra = h264_idct_add16intra_altivec;
c->h264_idct_dc_add= h264_idct_dc_add_altivec;
- c->h264_idct8_dc_add = ff_h264_idct8_dc_add_altivec;
- c->h264_idct8_add = ff_h264_idct8_add_altivec;
- c->h264_idct8_add4 = ff_h264_idct8_add4_altivec;
+ c->h264_idct8_dc_add = h264_idct8_dc_add_altivec;
+ c->h264_idct8_add = h264_idct8_add_altivec;
+ c->h264_idct8_add4 = h264_idct8_add4_altivec;
c->h264_v_loop_filter_luma= h264_v_loop_filter_luma_altivec;
c->h264_h_loop_filter_luma= h264_h_loop_filter_luma_altivec;
- c->weight_h264_pixels_tab[0] = ff_weight_h264_pixels16_altivec;
- c->weight_h264_pixels_tab[1] = ff_weight_h264_pixels8_altivec;
- c->biweight_h264_pixels_tab[0] = ff_biweight_h264_pixels16_altivec;
- c->biweight_h264_pixels_tab[1] = ff_biweight_h264_pixels8_altivec;
+ c->weight_h264_pixels_tab[0] = weight_h264_pixels16_altivec;
+ c->weight_h264_pixels_tab[1] = weight_h264_pixels8_altivec;
+ c->biweight_h264_pixels_tab[0] = biweight_h264_pixels16_altivec;
+ c->biweight_h264_pixels_tab[1] = biweight_h264_pixels8_altivec;
}
}
#endif /* HAVE_ALTIVEC */
diff --git a/libswscale/ppc/yuv2rgb_altivec.c b/libswscale/ppc/yuv2rgb_altivec.c
index 94e87fe62f..df435fc198 100644
--- a/libswscale/ppc/yuv2rgb_altivec.c
+++ b/libswscale/ppc/yuv2rgb_altivec.c
@@ -624,18 +624,18 @@ av_cold void ff_yuv2rgb_init_tables_altivec(SwsContext *c,
return;
}
-static av_always_inline void ff_yuv2packedX_altivec(SwsContext *c,
- const int16_t *lumFilter,
- const int16_t **lumSrc,
- int lumFilterSize,
- const int16_t *chrFilter,
- const int16_t **chrUSrc,
- const int16_t **chrVSrc,
- int chrFilterSize,
- const int16_t **alpSrc,
- uint8_t *dest,
- int dstW, int dstY,
- enum AVPixelFormat target)
+static av_always_inline void yuv2packedX_altivec(SwsContext *c,
+ const int16_t *lumFilter,
+ const int16_t **lumSrc,
+ int lumFilterSize,
+ const int16_t *chrFilter,
+ const int16_t **chrUSrc,
+ const int16_t **chrVSrc,
+ int chrFilterSize,
+ const int16_t **alpSrc,
+ uint8_t *dest,
+ int dstW, int dstY,
+ enum AVPixelFormat target)
{
int i, j;
vector signed short X, X0, X1, Y0, U0, V0, Y1, U1, V1, U, V;
@@ -844,10 +844,10 @@ void ff_yuv2 ## suffix ## _X_altivec(SwsContext *c, \
const int16_t **alpSrc, \
uint8_t *dest, int dstW, int dstY) \
{ \
- ff_yuv2packedX_altivec(c, lumFilter, lumSrc, lumFilterSize, \
- chrFilter, chrUSrc, chrVSrc, \
- chrFilterSize, alpSrc, \
- dest, dstW, dstY, pixfmt); \
+ yuv2packedX_altivec(c, lumFilter, lumSrc, lumFilterSize, \
+ chrFilter, chrUSrc, chrVSrc, \
+ chrFilterSize, alpSrc, \
+ dest, dstW, dstY, pixfmt); \
}
YUV2PACKEDX_WRAPPER(abgr, AV_PIX_FMT_ABGR);
generated by cgit v1.2.3 (git 2.39.1) at 2024-06-09 01:16:31 +0000