swscale: [LA] Optimize range convert for yuvj420p.

Reviewed-by: 陈昊 <chenhao@loongson.cn>
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>

libswscale/loongarch/swscale_init_loongarch.c

@@ -24,6 +24,38 @@
 #include "libswscale/rgb2rgb.h"
 #include "libavutil/loongarch/cpu.h"
 
+av_cold void ff_sws_init_range_convert_loongarch(SwsContext *c)
+{
+    int cpu_flags = av_get_cpu_flags();
+
+    if (have_lsx(cpu_flags)) {
+        if (c->srcRange != c->dstRange && !isAnyRGB(c->dstFormat)) {
+            if (c->dstBpc <= 14) {
+                if (c->srcRange) {
+                    c->lumConvertRange = lumRangeFromJpeg_lsx;
+                    c->chrConvertRange = chrRangeFromJpeg_lsx;
+                } else {
+                    c->lumConvertRange = lumRangeToJpeg_lsx;
+                    c->chrConvertRange = chrRangeToJpeg_lsx;
+                }
+            }
+        }
+    }
+    if (have_lasx(cpu_flags)) {
+        if (c->srcRange != c->dstRange && !isAnyRGB(c->dstFormat)) {
+            if (c->dstBpc <= 14) {
+                if (c->srcRange) {
+                    c->lumConvertRange = lumRangeFromJpeg_lasx;
+                    c->chrConvertRange = chrRangeFromJpeg_lasx;
+                } else {
+                    c->lumConvertRange = lumRangeToJpeg_lasx;
+                    c->chrConvertRange = chrRangeToJpeg_lasx;
+                }
+            }
+        }
+    }
+}
+
 av_cold void ff_sws_init_swscale_loongarch(SwsContext *c)
 {
     int cpu_flags = av_get_cpu_flags();
@@ -77,6 +109,7 @@ av_cold void ff_sws_init_swscale_loongarch(SwsContext *c)
             c->yuv2planeX = ff_yuv2planeX_8_lasx;
     }
 #endif // #if HAVE_LASX
+    ff_sws_init_range_convert_loongarch(c);
 }
 
 av_cold void rgb2rgb_init_loongarch(void)

libswscale/loongarch/swscale_loongarch.h

@@ -50,6 +50,11 @@ void ff_hscale_16_to_19_sub_lsx(SwsContext *c, int16_t *_dst, int dstW,
                                 const uint8_t *_src, const int16_t *filter,
                                 const int32_t *filterPos, int filterSize, int sh);
 
+void lumRangeFromJpeg_lsx(int16_t *dst, int width);
+void chrRangeFromJpeg_lsx(int16_t *dstU, int16_t *dstV, int width);
+void lumRangeToJpeg_lsx(int16_t *dst, int width);
+void chrRangeToJpeg_lsx(int16_t *dstU, int16_t *dstV, int width);
+
 void planar_rgb_to_uv_lsx(uint8_t *_dstU, uint8_t *_dstV, const uint8_t *src[4],
                           int width, int32_t *rgb2yuv, void *opq);
 
@@ -97,6 +102,11 @@ void ff_hscale_16_to_15_lasx(SwsContext *c, int16_t *dst, int dstW,
                              const uint8_t *_src, const int16_t *filter,
                              const int32_t *filterPos, int filterSize);
 
+void lumRangeFromJpeg_lasx(int16_t *dst, int width);
+void chrRangeFromJpeg_lasx(int16_t *dstU, int16_t *dstV, int width);
+void lumRangeToJpeg_lasx(int16_t *dst, int width);
+void chrRangeToJpeg_lasx(int16_t *dstU, int16_t *dstV, int width);
+
 void planar_rgb_to_uv_lasx(uint8_t *_dstU, uint8_t *_dstV, const uint8_t *src[4],
                            int width, int32_t *rgb2yuv, void *opq);
 
@@ -130,6 +140,7 @@ void ff_yuv2planeX_8_lasx(const int16_t *filter, int filterSize,
                           const uint8_t *dither, int offset);
 
 av_cold void ff_sws_init_output_lasx(SwsContext *c);
+
 #endif // #if HAVE_LASX
 
 #endif /* SWSCALE_LOONGARCH_SWSCALE_LOONGARCH_H */

libswscale/swscale_internal.h

@@ -697,6 +697,7 @@ void ff_yuv2rgb_init_tables_ppc(SwsContext *c, const int inv_table[4],
 void ff_updateMMXDitherTables(SwsContext *c, int dstY);
 
 av_cold void ff_sws_init_range_convert(SwsContext *c);
+av_cold void ff_sws_init_range_convert_loongarch(SwsContext *c);
 
 SwsFunc ff_yuv2rgb_init_x86(SwsContext *c);
 SwsFunc ff_yuv2rgb_init_ppc(SwsContext *c);

libswscale/utils.c

@@ -1078,8 +1078,12 @@ int sws_setColorspaceDetails(struct SwsContext *c, const int inv_table[4],
     c->srcRange   = srcRange;
     c->dstRange   = dstRange;
 
-    if (need_reinit)
+    if (need_reinit) {
         ff_sws_init_range_convert(c);
+#if ARCH_LOONGARCH64
+        ff_sws_init_range_convert_loongarch(c);
+#endif
+    }
 
     c->dstFormatBpp = av_get_bits_per_pixel(desc_dst);
     c->srcFormatBpp = av_get_bits_per_pixel(desc_src);