swscale: [LA] Optimize range convert for yuvj420p.

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

3 files changed, 412 insertions, 0 deletions

diff --git a/libswscale/loongarch/swscale.S b/libswscale/loongarch/swscale.S
index aa4c5cbe28..67b1bc834d 100644
--- a/libswscale/loongarch/swscale.S
+++ b/libswscale/loongarch/swscale.S
@@ -1866,3 +1866,371 @@ function ff_hscale_16_to_19_sub_lsx
     ld.d             s8,      sp,     64
     addi.d           sp,      sp,     72
 endfunc
+
+function lumRangeFromJpeg_lsx
+    li.w          t0,    14071
+    li.w          t1,    33561947
+    vreplgr2vr.h  vr0,   t0
+    srli.w        t2,    a1,    3
+    andi          t3,    a1,    7
+    beqz          t2,    2f
+1:
+    vld           vr1,   a0,    0
+    vreplgr2vr.w  vr2,   t1
+    vreplgr2vr.w  vr3,   t1
+    vmaddwev.w.h  vr2,   vr0,   vr1
+    vmaddwod.w.h  vr3,   vr0,   vr1
+    vsrai.w       vr2,   vr2,   14
+    vsrai.w       vr3,   vr3,   14
+    vpackev.h     vr1,   vr3,   vr2
+    vst           vr1,   a0,    0
+    addi.d        a0,    a0,    16
+    addi.d        t2,    t2,    -1
+    bnez          t2,    1b
+2:
+    beqz          t3,    4f
+3:
+    ld.h          t4,    a0,    0
+    mul.w         t4,    t4,    t0
+    add.w         t4,    t4,    t1
+    srai.w        t4,    t4,    14
+    st.h          t4,    a0,    0
+    addi.d        a0,    a0,    2
+    addi.d        t3,    t3,    -1
+    bnez          t3,    3b
+4:
+endfunc
+
+function lumRangeFromJpeg_lasx
+    li.w           t0,    14071
+    li.w           t1,    33561947
+    xvreplgr2vr.h  xr0,   t0
+    srli.w         t2,    a1,    4
+    andi           t3,    a1,    15
+    beqz           t2,    2f
+1:
+    xvld           xr1,   a0,    0
+    xvreplgr2vr.w  xr2,   t1
+    xvreplgr2vr.w  xr3,   t1
+    xvmaddwev.w.h  xr2,   xr0,   xr1
+    xvmaddwod.w.h  xr3,   xr0,   xr1
+    xvsrai.w       xr2,   xr2,   14
+    xvsrai.w       xr3,   xr3,   14
+    xvpackev.h     xr1,   xr3,   xr2
+    xvst           xr1,   a0,    0
+    addi.d         a0,    a0,    32
+    addi.d         t2,    t2,    -1
+    bnez           t2,    1b
+2:
+    beqz          t3,    4f
+3:
+    ld.h          t4,    a0,    0
+    mul.w         t4,    t4,    t0
+    add.w         t4,    t4,    t1
+    srai.w        t4,    t4,    14
+    st.h          t4,    a0,    0
+    addi.d        a0,    a0,    2
+    addi.d        t3,    t3,    -1
+    bnez          t3,    3b
+4:
+endfunc
+
+function lumRangeToJpeg_lsx
+    li.w          t0,    19077
+    li.w          t1,    -39057361
+    li.w          t2,    30189
+    vreplgr2vr.h  vr0,   t0
+    vreplgr2vr.h  vr4,   t2
+    srli.w        t2,    a1,    3
+    andi          t3,    a1,    7
+    beqz          t2,    2f
+1:
+    vld           vr1,   a0,    0
+    vreplgr2vr.w  vr2,   t1
+    vreplgr2vr.w  vr3,   t1
+    vmin.h        vr1,   vr1,   vr4
+    vmaddwev.w.h  vr2,   vr0,   vr1
+    vmaddwod.w.h  vr3,   vr0,   vr1
+    vsrai.w       vr2,   vr2,   14
+    vsrai.w       vr3,   vr3,   14
+    vpackev.h     vr1,   vr3,   vr2
+    vst           vr1,   a0,    0
+    addi.d        a0,    a0,    16
+    addi.d        t2,    t2,    -1
+    bnez          t2,    1b
+2:
+    beqz          t3,    4f
+3:
+    ld.h          t4,    a0,    0
+    vreplgr2vr.h  vr1,   t4
+    vmin.h        vr1,   vr1,   vr4
+    vpickve2gr.h  t4,    vr1,   0
+    mul.w         t4,    t4,    t0
+    add.w         t4,    t4,    t1
+    srai.w        t4,    t4,    14
+    st.h          t4,    a0,    0
+    addi.d        a0,    a0,    2
+    addi.d        t3,    t3,    -1
+    bnez          t3,    3b
+4:
+endfunc
+
+function lumRangeToJpeg_lasx
+    li.w           t0,    19077
+    li.w           t1,    -39057361
+    li.w           t2,    30189
+    xvreplgr2vr.h  xr0,   t0
+    xvreplgr2vr.h  xr4,   t2
+    srli.w         t2,    a1,    4
+    andi           t3,    a1,    15
+    beqz           t2,    2f
+1:
+    xvld           xr1,   a0,    0
+    xvreplgr2vr.w  xr2,   t1
+    xvreplgr2vr.w  xr3,   t1
+    xvmin.h        xr1,   xr1,   xr4
+    xvmaddwev.w.h  xr2,   xr0,   xr1
+    xvmaddwod.w.h  xr3,   xr0,   xr1
+    xvsrai.w       xr2,   xr2,   14
+    xvsrai.w       xr3,   xr3,   14
+    xvpackev.h     xr1,   xr3,   xr2
+    xvst           xr1,   a0,    0
+    addi.d         a0,    a0,    32
+    addi.d         t2,    t2,    -1
+    bnez           t2,    1b
+2:
+    beqz           t3,    4f
+3:
+    ld.h           t4,    a0,    0
+    vreplgr2vr.h   vr1,   t4
+    vmin.h         vr1,   vr1,   vr4
+    vpickve2gr.h   t4,    vr1,   0
+    mul.w          t4,    t4,    t0
+    add.w          t4,    t4,    t1
+    srai.w         t4,    t4,    14
+    st.h           t4,    a0,    0
+    addi.d         a0,    a0,    2
+    addi.d         t3,    t3,    -1
+    bnez           t3,    3b
+4:
+endfunc
+
+function chrRangeFromJpeg_lsx
+    li.w          t0,    1799
+    li.w          t1,    4081085
+    vreplgr2vr.h  vr0,   t0
+    srli.w        t2,    a2,    3
+    andi          t3,    a2,    7
+    beqz          t2,    2f
+1:
+    vld           vr1,   a0,    0
+    vld           vr2,   a1,    0
+    vreplgr2vr.w  vr3,   t1
+    vreplgr2vr.w  vr4,   t1
+    vreplgr2vr.w  vr5,   t1
+    vreplgr2vr.w  vr6,   t1
+    vmaddwev.w.h  vr3,   vr0,   vr1
+    vmaddwod.w.h  vr4,   vr0,   vr1
+    vmaddwev.w.h  vr5,   vr0,   vr2
+    vmaddwod.w.h  vr6,   vr0,   vr2
+    vsrai.w       vr3,   vr3,   11
+    vsrai.w       vr4,   vr4,   11
+    vsrai.w       vr5,   vr5,   11
+    vsrai.w       vr6,   vr6,   11
+    vpackev.h     vr1,   vr4,   vr3
+    vpackev.h     vr2,   vr6,   vr5
+    vst           vr1,   a0,    0
+    vst           vr2,   a1,    0
+    addi.d        a0,    a0,    16
+    addi.d        a1,    a1,    16
+    addi.d        t2,    t2,    -1
+    bnez          t2,    1b
+2:
+    beqz          t3,    4f
+3:
+    ld.h          t4,    a0,    0
+    ld.h          t5,    a1,    0
+    mul.w         t4,    t4,    t0
+    mul.w         t5,    t5,    t0
+    add.w         t4,    t4,    t1
+    add.w         t5,    t5,    t1
+    srai.w        t4,    t4,    11
+    srai.w        t5,    t5,    11
+    st.h          t4,    a0,    0
+    st.h          t5,    a1,    0
+    addi.d        a0,    a0,    2
+    addi.d        a1,    a1,    2
+    addi.d        t3,    t3,    -1
+    bnez          t3,    3b
+4:
+endfunc
+
+function chrRangeFromJpeg_lasx
+    li.w           t0,    1799
+    li.w           t1,    4081085
+    xvreplgr2vr.h  xr0,   t0
+    srli.w         t2,    a2,    4
+    andi           t3,    a2,    15
+    beqz           t2,    2f
+1:
+    xvld           xr1,   a0,    0
+    xvld           xr2,   a1,    0
+    xvreplgr2vr.w  xr3,   t1
+    xvreplgr2vr.w  xr4,   t1
+    xvreplgr2vr.w  xr5,   t1
+    xvreplgr2vr.w  xr6,   t1
+    xvmaddwev.w.h  xr3,   xr0,   xr1
+    xvmaddwod.w.h  xr4,   xr0,   xr1
+    xvmaddwev.w.h  xr5,   xr0,   xr2
+    xvmaddwod.w.h  xr6,   xr0,   xr2
+    xvsrai.w       xr3,   xr3,   11
+    xvsrai.w       xr4,   xr4,   11
+    xvsrai.w       xr5,   xr5,   11
+    xvsrai.w       xr6,   xr6,   11
+    xvpackev.h     xr1,   xr4,   xr3
+    xvpackev.h     xr2,   xr6,   xr5
+    xvst           xr1,   a0,    0
+    xvst           xr2,   a1,    0
+    addi.d         a0,    a0,    32
+    addi.d         a1,    a1,    32
+    addi.d         t2,    t2,    -1
+    bnez           t2,    1b
+2:
+    beqz          t3,    4f
+3:
+    ld.h          t4,    a0,    0
+    ld.h          t5,    a1,    0
+    mul.w         t4,    t4,    t0
+    mul.w         t5,    t5,    t0
+    add.w         t4,    t4,    t1
+    add.w         t5,    t5,    t1
+    srai.w        t4,    t4,    11
+    srai.w        t5,    t5,    11
+    st.h          t4,    a0,    0
+    st.h          t5,    a1,    0
+    addi.d        a0,    a0,    2
+    addi.d        a1,    a1,    2
+    addi.d        t3,    t3,    -1
+    bnez          t3,    3b
+4:
+endfunc
+
+function chrRangeToJpeg_lsx
+    li.w          t0,    4663
+    li.w          t1,    -9289992
+    li.w          t2,    30775
+    vreplgr2vr.h  vr0,   t0
+    vreplgr2vr.h  vr7,   t2
+    srli.w        t2,    a2,    3
+    andi          t3,    a2,    7
+    beqz          t2,    2f
+1:
+    vld           vr1,   a0,    0
+    vld           vr2,   a1,    0
+    vreplgr2vr.w  vr3,   t1
+    vreplgr2vr.w  vr4,   t1
+    vreplgr2vr.w  vr5,   t1
+    vreplgr2vr.w  vr6,   t1
+    vmin.h        vr1,   vr1,   vr7
+    vmin.h        vr2,   vr2,   vr7
+    vmaddwev.w.h  vr3,   vr0,   vr1
+    vmaddwod.w.h  vr4,   vr0,   vr1
+    vmaddwev.w.h  vr5,   vr0,   vr2
+    vmaddwod.w.h  vr6,   vr0,   vr2
+    vsrai.w       vr3,   vr3,   12
+    vsrai.w       vr4,   vr4,   12
+    vsrai.w       vr5,   vr5,   12
+    vsrai.w       vr6,   vr6,   12
+    vpackev.h     vr1,   vr4,   vr3
+    vpackev.h     vr2,   vr6,   vr5
+    vst           vr1,   a0,    0
+    vst           vr2,   a1,    0
+    addi.d        a0,    a0,    16
+    addi.d        a1,    a1,    16
+    addi.d        t2,    t2,    -1
+    bnez          t2,    1b
+2:
+    beqz          t3,    4f
+3:
+    ld.h          t4,    a0,    0
+    ld.h          t5,    a1,    0
+    vreplgr2vr.h  vr1,   t4
+    vreplgr2vr.h  vr2,   t5
+    vmin.h        vr1,   vr1,   vr7
+    vmin.h        vr2,   vr2,   vr7
+    vpickve2gr.h  t4,    vr1,   0
+    vpickve2gr.h  t5,    vr2,   0
+    mul.w         t4,    t4,    t0
+    mul.w         t5,    t5,    t0
+    add.w         t4,    t4,    t1
+    add.w         t5,    t5,    t1
+    srai.w        t4,    t4,    12
+    srai.w        t5,    t5,    12
+    st.h          t4,    a0,    0
+    st.h          t5,    a1,    0
+    addi.d        a0,    a0,    2
+    addi.d        a1,    a1,    2
+    addi.d        t3,    t3,    -1
+    bnez          t3,    3b
+4:
+endfunc
+
+function chrRangeToJpeg_lasx
+    li.w           t0,    4663
+    li.w           t1,    -9289992
+    li.w           t2,    30775
+    xvreplgr2vr.h  xr0,   t0
+    xvreplgr2vr.h  xr7,   t2
+    srli.w         t2,    a2,    4
+    andi           t3,    a2,    15
+    beqz           t2,    2f
+1:
+    xvld           xr1,   a0,    0
+    xvld           xr2,   a1,    0
+    xvreplgr2vr.w  xr3,   t1
+    xvreplgr2vr.w  xr4,   t1
+    xvreplgr2vr.w  xr5,   t1
+    xvreplgr2vr.w  xr6,   t1
+    xvmin.h        xr1,   xr1,   xr7
+    xvmin.h        xr2,   xr2,   xr7
+    xvmaddwev.w.h  xr3,   xr0,   xr1
+    xvmaddwod.w.h  xr4,   xr0,   xr1
+    xvmaddwev.w.h  xr5,   xr0,   xr2
+    xvmaddwod.w.h  xr6,   xr0,   xr2
+    xvsrai.w       xr3,   xr3,   12
+    xvsrai.w       xr4,   xr4,   12
+    xvsrai.w       xr5,   xr5,   12
+    xvsrai.w       xr6,   xr6,   12
+    xvpackev.h     xr1,   xr4,   xr3
+    xvpackev.h     xr2,   xr6,   xr5
+    xvst           xr1,   a0,    0
+    xvst           xr2,   a1,    0
+    addi.d         a0,    a0,    32
+    addi.d         a1,    a1,    32
+    addi.d         t2,    t2,    -1
+    bnez           t2,    1b
+2:
+    beqz          t3,    4f
+3:
+    ld.h          t4,    a0,    0
+    ld.h          t5,    a1,    0
+    vreplgr2vr.h  vr1,   t4
+    vreplgr2vr.h  vr2,   t5
+    vmin.h        vr1,   vr1,   vr7
+    vmin.h        vr2,   vr2,   vr7
+    vpickve2gr.h  t4,    vr1,   0
+    vpickve2gr.h  t5,    vr2,   0
+    mul.w         t4,    t4,    t0
+    mul.w         t5,    t5,    t0
+    add.w         t4,    t4,    t1
+    add.w         t5,    t5,    t1
+    srai.w        t4,    t4,    12
+    srai.w        t5,    t5,    12
+    st.h          t4,    a0,    0
+    st.h          t5,    a1,    0
+    addi.d        a0,    a0,    2
+    addi.d        a1,    a1,    2
+    addi.d        t3,    t3,    -1
+    bnez          t3,    3b
+4:
+endfunc
diff --git a/libswscale/loongarch/swscale_init_loongarch.c b/libswscale/loongarch/swscale_init_loongarch.c
index 53e4f970b6..6d2786c55f 100644
--- a/libswscale/loongarch/swscale_init_loongarch.c
+++ b/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)
diff --git a/libswscale/loongarch/swscale_loongarch.h b/libswscale/loongarch/swscale_loongarch.h
index 0514abae21..c96b085982 100644
--- a/libswscale/loongarch/swscale_loongarch.h
+++ b/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 */