swscale/x86/range_convert: update sse2 and avx2 range_convert functions to new API

chrRangeFromJpeg8_1920_c:    2127.4 (1.00x)
chrRangeFromJpeg8_1920_sse2:  816.0 (2.61x)  813.5 (2.62x)
chrRangeFromJpeg8_1920_avx2:  408.9 (5.20x)  405.4 (5.25x)
chrRangeToJpeg8_1920_c:      3166.9 (1.00x)
chrRangeToJpeg8_1920_sse2:    815.0 (3.89x)  815.0 (3.89x)
chrRangeToJpeg8_1920_avx2:    404.5 (7.83x)  405.5 (7.81x)
lumRangeFromJpeg8_1920_c:    1263.0 (1.00x)
lumRangeFromJpeg8_1920_sse2:  411.0 (3.07x)  413.2 (3.06x)
lumRangeFromJpeg8_1920_avx2:  200.5 (6.30x)  201.9 (6.26x)
lumRangeToJpeg8_1920_c:      1886.8 (1.00x)
lumRangeToJpeg8_1920_sse2:    412.0 (4.58x)  408.9 (4.61x)
lumRangeToJpeg8_1920_avx2:    208.5 (9.05x)  205.7 (9.17x)

libswscale/x86/range_convert.asm

@@ -20,39 +20,29 @@
 
 %include "libavutil/x86/x86util.asm"
 
-SECTION_RODATA
-
-chr_to_mult:        times 4 dw 4663, 0
-chr_to_offset:      times 4 dd -9289992
-%define chr_to_shift 12
-
-chr_from_mult:      times 4 dw 1799, 0
-chr_from_offset:    times 4 dd 4081085
-%define chr_from_shift 11
-
-lum_to_mult:        times 4 dw 19077, 0
-lum_to_offset:      times 4 dd -39057361
-%define lum_to_shift 14
-
-lum_from_mult:      times 4 dw 14071, 0
-lum_from_offset:    times 4 dd 33561947
-%define lum_from_shift 14
-
 SECTION .text
 
 ;-----------------------------------------------------------------------------
 ; lumConvertRange
 ;
-; void ff_lumRangeToJpeg_<opt>(int16_t *dst, int width);
-; void ff_lumRangeFromJpeg_<opt>(int16_t *dst, int width);
+; void ff_lumRangeToJpeg_<opt>(int16_t *dst, int width,
+;                              uint32_t coeff, int64_t offset);
+; void ff_lumRangeFromJpeg_<opt>(int16_t *dst, int width,
+;                                uint32_t coeff, int64_t offset);
 ;
 ;-----------------------------------------------------------------------------
 
-%macro LUMCONVERTRANGE 4
-cglobal %1, 2, 2, 5, dst, width
+%macro LUMCONVERTRANGE 1
+cglobal lumRange%1Jpeg, 4, 4, 5, dst, width, coeff, offset
     shl          widthd, 1
-    VBROADCASTI128   m2, [%2]
-    VBROADCASTI128   m3, [%3]
+    movd            xm2, coeffd
+    VBROADCASTSS     m2, xm2
+%if ARCH_X86_64
+    movq            xm3, offsetq
+%else
+    movq            xm3, offsetm
+%endif
+    VBROADCASTSS     m3, xm3
     pxor             m4, m4
     add            dstq, widthq
     neg          widthq
@@ -64,8 +54,8 @@ cglobal %1, 2, 2, 5, dst, width
     pmaddwd          m1, m2
     paddd            m0, m3
     paddd            m1, m3
-    psrad            m0, %4
-    psrad            m1, %4
+    psrad            m0, 14
+    psrad            m1, 14
     packssdw         m0, m1
     movu  [dstq+widthq], m0
     add          widthq, mmsize
@@ -76,16 +66,24 @@ cglobal %1, 2, 2, 5, dst, width
 ;-----------------------------------------------------------------------------
 ; chrConvertRange
 ;
-; void ff_chrRangeToJpeg_<opt>(int16_t *dstU, int16_t *dstV, int width);
-; void ff_chrRangeFromJpeg_<opt>(int16_t *dstU, int16_t *dstV, int width);
+; void ff_chrRangeToJpeg_<opt>(int16_t *dstU, int16_t *dstV, int width,
+;                              uint32_t coeff, int64_t offset);
+; void ff_chrRangeFromJpeg_<opt>(int16_t *dstU, int16_t *dstV, int width,
+;                                uint32_t coeff, int64_t offset);
 ;
 ;-----------------------------------------------------------------------------
 
-%macro CHRCONVERTRANGE 4
-cglobal %1, 3, 3, 7, dstU, dstV, width
+%macro CHRCONVERTRANGE 1
+cglobal chrRange%1Jpeg, 5, 5, 7, dstU, dstV, width, coeff, offset
     shl          widthd, 1
-    VBROADCASTI128   m4, [%2]
-    VBROADCASTI128   m5, [%3]
+    movd            xm4, coeffd
+    VBROADCASTSS     m4, xm4
+%if ARCH_X86_64
+    movq            xm5, offsetq
+%else
+    movq            xm5, offsetm
+%endif
+    VBROADCASTSS     m5, xm5
     pxor             m6, m6
     add           dstUq, widthq
     add           dstVq, widthq
@@ -105,10 +103,10 @@ cglobal %1, 3, 3, 7, dstU, dstV, width
     paddd            m1, m5
     paddd            m2, m5
     paddd            m3, m5
-    psrad            m0, %4
-    psrad            m1, %4
-    psrad            m2, %4
-    psrad            m3, %4
+    psrad            m0, 14
+    psrad            m1, 14
+    psrad            m2, 14
+    psrad            m3, 14
     packssdw         m0, m1
     packssdw         m2, m3
     movu [dstUq+widthq], m0
@@ -119,15 +117,15 @@ cglobal %1, 3, 3, 7, dstU, dstV, width
 %endmacro
 
 INIT_XMM sse2
-LUMCONVERTRANGE lumRangeToJpeg,   lum_to_mult,   lum_to_offset,   lum_to_shift
-CHRCONVERTRANGE chrRangeToJpeg,   chr_to_mult,   chr_to_offset,   chr_to_shift
-LUMCONVERTRANGE lumRangeFromJpeg, lum_from_mult, lum_from_offset, lum_from_shift
-CHRCONVERTRANGE chrRangeFromJpeg, chr_from_mult, chr_from_offset, chr_from_shift
+LUMCONVERTRANGE To
+CHRCONVERTRANGE To
+LUMCONVERTRANGE From
+CHRCONVERTRANGE From
 
 %if HAVE_AVX2_EXTERNAL
 INIT_YMM avx2
-LUMCONVERTRANGE lumRangeToJpeg,   lum_to_mult,   lum_to_offset,   lum_to_shift
-CHRCONVERTRANGE chrRangeToJpeg,   chr_to_mult,   chr_to_offset,   chr_to_shift
-LUMCONVERTRANGE lumRangeFromJpeg, lum_from_mult, lum_from_offset, lum_from_shift
-CHRCONVERTRANGE chrRangeFromJpeg, chr_from_mult, chr_from_offset, chr_from_shift
+LUMCONVERTRANGE To
+CHRCONVERTRANGE To
+LUMCONVERTRANGE From
+CHRCONVERTRANGE From
 %endif

libswscale/x86/swscale.c

@@ -464,27 +464,26 @@ INPUT_PLANAR_RGB_A_ALL_DECL(avx2);
 } while (0)
 
 #define RANGE_CONVERT_FUNCS_DECL(opt)                                       \
-void ff_lumRangeFromJpeg_ ##opt(int16_t *dst, int width);                   \
-void ff_chrRangeFromJpeg_ ##opt(int16_t *dstU, int16_t *dstV, int width);   \
-void ff_lumRangeToJpeg_ ##opt(int16_t *dst, int width);                     \
-void ff_chrRangeToJpeg_ ##opt(int16_t *dstU, int16_t *dstV, int width);     \
+void ff_lumRangeFromJpeg_ ##opt(int16_t *dst, int width,                    \
+                                uint32_t coeff, int64_t offset);            \
+void ff_chrRangeFromJpeg_ ##opt(int16_t *dstU, int16_t *dstV, int width,    \
+                                uint32_t coeff, int64_t offset);            \
+void ff_lumRangeToJpeg_ ##opt(int16_t *dst, int width,                      \
+                              uint32_t coeff, int64_t offset);              \
+void ff_chrRangeToJpeg_ ##opt(int16_t *dstU, int16_t *dstV, int width,      \
+                              uint32_t coeff, int64_t offset);              \
 
 RANGE_CONVERT_FUNCS_DECL(sse2);
 RANGE_CONVERT_FUNCS_DECL(avx2);
 
 av_cold void ff_sws_init_range_convert_x86(SwsInternal *c)
 {
-    /* This code is currently disabled because of changes in the base
-     * implementation of these functions. This code should be enabled
-     * again once those changes are ported to this architecture. */
-#if 0
     int cpu_flags = av_get_cpu_flags();
     if (EXTERNAL_AVX2_FAST(cpu_flags)) {
         RANGE_CONVERT_FUNCS(avx2);
     } else if (EXTERNAL_SSE2(cpu_flags)) {
         RANGE_CONVERT_FUNCS(sse2);
     }
-#endif
 }
 
 av_cold void ff_sws_init_swscale_x86(SwsInternal *c)