libswscale/x86/yuv2rgb: add ssse3 version

Tested using this command:
/ffmpeg -pix_fmt yuv420p -s 1920*1080 -i ArashRawYuv420.yuv \
-vcodec rawvideo -s 1920*1080 -pix_fmt rgb24 -f null /dev/null

The fps increase from 389 to 640 on Intel(R) Core(TM) i7-8700K CPU @ 3.70GHz

Signed-off-by: Ting Fu <ting.fu@intel.com>

2 files changed, 167 insertions, 16 deletions

diff --git a/libswscale/x86/yuv2rgb.c b/libswscale/x86/yuv2rgb.c
index c7668f487c..c12e88cbb5 100644
--- a/libswscale/x86/yuv2rgb.c
+++ b/libswscale/x86/yuv2rgb.c
@@ -67,6 +67,15 @@ DECLARE_ASM_CONST(8, uint64_t, pb_07) = 0x0707070707070707ULL;
 #include "yuv2rgb_template.c"
 #endif /* HAVE_MMXEXT */
 
+//SSSE3 versions
+#if HAVE_SSSE3
+#undef RENAME
+#undef COMPILE_TEMPLATE_MMXEXT
+#define COMPILE_TEMPLATE_MMXEXT 0
+#define RENAME(a) a ## _ssse3
+#include "yuv2rgb_template.c"
+#endif
+
 #endif /* HAVE_X86ASM */
 
 av_cold SwsFunc ff_yuv2rgb_init_x86(SwsContext *c)
@@ -74,6 +83,35 @@ av_cold SwsFunc ff_yuv2rgb_init_x86(SwsContext *c)
 #if HAVE_X86ASM
     int cpu_flags = av_get_cpu_flags();
 
+    if (EXTERNAL_SSSE3(cpu_flags)) {
+        switch (c->dstFormat) {
+        case AV_PIX_FMT_RGB32:
+            if (c->srcFormat == AV_PIX_FMT_YUVA420P) {
+#if CONFIG_SWSCALE_ALPHA
+                return yuva420_rgb32_ssse3;
+#endif
+                break;
+            } else
+                return yuv420_rgb32_ssse3;
+        case AV_PIX_FMT_BGR32:
+            if (c->srcFormat == AV_PIX_FMT_YUVA420P) {
+#if CONFIG_SWSCALE_ALPHA
+                return yuva420_bgr32_ssse3;
+#endif
+                break;
+            } else
+                return yuv420_bgr32_ssse3;
+        case AV_PIX_FMT_RGB24:
+            return yuv420_rgb24_ssse3;
+        case AV_PIX_FMT_BGR24:
+            return yuv420_bgr24_ssse3;
+        case AV_PIX_FMT_RGB565:
+            return yuv420_rgb16_ssse3;
+        case AV_PIX_FMT_RGB555:
+            return yuv420_rgb15_ssse3;
+        }
+    }
+
     if (EXTERNAL_MMXEXT(cpu_flags)) {
         switch (c->dstFormat) {
         case AV_PIX_FMT_RGB24:
diff --git a/libswscale/x86/yuv_2_rgb.asm b/libswscale/x86/yuv_2_rgb.asm
index a44ab1607b..e05bbb89f5 100644
--- a/libswscale/x86/yuv_2_rgb.asm
+++ b/libswscale/x86/yuv_2_rgb.asm
@@ -25,11 +25,18 @@
 
 SECTION_RODATA
 
-pw_00ff: times 4 dw 255
-pb_f8:   times 8 db 248
-pb_e0:   times 8 db 224
-pb_03:   times 8 db 3
-pb_07:   times 8 db 7
+; below variables are named like mask_dwXY, which means to preserve dword No.X & No.Y
+mask_dw036 : db -1, -1,  0,  0,  0,  0, -1, -1,  0,  0,  0,  0, -1, -1,  0,  0
+mask_dw147 : db  0,  0, -1, -1,  0,  0,  0,  0, -1, -1,  0,  0,  0,  0, -1, -1
+mask_dw25  : db  0,  0,  0,  0, -1, -1,  0,  0,  0,  0, -1, -1,  0,  0,  0,  0
+rgb24_shuf1: db  0,  1,  6,  7, 12, 13,  2,  3,  8,  9, 14, 15,  4,  5, 10, 11
+rgb24_shuf2: db 10, 11,  0,  1,  6,  7, 12, 13,  2,  3,  8,  9, 14, 15,  4,  5
+rgb24_shuf3: db  4,  5, 10, 11,  0,  1,  6,  7, 12, 13,  2,  3,  8,  9, 14, 15
+pw_00ff: times 8 dw 255
+pb_f8:   times 16 db 248
+pb_e0:   times 16 db 224
+pb_03:   times 16 db 3
+pb_07:   times 16 db 7
 
 mask_1101: dw -1, -1,  0, -1
 mask_0010: dw  0,  0, -1,  0
@@ -49,7 +56,11 @@ SECTION .text
 ;-----------------------------------------------------------------------------
 
 %macro MOV_H2L 1
-psrlq %1, 32
+%if mmsize == 8
+    psrlq %1, 32
+%else ; mmsize == 16
+    psrldq %1, 8
+%endif
 %endmacro
 
 %macro yuv2rgb_fn 3
@@ -77,6 +88,7 @@ psrlq %1, 32
 %define m_blue m1
 %endif
 
+%if mmsize == 8
 %define time_num 1
 %define reg_num 8
 %define y_offset [pointer_c_ditherq + 8  * 8]
@@ -87,11 +99,45 @@ psrlq %1, 32
 %define y_coff   [pointer_c_ditherq + 3  * 8]
 %define ub_coff  [pointer_c_ditherq + 5  * 8]
 %define vr_coff  [pointer_c_ditherq + 4  * 8]
+%elif mmsize == 16
+%define time_num 2
+%if ARCH_X86_32
+%define reg_num 8
+%define my_offset [pointer_c_ditherq + 8  * 8]
+%define mu_offset [pointer_c_ditherq + 9  * 8]
+%define mv_offset [pointer_c_ditherq + 10 * 8]
+%define mug_coff  [pointer_c_ditherq + 7  * 8]
+%define mvg_coff  [pointer_c_ditherq + 6  * 8]
+%define my_coff   [pointer_c_ditherq + 3  * 8]
+%define mub_coff  [pointer_c_ditherq + 5  * 8]
+%define mvr_coff  [pointer_c_ditherq + 4  * 8]
+%else ; ARCH_X86_64
+%define reg_num 16
+%define y_offset m8
+%define u_offset m9
+%define v_offset m10
+%define ug_coff  m11
+%define vg_coff  m12
+%define y_coff   m13
+%define ub_coff  m14
+%define vr_coff  m15
+%endif ; ARCH_X86_32/64
+%endif ; coeff define mmsize == 8/16
 
 cglobal %1_420_%2%3, GPR_num, GPR_num, reg_num, parameters
 
 %if ARCH_X86_64
     movsxd indexq, indexd
+%if mmsize == 16
+    VBROADCASTSD y_offset, [pointer_c_ditherq + 8  * 8]
+    VBROADCASTSD u_offset, [pointer_c_ditherq + 9  * 8]
+    VBROADCASTSD v_offset, [pointer_c_ditherq + 10 * 8]
+    VBROADCASTSD ug_coff,  [pointer_c_ditherq + 7  * 8]
+    VBROADCASTSD vg_coff,  [pointer_c_ditherq + 6  * 8]
+    VBROADCASTSD y_coff,   [pointer_c_ditherq + 3  * 8]
+    VBROADCASTSD ub_coff,  [pointer_c_ditherq + 5  * 8]
+    VBROADCASTSD vr_coff,  [pointer_c_ditherq + 4  * 8]
+%endif
 %endif
     mova m_y, [py_2indexq + 2 * indexq]
     movh m_u, [pu_indexq  +     indexq]
@@ -108,10 +154,30 @@ cglobal %1_420_%2%3, GPR_num, GPR_num, reg_num, parameters
     psllw m1, 3
     psllw m6, 3
     psllw m7, 3
+%if (ARCH_X86_32 && mmsize == 16)
+    VBROADCASTSD m2, mu_offset
+    VBROADCASTSD m3, mv_offset
+    VBROADCASTSD m4, my_offset
+    psubsw m0, m2 ; U = U - 128
+    psubsw m1, m3 ; V = V - 128
+    psubw  m6, m4
+    psubw  m7, m4
+    VBROADCASTSD m2, mug_coff
+    VBROADCASTSD m3, mvg_coff
+    VBROADCASTSD m4, my_coff
+    VBROADCASTSD m5, mub_coff
+    pmulhw m2, m0
+    pmulhw m3, m1
+    pmulhw m6, m4
+    pmulhw m7, m4
+    pmulhw m0, m5
+    VBROADCASTSD m4, mvr_coff
+    pmulhw m1, m4
+%else ; ARCH_X86_64 || mmsize == 8
     psubsw m0, u_offset ; U = U - 128
     psubsw m1, v_offset ; V = V - 128
-    psubw m6, y_offset
-    psubw m7, y_offset
+    psubw  m6, y_offset
+    psubw  m7, y_offset
     mova m2, m0
     mova m3, m1
     pmulhw m2, ug_coff
@@ -120,6 +186,7 @@ cglobal %1_420_%2%3, GPR_num, GPR_num, reg_num, parameters
     pmulhw m7, y_coff
     pmulhw m0, ub_coff
     pmulhw m1, vr_coff
+%endif
     paddsw m2, m3
     mova m3, m7
     mova m5, m7
@@ -142,6 +209,7 @@ cglobal %1_420_%2%3, GPR_num, GPR_num, reg_num, parameters
     punpcklbw m6, m_red  ; B0 R1 B2 R3 B4 R5 B6 R7 B8 R9 ...
     mova m5, m3
     punpckhbw m2, m_blue ; G1 B1 G3 B3 G5 B5 G7 B7 G9 B9 ...
+%if  mmsize == 8
     punpcklwd m3 ,m6     ; R0 G0 B0 R1 R2 G2 B2 R3
     punpckhwd m5, m6     ; R4 G4 B4 R5 R6 G6 B6 R7
 %if cpuflag(mmxext)
@@ -177,7 +245,33 @@ cglobal %1_420_%2%3, GPR_num, GPR_num, reg_num, parameters
     psrlq m5, 32
     movd [imageq + 20], m2 ; -- -- G7 B7
     movd [imageq + 18], m5 ; R6 G6 B6 R7
-%endif
+%endif ; mmsize = 8
+%else ; mmsize == 16
+    pshufb m3, [rgb24_shuf1] ; r0  g0  r6  g6  r12 g12 r2  g2  r8  g8  r14 g14 r4  g4  r10 g10
+    pshufb m6, [rgb24_shuf2] ; b10 r11 b0  r1  b6  r7  b12 r13 b2  r3  b8  r9  b14 r15 b4  r5
+    pshufb m2, [rgb24_shuf3] ; g5  b5  g11 b11 g1  b1  g7  b7  g13 b13 g3  b3  g9  b9  g15 b15
+    mova   m7, [mask_dw036]
+    mova   m4, [mask_dw147]
+    mova   m5, [mask_dw25]
+    pand   m0, m7, m3      ; r0  g0  --- --- --- --- r2  g2  --- --- --- --- r4  g4  --- ---
+    pand   m1, m4, m6      ; --- --- b0  r1  --- --- --- --- b2  r3  --- --- --- --- b4  r5
+    por    m0, m1
+    pand   m1, m5, m2      ; --- --- --- --- g1  b1  --- --- --- --- g3  b3  --- --- --- ---
+    por    m0, m1          ; r0  g0  b0  r1  g1  b1  r2  g2  b2  r3  g3  b3  r4  g4  b4  r5
+    pand   m1, m7, m2      ; g5  b5  --- --- --- --- g7  b7  --- --- --- --- g9  b9  --- ---
+    pand   m7, m6          ; b10 r11 --- --- --- --- b12 r13 --- --- --- --- b14 r15 --- ---
+    pand   m6, m5          ; --- --- --- --- b6  r7  --- --- --- --- b8  r9  --- --- --- ---
+    por    m1, m6
+    pand   m6, m4, m3      ; --- --- r6  g6  --- --- --- --- r8  g8  --- --- --- --- r10 g10
+    pand   m2, m4          ; --- --- g11 b11 --- --- --- --- g13 b13 --- --- --- --- g15 b15
+    pand   m3, m5          ; --- --- --- --- r12 g12 --- --- --- --- r14 g14 --- --- --- ---
+    por    m2, m7
+    por    m1, m6          ; g5  b5  r6  g6  b6  r7  g7  b7  r8  g8  b8  r9  g9  b9  r10 g10
+    por    m2, m3          ; b10 r11 g11 b11 r12 g12 b12 r13 g13 b13 r14 g14 b14 r15 g15 b15
+    mova [imageq], m0
+    mova [imageq + 16], m1
+    mova [imageq + 32], m2
+%endif ; mmsize = 16
 %else ; PACK RGB15/16/32
     packuswb m0, m1
     packuswb m3, m5
@@ -196,10 +290,10 @@ cglobal %1_420_%2%3, GPR_num, GPR_num, reg_num, parameters
 %endif
     mova m5, m_blue
     mova m6, m_red
-    punpckhbw m5, m_green
+    punpckhbw m5,     m_green
     punpcklbw m_blue, m_green
-    punpckhbw m6, m_alpha
-    punpcklbw m_red, m_alpha
+    punpckhbw m6,     m_alpha
+    punpcklbw m_red,  m_alpha
     mova m_green, m_blue
     mova m_alpha, m5
     punpcklwd m_blue, m_red
@@ -207,14 +301,23 @@ cglobal %1_420_%2%3, GPR_num, GPR_num, reg_num, parameters
     punpcklwd m5, m6
     punpckhwd m_alpha, m6
     mova [imageq + 0], m_blue
-    mova [imageq + 8 * time_num], m_green
+    mova [imageq + 8  * time_num], m_green
     mova [imageq + 16 * time_num], m5
     mova [imageq + 24 * time_num], m_alpha
 %else ; PACK RGB15/16
 %define depth 2
-%define blue_dither  [pointer_c_ditherq + 2 * 8]
-%define green_dither [pointer_c_ditherq + 1 * 8]
-%define red_dither   [pointer_c_ditherq + 0 * 8]
+%if cpuflag(ssse3)
+    %define red_dither m3
+    %define green_dither m4
+    %define blue_dither m5
+    VBROADCASTSD red_dither,   [pointer_c_ditherq + 0 * 8]
+    VBROADCASTSD green_dither, [pointer_c_ditherq + 1 * 8]
+    VBROADCASTSD blue_dither,  [pointer_c_ditherq + 2 * 8]
+%else ; cpuflag(mmx/mmxext)
+%define blue_dither  [pointer_c_ditherq + 2  * 8]
+%define green_dither [pointer_c_ditherq + 1  * 8]
+%define red_dither   [pointer_c_ditherq + 0  * 8]
+%endif
 %if %3 == 15
 %define gmask pb_03
 %define isRGB15 1
@@ -268,3 +371,13 @@ yuv2rgb_fn yuv,  rgb, 16
 INIT_MMX mmxext
 yuv2rgb_fn yuv, rgb, 24
 yuv2rgb_fn yuv, bgr, 24
+
+INIT_XMM ssse3
+yuv2rgb_fn yuv,  rgb, 24
+yuv2rgb_fn yuv,  bgr, 24
+yuv2rgb_fn yuv,  rgb, 32
+yuv2rgb_fn yuv,  bgr, 32
+yuv2rgb_fn yuva, rgb, 32
+yuv2rgb_fn yuva, bgr, 32
+yuv2rgb_fn yuv,  rgb, 15
+yuv2rgb_fn yuv,  rgb, 16