[FFmpeg-cvslog] swscale/x86/rgb2rgb: remove mmxext version of shuffle_bytes_2103

[James Almer]

ffmpeg | branch: master | James Almer <jamrial at gmail.com> | Sun Jun  9 12:39:48 2024 -0300| [e8cef5e1529b1975cb36a35b3848eff0c5aeda95] | committer: James Almer

swscale/x86/rgb2rgb: remove mmxext version of shuffle_bytes_2103

Signed-off-by: James Almer <jamrial at gmail.com>

> http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=e8cef5e1529b1975cb36a35b3848eff0c5aeda95
---

 libswscale/x86/rgb2rgb.c     |  4 ---
 libswscale/x86/rgb_2_rgb.asm | 64 --------------------------------------------
 2 files changed, 68 deletions(-)

diff --git a/libswscale/x86/rgb2rgb.c b/libswscale/x86/rgb2rgb.c
index 1dc8f1549c..4b567e8049 100644
--- a/libswscale/x86/rgb2rgb.c
+++ b/libswscale/x86/rgb2rgb.c
@@ -2343,7 +2343,6 @@ static void interleave_bytes_sse2(const uint8_t *src1, const uint8_t *src2, uint
 
 #endif /* HAVE_INLINE_ASM */
 
-void ff_shuffle_bytes_2103_mmxext(const uint8_t *src, uint8_t *dst, int src_size);
 void ff_shuffle_bytes_2103_ssse3(const uint8_t *src, uint8_t *dst, int src_size);
 void ff_shuffle_bytes_0321_ssse3(const uint8_t *src, uint8_t *dst, int src_size);
 void ff_shuffle_bytes_1230_ssse3(const uint8_t *src, uint8_t *dst, int src_size);
@@ -2406,9 +2405,6 @@ av_cold void rgb2rgb_init_x86(void)
         interleaveBytes = interleave_bytes_sse2;
 #endif /* HAVE_INLINE_ASM */
 
-    if (EXTERNAL_MMXEXT(cpu_flags)) {
-        shuffle_bytes_2103 = ff_shuffle_bytes_2103_mmxext;
-    }
 #if HAVE_SSE2_EXTERNAL
     if (EXTERNAL_SSE2(cpu_flags)) {
 #if ARCH_X86_64
diff --git a/libswscale/x86/rgb_2_rgb.asm b/libswscale/x86/rgb_2_rgb.asm
index 0bf1278718..c4aa8d883c 100644
--- a/libswscale/x86/rgb_2_rgb.asm
+++ b/libswscale/x86/rgb_2_rgb.asm
@@ -25,7 +25,6 @@
 
 SECTION_RODATA
 
-pb_mask_shuffle2103_mmx times 8 dw 255
 pb_shuffle2103: db 2, 1, 0, 3, 6, 5, 4, 7, 10, 9, 8, 11, 14, 13, 12, 15
 pb_shuffle0321: db 0, 3, 2, 1, 4, 7, 6, 5, 8, 11, 10, 9, 12, 15, 14, 13
 pb_shuffle1230: db 1, 2, 3, 0, 5, 6, 7, 4, 9, 10, 11, 8, 13, 14, 15, 12
@@ -47,69 +46,6 @@ SECTION .text
 %endif
 %endmacro
 
-;------------------------------------------------------------------------------
-; shuffle_bytes_2103_mmext (const uint8_t *src, uint8_t *dst, int src_size)
-;------------------------------------------------------------------------------
-INIT_MMX mmxext
-cglobal shuffle_bytes_2103, 3, 5, 8, src, dst, w, tmp, x
-    mova   m6, [pb_mask_shuffle2103_mmx]
-    mova   m7, m6
-    psllq  m7, 8
-
-    movsxdifnidn wq, wd
-    mov xq, wq
-
-    add        srcq, wq
-    add        dstq, wq
-    neg          wq
-
-;calc scalar loop
-    and xq, mmsize*2 -4
-    je .loop_simd
-
-.loop_scalar:
-   mov          tmpb, [srcq + wq + 2]
-   mov [dstq+wq + 0], tmpb
-   mov          tmpb, [srcq + wq + 1]
-   mov [dstq+wq + 1], tmpb
-   mov          tmpb, [srcq + wq + 0]
-   mov [dstq+wq + 2], tmpb
-   mov          tmpb, [srcq + wq + 3]
-   mov [dstq+wq + 3], tmpb
-   add            wq, 4
-   sub            xq, 4
-   jg .loop_scalar
-
-;check if src_size < mmsize * 2
-cmp wq, 0
-jge .end
-
-.loop_simd:
-    movu     m0, [srcq+wq]
-    movu     m1, [srcq+wq+8]
-
-    pshufw   m3, m0, 177
-    pshufw   m5, m1, 177
-
-    pand     m0, m7
-    pand     m3, m6
-
-    pand     m1, m7
-    pand     m5, m6
-
-    por      m0, m3
-    por      m1, m5
-
-    movu      [dstq+wq], m0
-    movu  [dstq+wq + 8], m1
-
-    add              wq, mmsize*2
-    jl .loop_simd
-
-.end:
-    emms
-    RET
-
 ;------------------------------------------------------------------------------
 ; shuffle_bytes_## (const uint8_t *src, uint8_t *dst, int src_size)
 ;------------------------------------------------------------------------------