[FFmpeg-devel] [PATCH] h264_intrapred: Remove ff_pred16x16_horizontal_8_mmxext

[James Almer]

On 2/11/2024 6:24 PM, Kieran Kunhya wrote:
> $subj, now with forward declaration also removed.

This function is trivial to convert to SSE2, so better do that than 
removing it. Attached.
If other functions are harder to port to SSE2, then sure, they can be 
removed.
-------------- next part --------------
From fdf1db323c1209fcb927f7df0d041d78f6214bf7 Mon Sep 17 00:00:00 2001
From: James Almer <jamrial at gmail.com>
Date: Sun, 11 Feb 2024 18:35:31 -0300
Subject: [PATCH] x86/h264_intrapred: convert ff_pred16x16_horizontal_8_mmxext
 to sse2

Signed-off-by: James Almer <jamrial at gmail.com>
---
 libavcodec/x86/h264_intrapred.asm    | 4 +---
 libavcodec/x86/h264_intrapred_init.c | 4 ++--
 2 files changed, 3 insertions(+), 5 deletions(-)

diff --git a/libavcodec/x86/h264_intrapred.asm b/libavcodec/x86/h264_intrapred.asm
index 8a38ba2bb5..49a63f900e 100644
--- a/libavcodec/x86/h264_intrapred.asm
+++ b/libavcodec/x86/h264_intrapred.asm
@@ -86,8 +86,6 @@ cglobal pred16x16_horizontal_8, 2,3
     punpcklbw m1, m1
     SPLATW    m0, m0, 3
     SPLATW    m1, m1, 3
-    mova [r0+r1*0+8], m0
-    mova [r0+r1*1+8], m1
 %endif
 
     mova [r0+r1*0], m0
@@ -98,7 +96,7 @@ cglobal pred16x16_horizontal_8, 2,3
     RET
 %endmacro
 
-INIT_MMX mmxext
+INIT_XMM sse2
 PRED16x16_H
 INIT_XMM ssse3
 PRED16x16_H
diff --git a/libavcodec/x86/h264_intrapred_init.c b/libavcodec/x86/h264_intrapred_init.c
index ee46927a24..06cb0ea8fe 100644
--- a/libavcodec/x86/h264_intrapred_init.c
+++ b/libavcodec/x86/h264_intrapred_init.c
@@ -100,7 +100,7 @@ PRED16x16(horizontal, 10, sse2)
 
 /* 8-bit versions */
 PRED16x16(vertical, 8, sse)
-PRED16x16(horizontal, 8, mmxext)
+PRED16x16(horizontal, 8, sse2)
 PRED16x16(horizontal, 8, ssse3)
 PRED16x16(dc, 8, sse2)
 PRED16x16(dc, 8, ssse3)
@@ -170,7 +170,6 @@ av_cold void ff_h264_pred_init_x86(H264PredContext *h, int codec_id,
         }
 
         if (EXTERNAL_MMXEXT(cpu_flags)) {
-            h->pred16x16[HOR_PRED8x8            ] = ff_pred16x16_horizontal_8_mmxext;
             if (chroma_format_idc <= 1)
                 h->pred8x8[HOR_PRED8x8          ] = ff_pred8x8_horizontal_8_mmxext;
             h->pred8x8l [TOP_DC_PRED            ] = ff_pred8x8l_top_dc_8_mmxext;
@@ -210,6 +209,7 @@ av_cold void ff_h264_pred_init_x86(H264PredContext *h, int codec_id,
         }
 
         if (EXTERNAL_SSE2(cpu_flags)) {
+            h->pred16x16[HOR_PRED8x8          ] = ff_pred16x16_horizontal_8_sse2;
             h->pred16x16[DC_PRED8x8           ] = ff_pred16x16_dc_8_sse2;
             h->pred8x8l [DIAG_DOWN_LEFT_PRED  ] = ff_pred8x8l_down_left_8_sse2;
             h->pred8x8l [DIAG_DOWN_RIGHT_PRED ] = ff_pred8x8l_down_right_8_sse2;
-- 
2.43.0