Merge commit '8438b3f0'

* commit '8438b3f0':
  aarch64: h264 idct NEON assembler optimizations
Merged-by: Michael Niedermayer <michaelni@gmx.at>

libavcodec/aarch64/Makefile

 OBJS-$(CONFIG_H264CHROMA)               += aarch64/h264chroma_init_aarch64.o
+OBJS-$(CONFIG_H264DSP)                  += aarch64/h264dsp_init_aarch64.o
 OBJS-$(CONFIG_RV40_DECODER)             += aarch64/rv40dsp_init_aarch64.o
 OBJS-$(CONFIG_VC1_DECODER)              += aarch64/vc1dsp_init_aarch64.o
 
 NEON-OBJS-$(CONFIG_H264CHROMA)          += aarch64/h264cmc_neon.o
+NEON-OBJS-$(CONFIG_H264DSP)             += aarch64/h264idct_neon.o

libavcodec/aarch64/h264dsp_init_aarch64.c

+/*
+ * Copyright (c) 2010 Mans Rullgard <mans@mansr.com>
+ *
+ * This file is part of FFmpeg.
+ *
+ * FFmpeg is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation; either
+ * version 2.1 of the License, or (at your option) any later version.
+ *
+ * FFmpeg is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with FFmpeg; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
+ */
+
+#include <stdint.h>
+
+#include "libavutil/attributes.h"
+#include "libavutil/cpu.h"
+#include "libavutil/aarch64/cpu.h"
+#include "libavcodec/h264dsp.h"
+
+void ff_h264_idct_add_neon(uint8_t *dst, int16_t *block, int stride);
+void ff_h264_idct_dc_add_neon(uint8_t *dst, int16_t *block, int stride);
+void ff_h264_idct_add16_neon(uint8_t *dst, const int *block_offset,
+                             int16_t *block, int stride,
+                             const uint8_t nnzc[6*8]);
+void ff_h264_idct_add16intra_neon(uint8_t *dst, const int *block_offset,
+                                  int16_t *block, int stride,
+                                  const uint8_t nnzc[6*8]);
+void ff_h264_idct_add8_neon(uint8_t **dest, const int *block_offset,
+                            int16_t *block, int stride,
+                            const uint8_t nnzc[6*8]);
+
+void ff_h264_idct8_add_neon(uint8_t *dst, int16_t *block, int stride);
+void ff_h264_idct8_dc_add_neon(uint8_t *dst, int16_t *block, int stride);
+void ff_h264_idct8_add4_neon(uint8_t *dst, const int *block_offset,
+                             int16_t *block, int stride,
+                             const uint8_t nnzc[6*8]);
+
+av_cold void ff_h264dsp_init_aarch64(H264DSPContext *c, const int bit_depth,
+                                     const int chroma_format_idc)
+{
+    int cpu_flags = av_get_cpu_flags();
+
+    if (have_neon(cpu_flags) && bit_depth == 8) {
+        c->h264_idct_add        = ff_h264_idct_add_neon;
+        c->h264_idct_dc_add     = ff_h264_idct_dc_add_neon;
+        c->h264_idct_add16      = ff_h264_idct_add16_neon;
+        c->h264_idct_add16intra = ff_h264_idct_add16intra_neon;
+        if (chroma_format_idc <= 1)
+            c->h264_idct_add8   = ff_h264_idct_add8_neon;
+        c->h264_idct8_add       = ff_h264_idct8_add_neon;
+        c->h264_idct8_dc_add    = ff_h264_idct8_dc_add_neon;
+        c->h264_idct8_add4      = ff_h264_idct8_add4_neon;
+    }
+}

libavcodec/aarch64/neon.S

+/*
+ * This file is part of FFmpeg.
+ *
+ * FFmpeg is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation; either
+ * version 2.1 of the License, or (at your option) any later version.
+ *
+ * FFmpeg is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with FFmpeg; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
+ */
+
+.macro  transpose_4x4H  r0, r1, r2, r3, r4, r5, r6, r7
+        trn1            \r4\().4H,  \r0\().4H,  \r1\().4H
+        trn2            \r5\().4H,  \r0\().4H,  \r1\().4H
+        trn1            \r7\().4H,  \r3\().4H,  \r2\().4H
+        trn2            \r6\().4H,  \r3\().4H,  \r2\().4H
+        trn1            \r0\().2S,  \r4\().2S,  \r7\().2S
+        trn2            \r3\().2S,  \r4\().2S,  \r7\().2S
+        trn1            \r1\().2S,  \r5\().2S,  \r6\().2S
+        trn2            \r2\().2S,  \r5\().2S,  \r6\().2S
+.endm
+
+.macro  transpose_8x8H  r0, r1, r2, r3, r4, r5, r6, r7, r8, r9
+        trn1            \r8\().8H,  \r0\().8H,  \r1\().8H
+        trn2            \r9\().8H,  \r0\().8H,  \r1\().8H
+        trn1            \r1\().8H,  \r2\().8H,  \r3\().8H
+        trn2            \r3\().8H,  \r2\().8H,  \r3\().8H
+        trn1            \r0\().8H,  \r4\().8H,  \r5\().8H
+        trn2            \r5\().8H,  \r4\().8H,  \r5\().8H
+        trn1            \r2\().8H,  \r6\().8H,  \r7\().8H
+        trn2            \r7\().8H,  \r6\().8H,  \r7\().8H
+
+        trn1            \r4\().4S,  \r0\().4S,  \r2\().4S
+        trn2            \r2\().4S,  \r0\().4S,  \r2\().4S
+        trn1            \r6\().4S,  \r5\().4S,  \r7\().4S
+        trn2            \r7\().4S,  \r5\().4S,  \r7\().4S
+        trn1            \r5\().4S,  \r9\().4S,  \r3\().4S
+        trn2            \r9\().4S,  \r9\().4S,  \r3\().4S
+        trn1            \r3\().4S,  \r8\().4S,  \r1\().4S
+        trn2            \r8\().4S,  \r8\().4S,  \r1\().4S
+
+        trn1            \r0\().2D,  \r3\().2D,  \r4\().2D
+        trn2            \r4\().2D,  \r3\().2D,  \r4\().2D
+
+        trn1            \r1\().2D,  \r5\().2D,  \r6\().2D
+        trn2            \r5\().2D,  \r5\().2D,  \r6\().2D
+
+        trn2            \r6\().2D,  \r8\().2D,  \r2\().2D
+        trn1            \r2\().2D,  \r8\().2D,  \r2\().2D
+
+        trn1            \r3\().2D,  \r9\().2D,  \r7\().2D
+        trn2            \r7\().2D,  \r9\().2D,  \r7\().2D
+
+.endm

libavcodec/h264dsp.c

@@ -180,6 +180,7 @@ av_cold void ff_h264dsp_init(H264DSPContext *c, const int bit_depth,
     }
     c->h264_find_start_code_candidate = h264_find_start_code_candidate_c;
 
+    if (ARCH_AARCH64) ff_h264dsp_init_aarch64(c, bit_depth, chroma_format_idc);
     if (ARCH_ARM) ff_h264dsp_init_arm(c, bit_depth, chroma_format_idc);
     if (ARCH_PPC) ff_h264dsp_init_ppc(c, bit_depth, chroma_format_idc);
     if (ARCH_X86) ff_h264dsp_init_x86(c, bit_depth, chroma_format_idc);

libavcodec/h264dsp.h

@@ -118,6 +118,8 @@ typedef struct H264DSPContext {
 
 void ff_h264dsp_init(H264DSPContext *c, const int bit_depth,
                      const int chroma_format_idc);
+void ff_h264dsp_init_aarch64(H264DSPContext *c, const int bit_depth,
+                             const int chroma_format_idc);
 void ff_h264dsp_init_arm(H264DSPContext *c, const int bit_depth,
                          const int chroma_format_idc);
 void ff_h264dsp_init_ppc(H264DSPContext *c, const int bit_depth,