[FFmpeg-devel] [PATCH 5/6] add x86_64 8-bit simple_idct function

[James Darnley]

---
 libavcodec/tests/x86/dct.c       |  2 ++
 libavcodec/x86/idctdsp_init.c    | 10 ++++++++++
 libavcodec/x86/simple_idct.h     |  3 +++
 libavcodec/x86/simple_idct10.asm |  6 ++++++
 4 files changed, 21 insertions(+)

diff --git a/libavcodec/tests/x86/dct.c b/libavcodec/tests/x86/dct.c
index 97116570f4..a9b949f2b1 100644
--- a/libavcodec/tests/x86/dct.c
+++ b/libavcodec/tests/x86/dct.c
@@ -88,10 +88,12 @@ static const struct algo idct_tab_arch[] = {
 #if HAVE_YASM
 #if ARCH_X86_64
 #if HAVE_SSE2_EXTERNAL
+    { "SIMPLE8-SSE2",   ff_simple_idct8_sse2,  FF_IDCT_PERM_TRANSPOSE, 
AV_CPU_FLAG_SSE2},
     { "SIMPLE10-SSE2",  ff_simple_idct10_sse2, FF_IDCT_PERM_TRANSPOSE, 
AV_CPU_FLAG_SSE2},
     { "SIMPLE12-SSE2",  ff_simple_idct12_sse2, FF_IDCT_PERM_TRANSPOSE, 
AV_CPU_FLAG_SSE2, 1 },
 #endif
 #if HAVE_AVX_EXTERNAL
+    { "SIMPLE8-AVX",    ff_simple_idct8_avx,   FF_IDCT_PERM_TRANSPOSE, 
AV_CPU_FLAG_AVX},
     { "SIMPLE10-AVX",   ff_simple_idct10_avx,  FF_IDCT_PERM_TRANSPOSE, 
AV_CPU_FLAG_AVX},
     { "SIMPLE12-AVX",   ff_simple_idct12_avx,  FF_IDCT_PERM_TRANSPOSE, 
AV_CPU_FLAG_AVX,  1 },
 #endif
diff --git a/libavcodec/x86/idctdsp_init.c b/libavcodec/x86/idctdsp_init.c
index 82530a5cc4..1e30496da0 100644
--- a/libavcodec/x86/idctdsp_init.c
+++ b/libavcodec/x86/idctdsp_init.c
@@ -95,6 +95,16 @@ av_cold void ff_idctdsp_init_x86(IDCTDSPContext *c, 
AVCodecContext *avctx,
                 c->idct      = ff_simple_idct_sse2;
                 c->perm_type = FF_IDCT_PERM_SIMPLE;
         }
+
+        if (ARCH_X86_64 &&
+            !high_bit_depth &&
+            avctx->lowres == 0 &&
+            (avctx->idct_algo == FF_IDCT_AUTO ||
+                avctx->idct_algo == FF_IDCT_SIMPLEAUTO ||
+                avctx->idct_algo == FF_IDCT_SIMPLE)) {
+                c->idct      = ff_simple_idct8_sse2;
+                c->perm_type = FF_IDCT_PERM_TRANSPOSE;
+        }
     }
 
     if (ARCH_X86_64 && avctx->lowres == 0) {
diff --git a/libavcodec/x86/simple_idct.h b/libavcodec/x86/simple_idct.h
index b19e910372..7a26e96b60 100644
--- a/libavcodec/x86/simple_idct.h
+++ b/libavcodec/x86/simple_idct.h
@@ -30,6 +30,9 @@ void ff_simple_idct_sse2(int16_t *block);
 void ff_simple_idct_add_sse2(uint8_t *dest, ptrdiff_t line_size, int16_t 
*block);
 void ff_simple_idct_put_sse2(uint8_t *dest, ptrdiff_t line_size, int16_t 
*block);
 
+void ff_simple_idct8_sse2(int16_t *block);
+void ff_simple_idct8_avx(int16_t *block);
+
 void ff_simple_idct10_sse2(int16_t *block);
 void ff_simple_idct10_avx(int16_t *block);
 
diff --git a/libavcodec/x86/simple_idct10.asm b/libavcodec/x86/simple_idct10.asm
index 7cfd33eaa3..b4b47afcee 100644
--- a/libavcodec/x86/simple_idct10.asm
+++ b/libavcodec/x86/simple_idct10.asm
@@ -33,9 +33,11 @@ cextern pw_2
 cextern pw_16
 cextern pw_1023
 cextern pw_4095
+pd_round_11: times 4 dd 1<<(11-1)
 pd_round_12: times 4 dd 1<<(12-1)
 pd_round_15: times 4 dd 1<<(15-1)
 pd_round_19: times 4 dd 1<<(19-1)
+pd_round_20: times 4 dd 1<<(20-1)
 
 %macro CONST_DEC  3
 const %1
@@ -68,6 +70,10 @@ CONST_DEC  w7_min_w5,    W7sh2, -W5sh2
 SECTION .text
 
 %macro idct_fn 0
+cglobal simple_idct8, 1, 1, 16, block
+    IDCT_FN    "", 11, "", 20
+    RET
+
 cglobal simple_idct10, 1, 1, 16, block
     IDCT_FN    "", 12, "", 19
     RET
-- 
2.12.2

_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
http://ffmpeg.org/mailman/listinfo/ffmpeg-devel