[FFmpeg-cvslog] swresample/x86/resample: extend resample_double to support avx and fma3

[Muhammad Faiz]

ffmpeg | branch: master | Muhammad Faiz <mfcc64 at gmail.com> | Thu Mar 16 11:33:16 2017 +0700| [de1308429ae649c899b74365f0dc72847676ba75] | committer: Muhammad Faiz

swresample/x86/resample: extend resample_double to support avx and fma3

benchmark:
sse2 10.670s
avx   8.763s
fma3  8.380s

Signed-off-by: Muhammad Faiz <mfcc64 at gmail.com>

> http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=de1308429ae649c899b74365f0dc72847676ba75
---

 libswresample/x86/resample.asm    | 15 ++++++++++++---
 libswresample/x86/resample_init.c | 10 ++++++++++
 2 files changed, 22 insertions(+), 3 deletions(-)

diff --git a/libswresample/x86/resample.asm b/libswresample/x86/resample.asm
index 4163df1..7107cf9 100644
--- a/libswresample/x86/resample.asm
+++ b/libswresample/x86/resample.asm
@@ -203,7 +203,7 @@ cglobal resample_common_%1, 1, 7, 2, ctx, phase_count, dst, frac, \
     ; horizontal sum & store
 %if mmsize == 32
     vextractf128                 xm1, m0, 0x1
-    addps                        xm0, xm1
+    addp%4                       xm0, xm1
 %endif
     movhlps                      xm1, xm0
 %ifidn %1, float
@@ -489,8 +489,8 @@ cglobal resample_linear_%1, 1, 7, 5, ctx, min_filter_length_x4, filter2, \
 %if mmsize == 32
     vextractf128                 xm1, m0, 0x1
     vextractf128                 xm3, m2, 0x1
-    addps                        xm0, xm1
-    addps                        xm2, xm3
+    addp%4                       xm0, xm1
+    addp%4                       xm2, xm3
 %endif
     cvtsi2s%4                    xm1, fracd
     subp%4                       xm2, xm0
@@ -608,3 +608,12 @@ RESAMPLE_FNS int16, 2, 1
 
 INIT_XMM sse2
 RESAMPLE_FNS double, 8, 3, d, pdbl_1
+
+%if HAVE_AVX_EXTERNAL
+INIT_YMM avx
+RESAMPLE_FNS double, 8, 3, d, pdbl_1
+%endif
+%if HAVE_FMA3_EXTERNAL
+INIT_YMM fma3
+RESAMPLE_FNS double, 8, 3, d, pdbl_1
+%endif
diff --git a/libswresample/x86/resample_init.c b/libswresample/x86/resample_init.c
index e515762..c6b2a36 100644
--- a/libswresample/x86/resample_init.c
+++ b/libswresample/x86/resample_init.c
@@ -42,6 +42,8 @@ RESAMPLE_FUNCS(float,  avx);
 RESAMPLE_FUNCS(float,  fma3);
 RESAMPLE_FUNCS(float,  fma4);
 RESAMPLE_FUNCS(double, sse2);
+RESAMPLE_FUNCS(double, avx);
+RESAMPLE_FUNCS(double, fma3);
 
 av_cold void swri_resample_dsp_x86_init(ResampleContext *c)
 {
@@ -85,6 +87,14 @@ av_cold void swri_resample_dsp_x86_init(ResampleContext *c)
             c->dsp.resample_linear = ff_resample_linear_double_sse2;
             c->dsp.resample_common = ff_resample_common_double_sse2;
         }
+        if (EXTERNAL_AVX_FAST(mm_flags)) {
+            c->dsp.resample_linear = ff_resample_linear_double_avx;
+            c->dsp.resample_common = ff_resample_common_double_avx;
+        }
+        if (EXTERNAL_FMA3_FAST(mm_flags)) {
+            c->dsp.resample_linear = ff_resample_linear_double_fma3;
+            c->dsp.resample_common = ff_resample_common_double_fma3;
+        }
         break;
     }
 }