x86/takdsp: add avx2 versions of all functions

On an Intel Core i7 12700k:

decorrelate_ls_c: 814.3
decorrelate_ls_sse2: 165.8
decorrelate_ls_avx2: 101.3
decorrelate_sf_c: 1602.6
decorrelate_sf_sse4: 640.1
decorrelate_sf_avx2: 324.6
decorrelate_sm_c: 1564.8
decorrelate_sm_sse2: 379.3
decorrelate_sm_avx2: 203.3
decorrelate_sr_c: 785.3
decorrelate_sr_sse2: 176.3
decorrelate_sr_avx2: 99.8

Tested-by: Lynne <dev@lynne.ee>
Signed-off-by: James Almer <jamrial@gmail.com>

libavcodec/x86/takdsp.asm

@@ -28,7 +28,7 @@ pd_128: times 4 dd 128
 
 SECTION .text
 
-INIT_XMM sse2
+%macro TAK_DECORRELATE 0
 cglobal tak_decorrelate_ls, 3, 3, 2, p1, p2, length
     shl                     lengthd, 2
     add                         p1q, lengthq
@@ -73,10 +73,8 @@ cglobal tak_decorrelate_sm, 3, 3, 6, p1, p2, length
     mova                         m1, [p2q+lengthq]
     mova                         m3, [p1q+lengthq+mmsize]
     mova                         m4, [p2q+lengthq+mmsize]
-    mova                         m2, m1
-    mova                         m5, m4
-    psrad                        m2, 1
-    psrad                        m5, 1
+    psrad                        m2, m1, 1
+    psrad                        m5, m4, 1
     psubd                        m0, m2
     psubd                        m3, m5
     paddd                        m1, m0
@@ -88,29 +86,44 @@ cglobal tak_decorrelate_sm, 3, 3, 6, p1, p2, length
     add                     lengthq, mmsize*2
     jl .loop
     RET
+%endmacro
 
-INIT_XMM sse4
+INIT_XMM sse2
+TAK_DECORRELATE
+INIT_YMM avx2
+TAK_DECORRELATE
+
+%macro TAK_DECORRELATE_SF 0
 cglobal tak_decorrelate_sf, 3, 3, 5, p1, p2, length, dshift, dfactor
     shl             lengthd, 2
     add                 p1q, lengthq
     add                 p2q, lengthq
     neg             lengthq
 
-    movd                 m2, dshiftm
-    movd                 m3, dfactorm
-    pshufd               m3, m3, 0
-    mova                 m4, [pd_128]
+    movd                xm2, dshiftm
+%if UNIX64
+    movd                xm3, dfactorm
+    VPBROADCASTD         m3, xm3
+%else
+    VPBROADCASTD         m3, dfactorm
+%endif
+    VBROADCASTI128       m4, [pd_128]
 
 .loop:
-    mova                 m0, [p1q+lengthq]
     mova                 m1, [p2q+lengthq]
-    psrad                m1, m2
+    psrad                m1, xm2
     pmulld               m1, m3
     paddd                m1, m4
     psrad                m1, 8
-    pslld                m1, m2
-    psubd                m1, m0
+    pslld                m1, xm2
+    psubd                m1, [p1q+lengthq]
     mova      [p1q+lengthq], m1
     add             lengthq, mmsize
     jl .loop
     RET
+%endmacro
+
+INIT_XMM sse4
+TAK_DECORRELATE_SF
+INIT_YMM avx2
+TAK_DECORRELATE_SF

libavcodec/x86/takdsp_init.c

@@ -24,9 +24,13 @@
 #include "config.h"
 
 void ff_tak_decorrelate_ls_sse2(const int32_t *p1, int32_t *p2, int length);
+void ff_tak_decorrelate_ls_avx2(const int32_t *p1, int32_t *p2, int length);
 void ff_tak_decorrelate_sr_sse2(int32_t *p1, const int32_t *p2, int length);
+void ff_tak_decorrelate_sr_avx2(int32_t *p1, const int32_t *p2, int length);
 void ff_tak_decorrelate_sm_sse2(int32_t *p1, int32_t *p2, int length);
+void ff_tak_decorrelate_sm_avx2(int32_t *p1, int32_t *p2, int length);
 void ff_tak_decorrelate_sf_sse4(int32_t *p1, const int32_t *p2, int length, int dshift, int dfactor);
+void ff_tak_decorrelate_sf_avx2(int32_t *p1, const int32_t *p2, int length, int dshift, int dfactor);
 
 av_cold void ff_takdsp_init_x86(TAKDSPContext *c)
 {
@@ -42,5 +46,12 @@ av_cold void ff_takdsp_init_x86(TAKDSPContext *c)
     if (EXTERNAL_SSE4(cpu_flags)) {
         c->decorrelate_sf = ff_tak_decorrelate_sf_sse4;
     }
+
+    if (EXTERNAL_AVX2_FAST(cpu_flags)) {
+        c->decorrelate_ls = ff_tak_decorrelate_ls_avx2;
+        c->decorrelate_sr = ff_tak_decorrelate_sr_avx2;
+        c->decorrelate_sm = ff_tak_decorrelate_sm_avx2;
+        c->decorrelate_sf = ff_tak_decorrelate_sf_avx2;
+    }
 #endif
 }