aarch64: hevc: Produce epel_bi_hv functions for both neon and i8mm

In addition to just templating, this contains one change to
ff_hevc_put_hevc_epel_bi_hv32_8, by setting the w6 register
which ff_hevc_put_hevc_epel_h32_8_neon requires.

AWS Graviton 3:
put_hevc_epel_bi_hv4_8_c: 176.5
put_hevc_epel_bi_hv4_8_neon: 62.0
put_hevc_epel_bi_hv4_8_i8mm: 58.0
put_hevc_epel_bi_hv6_8_c: 343.7
put_hevc_epel_bi_hv6_8_neon: 109.7
put_hevc_epel_bi_hv6_8_i8mm: 105.7
put_hevc_epel_bi_hv8_8_c: 536.0
put_hevc_epel_bi_hv8_8_neon: 112.7
put_hevc_epel_bi_hv8_8_i8mm: 111.7
put_hevc_epel_bi_hv12_8_c: 1107.7
put_hevc_epel_bi_hv12_8_neon: 254.7
put_hevc_epel_bi_hv12_8_i8mm: 239.0
put_hevc_epel_bi_hv16_8_c: 1927.7
put_hevc_epel_bi_hv16_8_neon: 356.2
put_hevc_epel_bi_hv16_8_i8mm: 334.2
put_hevc_epel_bi_hv24_8_c: 4195.2
put_hevc_epel_bi_hv24_8_neon: 736.7
put_hevc_epel_bi_hv24_8_i8mm: 715.5
put_hevc_epel_bi_hv32_8_c: 7280.5
put_hevc_epel_bi_hv32_8_neon: 1287.7
put_hevc_epel_bi_hv32_8_i8mm: 1162.2
put_hevc_epel_bi_hv48_8_c: 16857.7
put_hevc_epel_bi_hv48_8_neon: 2836.2
put_hevc_epel_bi_hv48_8_i8mm: 2908.5
put_hevc_epel_bi_hv64_8_c: 29248.2
put_hevc_epel_bi_hv64_8_neon: 5051.7
put_hevc_epel_bi_hv64_8_i8mm: 4491.5

Signed-off-by: Martin Storsjö <martin@martin.st>

2 files changed, 36 insertions, 31 deletions

diff --git a/libavcodec/aarch64/hevcdsp_epel_neon.S b/libavcodec/aarch64/hevcdsp_epel_neon.S
index 4d37cab572..378b0f7fb2 100644
--- a/libavcodec/aarch64/hevcdsp_epel_neon.S
+++ b/libavcodec/aarch64/hevcdsp_epel_neon.S
@@ -3792,14 +3792,6 @@ endfunc
 
 epel_uni_w_hv neon
 
-#if HAVE_I8MM
-ENABLE_I8MM
-
-epel_uni_w_hv neon_i8mm
-
-DISABLE_I8MM
-#endif
-
 
 function hevc_put_hevc_epel_bi_hv4_8_end_neon
         load_epel_filterh x7, x6
@@ -3979,10 +3971,8 @@ function hevc_put_hevc_epel_bi_hv32_8_end_neon
         ret
 endfunc
 
-#if HAVE_I8MM
-ENABLE_I8MM
-
-function ff_hevc_put_hevc_epel_bi_hv4_8_neon_i8mm, export=1
+.macro epel_bi_hv suffix
+function ff_hevc_put_hevc_epel_bi_hv4_8_\suffix, export=1
         add             w10, w5, #3
         lsl             x10, x10, #7
         sub             sp, sp, x10 // tmp_array
@@ -3995,14 +3985,14 @@ function ff_hevc_put_hevc_epel_bi_hv4_8_neon_i8mm, export=1
         add             w3, w5, #3
         mov             x4, x6
         mov             x5, x7
-        bl              X(ff_hevc_put_hevc_epel_h4_8_neon_i8mm)
+        bl              X(ff_hevc_put_hevc_epel_h4_8_\suffix)
         ldp             x4, x5, [sp, #16]
         ldp             x0, x1, [sp, #32]
         ldp             x7, x30, [sp], #48
         b               hevc_put_hevc_epel_bi_hv4_8_end_neon
 endfunc
 
-function ff_hevc_put_hevc_epel_bi_hv6_8_neon_i8mm, export=1
+function ff_hevc_put_hevc_epel_bi_hv6_8_\suffix, export=1
         add             w10, w5, #3
         lsl             x10, x10, #7
         sub             sp, sp, x10 // tmp_array
@@ -4015,14 +4005,14 @@ function ff_hevc_put_hevc_epel_bi_hv6_8_neon_i8mm, export=1
         add             w3, w5, #3
         mov             x4, x6
         mov             x5, x7
-        bl              X(ff_hevc_put_hevc_epel_h6_8_neon_i8mm)
+        bl              X(ff_hevc_put_hevc_epel_h6_8_\suffix)
         ldp             x4, x5, [sp, #16]
         ldp             x0, x1, [sp, #32]
         ldp             x7, x30, [sp], #48
         b               hevc_put_hevc_epel_bi_hv6_8_end_neon
 endfunc
 
-function ff_hevc_put_hevc_epel_bi_hv8_8_neon_i8mm, export=1
+function ff_hevc_put_hevc_epel_bi_hv8_8_\suffix, export=1
         add             w10, w5, #3
         lsl             x10, x10, #7
         sub             sp, sp, x10 // tmp_array
@@ -4035,14 +4025,14 @@ function ff_hevc_put_hevc_epel_bi_hv8_8_neon_i8mm, export=1
         add             w3, w5, #3
         mov             x4, x6
         mov             x5, x7
-        bl              X(ff_hevc_put_hevc_epel_h8_8_neon_i8mm)
+        bl              X(ff_hevc_put_hevc_epel_h8_8_\suffix)
         ldp             x4, x5, [sp, #16]
         ldp             x0, x1, [sp, #32]
         ldp             x7, x30, [sp], #48
         b               hevc_put_hevc_epel_bi_hv8_8_end_neon
 endfunc
 
-function ff_hevc_put_hevc_epel_bi_hv12_8_neon_i8mm, export=1
+function ff_hevc_put_hevc_epel_bi_hv12_8_\suffix, export=1
         add             w10, w5, #3
         lsl             x10, x10, #7
         sub             sp, sp, x10 // tmp_array
@@ -4055,14 +4045,14 @@ function ff_hevc_put_hevc_epel_bi_hv12_8_neon_i8mm, export=1
         add             w3, w5, #3
         mov             x4, x6
         mov             x5, x7
-        bl              X(ff_hevc_put_hevc_epel_h12_8_neon_i8mm)
+        bl              X(ff_hevc_put_hevc_epel_h12_8_\suffix)
         ldp             x4, x5, [sp, #16]
         ldp             x0, x1, [sp, #32]
         ldp             x7, x30, [sp], #48
         b               hevc_put_hevc_epel_bi_hv12_8_end_neon
 endfunc
 
-function ff_hevc_put_hevc_epel_bi_hv16_8_neon_i8mm, export=1
+function ff_hevc_put_hevc_epel_bi_hv16_8_\suffix, export=1
         add             w10, w5, #3
         lsl             x10, x10, #7
         sub             sp, sp, x10 // tmp_array
@@ -4075,14 +4065,14 @@ function ff_hevc_put_hevc_epel_bi_hv16_8_neon_i8mm, export=1
         add             w3, w5, #3
         mov             x4, x6
         mov             x5, x7
-        bl              X(ff_hevc_put_hevc_epel_h16_8_neon_i8mm)
+        bl              X(ff_hevc_put_hevc_epel_h16_8_\suffix)
         ldp             x4, x5, [sp, #16]
         ldp             x0, x1, [sp, #32]
         ldp             x7, x30, [sp], #48
         b               hevc_put_hevc_epel_bi_hv16_8_end_neon
 endfunc
 
-function ff_hevc_put_hevc_epel_bi_hv24_8_neon_i8mm, export=1
+function ff_hevc_put_hevc_epel_bi_hv24_8_\suffix, export=1
         add             w10, w5, #3
         lsl             x10, x10, #7
         sub             sp, sp, x10 // tmp_array
@@ -4095,14 +4085,14 @@ function ff_hevc_put_hevc_epel_bi_hv24_8_neon_i8mm, export=1
         add             w3, w5, #3
         mov             x4, x6
         mov             x5, x7
-        bl              X(ff_hevc_put_hevc_epel_h24_8_neon_i8mm)
+        bl              X(ff_hevc_put_hevc_epel_h24_8_\suffix)
         ldp             x4, x5, [sp, #16]
         ldp             x0, x1, [sp, #32]
         ldp             x7, x30, [sp], #48
         b               hevc_put_hevc_epel_bi_hv24_8_end_neon
 endfunc
 
-function ff_hevc_put_hevc_epel_bi_hv32_8_neon_i8mm, export=1
+function ff_hevc_put_hevc_epel_bi_hv32_8_\suffix, export=1
         str             d8, [sp, #-16]!
         add             w10, w5, #3
         lsl             x10, x10, #7
@@ -4116,20 +4106,21 @@ function ff_hevc_put_hevc_epel_bi_hv32_8_neon_i8mm, export=1
         add             w3, w5, #3
         mov             x4, x6
         mov             x5, x7
-        bl              X(ff_hevc_put_hevc_epel_h32_8_neon_i8mm)
+        mov             w6, #32
+        bl              X(ff_hevc_put_hevc_epel_h32_8_\suffix)
         ldp             x4, x5, [sp, #16]
         ldp             x0, x1, [sp, #32]
         ldp             x7, x30, [sp], #48
         b               hevc_put_hevc_epel_bi_hv32_8_end_neon
 endfunc
 
-function ff_hevc_put_hevc_epel_bi_hv48_8_neon_i8mm, export=1
+function ff_hevc_put_hevc_epel_bi_hv48_8_\suffix, export=1
         stp             x6, x7, [sp, #-80]!
         stp             x4, x5, [sp, #16]
         stp             x2, x3, [sp, #32]
         stp             x0, x1, [sp, #48]
         str             x30, [sp, #64]
-        bl              X(ff_hevc_put_hevc_epel_bi_hv24_8_neon_i8mm)
+        bl              X(ff_hevc_put_hevc_epel_bi_hv24_8_\suffix)
         ldp             x4, x5, [sp, #16]
         ldp             x2, x3, [sp, #32]
         ldp             x0, x1, [sp, #48]
@@ -4137,18 +4128,18 @@ function ff_hevc_put_hevc_epel_bi_hv48_8_neon_i8mm, export=1
         add             x0, x0, #24
         add             x2, x2, #24
         add             x4, x4, #48
-        bl              X(ff_hevc_put_hevc_epel_bi_hv24_8_neon_i8mm)
+        bl              X(ff_hevc_put_hevc_epel_bi_hv24_8_\suffix)
         ldr             x30, [sp], #16
         ret
 endfunc
 
-function ff_hevc_put_hevc_epel_bi_hv64_8_neon_i8mm, export=1
+function ff_hevc_put_hevc_epel_bi_hv64_8_\suffix, export=1
         stp             x6, x7, [sp, #-80]!
         stp             x4, x5, [sp, #16]
         stp             x2, x3, [sp, #32]
         stp             x0, x1, [sp, #48]
         str             x30, [sp, #64]
-        bl              X(ff_hevc_put_hevc_epel_bi_hv32_8_neon_i8mm)
+        bl              X(ff_hevc_put_hevc_epel_bi_hv32_8_\suffix)
         ldp             x4, x5, [sp, #16]
         ldp             x2, x3, [sp, #32]
         ldp             x0, x1, [sp, #48]
@@ -4156,10 +4147,19 @@ function ff_hevc_put_hevc_epel_bi_hv64_8_neon_i8mm, export=1
         add             x0, x0, #32
         add             x2, x2, #32
         add             x4, x4, #64
-        bl              X(ff_hevc_put_hevc_epel_bi_hv32_8_neon_i8mm)
+        bl              X(ff_hevc_put_hevc_epel_bi_hv32_8_\suffix)
         ldr             x30, [sp], #16
         ret
 endfunc
+.endm
+
+epel_bi_hv neon
+
+#if HAVE_I8MM
+ENABLE_I8MM
+
+epel_uni_w_hv neon_i8mm
+epel_bi_hv neon_i8mm
 
 DISABLE_I8MM
 #endif
diff --git a/libavcodec/aarch64/hevcdsp_init_aarch64.c b/libavcodec/aarch64/hevcdsp_init_aarch64.c
index 948103aa09..6110a360d8 100644
--- a/libavcodec/aarch64/hevcdsp_init_aarch64.c
+++ b/libavcodec/aarch64/hevcdsp_init_aarch64.c
@@ -190,6 +190,10 @@ NEON8_FNPROTO(epel_bi_v, (uint8_t *dst, ptrdiff_t dststride,
 
 NEON8_FNPROTO(epel_bi_hv, (uint8_t *dst, ptrdiff_t dststride,
         const uint8_t *src, ptrdiff_t srcstride, const int16_t *src2,
+        int height, intptr_t mx, intptr_t my, int width),);
+
+NEON8_FNPROTO(epel_bi_hv, (uint8_t *dst, ptrdiff_t dststride,
+        const uint8_t *src, ptrdiff_t srcstride, const int16_t *src2,
         int height, intptr_t mx, intptr_t my, int width), _i8mm);
 
 NEON8_FNPROTO(epel_v, (int16_t *dst,
@@ -423,6 +427,7 @@ av_cold void ff_hevc_dsp_init_aarch64(HEVCDSPContext *c, const int bit_depth)
         NEON8_FNASSIGN(c->put_hevc_epel, 1, 1, epel_hv,);
         NEON8_FNASSIGN(c->put_hevc_epel_uni, 1, 1, epel_uni_hv,);
         NEON8_FNASSIGN(c->put_hevc_epel_uni_w, 1, 1, epel_uni_w_hv,);
+        NEON8_FNASSIGN(c->put_hevc_epel_bi, 1, 1, epel_bi_hv,);
 
         if (have_i8mm(cpu_flags)) {
             NEON8_FNASSIGN(c->put_hevc_epel, 0, 1, epel_h, _i8mm);