[FFmpeg-devel] [PATCH 12/21] aarch64: hevc: Produce epel_uni_w_hv functions for both neon and i8mm
Martin Storsjö
martin at martin.st
Mon Mar 25 17:02:34 EET 2024
AWS Graviton 3:
put_hevc_epel_uni_w_hv4_8_c: 191.2
put_hevc_epel_uni_w_hv4_8_neon: 87.7
put_hevc_epel_uni_w_hv4_8_i8mm: 83.2
put_hevc_epel_uni_w_hv6_8_c: 349.5
put_hevc_epel_uni_w_hv6_8_neon: 153.0
put_hevc_epel_uni_w_hv6_8_i8mm: 148.5
put_hevc_epel_uni_w_hv8_8_c: 581.2
put_hevc_epel_uni_w_hv8_8_neon: 166.7
put_hevc_epel_uni_w_hv8_8_i8mm: 163.5
put_hevc_epel_uni_w_hv12_8_c: 1230.0
put_hevc_epel_uni_w_hv12_8_neon: 387.7
put_hevc_epel_uni_w_hv12_8_i8mm: 370.2
put_hevc_epel_uni_w_hv16_8_c: 2003.2
put_hevc_epel_uni_w_hv16_8_neon: 501.5
put_hevc_epel_uni_w_hv16_8_i8mm: 490.2
put_hevc_epel_uni_w_hv24_8_c: 4448.7
put_hevc_epel_uni_w_hv24_8_neon: 1092.2
put_hevc_epel_uni_w_hv24_8_i8mm: 1069.7
put_hevc_epel_uni_w_hv32_8_c: 7817.2
put_hevc_epel_uni_w_hv32_8_neon: 1916.2
put_hevc_epel_uni_w_hv32_8_i8mm: 1829.5
put_hevc_epel_uni_w_hv48_8_c: 16728.2
put_hevc_epel_uni_w_hv48_8_neon: 4263.7
put_hevc_epel_uni_w_hv48_8_i8mm: 4342.7
put_hevc_epel_uni_w_hv64_8_c: 29563.2
put_hevc_epel_uni_w_hv64_8_neon: 7474.2
put_hevc_epel_uni_w_hv64_8_i8mm: 7128.5
---
libavcodec/aarch64/hevcdsp_epel_neon.S | 55 ++++++++++++-----------
libavcodec/aarch64/hevcdsp_init_aarch64.c | 6 +++
2 files changed, 36 insertions(+), 25 deletions(-)
diff --git a/libavcodec/aarch64/hevcdsp_epel_neon.S b/libavcodec/aarch64/hevcdsp_epel_neon.S
index 876db9d449..d0c6205e1c 100644
--- a/libavcodec/aarch64/hevcdsp_epel_neon.S
+++ b/libavcodec/aarch64/hevcdsp_epel_neon.S
@@ -3573,10 +3573,8 @@ function hevc_put_hevc_epel_uni_w_hv24_8_end_neon
ret
endfunc
-#if HAVE_I8MM
-ENABLE_I8MM
-
-function ff_hevc_put_hevc_epel_uni_w_hv4_8_neon_i8mm, export=1
+.macro epel_uni_w_hv suffix
+function ff_hevc_put_hevc_epel_uni_w_hv4_8_\suffix, export=1
epel_uni_w_hv_start
sxtw x4, w4
@@ -3591,14 +3589,14 @@ function ff_hevc_put_hevc_epel_uni_w_hv4_8_neon_i8mm, export=1
mov x2, x3
add x3, x4, #3
mov x4, x5
- bl X(ff_hevc_put_hevc_epel_h4_8_neon_i8mm)
+ bl X(ff_hevc_put_hevc_epel_h4_8_\suffix)
ldp x4, x6, [sp, #16]
ldp x0, x1, [sp, #32]
ldr x30, [sp], #48
b hevc_put_hevc_epel_uni_w_hv4_8_end_neon
endfunc
-function ff_hevc_put_hevc_epel_uni_w_hv6_8_neon_i8mm, export=1
+function ff_hevc_put_hevc_epel_uni_w_hv6_8_\suffix, export=1
epel_uni_w_hv_start
sxtw x4, w4
@@ -3613,14 +3611,14 @@ function ff_hevc_put_hevc_epel_uni_w_hv6_8_neon_i8mm, export=1
mov x2, x3
add x3, x4, #3
mov x4, x5
- bl X(ff_hevc_put_hevc_epel_h6_8_neon_i8mm)
+ bl X(ff_hevc_put_hevc_epel_h6_8_\suffix)
ldp x4, x6, [sp, #16]
ldp x0, x1, [sp, #32]
ldr x30, [sp], #48
b hevc_put_hevc_epel_uni_w_hv6_8_end_neon
endfunc
-function ff_hevc_put_hevc_epel_uni_w_hv8_8_neon_i8mm, export=1
+function ff_hevc_put_hevc_epel_uni_w_hv8_8_\suffix, export=1
epel_uni_w_hv_start
sxtw x4, w4
@@ -3635,14 +3633,14 @@ function ff_hevc_put_hevc_epel_uni_w_hv8_8_neon_i8mm, export=1
mov x2, x3
add x3, x4, #3
mov x4, x5
- bl X(ff_hevc_put_hevc_epel_h8_8_neon_i8mm)
+ bl X(ff_hevc_put_hevc_epel_h8_8_\suffix)
ldp x4, x6, [sp, #16]
ldp x0, x1, [sp, #32]
ldr x30, [sp], #48
b hevc_put_hevc_epel_uni_w_hv8_8_end_neon
endfunc
-function ff_hevc_put_hevc_epel_uni_w_hv12_8_neon_i8mm, export=1
+function ff_hevc_put_hevc_epel_uni_w_hv12_8_\suffix, export=1
epel_uni_w_hv_start
sxtw x4, w4
@@ -3657,14 +3655,14 @@ function ff_hevc_put_hevc_epel_uni_w_hv12_8_neon_i8mm, export=1
mov x2, x3
add x3, x4, #3
mov x4, x5
- bl X(ff_hevc_put_hevc_epel_h12_8_neon_i8mm)
+ bl X(ff_hevc_put_hevc_epel_h12_8_\suffix)
ldp x4, x6, [sp, #16]
ldp x0, x1, [sp, #32]
ldr x30, [sp], #48
b hevc_put_hevc_epel_uni_w_hv12_8_end_neon
endfunc
-function ff_hevc_put_hevc_epel_uni_w_hv16_8_neon_i8mm, export=1
+function ff_hevc_put_hevc_epel_uni_w_hv16_8_\suffix, export=1
epel_uni_w_hv_start
sxtw x4, w4
@@ -3679,14 +3677,14 @@ function ff_hevc_put_hevc_epel_uni_w_hv16_8_neon_i8mm, export=1
mov x2, x3
add x3, x4, #3
mov x4, x5
- bl X(ff_hevc_put_hevc_epel_h16_8_neon_i8mm)
+ bl X(ff_hevc_put_hevc_epel_h16_8_\suffix)
ldp x4, x6, [sp, #16]
ldp x0, x1, [sp, #32]
ldr x30, [sp], #48
b hevc_put_hevc_epel_uni_w_hv16_8_end_neon
endfunc
-function ff_hevc_put_hevc_epel_uni_w_hv24_8_neon_i8mm, export=1
+function ff_hevc_put_hevc_epel_uni_w_hv24_8_\suffix, export=1
epel_uni_w_hv_start
sxtw x4, w4
@@ -3701,14 +3699,14 @@ function ff_hevc_put_hevc_epel_uni_w_hv24_8_neon_i8mm, export=1
mov x2, x3
add x3, x4, #3
mov x4, x5
- bl X(ff_hevc_put_hevc_epel_h24_8_neon_i8mm)
+ bl X(ff_hevc_put_hevc_epel_h24_8_\suffix)
ldp x4, x6, [sp, #16]
ldp x0, x1, [sp, #32]
ldr x30, [sp], #48
b hevc_put_hevc_epel_uni_w_hv24_8_end_neon
endfunc
-function ff_hevc_put_hevc_epel_uni_w_hv32_8_neon_i8mm, export=1
+function ff_hevc_put_hevc_epel_uni_w_hv32_8_\suffix, export=1
ldp x15, x16, [sp]
mov x17, #16
stp x15, x16, [sp, #-96]!
@@ -3718,7 +3716,7 @@ function ff_hevc_put_hevc_epel_uni_w_hv32_8_neon_i8mm, export=1
stp x5, x6, [sp, #64]
stp x17, x7, [sp, #80]
- bl X(ff_hevc_put_hevc_epel_uni_w_hv16_8_neon_i8mm)
+ bl X(ff_hevc_put_hevc_epel_uni_w_hv16_8_\suffix)
ldp x0, x30, [sp, #16]
ldp x1, x2, [sp, #32]
ldp x3, x4, [sp, #48]
@@ -3730,13 +3728,13 @@ function ff_hevc_put_hevc_epel_uni_w_hv32_8_neon_i8mm, export=1
mov x17, #16
stp x15, x16, [sp, #-32]!
stp x17, x30, [sp, #16]
- bl X(ff_hevc_put_hevc_epel_uni_w_hv16_8_neon_i8mm)
+ bl X(ff_hevc_put_hevc_epel_uni_w_hv16_8_\suffix)
ldp x17, x30, [sp, #16]
ldp x15, x16, [sp], #32
ret
endfunc
-function ff_hevc_put_hevc_epel_uni_w_hv48_8_neon_i8mm, export=1
+function ff_hevc_put_hevc_epel_uni_w_hv48_8_\suffix, export=1
ldp x15, x16, [sp]
mov x17, #24
stp x15, x16, [sp, #-96]!
@@ -3745,7 +3743,7 @@ function ff_hevc_put_hevc_epel_uni_w_hv48_8_neon_i8mm, export=1
stp x3, x4, [sp, #48]
stp x5, x6, [sp, #64]
stp x17, x7, [sp, #80]
- bl X(ff_hevc_put_hevc_epel_uni_w_hv24_8_neon_i8mm)
+ bl X(ff_hevc_put_hevc_epel_uni_w_hv24_8_\suffix)
ldp x0, x30, [sp, #16]
ldp x1, x2, [sp, #32]
ldp x3, x4, [sp, #48]
@@ -3757,13 +3755,13 @@ function ff_hevc_put_hevc_epel_uni_w_hv48_8_neon_i8mm, export=1
mov x17, #24
stp x15, x16, [sp, #-32]!
stp x17, x30, [sp, #16]
- bl X(ff_hevc_put_hevc_epel_uni_w_hv24_8_neon_i8mm)
+ bl X(ff_hevc_put_hevc_epel_uni_w_hv24_8_\suffix)
ldp x17, x30, [sp, #16]
ldp x15, x16, [sp], #32
ret
endfunc
-function ff_hevc_put_hevc_epel_uni_w_hv64_8_neon_i8mm, export=1
+function ff_hevc_put_hevc_epel_uni_w_hv64_8_\suffix, export=1
ldp x15, x16, [sp]
mov x17, #32
stp x15, x16, [sp, #-96]!
@@ -3773,7 +3771,7 @@ function ff_hevc_put_hevc_epel_uni_w_hv64_8_neon_i8mm, export=1
stp x5, x6, [sp, #64]
stp x17, x7, [sp, #80]
- bl X(ff_hevc_put_hevc_epel_uni_w_hv32_8_neon_i8mm)
+ bl X(ff_hevc_put_hevc_epel_uni_w_hv32_8_\suffix)
ldp x0, x30, [sp, #16]
ldp x1, x2, [sp, #32]
ldp x3, x4, [sp, #48]
@@ -3785,16 +3783,23 @@ function ff_hevc_put_hevc_epel_uni_w_hv64_8_neon_i8mm, export=1
mov x17, #32
stp x15, x16, [sp, #-32]!
stp x17, x30, [sp, #16]
- bl X(ff_hevc_put_hevc_epel_uni_w_hv32_8_neon_i8mm)
+ bl X(ff_hevc_put_hevc_epel_uni_w_hv32_8_\suffix)
ldp x17, x30, [sp, #16]
ldp x15, x16, [sp], #32
ret
endfunc
+.endm
+
+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
mov x10, #(MAX_PB_SIZE * 2)
diff --git a/libavcodec/aarch64/hevcdsp_init_aarch64.c b/libavcodec/aarch64/hevcdsp_init_aarch64.c
index 447ae80bfb..948103aa09 100644
--- a/libavcodec/aarch64/hevcdsp_init_aarch64.c
+++ b/libavcodec/aarch64/hevcdsp_init_aarch64.c
@@ -278,6 +278,11 @@ NEON8_FNPROTO(qpel_uni_w_h, (uint8_t *_dst, ptrdiff_t _dststride,
int height, int denom, int wx, int ox,
intptr_t mx, intptr_t my, int width), _i8mm);
+NEON8_FNPROTO(epel_uni_w_hv, (uint8_t *_dst, ptrdiff_t _dststride,
+ const uint8_t *_src, ptrdiff_t _srcstride,
+ int height, int denom, int wx, int ox,
+ intptr_t mx, intptr_t my, int width),);
+
NEON8_FNPROTO(epel_uni_w_hv, (uint8_t *_dst, ptrdiff_t _dststride,
const uint8_t *_src, ptrdiff_t _srcstride,
int height, int denom, int wx, int ox,
@@ -417,6 +422,7 @@ 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,);
if (have_i8mm(cpu_flags)) {
NEON8_FNASSIGN(c->put_hevc_epel, 0, 1, epel_h, _i8mm);
--
2.39.3 (Apple Git-146)
More information about the ffmpeg-devel
mailing list