[FFmpeg-cvslog] aarch64: hevc: Split the qpel_*_hv functions into two parts
Martin Storsjö
git at videolan.org
Tue Mar 26 09:06:47 EET 2024
ffmpeg | branch: master | Martin Storsjö <martin at martin.st> | Thu Mar 21 23:57:44 2024 +0200| [4063e50eeca0f520a4dc045328ea1c1d8ba6aa4e] | committer: Martin Storsjö
aarch64: hevc: Split the qpel_*_hv functions into two parts
The first horizontal filter can use either i8mm or plain neon
versions, while the second part is a pure neon implementation.
Signed-off-by: Martin Storsjö <martin at martin.st>
> http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=4063e50eeca0f520a4dc045328ea1c1d8ba6aa4e
---
libavcodec/aarch64/hevcdsp_qpel_neon.S | 94 +++++++++++++++++++++++++++++++---
1 file changed, 86 insertions(+), 8 deletions(-)
diff --git a/libavcodec/aarch64/hevcdsp_qpel_neon.S b/libavcodec/aarch64/hevcdsp_qpel_neon.S
index fba063186c..c04e8dbea8 100644
--- a/libavcodec/aarch64/hevcdsp_qpel_neon.S
+++ b/libavcodec/aarch64/hevcdsp_qpel_neon.S
@@ -2166,6 +2166,10 @@ function ff_hevc_put_hevc_qpel_uni_hv4_8_neon_i8mm, export=1
ldp x4, x6, [sp, #16]
ldp x0, x1, [sp, #32]
ldr x30, [sp], #48
+ b hevc_put_hevc_qpel_uni_hv4_8_end_neon
+endfunc
+
+function hevc_put_hevc_qpel_uni_hv4_8_end_neon
mov x9, #(MAX_PB_SIZE * 2)
load_qpel_filterh x6, x5
ldr d16, [sp]
@@ -2208,6 +2212,10 @@ function ff_hevc_put_hevc_qpel_uni_hv6_8_neon_i8mm, export=1
ldp x4, x6, [sp, #16]
ldp x0, x1, [sp, #32]
ldr x30, [sp], #48
+ b hevc_put_hevc_qpel_uni_hv6_8_end_neon
+endfunc
+
+function hevc_put_hevc_qpel_uni_hv6_8_end_neon
mov x9, #(MAX_PB_SIZE * 2)
load_qpel_filterh x6, x5
sub x1, x1, #4
@@ -2253,6 +2261,10 @@ function ff_hevc_put_hevc_qpel_uni_hv8_8_neon_i8mm, export=1
ldp x4, x6, [sp, #16]
ldp x0, x1, [sp, #32]
ldr x30, [sp], #48
+ b hevc_put_hevc_qpel_uni_hv8_8_end_neon
+endfunc
+
+function hevc_put_hevc_qpel_uni_hv8_8_end_neon
mov x9, #(MAX_PB_SIZE * 2)
load_qpel_filterh x6, x5
ldr q16, [sp]
@@ -2296,6 +2308,10 @@ function ff_hevc_put_hevc_qpel_uni_hv12_8_neon_i8mm, export=1
ldp x4, x6, [sp, #16]
ldp x0, x1, [sp, #32]
ldp x7, x30, [sp], #48
+ b hevc_put_hevc_qpel_uni_hv12_8_end_neon
+endfunc
+
+function hevc_put_hevc_qpel_uni_hv12_8_end_neon
mov x9, #(MAX_PB_SIZE * 2)
load_qpel_filterh x6, x5
sub x1, x1, #8
@@ -2339,7 +2355,10 @@ function ff_hevc_put_hevc_qpel_uni_hv16_8_neon_i8mm, export=1
ldp x4, x6, [sp, #16]
ldp x0, x1, [sp, #32]
ldp x7, x30, [sp], #48
-.Lqpel_uni_hv16_loop:
+ b hevc_put_hevc_qpel_uni_hv16_8_end_neon
+endfunc
+
+function hevc_put_hevc_qpel_uni_hv16_8_end_neon
mov x9, #(MAX_PB_SIZE * 2)
load_qpel_filterh x6, x5
sub w12, w9, w7, lsl #1
@@ -2414,7 +2433,7 @@ function ff_hevc_put_hevc_qpel_uni_hv32_8_neon_i8mm, export=1
ldp x4, x6, [sp, #16]
ldp x0, x1, [sp, #32]
ldp x7, x30, [sp], #48
- b .Lqpel_uni_hv16_loop
+ b hevc_put_hevc_qpel_uni_hv16_8_end_neon
endfunc
function ff_hevc_put_hevc_qpel_uni_hv48_8_neon_i8mm, export=1
@@ -2434,7 +2453,7 @@ function ff_hevc_put_hevc_qpel_uni_hv48_8_neon_i8mm, export=1
ldp x4, x6, [sp, #16]
ldp x0, x1, [sp, #32]
ldp x7, x30, [sp], #48
- b .Lqpel_uni_hv16_loop
+ b hevc_put_hevc_qpel_uni_hv16_8_end_neon
endfunc
function ff_hevc_put_hevc_qpel_uni_hv64_8_neon_i8mm, export=1
@@ -2454,7 +2473,7 @@ function ff_hevc_put_hevc_qpel_uni_hv64_8_neon_i8mm, export=1
ldp x4, x6, [sp, #16]
ldp x0, x1, [sp, #32]
ldp x7, x30, [sp], #48
- b .Lqpel_uni_hv16_loop
+ b hevc_put_hevc_qpel_uni_hv16_8_end_neon
endfunc
DISABLE_I8MM
#endif
@@ -3776,6 +3795,10 @@ function ff_hevc_put_hevc_qpel_hv4_8_neon_i8mm, export=1
bl X(ff_hevc_put_hevc_qpel_h4_8_neon_i8mm)
ldp x0, x3, [sp, #16]
ldp x5, x30, [sp], #32
+ b hevc_put_hevc_qpel_hv4_8_end_neon
+endfunc
+
+function hevc_put_hevc_qpel_hv4_8_end_neon
load_qpel_filterh x5, x4
ldr d16, [sp]
ldr d17, [sp, x7]
@@ -3813,6 +3836,10 @@ function ff_hevc_put_hevc_qpel_hv6_8_neon_i8mm, export=1
bl X(ff_hevc_put_hevc_qpel_h6_8_neon_i8mm)
ldp x0, x3, [sp, #16]
ldp x5, x30, [sp], #32
+ b hevc_put_hevc_qpel_hv6_8_end_neon
+endfunc
+
+function hevc_put_hevc_qpel_hv6_8_end_neon
mov x8, #120
load_qpel_filterh x5, x4
ldr q16, [sp]
@@ -3852,6 +3879,10 @@ function ff_hevc_put_hevc_qpel_hv8_8_neon_i8mm, export=1
bl X(ff_hevc_put_hevc_qpel_h8_8_neon_i8mm)
ldp x0, x3, [sp, #16]
ldp x5, x30, [sp], #32
+ b hevc_put_hevc_qpel_hv8_8_end_neon
+endfunc
+
+function hevc_put_hevc_qpel_hv8_8_end_neon
mov x7, #128
load_qpel_filterh x5, x4
ldr q16, [sp]
@@ -3890,6 +3921,10 @@ function ff_hevc_put_hevc_qpel_hv12_8_neon_i8mm, export=1
bl X(ff_hevc_put_hevc_qpel_h12_8_neon_i8mm)
ldp x0, x3, [sp, #16]
ldp x5, x30, [sp], #32
+ b hevc_put_hevc_qpel_hv12_8_end_neon
+endfunc
+
+function hevc_put_hevc_qpel_hv12_8_end_neon
mov x7, #128
load_qpel_filterh x5, x4
mov x8, #112
@@ -3927,6 +3962,10 @@ function ff_hevc_put_hevc_qpel_hv16_8_neon_i8mm, export=1
bl X(ff_hevc_put_hevc_qpel_h16_8_neon_i8mm)
ldp x0, x3, [sp, #16]
ldp x5, x30, [sp], #32
+ b hevc_put_hevc_qpel_hv16_8_end_neon
+endfunc
+
+function hevc_put_hevc_qpel_hv16_8_end_neon
mov x7, #128
load_qpel_filterh x5, x4
ld1 {v16.8h, v17.8h}, [sp], x7
@@ -3979,6 +4018,10 @@ function ff_hevc_put_hevc_qpel_hv32_8_neon_i8mm, export=1
bl X(ff_hevc_put_hevc_qpel_h32_8_neon_i8mm)
ldp x0, x3, [sp, #16]
ldp x5, x30, [sp], #32
+ b hevc_put_hevc_qpel_hv32_8_end_neon
+endfunc
+
+function hevc_put_hevc_qpel_hv32_8_end_neon
mov x7, #128
load_qpel_filterh x5, x4
0: mov x8, sp // src
@@ -4127,6 +4170,10 @@ endfunc
function ff_hevc_put_hevc_qpel_uni_w_hv4_8_neon_i8mm, export=1
QPEL_UNI_W_HV_HEADER 4
+ b hevc_put_hevc_qpel_uni_w_hv4_8_end_neon
+endfunc
+
+function hevc_put_hevc_qpel_uni_w_hv4_8_end_neon
ldr d16, [sp]
ldr d17, [sp, x10]
add sp, sp, x10, lsl #1
@@ -4217,6 +4264,10 @@ endfunc
function ff_hevc_put_hevc_qpel_uni_w_hv8_8_neon_i8mm, export=1
QPEL_UNI_W_HV_HEADER 8
+ b hevc_put_hevc_qpel_uni_w_hv8_8_end_neon
+endfunc
+
+function hevc_put_hevc_qpel_uni_w_hv8_8_end_neon
ldr q16, [sp]
ldr q17, [sp, x10]
add sp, sp, x10, lsl #1
@@ -4327,6 +4378,10 @@ endfunc
function ff_hevc_put_hevc_qpel_uni_w_hv16_8_neon_i8mm, export=1
QPEL_UNI_W_HV_HEADER 16
+ b hevc_put_hevc_qpel_uni_w_hv16_8_end_neon
+endfunc
+
+function hevc_put_hevc_qpel_uni_w_hv16_8_end_neon
ldp q16, q1, [sp]
add sp, sp, x10
ldp q17, q2, [sp]
@@ -4430,6 +4485,10 @@ endfunc
function ff_hevc_put_hevc_qpel_uni_w_hv32_8_neon_i8mm, export=1
QPEL_UNI_W_HV_HEADER 32
+ b hevc_put_hevc_qpel_uni_w_hv32_8_end_neon
+endfunc
+
+function hevc_put_hevc_qpel_uni_w_hv32_8_end_neon
mov x11, sp
mov w12, w22
mov x13, x20
@@ -4543,6 +4602,10 @@ endfunc
function ff_hevc_put_hevc_qpel_uni_w_hv64_8_neon_i8mm, export=1
QPEL_UNI_W_HV_HEADER 64
+ b hevc_put_hevc_qpel_uni_w_hv64_8_end_neon
+endfunc
+
+function hevc_put_hevc_qpel_uni_w_hv64_8_end_neon
mov x11, sp
mov w12, w22
mov x13, x20
@@ -4671,6 +4734,10 @@ function ff_hevc_put_hevc_qpel_bi_hv4_8_neon_i8mm, export=1
ldp x4, x5, [sp, #16]
ldp x0, x1, [sp, #32]
ldp x7, x30, [sp], #48
+ b hevc_put_hevc_qpel_bi_hv4_8_end_neon
+endfunc
+
+function hevc_put_hevc_qpel_bi_hv4_8_end_neon
mov x9, #(MAX_PB_SIZE * 2)
load_qpel_filterh x7, x6
ld1 {v16.4h}, [sp], x9
@@ -4712,6 +4779,10 @@ function ff_hevc_put_hevc_qpel_bi_hv6_8_neon_i8mm, export=1
ldp x4, x5, [sp, #16]
ldp x0, x1, [sp, #32]
ldp x7, x30, [sp], #48
+ b hevc_put_hevc_qpel_bi_hv6_8_end_neon
+endfunc
+
+function hevc_put_hevc_qpel_bi_hv6_8_end_neon
mov x9, #(MAX_PB_SIZE * 2)
load_qpel_filterh x7, x6
sub x1, x1, #4
@@ -4758,6 +4829,10 @@ function ff_hevc_put_hevc_qpel_bi_hv8_8_neon_i8mm, export=1
ldp x4, x5, [sp, #16]
ldp x0, x1, [sp, #32]
ldp x7, x30, [sp], #48
+ b hevc_put_hevc_qpel_bi_hv8_8_end_neon
+endfunc
+
+function hevc_put_hevc_qpel_bi_hv8_8_end_neon
mov x9, #(MAX_PB_SIZE * 2)
load_qpel_filterh x7, x6
ld1 {v16.8h}, [sp], x9
@@ -4822,7 +4897,10 @@ function ff_hevc_put_hevc_qpel_bi_hv16_8_neon_i8mm, export=1
ldp x0, x1, [sp, #32]
ldp x7, x30, [sp], #48
mov x6, #16 // width
-.Lqpel_bi_hv16_loop:
+ b hevc_put_hevc_qpel_bi_hv16_8_end_neon
+endfunc
+
+function hevc_put_hevc_qpel_bi_hv16_8_end_neon
load_qpel_filterh x7, x8
mov x9, #(MAX_PB_SIZE * 2)
mov x10, x6
@@ -4908,7 +4986,7 @@ function ff_hevc_put_hevc_qpel_bi_hv32_8_neon_i8mm, export=1
ldp x0, x1, [sp, #32]
ldp x7, x30, [sp], #48
mov x6, #32 // width
- b .Lqpel_bi_hv16_loop
+ b hevc_put_hevc_qpel_bi_hv16_8_end_neon
endfunc
function ff_hevc_put_hevc_qpel_bi_hv48_8_neon_i8mm, export=1
@@ -4929,7 +5007,7 @@ function ff_hevc_put_hevc_qpel_bi_hv48_8_neon_i8mm, export=1
ldp x0, x1, [sp, #32]
ldp x7, x30, [sp], #48
mov x6, #48 // width
- b .Lqpel_bi_hv16_loop
+ b hevc_put_hevc_qpel_bi_hv16_8_end_neon
endfunc
function ff_hevc_put_hevc_qpel_bi_hv64_8_neon_i8mm, export=1
@@ -4950,7 +5028,7 @@ function ff_hevc_put_hevc_qpel_bi_hv64_8_neon_i8mm, export=1
ldp x0, x1, [sp, #32]
ldp x7, x30, [sp], #48
mov x6, #64 // width
- b .Lqpel_bi_hv16_loop
+ b hevc_put_hevc_qpel_bi_hv16_8_end_neon
endfunc
DISABLE_I8MM
More information about the ffmpeg-cvslog
mailing list