From: "Martin Storsjö" <martin@martin.st>
To: ffmpeg-devel@ffmpeg.org
Cc: Logan Lyu <Logan.Lyu@myais.com.cn>, "J . Dekker" <jdek@itanimul.li>
Subject: [FFmpeg-devel] [PATCH 08/21] aarch64: hevc: Split the epel_*_hv functions into two parts
Date: Mon, 25 Mar 2024 17:02:30 +0200
Message-ID: <20240325150243.59058-9-martin@martin.st> (raw)
In-Reply-To: <20240325150243.59058-1-martin@martin.st>
The first horizontal filter can use either i8mm or plain neon
versions, while the second part is a pure neon implementation.
---
libavcodec/aarch64/hevcdsp_epel_neon.S | 100 +++++++++++++++++++++++++
1 file changed, 100 insertions(+)
diff --git a/libavcodec/aarch64/hevcdsp_epel_neon.S b/libavcodec/aarch64/hevcdsp_epel_neon.S
index 0e49491a81..6be171ece1 100644
--- a/libavcodec/aarch64/hevcdsp_epel_neon.S
+++ b/libavcodec/aarch64/hevcdsp_epel_neon.S
@@ -2186,6 +2186,10 @@ function ff_hevc_put_hevc_epel_hv4_8_neon_i8mm, export=1
bl X(ff_hevc_put_hevc_epel_h4_8_neon_i8mm)
ldp x0, x3, [sp, #16]
ldp x5, x30, [sp], #32
+ b hevc_put_hevc_epel_hv4_8_end_neon
+endfunc
+
+function hevc_put_hevc_epel_hv4_8_end_neon
load_epel_filterh x5, x4
mov x10, #(MAX_PB_SIZE * 2)
ldr d16, [sp]
@@ -2215,6 +2219,10 @@ function ff_hevc_put_hevc_epel_hv6_8_neon_i8mm, export=1
bl X(ff_hevc_put_hevc_epel_h6_8_neon_i8mm)
ldp x0, x3, [sp, #16]
ldp x5, x30, [sp], #32
+ b hevc_put_hevc_epel_hv6_8_end_neon
+endfunc
+
+function hevc_put_hevc_epel_hv6_8_end_neon
load_epel_filterh x5, x4
mov x5, #120
mov x10, #(MAX_PB_SIZE * 2)
@@ -2247,6 +2255,10 @@ function ff_hevc_put_hevc_epel_hv8_8_neon_i8mm, export=1
bl X(ff_hevc_put_hevc_epel_h8_8_neon_i8mm)
ldp x0, x3, [sp, #16]
ldp x5, x30, [sp], #32
+ b hevc_put_hevc_epel_hv8_8_end_neon
+endfunc
+
+function hevc_put_hevc_epel_hv8_8_end_neon
load_epel_filterh x5, x4
mov x10, #(MAX_PB_SIZE * 2)
ldr q16, [sp]
@@ -2277,6 +2289,10 @@ function ff_hevc_put_hevc_epel_hv12_8_neon_i8mm, export=1
bl X(ff_hevc_put_hevc_epel_h12_8_neon_i8mm)
ldp x0, x3, [sp, #16]
ldp x5, x30, [sp], #32
+ b hevc_put_hevc_epel_hv12_8_end_neon
+endfunc
+
+function hevc_put_hevc_epel_hv12_8_end_neon
load_epel_filterh x5, x4
mov x5, #112
mov x10, #(MAX_PB_SIZE * 2)
@@ -2309,6 +2325,10 @@ function ff_hevc_put_hevc_epel_hv16_8_neon_i8mm, export=1
bl X(ff_hevc_put_hevc_epel_h16_8_neon_i8mm)
ldp x0, x3, [sp, #16]
ldp x5, x30, [sp], #32
+ b hevc_put_hevc_epel_hv16_8_end_neon
+endfunc
+
+function hevc_put_hevc_epel_hv16_8_end_neon
load_epel_filterh x5, x4
mov x10, #(MAX_PB_SIZE * 2)
ld1 {v16.8h, v17.8h}, [sp], x10
@@ -2340,6 +2360,10 @@ function ff_hevc_put_hevc_epel_hv24_8_neon_i8mm, export=1
bl X(ff_hevc_put_hevc_epel_h24_8_neon_i8mm)
ldp x0, x3, [sp, #16]
ldp x5, x30, [sp], #32
+ b hevc_put_hevc_epel_hv24_8_end_neon
+endfunc
+
+function hevc_put_hevc_epel_hv24_8_end_neon
load_epel_filterh x5, x4
mov x10, #(MAX_PB_SIZE * 2)
ld1 {v16.8h, v17.8h, v18.8h}, [sp], x10
@@ -2445,6 +2469,10 @@ function ff_hevc_put_hevc_epel_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_epel_uni_hv4_8_end_neon
+endfunc
+
+function hevc_put_hevc_epel_uni_hv4_8_end_neon
load_epel_filterh x6, x5
mov x10, #(MAX_PB_SIZE * 2)
ld1 {v16.4h}, [sp], x10
@@ -2478,6 +2506,10 @@ function ff_hevc_put_hevc_epel_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_epel_uni_hv6_8_end_neon
+endfunc
+
+function hevc_put_hevc_epel_uni_hv6_8_end_neon
load_epel_filterh x6, x5
sub x1, x1, #4
mov x10, #(MAX_PB_SIZE * 2)
@@ -2514,6 +2546,10 @@ function ff_hevc_put_hevc_epel_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_epel_uni_hv8_8_end_neon
+endfunc
+
+function hevc_put_hevc_epel_uni_hv8_8_end_neon
load_epel_filterh x6, x5
mov x10, #(MAX_PB_SIZE * 2)
ld1 {v16.8h}, [sp], x10
@@ -2548,6 +2584,10 @@ function ff_hevc_put_hevc_epel_uni_hv12_8_neon_i8mm, export=1
ldp x4, x6, [sp, #16]
ldp x0, x1, [sp, #32]
ldr x30, [sp], #48
+ b hevc_put_hevc_epel_uni_hv12_8_end_neon
+endfunc
+
+function hevc_put_hevc_epel_uni_hv12_8_end_neon
load_epel_filterh x6, x5
sub x1, x1, #8
mov x10, #(MAX_PB_SIZE * 2)
@@ -2586,6 +2626,10 @@ function ff_hevc_put_hevc_epel_uni_hv16_8_neon_i8mm, export=1
ldp x4, x6, [sp, #16]
ldp x0, x1, [sp, #32]
ldr x30, [sp], #48
+ b hevc_put_hevc_epel_uni_hv16_8_end_neon
+endfunc
+
+function hevc_put_hevc_epel_uni_hv16_8_end_neon
load_epel_filterh x6, x5
mov x10, #(MAX_PB_SIZE * 2)
ld1 {v16.8h, v17.8h}, [sp], x10
@@ -2623,6 +2667,10 @@ function ff_hevc_put_hevc_epel_uni_hv24_8_neon_i8mm, export=1
ldp x4, x6, [sp, #16]
ldp x0, x1, [sp, #32]
ldr x30, [sp], #48
+ b hevc_put_hevc_epel_uni_hv24_8_end_neon
+endfunc
+
+function hevc_put_hevc_epel_uni_hv24_8_end_neon
load_epel_filterh x6, x5
mov x10, #(MAX_PB_SIZE * 2)
ld1 {v16.8h, v17.8h, v18.8h}, [sp], x10
@@ -3173,6 +3221,10 @@ function ff_hevc_put_hevc_epel_uni_w_hv4_8_neon_i8mm, export=1
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 hevc_put_hevc_epel_uni_w_hv4_8_end_neon
load_epel_filterh x6, x5
mov x10, #(MAX_PB_SIZE * 2)
ld1 {v16.4h}, [sp], x10
@@ -3240,6 +3292,10 @@ function ff_hevc_put_hevc_epel_uni_w_hv6_8_neon_i8mm, export=1
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 hevc_put_hevc_epel_uni_w_hv6_8_end_neon
load_epel_filterh x6, x5
sub x1, x1, #4
mov x10, #(MAX_PB_SIZE * 2)
@@ -3312,6 +3368,10 @@ function ff_hevc_put_hevc_epel_uni_w_hv8_8_neon_i8mm, export=1
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 hevc_put_hevc_epel_uni_w_hv8_8_end_neon
load_epel_filterh x6, x5
mov x10, #(MAX_PB_SIZE * 2)
ld1 {v16.8h}, [sp], x10
@@ -3379,6 +3439,10 @@ function ff_hevc_put_hevc_epel_uni_w_hv12_8_neon_i8mm, export=1
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 hevc_put_hevc_epel_uni_w_hv12_8_end_neon
load_epel_filterh x6, x5
sub x1, x1, #8
mov x10, #(MAX_PB_SIZE * 2)
@@ -3459,6 +3523,10 @@ function ff_hevc_put_hevc_epel_uni_w_hv16_8_neon_i8mm, export=1
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 hevc_put_hevc_epel_uni_w_hv16_8_end_neon
load_epel_filterh x6, x5
mov x10, #(MAX_PB_SIZE * 2)
ld1 {v16.8h, v17.8h}, [sp], x10
@@ -3538,6 +3606,10 @@ function ff_hevc_put_hevc_epel_uni_w_hv24_8_neon_i8mm, export=1
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 hevc_put_hevc_epel_uni_w_hv24_8_end_neon
load_epel_filterh x6, x5
mov x10, #(MAX_PB_SIZE * 2)
ld1 {v16.8h, v17.8h, v18.8h}, [sp], x10
@@ -3715,6 +3787,10 @@ function ff_hevc_put_hevc_epel_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_epel_bi_hv4_8_end_neon
+endfunc
+
+function hevc_put_hevc_epel_bi_hv4_8_end_neon
load_epel_filterh x7, x6
mov x10, #(MAX_PB_SIZE * 2)
ld1 {v16.4h}, [sp], x10
@@ -3751,6 +3827,10 @@ function ff_hevc_put_hevc_epel_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_epel_bi_hv6_8_end_neon
+endfunc
+
+function hevc_put_hevc_epel_bi_hv6_8_end_neon
load_epel_filterh x7, x6
sub x1, x1, #4
mov x10, #(MAX_PB_SIZE * 2)
@@ -3790,6 +3870,10 @@ function ff_hevc_put_hevc_epel_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_epel_bi_hv8_8_end_neon
+endfunc
+
+function hevc_put_hevc_epel_bi_hv8_8_end_neon
load_epel_filterh x7, x6
mov x10, #(MAX_PB_SIZE * 2)
ld1 {v16.8h}, [sp], x10
@@ -3827,6 +3911,10 @@ function ff_hevc_put_hevc_epel_bi_hv12_8_neon_i8mm, export=1
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 hevc_put_hevc_epel_bi_hv12_8_end_neon
load_epel_filterh x7, x6
sub x1, x1, #8
mov x10, #(MAX_PB_SIZE * 2)
@@ -3869,6 +3957,10 @@ function ff_hevc_put_hevc_epel_bi_hv16_8_neon_i8mm, export=1
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 hevc_put_hevc_epel_bi_hv16_8_end_neon
load_epel_filterh x7, x6
mov x10, #(MAX_PB_SIZE * 2)
ld1 {v16.8h, v17.8h}, [sp], x10
@@ -3910,6 +4002,10 @@ function ff_hevc_put_hevc_epel_bi_hv24_8_neon_i8mm, export=1
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 hevc_put_hevc_epel_bi_hv24_8_end_neon
load_epel_filterh x7, x6
mov x10, #(MAX_PB_SIZE * 2)
ld1 {v16.8h, v17.8h, v18.8h}, [sp], x10
@@ -3956,6 +4052,10 @@ function ff_hevc_put_hevc_epel_bi_hv32_8_neon_i8mm, export=1
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 hevc_put_hevc_epel_bi_hv32_8_end_neon
load_epel_filterh x7, x6
mov x10, #(MAX_PB_SIZE * 2)
ld1 {v16.8h, v17.8h, v18.8h, v19.8h}, [sp], x10
--
2.39.3 (Apple Git-146)
_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
To unsubscribe, visit link above, or email
ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe".
next prev parent reply other threads:[~2024-03-25 15:05 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-03-25 15:02 [FFmpeg-devel] [PATCH 00/21] aarch64: hevc: Add missing hevc_pel NEON functions Martin Storsjö
2024-03-25 15:02 ` [FFmpeg-devel] [PATCH 01/21] aarch64: hevc: Reorder a misplaced function init line Martin Storsjö
2024-03-25 15:02 ` [FFmpeg-devel] [PATCH 02/21] aarch64: hevc: Don't iterate with sp in ff_hevc_put_hevc_qpel_uni_w_hv32/64_8_neon_i8mm Martin Storsjö
2024-03-25 15:02 ` [FFmpeg-devel] [PATCH 03/21] aarch64: hevc: Merge consecutive stores in put_hevc_\type\()_h16_8_neon Martin Storsjö
2024-03-25 15:02 ` [FFmpeg-devel] [PATCH 04/21] aarch64: hevc: Specialize put_hevc_\type\()_h*_8_neon for horizontal looping Martin Storsjö
2024-03-25 15:02 ` [FFmpeg-devel] [PATCH 05/21] aarch64: hevc: Use ld1r instead of ldr+dup in hevc_qpel_uni_w_h Martin Storsjö
2024-03-25 15:02 ` [FFmpeg-devel] [PATCH 06/21] aarch64: hevc: Implement a neon version of put_hevc_epel_h*_8 Martin Storsjö
2024-03-25 15:02 ` [FFmpeg-devel] [PATCH 07/21] aarch64: hevc: Implement a neon version of hevc_epel_uni_w_h*_8 Martin Storsjö
2024-03-25 15:02 ` Martin Storsjö [this message]
2024-03-25 15:02 ` [FFmpeg-devel] [PATCH 09/21] aarch64: hevc: Reorder epel_hv functions to prepare for templating Martin Storsjö
2024-03-25 15:02 ` [FFmpeg-devel] [PATCH 10/21] aarch64: hevc: Produce epel_hv functions for both plain neon and i8mm Martin Storsjö
2024-03-25 15:02 ` [FFmpeg-devel] [PATCH 11/21] aarch64: hevc: Produce epel_uni_hv functions for both " Martin Storsjö
2024-03-25 15:02 ` [FFmpeg-devel] [PATCH 12/21] aarch64: hevc: Produce epel_uni_w_hv " Martin Storsjö
2024-03-25 15:02 ` [FFmpeg-devel] [PATCH 13/21] aarch64: hevc: Produce epel_bi_hv " Martin Storsjö
2024-03-25 15:02 ` [FFmpeg-devel] [PATCH 14/21] aarch64: hevc: Implement a neon version of hevc_qpel_uni_w_h*_8 Martin Storsjö
2024-03-25 15:02 ` [FFmpeg-devel] [PATCH 15/21] aarch64: hevc: Split the qpel_*_hv functions into two parts Martin Storsjö
2024-03-25 15:02 ` [FFmpeg-devel] [PATCH 16/21] aarch64: hevc: Deduplicate the hevc_put_hevc_qpel_uni_w_hv*_8_end_neon functions Martin Storsjö
2024-03-25 15:02 ` [FFmpeg-devel] [PATCH 17/21] aarch64: hevc: Reorder qpel_hv functions to prepare for templating Martin Storsjö
2024-03-25 15:02 ` [FFmpeg-devel] [PATCH 18/21] aarch64: hevc: Produce plain neon versions of qpel_hv Martin Storsjö
2024-03-25 15:02 ` [FFmpeg-devel] [PATCH 19/21] aarch64: hevc: Produce plain neon versions of qpel_uni_hv Martin Storsjö
2024-03-25 15:02 ` [FFmpeg-devel] [PATCH 20/21] aarch64: hevc: Produce plain neon versions of qpel_uni_w_hv Martin Storsjö
2024-03-25 15:02 ` [FFmpeg-devel] [PATCH 21/21] aarch64: hevc: Produce plain neon versions of qpel_bi_hv Martin Storsjö
2024-03-25 21:15 ` [FFmpeg-devel] [PATCH 00/21] aarch64: hevc: Add missing hevc_pel NEON functions Martin Storsjö
2024-03-25 21:56 ` J. Dekker
2024-03-26 6:01 ` Jean-Baptiste Kempf
2024-03-26 7:09 ` Martin Storsjö
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20240325150243.59058-9-martin@martin.st \
--to=martin@martin.st \
--cc=Logan.Lyu@myais.com.cn \
--cc=ffmpeg-devel@ffmpeg.org \
--cc=jdek@itanimul.li \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Git Inbox Mirror of the ffmpeg-devel mailing list - see https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
This inbox may be cloned and mirrored by anyone:
git clone --mirror https://master.gitmailbox.com/ffmpegdev/0 ffmpegdev/git/0.git
# If you have public-inbox 1.1+ installed, you may
# initialize and index your mirror using the following commands:
public-inbox-init -V2 ffmpegdev ffmpegdev/ https://master.gitmailbox.com/ffmpegdev \
ffmpegdev@gitmailbox.com
public-inbox-index ffmpegdev
Example config snippet for mirrors.
AGPL code for this site: git clone https://public-inbox.org/public-inbox.git