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 10/21] aarch64: hevc: Produce epel_hv functions for both plain neon and i8mm
Date: Mon, 25 Mar 2024 17:02:32 +0200
Message-ID: <20240325150243.59058-11-martin@martin.st> (raw)
In-Reply-To: <20240325150243.59058-1-martin@martin.st>
AWS Graviton 3:
put_hevc_epel_hv4_8_c: 163.7
put_hevc_epel_hv4_8_neon: 52.5
put_hevc_epel_hv4_8_i8mm: 49.5
put_hevc_epel_hv6_8_c: 292.2
put_hevc_epel_hv6_8_neon: 97.7
put_hevc_epel_hv6_8_i8mm: 101.2
put_hevc_epel_hv8_8_c: 471.0
put_hevc_epel_hv8_8_neon: 106.7
put_hevc_epel_hv8_8_i8mm: 102.5
put_hevc_epel_hv12_8_c: 1030.2
put_hevc_epel_hv12_8_neon: 240.5
put_hevc_epel_hv12_8_i8mm: 215.0
put_hevc_epel_hv16_8_c: 1711.5
put_hevc_epel_hv16_8_neon: 340.2
put_hevc_epel_hv16_8_i8mm: 319.2
put_hevc_epel_hv24_8_c: 3670.0
put_hevc_epel_hv24_8_neon: 702.0
put_hevc_epel_hv24_8_i8mm: 666.5
put_hevc_epel_hv32_8_c: 6785.5
put_hevc_epel_hv32_8_neon: 1247.0
put_hevc_epel_hv32_8_i8mm: 1169.0
put_hevc_epel_hv48_8_c: 14689.7
put_hevc_epel_hv48_8_neon: 2665.2
put_hevc_epel_hv48_8_i8mm: 2740.0
put_hevc_epel_hv64_8_c: 25899.2
put_hevc_epel_hv64_8_neon: 4801.2
put_hevc_epel_hv64_8_i8mm: 4487.7
---
libavcodec/aarch64/hevcdsp_epel_neon.S | 58 +++++++++++++----------
libavcodec/aarch64/hevcdsp_init_aarch64.c | 6 +++
2 files changed, 38 insertions(+), 26 deletions(-)
diff --git a/libavcodec/aarch64/hevcdsp_epel_neon.S b/libavcodec/aarch64/hevcdsp_epel_neon.S
index 2088630da1..024464723b 100644
--- a/libavcodec/aarch64/hevcdsp_epel_neon.S
+++ b/libavcodec/aarch64/hevcdsp_epel_neon.S
@@ -2298,10 +2298,8 @@ function hevc_put_hevc_epel_hv24_8_end_neon
2: ret
endfunc
-#if HAVE_I8MM
-ENABLE_I8MM
-
-function ff_hevc_put_hevc_epel_hv4_8_neon_i8mm, export=1
+.macro epel_hv suffix
+function ff_hevc_put_hevc_epel_hv4_8_\suffix, export=1
add w10, w3, #3
lsl x10, x10, #7
sub sp, sp, x10 // tmp_array
@@ -2310,13 +2308,13 @@ function ff_hevc_put_hevc_epel_hv4_8_neon_i8mm, export=1
add x0, sp, #32
sub x1, x1, x2
add w3, w3, #3
- bl X(ff_hevc_put_hevc_epel_h4_8_neon_i8mm)
+ bl X(ff_hevc_put_hevc_epel_h4_8_\suffix)
ldp x0, x3, [sp, #16]
ldp x5, x30, [sp], #32
b hevc_put_hevc_epel_hv4_8_end_neon
endfunc
-function ff_hevc_put_hevc_epel_hv6_8_neon_i8mm, export=1
+function ff_hevc_put_hevc_epel_hv6_8_\suffix, export=1
add w10, w3, #3
lsl x10, x10, #7
sub sp, sp, x10 // tmp_array
@@ -2325,13 +2323,13 @@ function ff_hevc_put_hevc_epel_hv6_8_neon_i8mm, export=1
add x0, sp, #32
sub x1, x1, x2
add w3, w3, #3
- bl X(ff_hevc_put_hevc_epel_h6_8_neon_i8mm)
+ bl X(ff_hevc_put_hevc_epel_h6_8_\suffix)
ldp x0, x3, [sp, #16]
ldp x5, x30, [sp], #32
b hevc_put_hevc_epel_hv6_8_end_neon
endfunc
-function ff_hevc_put_hevc_epel_hv8_8_neon_i8mm, export=1
+function ff_hevc_put_hevc_epel_hv8_8_\suffix, export=1
add w10, w3, #3
lsl x10, x10, #7
sub sp, sp, x10 // tmp_array
@@ -2340,13 +2338,13 @@ function ff_hevc_put_hevc_epel_hv8_8_neon_i8mm, export=1
add x0, sp, #32
sub x1, x1, x2
add w3, w3, #3
- bl X(ff_hevc_put_hevc_epel_h8_8_neon_i8mm)
+ bl X(ff_hevc_put_hevc_epel_h8_8_\suffix)
ldp x0, x3, [sp, #16]
ldp x5, x30, [sp], #32
b hevc_put_hevc_epel_hv8_8_end_neon
endfunc
-function ff_hevc_put_hevc_epel_hv12_8_neon_i8mm, export=1
+function ff_hevc_put_hevc_epel_hv12_8_\suffix, export=1
add w10, w3, #3
lsl x10, x10, #7
sub sp, sp, x10 // tmp_array
@@ -2355,13 +2353,13 @@ function ff_hevc_put_hevc_epel_hv12_8_neon_i8mm, export=1
add x0, sp, #32
sub x1, x1, x2
add w3, w3, #3
- bl X(ff_hevc_put_hevc_epel_h12_8_neon_i8mm)
+ bl X(ff_hevc_put_hevc_epel_h12_8_\suffix)
ldp x0, x3, [sp, #16]
ldp x5, x30, [sp], #32
b hevc_put_hevc_epel_hv12_8_end_neon
endfunc
-function ff_hevc_put_hevc_epel_hv16_8_neon_i8mm, export=1
+function ff_hevc_put_hevc_epel_hv16_8_\suffix, export=1
add w10, w3, #3
lsl x10, x10, #7
sub sp, sp, x10 // tmp_array
@@ -2370,13 +2368,13 @@ function ff_hevc_put_hevc_epel_hv16_8_neon_i8mm, export=1
add x0, sp, #32
sub x1, x1, x2
add w3, w3, #3
- bl X(ff_hevc_put_hevc_epel_h16_8_neon_i8mm)
+ bl X(ff_hevc_put_hevc_epel_h16_8_\suffix)
ldp x0, x3, [sp, #16]
ldp x5, x30, [sp], #32
b hevc_put_hevc_epel_hv16_8_end_neon
endfunc
-function ff_hevc_put_hevc_epel_hv24_8_neon_i8mm, export=1
+function ff_hevc_put_hevc_epel_hv24_8_\suffix, export=1
add w10, w3, #3
lsl x10, x10, #7
sub sp, sp, x10 // tmp_array
@@ -2385,79 +2383,87 @@ function ff_hevc_put_hevc_epel_hv24_8_neon_i8mm, export=1
add x0, sp, #32
sub x1, x1, x2
add w3, w3, #3
- bl X(ff_hevc_put_hevc_epel_h24_8_neon_i8mm)
+ bl X(ff_hevc_put_hevc_epel_h24_8_\suffix)
ldp x0, x3, [sp, #16]
ldp x5, x30, [sp], #32
b hevc_put_hevc_epel_hv24_8_end_neon
endfunc
-function ff_hevc_put_hevc_epel_hv32_8_neon_i8mm, export=1
+function ff_hevc_put_hevc_epel_hv32_8_\suffix, export=1
stp x4, x5, [sp, #-64]!
stp x2, x3, [sp, #16]
stp x0, x1, [sp, #32]
str x30, [sp, #48]
mov x6, #16
- bl X(ff_hevc_put_hevc_epel_hv16_8_neon_i8mm)
+ bl X(ff_hevc_put_hevc_epel_hv16_8_\suffix)
ldp x0, x1, [sp, #32]
ldp x2, x3, [sp, #16]
ldp x4, x5, [sp], #48
add x0, x0, #32
add x1, x1, #16
mov x6, #16
- bl X(ff_hevc_put_hevc_epel_hv16_8_neon_i8mm)
+ bl X(ff_hevc_put_hevc_epel_hv16_8_\suffix)
ldr x30, [sp], #16
ret
endfunc
-function ff_hevc_put_hevc_epel_hv48_8_neon_i8mm, export=1
+function ff_hevc_put_hevc_epel_hv48_8_\suffix, export=1
stp x4, x5, [sp, #-64]!
stp x2, x3, [sp, #16]
stp x0, x1, [sp, #32]
str x30, [sp, #48]
mov x6, #24
- bl X(ff_hevc_put_hevc_epel_hv24_8_neon_i8mm)
+ bl X(ff_hevc_put_hevc_epel_hv24_8_\suffix)
ldp x0, x1, [sp, #32]
ldp x2, x3, [sp, #16]
ldp x4, x5, [sp], #48
add x0, x0, #48
add x1, x1, #24
mov x6, #24
- bl X(ff_hevc_put_hevc_epel_hv24_8_neon_i8mm)
+ bl X(ff_hevc_put_hevc_epel_hv24_8_\suffix)
ldr x30, [sp], #16
ret
endfunc
-function ff_hevc_put_hevc_epel_hv64_8_neon_i8mm, export=1
+function ff_hevc_put_hevc_epel_hv64_8_\suffix, export=1
stp x4, x5, [sp, #-64]!
stp x2, x3, [sp, #16]
stp x0, x1, [sp, #32]
str x30, [sp, #48]
mov x6, #16
- bl X(ff_hevc_put_hevc_epel_hv16_8_neon_i8mm)
+ bl X(ff_hevc_put_hevc_epel_hv16_8_\suffix)
ldp x4, x5, [sp]
ldp x2, x3, [sp, #16]
ldp x0, x1, [sp, #32]
add x0, x0, #32
add x1, x1, #16
mov x6, #16
- bl X(ff_hevc_put_hevc_epel_hv16_8_neon_i8mm)
+ bl X(ff_hevc_put_hevc_epel_hv16_8_\suffix)
ldp x4, x5, [sp]
ldp x2, x3, [sp, #16]
ldp x0, x1, [sp, #32]
add x0, x0, #64
add x1, x1, #32
mov x6, #16
- bl X(ff_hevc_put_hevc_epel_hv16_8_neon_i8mm)
+ bl X(ff_hevc_put_hevc_epel_hv16_8_\suffix)
ldp x0, x1, [sp, #32]
ldp x2, x3, [sp, #16]
ldp x4, x5, [sp], #48
add x0, x0, #96
add x1, x1, #48
mov x6, #16
- bl X(ff_hevc_put_hevc_epel_hv16_8_neon_i8mm)
+ bl X(ff_hevc_put_hevc_epel_hv16_8_\suffix)
ldr x30, [sp], #16
ret
endfunc
+.endm
+
+epel_hv neon
+
+#if HAVE_I8MM
+ENABLE_I8MM
+
+epel_hv neon_i8mm
DISABLE_I8MM
#endif
diff --git a/libavcodec/aarch64/hevcdsp_init_aarch64.c b/libavcodec/aarch64/hevcdsp_init_aarch64.c
index be24737c9c..87e321da71 100644
--- a/libavcodec/aarch64/hevcdsp_init_aarch64.c
+++ b/libavcodec/aarch64/hevcdsp_init_aarch64.c
@@ -227,6 +227,10 @@ NEON8_FNPROTO(epel_h, (int16_t *dst,
const uint8_t *_src, ptrdiff_t _srcstride,
int height, intptr_t mx, intptr_t my, int width),);
+NEON8_FNPROTO(epel_hv, (int16_t *dst,
+ const uint8_t *src, ptrdiff_t srcstride,
+ int height, intptr_t mx, intptr_t my, int width), );
+
NEON8_FNPROTO(epel_h, (int16_t *dst,
const uint8_t *_src, ptrdiff_t _srcstride,
int height, intptr_t mx, intptr_t my, int width), _i8mm);
@@ -407,6 +411,8 @@ av_cold void ff_hevc_dsp_init_aarch64(HEVCDSPContext *c, const int bit_depth)
NEON8_FNASSIGN_SHARED_32(c->put_hevc_epel, 0, 1, epel_h,);
NEON8_FNASSIGN_SHARED_32(c->put_hevc_epel_uni_w, 0, 1, epel_uni_w_h,);
+ NEON8_FNASSIGN(c->put_hevc_epel, 1, 1, epel_hv,);
+
if (have_i8mm(cpu_flags)) {
NEON8_FNASSIGN(c->put_hevc_epel, 0, 1, epel_h, _i8mm);
NEON8_FNASSIGN(c->put_hevc_epel, 1, 1, epel_hv, _i8mm);
--
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 15:03 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 ` [FFmpeg-devel] [PATCH 08/21] aarch64: hevc: Split the epel_*_hv functions into two parts Martin Storsjö
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 ` Martin Storsjö [this message]
2024-03-25 15:02 ` [FFmpeg-devel] [PATCH 11/21] aarch64: hevc: Produce epel_uni_hv functions for both neon and i8mm 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=20240325150243.59058-11-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