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 17/21] aarch64: hevc: Reorder qpel_hv functions to prepare for templating
Date: Mon, 25 Mar 2024 17:02:39 +0200
Message-ID: <20240325150243.59058-18-martin@martin.st> (raw)
In-Reply-To: <20240325150243.59058-1-martin@martin.st>
---
libavcodec/aarch64/hevcdsp_qpel_neon.S | 695 +++++++++++++------------
1 file changed, 355 insertions(+), 340 deletions(-)
diff --git a/libavcodec/aarch64/hevcdsp_qpel_neon.S b/libavcodec/aarch64/hevcdsp_qpel_neon.S
index 06832603d9..ad568e415b 100644
--- a/libavcodec/aarch64/hevcdsp_qpel_neon.S
+++ b/libavcodec/aarch64/hevcdsp_qpel_neon.S
@@ -2146,29 +2146,6 @@ function ff_hevc_put_hevc_qpel_uni_w_v64_8_neon, export=1
ret
endfunc
-#if HAVE_I8MM
-ENABLE_I8MM
-
-function ff_hevc_put_hevc_qpel_uni_hv4_8_neon_i8mm, export=1
- add w10, w4, #7
- lsl x10, x10, #7
- sub sp, sp, x10 // tmp_array
- str x30, [sp, #-48]!
- stp x4, x6, [sp, #16]
- stp x0, x1, [sp, #32]
- sub x1, x2, x3, lsl #1
- sub x1, x1, x3
- add x0, sp, #48
- mov x2, x3
- add x3, x4, #7
- mov x4, x5
- bl X(ff_hevc_put_hevc_qpel_h4_8_neon_i8mm)
- 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
@@ -2195,26 +2172,6 @@ function hevc_put_hevc_qpel_uni_hv4_8_end_neon
2: ret
endfunc
-function ff_hevc_put_hevc_qpel_uni_hv6_8_neon_i8mm, export=1
- add w10, w4, #7
- lsl x10, x10, #7
- sub sp, sp, x10 // tmp_array
- str x30, [sp, #-48]!
- stp x4, x6, [sp, #16]
- stp x0, x1, [sp, #32]
- sub x1, x2, x3, lsl #1
- sub x1, x1, x3
- add x0, sp, #48
- mov x2, x3
- add w3, w4, #7
- mov x4, x5
- bl X(ff_hevc_put_hevc_qpel_h6_8_neon_i8mm)
- 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
@@ -2244,26 +2201,6 @@ function hevc_put_hevc_qpel_uni_hv6_8_end_neon
2: ret
endfunc
-function ff_hevc_put_hevc_qpel_uni_hv8_8_neon_i8mm, export=1
- add w10, w4, #7
- lsl x10, x10, #7
- sub sp, sp, x10 // tmp_array
- str x30, [sp, #-48]!
- stp x4, x6, [sp, #16]
- stp x0, x1, [sp, #32]
- sub x1, x2, x3, lsl #1
- sub x1, x1, x3
- add x0, sp, #48
- mov x2, x3
- add w3, w4, #7
- mov x4, x5
- bl X(ff_hevc_put_hevc_qpel_h8_8_neon_i8mm)
- 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
@@ -2291,26 +2228,6 @@ function hevc_put_hevc_qpel_uni_hv8_8_end_neon
2: ret
endfunc
-function ff_hevc_put_hevc_qpel_uni_hv12_8_neon_i8mm, export=1
- add w10, w4, #7
- lsl x10, x10, #7
- sub sp, sp, x10 // tmp_array
- stp x7, x30, [sp, #-48]!
- stp x4, x6, [sp, #16]
- stp x0, x1, [sp, #32]
- sub x1, x2, x3, lsl #1
- sub x1, x1, x3
- mov x2, x3
- add x0, sp, #48
- add w3, w4, #7
- mov x4, x5
- bl X(ff_hevc_put_hevc_qpel_h12_8_neon_i8mm)
- 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
@@ -2338,26 +2255,6 @@ function hevc_put_hevc_qpel_uni_hv12_8_end_neon
2: ret
endfunc
-function ff_hevc_put_hevc_qpel_uni_hv16_8_neon_i8mm, export=1
- add w10, w4, #7
- lsl x10, x10, #7
- sub sp, sp, x10 // tmp_array
- stp x7, x30, [sp, #-48]!
- stp x4, x6, [sp, #16]
- stp x0, x1, [sp, #32]
- add x0, sp, #48
- sub x1, x2, x3, lsl #1
- sub x1, x1, x3
- mov x2, x3
- add w3, w4, #7
- mov x4, x5
- bl X(ff_hevc_put_hevc_qpel_h16_8_neon_i8mm)
- ldp x4, x6, [sp, #16]
- ldp x0, x1, [sp, #32]
- ldp x7, x30, [sp], #48
- 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
@@ -2396,6 +2293,109 @@ function hevc_put_hevc_qpel_uni_hv16_8_end_neon
ret
endfunc
+#if HAVE_I8MM
+ENABLE_I8MM
+
+function ff_hevc_put_hevc_qpel_uni_hv4_8_neon_i8mm, export=1
+ add w10, w4, #7
+ lsl x10, x10, #7
+ sub sp, sp, x10 // tmp_array
+ str x30, [sp, #-48]!
+ stp x4, x6, [sp, #16]
+ stp x0, x1, [sp, #32]
+ sub x1, x2, x3, lsl #1
+ sub x1, x1, x3
+ add x0, sp, #48
+ mov x2, x3
+ add x3, x4, #7
+ mov x4, x5
+ bl X(ff_hevc_put_hevc_qpel_h4_8_neon_i8mm)
+ 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 ff_hevc_put_hevc_qpel_uni_hv6_8_neon_i8mm, export=1
+ add w10, w4, #7
+ lsl x10, x10, #7
+ sub sp, sp, x10 // tmp_array
+ str x30, [sp, #-48]!
+ stp x4, x6, [sp, #16]
+ stp x0, x1, [sp, #32]
+ sub x1, x2, x3, lsl #1
+ sub x1, x1, x3
+ add x0, sp, #48
+ mov x2, x3
+ add w3, w4, #7
+ mov x4, x5
+ bl X(ff_hevc_put_hevc_qpel_h6_8_neon_i8mm)
+ 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 ff_hevc_put_hevc_qpel_uni_hv8_8_neon_i8mm, export=1
+ add w10, w4, #7
+ lsl x10, x10, #7
+ sub sp, sp, x10 // tmp_array
+ str x30, [sp, #-48]!
+ stp x4, x6, [sp, #16]
+ stp x0, x1, [sp, #32]
+ sub x1, x2, x3, lsl #1
+ sub x1, x1, x3
+ add x0, sp, #48
+ mov x2, x3
+ add w3, w4, #7
+ mov x4, x5
+ bl X(ff_hevc_put_hevc_qpel_h8_8_neon_i8mm)
+ 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 ff_hevc_put_hevc_qpel_uni_hv12_8_neon_i8mm, export=1
+ add w10, w4, #7
+ lsl x10, x10, #7
+ sub sp, sp, x10 // tmp_array
+ stp x7, x30, [sp, #-48]!
+ stp x4, x6, [sp, #16]
+ stp x0, x1, [sp, #32]
+ sub x1, x2, x3, lsl #1
+ sub x1, x1, x3
+ mov x2, x3
+ add x0, sp, #48
+ add w3, w4, #7
+ mov x4, x5
+ bl X(ff_hevc_put_hevc_qpel_h12_8_neon_i8mm)
+ 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 ff_hevc_put_hevc_qpel_uni_hv16_8_neon_i8mm, export=1
+ add w10, w4, #7
+ lsl x10, x10, #7
+ sub sp, sp, x10 // tmp_array
+ stp x7, x30, [sp, #-48]!
+ stp x4, x6, [sp, #16]
+ stp x0, x1, [sp, #32]
+ add x0, sp, #48
+ sub x1, x2, x3, lsl #1
+ sub x1, x1, x3
+ mov x2, x3
+ add w3, w4, #7
+ mov x4, x5
+ bl X(ff_hevc_put_hevc_qpel_h16_8_neon_i8mm)
+ ldp x4, x6, [sp, #16]
+ ldp x0, x1, [sp, #32]
+ ldp x7, x30, [sp], #48
+ b hevc_put_hevc_qpel_uni_hv16_8_end_neon
+endfunc
+
function ff_hevc_put_hevc_qpel_uni_hv24_8_neon_i8mm, export=1
stp x4, x5, [sp, #-64]!
stp x2, x3, [sp, #16]
@@ -3779,25 +3779,10 @@ function ff_hevc_put_hevc_qpel_h64_8_neon_i8mm, export=1
b.ne 1b
ret
endfunc
+DISABLE_I8MM
+#endif
-function ff_hevc_put_hevc_qpel_hv4_8_neon_i8mm, export=1
- add w10, w3, #7
- mov x7, #128
- lsl x10, x10, #7
- sub sp, sp, x10 // tmp_array
- stp x5, x30, [sp, #-32]!
- stp x0, x3, [sp, #16]
- add x0, sp, #32
- sub x1, x1, x2, lsl #1
- add x3, x3, #7
- sub x1, x1, x2
- 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]
@@ -3822,23 +3807,6 @@ function hevc_put_hevc_qpel_hv4_8_end_neon
2: ret
endfunc
-function ff_hevc_put_hevc_qpel_hv6_8_neon_i8mm, export=1
- add w10, w3, #7
- mov x7, #128
- lsl x10, x10, #7
- sub sp, sp, x10 // tmp_array
- stp x5, x30, [sp, #-32]!
- stp x0, x3, [sp, #16]
- add x0, sp, #32
- sub x1, x1, x2, lsl #1
- add x3, x3, #7
- sub x1, x1, x2
- 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
@@ -3866,22 +3834,6 @@ function hevc_put_hevc_qpel_hv6_8_end_neon
2: ret
endfunc
-function ff_hevc_put_hevc_qpel_hv8_8_neon_i8mm, export=1
- add w10, w3, #7
- lsl x10, x10, #7
- sub x1, x1, x2, lsl #1
- sub sp, sp, x10 // tmp_array
- stp x5, x30, [sp, #-32]!
- stp x0, x3, [sp, #16]
- add x0, sp, #32
- add x3, x3, #7
- sub x1, x1, x2
- 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
@@ -3908,22 +3860,6 @@ function hevc_put_hevc_qpel_hv8_8_end_neon
2: ret
endfunc
-function ff_hevc_put_hevc_qpel_hv12_8_neon_i8mm, export=1
- add w10, w3, #7
- lsl x10, x10, #7
- sub x1, x1, x2, lsl #1
- sub sp, sp, x10 // tmp_array
- stp x5, x30, [sp, #-32]!
- stp x0, x3, [sp, #16]
- add x0, sp, #32
- add x3, x3, #7
- sub x1, x1, x2
- 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
@@ -3949,22 +3885,6 @@ function hevc_put_hevc_qpel_hv12_8_end_neon
2: ret
endfunc
-function ff_hevc_put_hevc_qpel_hv16_8_neon_i8mm, export=1
- add w10, w3, #7
- lsl x10, x10, #7
- sub x1, x1, x2, lsl #1
- sub sp, sp, x10 // tmp_array
- stp x5, x30, [sp, #-32]!
- stp x0, x3, [sp, #16]
- add x3, x3, #7
- add x0, sp, #32
- sub x1, x1, x2
- 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
@@ -3989,38 +3909,6 @@ function hevc_put_hevc_qpel_hv16_8_end_neon
2: ret
endfunc
-function ff_hevc_put_hevc_qpel_hv24_8_neon_i8mm, export=1
- stp x4, x5, [sp, #-64]!
- stp x2, x3, [sp, #16]
- stp x0, x1, [sp, #32]
- str x30, [sp, #48]
- bl X(ff_hevc_put_hevc_qpel_hv12_8_neon_i8mm)
- ldp x0, x1, [sp, #32]
- ldp x2, x3, [sp, #16]
- ldp x4, x5, [sp], #48
- add x1, x1, #12
- add x0, x0, #24
- bl X(ff_hevc_put_hevc_qpel_hv12_8_neon_i8mm)
- ldr x30, [sp], #16
- ret
-endfunc
-
-function ff_hevc_put_hevc_qpel_hv32_8_neon_i8mm, export=1
- add w10, w3, #7
- sub x1, x1, x2, lsl #1
- lsl x10, x10, #7
- sub x1, x1, x2
- sub sp, sp, x10 // tmp_array
- stp x5, x30, [sp, #-32]!
- stp x0, x3, [sp, #16]
- add x3, x3, #7
- add x0, sp, #32
- 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
@@ -4056,6 +3944,122 @@ function hevc_put_hevc_qpel_hv32_8_end_neon
ret
endfunc
+#if HAVE_I8MM
+ENABLE_I8MM
+function ff_hevc_put_hevc_qpel_hv4_8_neon_i8mm, export=1
+ add w10, w3, #7
+ mov x7, #128
+ lsl x10, x10, #7
+ sub sp, sp, x10 // tmp_array
+ stp x5, x30, [sp, #-32]!
+ stp x0, x3, [sp, #16]
+ add x0, sp, #32
+ sub x1, x1, x2, lsl #1
+ add x3, x3, #7
+ sub x1, x1, x2
+ 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 ff_hevc_put_hevc_qpel_hv6_8_neon_i8mm, export=1
+ add w10, w3, #7
+ mov x7, #128
+ lsl x10, x10, #7
+ sub sp, sp, x10 // tmp_array
+ stp x5, x30, [sp, #-32]!
+ stp x0, x3, [sp, #16]
+ add x0, sp, #32
+ sub x1, x1, x2, lsl #1
+ add x3, x3, #7
+ sub x1, x1, x2
+ 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 ff_hevc_put_hevc_qpel_hv8_8_neon_i8mm, export=1
+ add w10, w3, #7
+ lsl x10, x10, #7
+ sub x1, x1, x2, lsl #1
+ sub sp, sp, x10 // tmp_array
+ stp x5, x30, [sp, #-32]!
+ stp x0, x3, [sp, #16]
+ add x0, sp, #32
+ add x3, x3, #7
+ sub x1, x1, x2
+ 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 ff_hevc_put_hevc_qpel_hv12_8_neon_i8mm, export=1
+ add w10, w3, #7
+ lsl x10, x10, #7
+ sub x1, x1, x2, lsl #1
+ sub sp, sp, x10 // tmp_array
+ stp x5, x30, [sp, #-32]!
+ stp x0, x3, [sp, #16]
+ add x0, sp, #32
+ add x3, x3, #7
+ sub x1, x1, x2
+ 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 ff_hevc_put_hevc_qpel_hv16_8_neon_i8mm, export=1
+ add w10, w3, #7
+ lsl x10, x10, #7
+ sub x1, x1, x2, lsl #1
+ sub sp, sp, x10 // tmp_array
+ stp x5, x30, [sp, #-32]!
+ stp x0, x3, [sp, #16]
+ add x3, x3, #7
+ add x0, sp, #32
+ sub x1, x1, x2
+ 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 ff_hevc_put_hevc_qpel_hv24_8_neon_i8mm, export=1
+ stp x4, x5, [sp, #-64]!
+ stp x2, x3, [sp, #16]
+ stp x0, x1, [sp, #32]
+ str x30, [sp, #48]
+ bl X(ff_hevc_put_hevc_qpel_hv12_8_neon_i8mm)
+ ldp x0, x1, [sp, #32]
+ ldp x2, x3, [sp, #16]
+ ldp x4, x5, [sp], #48
+ add x1, x1, #12
+ add x0, x0, #24
+ bl X(ff_hevc_put_hevc_qpel_hv12_8_neon_i8mm)
+ ldr x30, [sp], #16
+ ret
+endfunc
+
+function ff_hevc_put_hevc_qpel_hv32_8_neon_i8mm, export=1
+ add w10, w3, #7
+ sub x1, x1, x2, lsl #1
+ lsl x10, x10, #7
+ sub x1, x1, x2
+ sub sp, sp, x10 // tmp_array
+ stp x5, x30, [sp, #-32]!
+ stp x0, x3, [sp, #16]
+ add x3, x3, #7
+ add x0, sp, #32
+ 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 ff_hevc_put_hevc_qpel_hv48_8_neon_i8mm, export=1
stp x4, x5, [sp, #-64]!
stp x2, x3, [sp, #16]
@@ -4089,6 +4093,8 @@ function ff_hevc_put_hevc_qpel_hv64_8_neon_i8mm, export=1
ldr x30, [sp], #16
ret
endfunc
+DISABLE_I8MM
+#endif
.macro QPEL_UNI_W_HV_HEADER width
ldp x14, x15, [sp] // mx, my
@@ -4168,11 +4174,6 @@ endfunc
smlal2 \dst\().4s, \src7\().8h, v0.h[7]
.endm
-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]
@@ -4262,11 +4263,6 @@ endfunc
st1 {v24.d}[0], [x20], x21
.endm
-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]
@@ -4376,21 +4372,6 @@ endfunc
st1 {v24.16b}, [x20], x21
.endm
-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 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_hv16_8_end_neon
-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_hv16_8_end_neon
-endfunc
-
function hevc_put_hevc_qpel_uni_w_hv16_8_end_neon
mov x11, sp
mov w12, w22
@@ -4503,26 +4484,37 @@ function hevc_put_hevc_qpel_uni_w_hv16_8_end_neon
ret
endfunc
-function ff_hevc_put_hevc_qpel_bi_hv4_8_neon_i8mm, export=1
- add w10, w5, #7
- lsl x10, x10, #7
- sub sp, sp, x10 // tmp_array
- stp x7, x30, [sp, #-48]!
- stp x4, x5, [sp, #16]
- stp x0, x1, [sp, #32]
- sub x1, x2, x3, lsl #1
- sub x1, x1, x3
- add x0, sp, #48
- mov x2, x3
- add w3, w5, #7
- mov x4, x6
- bl X(ff_hevc_put_hevc_qpel_h4_8_neon_i8mm)
- 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
+#if HAVE_I8MM
+ENABLE_I8MM
+
+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 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 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 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_hv16_8_end_neon
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_hv16_8_end_neon
+endfunc
+
+DISABLE_I8MM
+#endif
+
function hevc_put_hevc_qpel_bi_hv4_8_end_neon
mov x9, #(MAX_PB_SIZE * 2)
load_qpel_filterh x7, x6
@@ -4548,26 +4540,6 @@ function hevc_put_hevc_qpel_bi_hv4_8_end_neon
2: ret
endfunc
-function ff_hevc_put_hevc_qpel_bi_hv6_8_neon_i8mm, export=1
- add w10, w5, #7
- lsl x10, x10, #7
- sub sp, sp, x10 // tmp_array
- stp x7, x30, [sp, #-48]!
- stp x4, x5, [sp, #16]
- stp x0, x1, [sp, #32]
- sub x1, x2, x3, lsl #1
- sub x1, x1, x3
- add x0, sp, #48
- mov x2, x3
- add x3, x5, #7
- mov x4, x6
- bl X(ff_hevc_put_hevc_qpel_h6_8_neon_i8mm)
- 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
@@ -4598,26 +4570,6 @@ function hevc_put_hevc_qpel_bi_hv6_8_end_neon
2: ret
endfunc
-function ff_hevc_put_hevc_qpel_bi_hv8_8_neon_i8mm, export=1
- add w10, w5, #7
- lsl x10, x10, #7
- sub sp, sp, x10 // tmp_array
- stp x7, x30, [sp, #-48]!
- stp x4, x5, [sp, #16]
- stp x0, x1, [sp, #32]
- sub x1, x2, x3, lsl #1
- sub x1, x1, x3
- add x0, sp, #48
- mov x2, x3
- add x3, x5, #7
- mov x4, x6
- bl X(ff_hevc_put_hevc_qpel_h8_8_neon_i8mm)
- 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
@@ -4646,46 +4598,6 @@ function hevc_put_hevc_qpel_bi_hv8_8_end_neon
2: ret
endfunc
-function ff_hevc_put_hevc_qpel_bi_hv12_8_neon_i8mm, 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_qpel_bi_hv8_8_neon_i8mm)
- ldp x4, x5, [sp, #16]
- ldp x2, x3, [sp, #32]
- ldp x0, x1, [sp, #48]
- ldp x6, x7, [sp], #64
- add x4, x4, #16
- add x2, x2, #8
- add x0, x0, #8
- bl X(ff_hevc_put_hevc_qpel_bi_hv4_8_neon_i8mm)
- ldr x30, [sp], #16
- ret
-endfunc
-
-function ff_hevc_put_hevc_qpel_bi_hv16_8_neon_i8mm, export=1
- add w10, w5, #7
- lsl x10, x10, #7
- sub sp, sp, x10 // tmp_array
- stp x7, x30, [sp, #-48]!
- stp x4, x5, [sp, #16]
- stp x0, x1, [sp, #32]
- add x0, sp, #48
- sub x1, x2, x3, lsl #1
- sub x1, x1, x3
- mov x2, x3
- add w3, w5, #7
- mov x4, x6
- bl X(ff_hevc_put_hevc_qpel_h16_8_neon_i8mm)
- ldp x4, x5, [sp, #16]
- ldp x0, x1, [sp, #32]
- ldp x7, x30, [sp], #48
- mov x6, #16 // width
- 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)
@@ -4735,6 +4647,109 @@ function hevc_put_hevc_qpel_bi_hv16_8_end_neon
ret
endfunc
+#if HAVE_I8MM
+ENABLE_I8MM
+
+function ff_hevc_put_hevc_qpel_bi_hv4_8_neon_i8mm, export=1
+ add w10, w5, #7
+ lsl x10, x10, #7
+ sub sp, sp, x10 // tmp_array
+ stp x7, x30, [sp, #-48]!
+ stp x4, x5, [sp, #16]
+ stp x0, x1, [sp, #32]
+ sub x1, x2, x3, lsl #1
+ sub x1, x1, x3
+ add x0, sp, #48
+ mov x2, x3
+ add w3, w5, #7
+ mov x4, x6
+ bl X(ff_hevc_put_hevc_qpel_h4_8_neon_i8mm)
+ 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 ff_hevc_put_hevc_qpel_bi_hv6_8_neon_i8mm, export=1
+ add w10, w5, #7
+ lsl x10, x10, #7
+ sub sp, sp, x10 // tmp_array
+ stp x7, x30, [sp, #-48]!
+ stp x4, x5, [sp, #16]
+ stp x0, x1, [sp, #32]
+ sub x1, x2, x3, lsl #1
+ sub x1, x1, x3
+ add x0, sp, #48
+ mov x2, x3
+ add x3, x5, #7
+ mov x4, x6
+ bl X(ff_hevc_put_hevc_qpel_h6_8_neon_i8mm)
+ 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 ff_hevc_put_hevc_qpel_bi_hv8_8_neon_i8mm, export=1
+ add w10, w5, #7
+ lsl x10, x10, #7
+ sub sp, sp, x10 // tmp_array
+ stp x7, x30, [sp, #-48]!
+ stp x4, x5, [sp, #16]
+ stp x0, x1, [sp, #32]
+ sub x1, x2, x3, lsl #1
+ sub x1, x1, x3
+ add x0, sp, #48
+ mov x2, x3
+ add x3, x5, #7
+ mov x4, x6
+ bl X(ff_hevc_put_hevc_qpel_h8_8_neon_i8mm)
+ 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 ff_hevc_put_hevc_qpel_bi_hv12_8_neon_i8mm, 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_qpel_bi_hv8_8_neon_i8mm)
+ ldp x4, x5, [sp, #16]
+ ldp x2, x3, [sp, #32]
+ ldp x0, x1, [sp, #48]
+ ldp x6, x7, [sp], #64
+ add x4, x4, #16
+ add x2, x2, #8
+ add x0, x0, #8
+ bl X(ff_hevc_put_hevc_qpel_bi_hv4_8_neon_i8mm)
+ ldr x30, [sp], #16
+ ret
+endfunc
+
+function ff_hevc_put_hevc_qpel_bi_hv16_8_neon_i8mm, export=1
+ add w10, w5, #7
+ lsl x10, x10, #7
+ sub sp, sp, x10 // tmp_array
+ stp x7, x30, [sp, #-48]!
+ stp x4, x5, [sp, #16]
+ stp x0, x1, [sp, #32]
+ add x0, sp, #48
+ sub x1, x2, x3, lsl #1
+ sub x1, x1, x3
+ mov x2, x3
+ add w3, w5, #7
+ mov x4, x6
+ bl X(ff_hevc_put_hevc_qpel_h16_8_neon_i8mm)
+ ldp x4, x5, [sp, #16]
+ ldp x0, x1, [sp, #32]
+ ldp x7, x30, [sp], #48
+ mov x6, #16 // width
+ b hevc_put_hevc_qpel_bi_hv16_8_end_neon
+endfunc
+
function ff_hevc_put_hevc_qpel_bi_hv24_8_neon_i8mm, export=1
stp x6, x7, [sp, #-80]!
stp x4, x5, [sp, #16]
--
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 ` [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 ` [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 ` Martin Storsjö [this message]
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=20240325150243.59058-18-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