Re: [FFmpeg-devel] [PATCH v2 2/4] avcodec/aarch64/hevcdsp: port add_residual functions
On Thu, 4 Feb 2021, Josh Dekker wrote:
From: Reimar Döffinger
Speedup is fairly small, around 1.5%, but these are fairly simple.
Signed-off-by: Josh Dekker
---
libavcodec/aarch64/hevcdsp_idct_neon.S| 190 ++
libavcodec/aarch64/hevcdsp_init_aarch64.c | 24 +++
2 files changed, 214 insertions(+)
diff --git a/libavcodec/aarch64/hevcdsp_idct_neon.S
b/libavcodec/aarch64/hevcdsp_idct_neon.S
index c70d6a906d..329038a958 100644
--- a/libavcodec/aarch64/hevcdsp_idct_neon.S
+++ b/libavcodec/aarch64/hevcdsp_idct_neon.S
@@ -36,6 +36,196 @@ const trans, align=4
.short 31, 22, 13, 4
endconst
+.macro clip10 in1, in2, c1, c2
+smax\in1, \in1, \c1
+smax\in2, \in2, \c1
+smin\in1, \in1, \c2
+smin\in2, \in2, \c2
+.endm
+
+function ff_hevc_add_residual_4x4_8_neon, export=1
+ld1 {v0.8h-v1.8h}, [x1]
+ld1 {v2.s}[0], [x0], x2
+ld1 {v2.s}[1], [x0], x2
+ld1 {v2.s}[2], [x0], x2
+ld1 {v2.s}[3], [x0], x2
+sub x0, x0, x2, lsl #2
+uxtlv6.8h, v2.8B
+uxtl2 v7.8h, v2.16B
Personal preference: I prefer the non-shouty forms like v2.16b instead of
v2.16B.
+sqadd v0.8h, v0.8h, v6.8h
+sqadd v1.8h, v1.8h, v7.8h
Nit: Incosistent alignment between columns 1-2 and 2-3. (And if one would
want to make space for full sized operands like v16.16b, they'd all need
another space.)
+sqxtun v0.8B, v0.8h
+sqxtun2 v0.16B, v1.8h
+st1 {v0.s}[0], [x0], x2
+st1 {v0.s}[1], [x0], x2
+st1 {v0.s}[2], [x0], x2
+st1 {v0.s}[3], [x0], x2
+ret
+endfunc
+
+function ff_hevc_add_residual_4x4_10_neon, export=1
+mov x12, x0
+ld1 {v0.8h-v1.8h}, [x1]
+ld1 {v2.d}[0], [x12], x2
+ld1 {v2.d}[1], [x12], x2
+ld1 {v3.d}[0], [x12], x2
+sqadd v0.8h, v0.8h, v2.8h
+ld1 {V3.d}[1], [x12], x2
+moviv4.8h, #0
+sqadd v1.8h, v1.8h, v3.8h
+mvniv5.8h, #0xFC, LSL #8 // movi #0x3FF
+clip10 v0.8h, v1.8h, v4.8h, v5.8h
+st1 {v0.d}[0], [x0], x2
+st1 {v0.d}[1], [x0], x2
+st1 {v1.d}[0], [x0], x2
+st1 {v1.d}[1], [x0], x2
+ret
+endfunc
+
+function ff_hevc_add_residual_8x8_8_neon, export=1
+add x12, x0, x2
+add x2, x2, x2
+mov x3, #8
+1: subsx3, x3, #2
Nit: Odd vertical alignment here?
+ld1 {v2.d}[0], [x0]
+ld1 {v2.d}[1], [x12]
+uxtlv3.8h, v2.8B
+ld1 {v0.8h-v1.8h}, [x1], #32
+uxtl2 v2.8h, v2.16B
+sqadd v0.8h, v0.8h, v3.8h
+sqadd v1.8h, v1.8h, v2.8h
+sqxtun v0.8B, v0.8h
+sqxtun2 v0.16B, v1.8h
+st1 {v0.d}[0], [x0], x2
+st1 {v0.d}[1], [x12], x2
+bne 1b
+ret
+endfunc
+
+function ff_hevc_add_residual_8x8_10_neon, export=1
+add x12, x0, x2
+add x2, x2, x2
+mov x3, #8
+moviv4.8h, #0
+mvniv5.8h, #0xFC, LSL #8 // movi #0x3FF
+1: subsx3, x3, #2
+ld1 {v0.8h-v1.8h}, [x1], #32
+ld1 {v2.8h},[x0]
+sqadd v0.8h, v0.8h, v2.8h
+ld1 {v3.8h},[x12]
+sqadd v1.8h, v1.8h, v3.8h
+clip10 v0.8h, v1.8h, v4.8h, v5.8h
+st1 {v0.8h}, [x0], x2
+st1 {v1.8h}, [x12], x2
+bne 1b
+ret
+endfunc
+
+function ff_hevc_add_residual_16x16_8_neon, export=1
+mov x3, #16
+add x12, x0, x2
+add x2, x2, x2
+1: subsx3, x3, #2
+ld1 {v16.16B}, [x0]
+ld1 {v0.8h-v3.8h}, [x1], #64
+ld1 {v19.16B},[x12]
+uxtlv17.8h, v16.8B
+uxtl2 v18.8h, v16.16B
+uxtlv20.8h, v19.8B
+uxtl2 v21.8h, v19.16B
+sqadd v0.8h, v0.8h, v17.8h
+sqadd v1.8h, v1.8h, v18.8h
+sqadd v2.8h, v2.8h, v20.8h
+sqadd v3.8h, v3.8h, v21.8h
+sqxtun v0.8B, v0.8h
+sqxtun2 v0.16B, v1.8h
+sqxtun v1.8B, v2.8h
+sqxtun2 v1.16B, v3.8h
+st1 {v0.16B}, [x0], x2
+st1
[FFmpeg-devel] [PATCH v2 2/4] avcodec/aarch64/hevcdsp: port add_residual functions
From: Reimar Döffinger
Speedup is fairly small, around 1.5%, but these are fairly simple.
Signed-off-by: Josh Dekker
---
libavcodec/aarch64/hevcdsp_idct_neon.S| 190 ++
libavcodec/aarch64/hevcdsp_init_aarch64.c | 24 +++
2 files changed, 214 insertions(+)
diff --git a/libavcodec/aarch64/hevcdsp_idct_neon.S
b/libavcodec/aarch64/hevcdsp_idct_neon.S
index c70d6a906d..329038a958 100644
--- a/libavcodec/aarch64/hevcdsp_idct_neon.S
+++ b/libavcodec/aarch64/hevcdsp_idct_neon.S
@@ -36,6 +36,196 @@ const trans, align=4
.short 31, 22, 13, 4
endconst
+.macro clip10 in1, in2, c1, c2
+smax\in1, \in1, \c1
+smax\in2, \in2, \c1
+smin\in1, \in1, \c2
+smin\in2, \in2, \c2
+.endm
+
+function ff_hevc_add_residual_4x4_8_neon, export=1
+ld1 {v0.8h-v1.8h}, [x1]
+ld1 {v2.s}[0], [x0], x2
+ld1 {v2.s}[1], [x0], x2
+ld1 {v2.s}[2], [x0], x2
+ld1 {v2.s}[3], [x0], x2
+sub x0, x0, x2, lsl #2
+uxtlv6.8h, v2.8B
+uxtl2 v7.8h, v2.16B
+sqadd v0.8h, v0.8h, v6.8h
+sqadd v1.8h, v1.8h, v7.8h
+sqxtun v0.8B, v0.8h
+sqxtun2 v0.16B, v1.8h
+st1 {v0.s}[0], [x0], x2
+st1 {v0.s}[1], [x0], x2
+st1 {v0.s}[2], [x0], x2
+st1 {v0.s}[3], [x0], x2
+ret
+endfunc
+
+function ff_hevc_add_residual_4x4_10_neon, export=1
+mov x12, x0
+ld1 {v0.8h-v1.8h}, [x1]
+ld1 {v2.d}[0], [x12], x2
+ld1 {v2.d}[1], [x12], x2
+ld1 {v3.d}[0], [x12], x2
+sqadd v0.8h, v0.8h, v2.8h
+ld1 {V3.d}[1], [x12], x2
+moviv4.8h, #0
+sqadd v1.8h, v1.8h, v3.8h
+mvniv5.8h, #0xFC, LSL #8 // movi #0x3FF
+clip10 v0.8h, v1.8h, v4.8h, v5.8h
+st1 {v0.d}[0], [x0], x2
+st1 {v0.d}[1], [x0], x2
+st1 {v1.d}[0], [x0], x2
+st1 {v1.d}[1], [x0], x2
+ret
+endfunc
+
+function ff_hevc_add_residual_8x8_8_neon, export=1
+add x12, x0, x2
+add x2, x2, x2
+mov x3, #8
+1: subsx3, x3, #2
+ld1 {v2.d}[0], [x0]
+ld1 {v2.d}[1], [x12]
+uxtlv3.8h, v2.8B
+ld1 {v0.8h-v1.8h}, [x1], #32
+uxtl2 v2.8h, v2.16B
+sqadd v0.8h, v0.8h, v3.8h
+sqadd v1.8h, v1.8h, v2.8h
+sqxtun v0.8B, v0.8h
+sqxtun2 v0.16B, v1.8h
+st1 {v0.d}[0], [x0], x2
+st1 {v0.d}[1], [x12], x2
+bne 1b
+ret
+endfunc
+
+function ff_hevc_add_residual_8x8_10_neon, export=1
+add x12, x0, x2
+add x2, x2, x2
+mov x3, #8
+moviv4.8h, #0
+mvniv5.8h, #0xFC, LSL #8 // movi #0x3FF
+1: subsx3, x3, #2
+ld1 {v0.8h-v1.8h}, [x1], #32
+ld1 {v2.8h},[x0]
+sqadd v0.8h, v0.8h, v2.8h
+ld1 {v3.8h},[x12]
+sqadd v1.8h, v1.8h, v3.8h
+clip10 v0.8h, v1.8h, v4.8h, v5.8h
+st1 {v0.8h}, [x0], x2
+st1 {v1.8h}, [x12], x2
+bne 1b
+ret
+endfunc
+
+function ff_hevc_add_residual_16x16_8_neon, export=1
+mov x3, #16
+add x12, x0, x2
+add x2, x2, x2
+1: subsx3, x3, #2
+ld1 {v16.16B}, [x0]
+ld1 {v0.8h-v3.8h}, [x1], #64
+ld1 {v19.16B},[x12]
+uxtlv17.8h, v16.8B
+uxtl2 v18.8h, v16.16B
+uxtlv20.8h, v19.8B
+uxtl2 v21.8h, v19.16B
+sqadd v0.8h, v0.8h, v17.8h
+sqadd v1.8h, v1.8h, v18.8h
+sqadd v2.8h, v2.8h, v20.8h
+sqadd v3.8h, v3.8h, v21.8h
+sqxtun v0.8B, v0.8h
+sqxtun2 v0.16B, v1.8h
+sqxtun v1.8B, v2.8h
+sqxtun2 v1.16B, v3.8h
+st1 {v0.16B}, [x0], x2
+st1 {v1.16B}, [x12], x2
+bne 1b
+ret
+endfunc
+
+function ff_hevc_add_residual_16x16_10_neon, export=1
+mov x3, #16
+moviv20.8h, #0
+mvniv21.8h, #0xFC, LSL #8 // movi #0x3FF
+add x12, x0, x2
+add
