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 14/21] aarch64: hevc: Implement a neon version of hevc_qpel_uni_w_h*_8
Date: Mon, 25 Mar 2024 17:02:36 +0200
Message-ID: <20240325150243.59058-15-martin@martin.st> (raw)
In-Reply-To: <20240325150243.59058-1-martin@martin.st>
AWS Graviton 3:
put_hevc_qpel_uni_w_h4_8_c: 159.0
put_hevc_qpel_uni_w_h4_8_neon: 64.2
put_hevc_qpel_uni_w_h4_8_i8mm: 40.0
put_hevc_qpel_uni_w_h6_8_c: 344.7
put_hevc_qpel_uni_w_h6_8_neon: 114.5
put_hevc_qpel_uni_w_h6_8_i8mm: 82.0
put_hevc_qpel_uni_w_h8_8_c: 596.2
put_hevc_qpel_uni_w_h8_8_neon: 132.2
put_hevc_qpel_uni_w_h8_8_i8mm: 106.0
put_hevc_qpel_uni_w_h12_8_c: 1325.0
put_hevc_qpel_uni_w_h12_8_neon: 299.0
put_hevc_qpel_uni_w_h12_8_i8mm: 211.5
put_hevc_qpel_uni_w_h16_8_c: 2300.0
put_hevc_qpel_uni_w_h16_8_neon: 422.0
put_hevc_qpel_uni_w_h16_8_i8mm: 286.2
put_hevc_qpel_uni_w_h24_8_c: 5059.0
put_hevc_qpel_uni_w_h24_8_neon: 912.2
put_hevc_qpel_uni_w_h24_8_i8mm: 664.2
put_hevc_qpel_uni_w_h32_8_c: 9198.2
put_hevc_qpel_uni_w_h32_8_neon: 1638.2
put_hevc_qpel_uni_w_h32_8_i8mm: 1033.7
put_hevc_qpel_uni_w_h48_8_c: 20754.7
put_hevc_qpel_uni_w_h48_8_neon: 3633.7
put_hevc_qpel_uni_w_h48_8_i8mm: 2300.7
put_hevc_qpel_uni_w_h64_8_c: 36854.7
put_hevc_qpel_uni_w_h64_8_neon: 6435.7
put_hevc_qpel_uni_w_h64_8_i8mm: 4039.2
---
libavcodec/aarch64/hevcdsp_init_aarch64.c | 7 +
libavcodec/aarch64/hevcdsp_qpel_neon.S | 405 +++++++++++++++++++++-
2 files changed, 410 insertions(+), 2 deletions(-)
diff --git a/libavcodec/aarch64/hevcdsp_init_aarch64.c b/libavcodec/aarch64/hevcdsp_init_aarch64.c
index 6110a360d8..ea0d26c019 100644
--- a/libavcodec/aarch64/hevcdsp_init_aarch64.c
+++ b/libavcodec/aarch64/hevcdsp_init_aarch64.c
@@ -277,6 +277,11 @@ NEON8_FNPROTO(qpel_uni_hv, (uint8_t *dst, ptrdiff_t dststride,
const uint8_t *src, ptrdiff_t srcstride,
int height, intptr_t mx, intptr_t my, int width), _i8mm);
+NEON8_FNPROTO(qpel_uni_w_h, (uint8_t *_dst, ptrdiff_t _dststride,
+ const uint8_t *_src, ptrdiff_t _srcstride,
+ int height, int denom, int wx, int ox,
+ intptr_t mx, intptr_t my, int width),);
+
NEON8_FNPROTO(qpel_uni_w_h, (uint8_t *_dst, ptrdiff_t _dststride,
const uint8_t *_src, ptrdiff_t _srcstride,
int height, int denom, int wx, int ox,
@@ -429,6 +434,8 @@ av_cold void ff_hevc_dsp_init_aarch64(HEVCDSPContext *c, const int bit_depth)
NEON8_FNASSIGN(c->put_hevc_epel_uni_w, 1, 1, epel_uni_w_hv,);
NEON8_FNASSIGN(c->put_hevc_epel_bi, 1, 1, epel_bi_hv,);
+ NEON8_FNASSIGN_SHARED_32(c->put_hevc_qpel_uni_w, 0, 1, qpel_uni_w_h,);
+
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);
diff --git a/libavcodec/aarch64/hevcdsp_qpel_neon.S b/libavcodec/aarch64/hevcdsp_qpel_neon.S
index 062b7d4d0f..fba063186c 100644
--- a/libavcodec/aarch64/hevcdsp_qpel_neon.S
+++ b/libavcodec/aarch64/hevcdsp_qpel_neon.S
@@ -2456,8 +2456,10 @@ function ff_hevc_put_hevc_qpel_uni_hv64_8_neon_i8mm, export=1
ldp x7, x30, [sp], #48
b .Lqpel_uni_hv16_loop
endfunc
+DISABLE_I8MM
+#endif
-.macro QPEL_UNI_W_H_HEADER
+.macro QPEL_UNI_W_H_HEADER elems=4s
ldr x12, [sp]
sub x2, x2, #3
movrel x9, qpel_filters
@@ -2465,11 +2467,410 @@ endfunc
ld1r {v28.2d}, [x9]
mov w10, #-6
sub w10, w10, w5
- dup v30.4s, w6 // wx
+ dup v30.\elems, w6 // wx
dup v31.4s, w10 // shift
dup v29.4s, w7 // ox
.endm
+function ff_hevc_put_hevc_qpel_uni_w_h4_8_neon, export=1
+ QPEL_UNI_W_H_HEADER 4h
+ sxtl v0.8h, v28.8b
+1:
+ ld1 {v1.8b, v2.8b}, [x2], x3
+ subs w4, w4, #1
+ uxtl v1.8h, v1.8b
+ uxtl v2.8h, v2.8b
+ ext v3.16b, v1.16b, v2.16b, #2
+ ext v4.16b, v1.16b, v2.16b, #4
+ ext v5.16b, v1.16b, v2.16b, #6
+ ext v6.16b, v1.16b, v2.16b, #8
+ ext v7.16b, v1.16b, v2.16b, #10
+ ext v16.16b, v1.16b, v2.16b, #12
+ ext v17.16b, v1.16b, v2.16b, #14
+ mul v18.4h, v1.4h, v0.h[0]
+ mla v18.4h, v3.4h, v0.h[1]
+ mla v18.4h, v4.4h, v0.h[2]
+ mla v18.4h, v5.4h, v0.h[3]
+ mla v18.4h, v6.4h, v0.h[4]
+ mla v18.4h, v7.4h, v0.h[5]
+ mla v18.4h, v16.4h, v0.h[6]
+ mla v18.4h, v17.4h, v0.h[7]
+ smull v16.4s, v18.4h, v30.4h
+ sqrshl v16.4s, v16.4s, v31.4s
+ sqadd v16.4s, v16.4s, v29.4s
+ sqxtn v16.4h, v16.4s
+ sqxtun v16.8b, v16.8h
+ str s16, [x0]
+ add x0, x0, x1
+ b.hi 1b
+ ret
+endfunc
+
+function ff_hevc_put_hevc_qpel_uni_w_h6_8_neon, export=1
+ QPEL_UNI_W_H_HEADER 8h
+ sub x1, x1, #4
+ sxtl v0.8h, v28.8b
+1:
+ ld1 {v1.8b, v2.8b}, [x2], x3
+ subs w4, w4, #1
+ uxtl v1.8h, v1.8b
+ uxtl v2.8h, v2.8b
+ ext v3.16b, v1.16b, v2.16b, #2
+ ext v4.16b, v1.16b, v2.16b, #4
+ ext v5.16b, v1.16b, v2.16b, #6
+ ext v6.16b, v1.16b, v2.16b, #8
+ ext v7.16b, v1.16b, v2.16b, #10
+ ext v16.16b, v1.16b, v2.16b, #12
+ ext v17.16b, v1.16b, v2.16b, #14
+ mul v18.8h, v1.8h, v0.h[0]
+ mla v18.8h, v3.8h, v0.h[1]
+ mla v18.8h, v4.8h, v0.h[2]
+ mla v18.8h, v5.8h, v0.h[3]
+ mla v18.8h, v6.8h, v0.h[4]
+ mla v18.8h, v7.8h, v0.h[5]
+ mla v18.8h, v16.8h, v0.h[6]
+ mla v18.8h, v17.8h, v0.h[7]
+ smull v16.4s, v18.4h, v30.4h
+ smull2 v17.4s, v18.8h, v30.8h
+ sqrshl v16.4s, v16.4s, v31.4s
+ sqrshl v17.4s, v17.4s, v31.4s
+ sqadd v16.4s, v16.4s, v29.4s
+ sqadd v17.4s, v17.4s, v29.4s
+ sqxtn v16.4h, v16.4s
+ sqxtn2 v16.8h, v17.4s
+ sqxtun v16.8b, v16.8h
+ str s16, [x0], #4
+ st1 {v16.h}[2], [x0], x1
+ b.hi 1b
+ ret
+endfunc
+
+function ff_hevc_put_hevc_qpel_uni_w_h8_8_neon, export=1
+ QPEL_UNI_W_H_HEADER 8h
+ sxtl v0.8h, v28.8b
+1:
+ ld1 {v1.8b, v2.8b}, [x2], x3
+ subs w4, w4, #1
+ uxtl v1.8h, v1.8b
+ uxtl v2.8h, v2.8b
+ ext v3.16b, v1.16b, v2.16b, #2
+ ext v4.16b, v1.16b, v2.16b, #4
+ ext v5.16b, v1.16b, v2.16b, #6
+ ext v6.16b, v1.16b, v2.16b, #8
+ ext v7.16b, v1.16b, v2.16b, #10
+ ext v16.16b, v1.16b, v2.16b, #12
+ ext v17.16b, v1.16b, v2.16b, #14
+ mul v18.8h, v1.8h, v0.h[0]
+ mla v18.8h, v3.8h, v0.h[1]
+ mla v18.8h, v4.8h, v0.h[2]
+ mla v18.8h, v5.8h, v0.h[3]
+ mla v18.8h, v6.8h, v0.h[4]
+ mla v18.8h, v7.8h, v0.h[5]
+ mla v18.8h, v16.8h, v0.h[6]
+ mla v18.8h, v17.8h, v0.h[7]
+ smull v16.4s, v18.4h, v30.4h
+ smull2 v17.4s, v18.8h, v30.8h
+ sqrshl v16.4s, v16.4s, v31.4s
+ sqrshl v17.4s, v17.4s, v31.4s
+ sqadd v16.4s, v16.4s, v29.4s
+ sqadd v17.4s, v17.4s, v29.4s
+ sqxtn v16.4h, v16.4s
+ sqxtn2 v16.8h, v17.4s
+ sqxtun v16.8b, v16.8h
+ st1 {v16.8b}, [x0], x1
+ b.hi 1b
+ ret
+endfunc
+
+function ff_hevc_put_hevc_qpel_uni_w_h12_8_neon, export=1
+ QPEL_UNI_W_H_HEADER 8h
+ add x13, x0, #8
+ sxtl v0.8h, v28.8b
+1:
+ ld1 {v1.8b, v2.8b, v3.8b}, [x2], x3
+ subs w4, w4, #1
+ uxtl v1.8h, v1.8b
+ uxtl v2.8h, v2.8b
+ uxtl v3.8h, v3.8b
+ ext v4.16b, v1.16b, v2.16b, #2
+ ext v5.16b, v1.16b, v2.16b, #4
+ ext v6.16b, v1.16b, v2.16b, #6
+ ext v7.16b, v1.16b, v2.16b, #8
+ ext v16.16b, v1.16b, v2.16b, #10
+ ext v17.16b, v1.16b, v2.16b, #12
+ ext v18.16b, v1.16b, v2.16b, #14
+ mul v19.8h, v1.8h, v0.h[0]
+ mla v19.8h, v4.8h, v0.h[1]
+ mla v19.8h, v5.8h, v0.h[2]
+ mla v19.8h, v6.8h, v0.h[3]
+ mla v19.8h, v7.8h, v0.h[4]
+ mla v19.8h, v16.8h, v0.h[5]
+ mla v19.8h, v17.8h, v0.h[6]
+ mla v19.8h, v18.8h, v0.h[7]
+ ext v4.16b, v2.16b, v3.16b, #2
+ ext v5.16b, v2.16b, v3.16b, #4
+ ext v6.16b, v2.16b, v3.16b, #6
+ ext v7.16b, v2.16b, v3.16b, #8
+ ext v16.16b, v2.16b, v3.16b, #10
+ ext v17.16b, v2.16b, v3.16b, #12
+ ext v18.16b, v2.16b, v3.16b, #14
+ mul v20.4h, v2.4h, v0.h[0]
+ mla v20.4h, v4.4h, v0.h[1]
+ mla v20.4h, v5.4h, v0.h[2]
+ mla v20.4h, v6.4h, v0.h[3]
+ mla v20.4h, v7.4h, v0.h[4]
+ mla v20.4h, v16.4h, v0.h[5]
+ mla v20.4h, v17.4h, v0.h[6]
+ mla v20.4h, v18.4h, v0.h[7]
+ smull v16.4s, v19.4h, v30.4h
+ smull2 v17.4s, v19.8h, v30.8h
+ smull v18.4s, v20.4h, v30.4h
+ sqrshl v16.4s, v16.4s, v31.4s
+ sqrshl v17.4s, v17.4s, v31.4s
+ sqrshl v18.4s, v18.4s, v31.4s
+ sqadd v16.4s, v16.4s, v29.4s
+ sqadd v17.4s, v17.4s, v29.4s
+ sqadd v18.4s, v18.4s, v29.4s
+ sqxtn v16.4h, v16.4s
+ sqxtn2 v16.8h, v17.4s
+ sqxtn v17.4h, v18.4s
+ sqxtun v16.8b, v16.8h
+ sqxtun v17.8b, v17.8h
+ st1 {v16.8b}, [x0], x1
+ st1 {v17.s}[0], [x13], x1
+ b.hi 1b
+ ret
+endfunc
+
+function ff_hevc_put_hevc_qpel_uni_w_h16_8_neon, export=1
+ QPEL_UNI_W_H_HEADER 8h
+ sxtl v0.8h, v28.8b
+1:
+ ld1 {v1.8b, v2.8b, v3.8b}, [x2], x3
+ subs w4, w4, #1
+ uxtl v1.8h, v1.8b
+ uxtl v2.8h, v2.8b
+ uxtl v3.8h, v3.8b
+ ext v4.16b, v1.16b, v2.16b, #2
+ ext v5.16b, v1.16b, v2.16b, #4
+ ext v6.16b, v1.16b, v2.16b, #6
+ ext v7.16b, v1.16b, v2.16b, #8
+ ext v16.16b, v1.16b, v2.16b, #10
+ ext v17.16b, v1.16b, v2.16b, #12
+ ext v18.16b, v1.16b, v2.16b, #14
+ mul v19.8h, v1.8h, v0.h[0]
+ mla v19.8h, v4.8h, v0.h[1]
+ mla v19.8h, v5.8h, v0.h[2]
+ mla v19.8h, v6.8h, v0.h[3]
+ mla v19.8h, v7.8h, v0.h[4]
+ mla v19.8h, v16.8h, v0.h[5]
+ mla v19.8h, v17.8h, v0.h[6]
+ mla v19.8h, v18.8h, v0.h[7]
+ ext v4.16b, v2.16b, v3.16b, #2
+ ext v5.16b, v2.16b, v3.16b, #4
+ ext v6.16b, v2.16b, v3.16b, #6
+ ext v7.16b, v2.16b, v3.16b, #8
+ ext v16.16b, v2.16b, v3.16b, #10
+ ext v17.16b, v2.16b, v3.16b, #12
+ ext v18.16b, v2.16b, v3.16b, #14
+ mul v20.8h, v2.8h, v0.h[0]
+ mla v20.8h, v4.8h, v0.h[1]
+ mla v20.8h, v5.8h, v0.h[2]
+ mla v20.8h, v6.8h, v0.h[3]
+ mla v20.8h, v7.8h, v0.h[4]
+ mla v20.8h, v16.8h, v0.h[5]
+ mla v20.8h, v17.8h, v0.h[6]
+ mla v20.8h, v18.8h, v0.h[7]
+ smull v16.4s, v19.4h, v30.4h
+ smull2 v17.4s, v19.8h, v30.8h
+ smull v18.4s, v20.4h, v30.4h
+ smull2 v19.4s, v20.8h, v30.8h
+ sqrshl v16.4s, v16.4s, v31.4s
+ sqrshl v17.4s, v17.4s, v31.4s
+ sqrshl v18.4s, v18.4s, v31.4s
+ sqrshl v19.4s, v19.4s, v31.4s
+ sqadd v16.4s, v16.4s, v29.4s
+ sqadd v17.4s, v17.4s, v29.4s
+ sqadd v18.4s, v18.4s, v29.4s
+ sqadd v19.4s, v19.4s, v29.4s
+ sqxtn v16.4h, v16.4s
+ sqxtn2 v16.8h, v17.4s
+ sqxtn v17.4h, v18.4s
+ sqxtn2 v17.8h, v19.4s
+ sqxtun v16.8b, v16.8h
+ sqxtun v17.8b, v17.8h
+ st1 {v16.8b, v17.8b}, [x0], x1
+ b.hi 1b
+ ret
+endfunc
+
+function ff_hevc_put_hevc_qpel_uni_w_h24_8_neon, export=1
+ QPEL_UNI_W_H_HEADER 8h
+ sxtl v0.8h, v28.8b
+1:
+ ld1 {v1.8b, v2.8b, v3.8b, v4.8b}, [x2], x3
+ subs w4, w4, #1
+ uxtl v1.8h, v1.8b
+ uxtl v2.8h, v2.8b
+ uxtl v3.8h, v3.8b
+ uxtl v4.8h, v4.8b
+ ext v5.16b, v1.16b, v2.16b, #2
+ ext v6.16b, v1.16b, v2.16b, #4
+ ext v7.16b, v1.16b, v2.16b, #6
+ ext v16.16b, v1.16b, v2.16b, #8
+ ext v17.16b, v1.16b, v2.16b, #10
+ ext v18.16b, v1.16b, v2.16b, #12
+ ext v19.16b, v1.16b, v2.16b, #14
+ mul v20.8h, v1.8h, v0.h[0]
+ mla v20.8h, v5.8h, v0.h[1]
+ mla v20.8h, v6.8h, v0.h[2]
+ mla v20.8h, v7.8h, v0.h[3]
+ mla v20.8h, v16.8h, v0.h[4]
+ mla v20.8h, v17.8h, v0.h[5]
+ mla v20.8h, v18.8h, v0.h[6]
+ mla v20.8h, v19.8h, v0.h[7]
+ ext v5.16b, v2.16b, v3.16b, #2
+ ext v6.16b, v2.16b, v3.16b, #4
+ ext v7.16b, v2.16b, v3.16b, #6
+ ext v16.16b, v2.16b, v3.16b, #8
+ ext v17.16b, v2.16b, v3.16b, #10
+ ext v18.16b, v2.16b, v3.16b, #12
+ ext v19.16b, v2.16b, v3.16b, #14
+ mul v21.8h, v2.8h, v0.h[0]
+ mla v21.8h, v5.8h, v0.h[1]
+ mla v21.8h, v6.8h, v0.h[2]
+ mla v21.8h, v7.8h, v0.h[3]
+ mla v21.8h, v16.8h, v0.h[4]
+ mla v21.8h, v17.8h, v0.h[5]
+ mla v21.8h, v18.8h, v0.h[6]
+ mla v21.8h, v19.8h, v0.h[7]
+ ext v5.16b, v3.16b, v4.16b, #2
+ ext v6.16b, v3.16b, v4.16b, #4
+ ext v7.16b, v3.16b, v4.16b, #6
+ ext v16.16b, v3.16b, v4.16b, #8
+ ext v17.16b, v3.16b, v4.16b, #10
+ ext v18.16b, v3.16b, v4.16b, #12
+ ext v19.16b, v3.16b, v4.16b, #14
+ mul v22.8h, v3.8h, v0.h[0]
+ mla v22.8h, v5.8h, v0.h[1]
+ mla v22.8h, v6.8h, v0.h[2]
+ mla v22.8h, v7.8h, v0.h[3]
+ mla v22.8h, v16.8h, v0.h[4]
+ mla v22.8h, v17.8h, v0.h[5]
+ mla v22.8h, v18.8h, v0.h[6]
+ mla v22.8h, v19.8h, v0.h[7]
+ smull v16.4s, v20.4h, v30.4h
+ smull2 v17.4s, v20.8h, v30.8h
+ smull v18.4s, v21.4h, v30.4h
+ smull2 v19.4s, v21.8h, v30.8h
+ smull v20.4s, v22.4h, v30.4h
+ smull2 v21.4s, v22.8h, v30.8h
+ sqrshl v16.4s, v16.4s, v31.4s
+ sqrshl v17.4s, v17.4s, v31.4s
+ sqrshl v18.4s, v18.4s, v31.4s
+ sqrshl v19.4s, v19.4s, v31.4s
+ sqrshl v20.4s, v20.4s, v31.4s
+ sqrshl v21.4s, v21.4s, v31.4s
+ sqadd v16.4s, v16.4s, v29.4s
+ sqadd v17.4s, v17.4s, v29.4s
+ sqadd v18.4s, v18.4s, v29.4s
+ sqadd v19.4s, v19.4s, v29.4s
+ sqadd v20.4s, v20.4s, v29.4s
+ sqadd v21.4s, v21.4s, v29.4s
+ sqxtn v16.4h, v16.4s
+ sqxtn2 v16.8h, v17.4s
+ sqxtn v17.4h, v18.4s
+ sqxtn2 v17.8h, v19.4s
+ sqxtn v18.4h, v20.4s
+ sqxtn2 v18.8h, v21.4s
+ sqxtun v16.8b, v16.8h
+ sqxtun v17.8b, v17.8h
+ sqxtun v18.8b, v18.8h
+ st1 {v16.8b, v17.8b, v18.8b}, [x0], x1
+ b.hi 1b
+ ret
+endfunc
+
+function ff_hevc_put_hevc_qpel_uni_w_h32_8_neon, export=1
+ QPEL_UNI_W_H_HEADER 8h
+ ldr w10, [sp, #16] // width
+ ld1 {v1.8b}, [x2], #8
+ sub x3, x3, w10, uxtw // decrement src stride
+ mov w11, w10 // original width
+ sub x3, x3, #8 // decrement src stride
+ sub x1, x1, w10, uxtw // decrement dst stride
+ sxtl v0.8h, v28.8b
+ uxtl v1.8h, v1.8b
+1:
+ ld1 {v2.8b, v3.8b}, [x2], #16
+ subs w10, w10, #16 // width
+ uxtl v2.8h, v2.8b
+ uxtl v3.8h, v3.8b
+ ext v4.16b, v1.16b, v2.16b, #2
+ ext v5.16b, v1.16b, v2.16b, #4
+ ext v6.16b, v1.16b, v2.16b, #6
+ ext v7.16b, v1.16b, v2.16b, #8
+ ext v16.16b, v1.16b, v2.16b, #10
+ ext v17.16b, v1.16b, v2.16b, #12
+ ext v18.16b, v1.16b, v2.16b, #14
+ mul v19.8h, v1.8h, v0.h[0]
+ mla v19.8h, v4.8h, v0.h[1]
+ mla v19.8h, v5.8h, v0.h[2]
+ mla v19.8h, v6.8h, v0.h[3]
+ mla v19.8h, v7.8h, v0.h[4]
+ mla v19.8h, v16.8h, v0.h[5]
+ mla v19.8h, v17.8h, v0.h[6]
+ mla v19.8h, v18.8h, v0.h[7]
+ ext v4.16b, v2.16b, v3.16b, #2
+ ext v5.16b, v2.16b, v3.16b, #4
+ ext v6.16b, v2.16b, v3.16b, #6
+ ext v7.16b, v2.16b, v3.16b, #8
+ ext v16.16b, v2.16b, v3.16b, #10
+ ext v17.16b, v2.16b, v3.16b, #12
+ ext v18.16b, v2.16b, v3.16b, #14
+ mul v20.8h, v2.8h, v0.h[0]
+ mla v20.8h, v4.8h, v0.h[1]
+ mla v20.8h, v5.8h, v0.h[2]
+ mla v20.8h, v6.8h, v0.h[3]
+ mla v20.8h, v7.8h, v0.h[4]
+ mla v20.8h, v16.8h, v0.h[5]
+ mla v20.8h, v17.8h, v0.h[6]
+ mla v20.8h, v18.8h, v0.h[7]
+ smull v16.4s, v19.4h, v30.4h
+ smull2 v17.4s, v19.8h, v30.8h
+ smull v18.4s, v20.4h, v30.4h
+ smull2 v19.4s, v20.8h, v30.8h
+ sqrshl v16.4s, v16.4s, v31.4s
+ sqrshl v17.4s, v17.4s, v31.4s
+ sqrshl v18.4s, v18.4s, v31.4s
+ sqrshl v19.4s, v19.4s, v31.4s
+ sqadd v16.4s, v16.4s, v29.4s
+ sqadd v17.4s, v17.4s, v29.4s
+ sqadd v18.4s, v18.4s, v29.4s
+ sqadd v19.4s, v19.4s, v29.4s
+ sqxtn v16.4h, v16.4s
+ sqxtn2 v16.8h, v17.4s
+ sqxtn v17.4h, v18.4s
+ sqxtn2 v17.8h, v19.4s
+ sqxtun v16.8b, v16.8h
+ sqxtun v17.8b, v17.8h
+ st1 {v16.8b, v17.8b}, [x0], #16
+ mov v1.16b, v3.16b
+ b.gt 1b
+ subs w4, w4, #1 // height
+ add x2, x2, x3
+ b.le 9f
+ ld1 {v1.8b}, [x2], #8
+ mov w10, w11
+ add x0, x0, x1
+ uxtl v1.8h, v1.8b
+ b 1b
+9:
+ ret
+endfunc
+
+#if HAVE_I8MM
+ENABLE_I8MM
function ff_hevc_put_hevc_qpel_uni_w_h4_8_neon_i8mm, export=1
QPEL_UNI_W_H_HEADER
1:
--
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 ` Martin Storsjö [this message]
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=20240325150243.59058-15-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