[FFmpeg-devel] [PATCH 16/21] aarch64: hevc: Deduplicate the hevc_put_hevc_qpel_uni_w_hv*_8_end_neon functions
Martin Storsjö
martin at martin.st
Mon Mar 25 17:02:38 EET 2024
The hv32 and hv64 functions were identical - both loop and
process 16 pixels at a time.
The hv16 function was near identical, except for the outer loop
(and using sp instead of a separate register).
Given the size of these functions, the extra cost of the outer
loop is negligible, so use the same function for hv16 as well.
This removes over 200 lines of duplicated assembly, and over 4 KB
of binary size.
---
libavcodec/aarch64/hevcdsp_qpel_neon.S | 220 +------------------------
1 file changed, 3 insertions(+), 217 deletions(-)
diff --git a/libavcodec/aarch64/hevcdsp_qpel_neon.S b/libavcodec/aarch64/hevcdsp_qpel_neon.S
index c04e8dbea8..06832603d9 100644
--- a/libavcodec/aarch64/hevcdsp_qpel_neon.S
+++ b/libavcodec/aarch64/hevcdsp_qpel_neon.S
@@ -4381,231 +4381,17 @@ function ff_hevc_put_hevc_qpel_uni_w_hv16_8_neon_i8mm, export=1
b hevc_put_hevc_qpel_uni_w_hv16_8_end_neon
endfunc
-function hevc_put_hevc_qpel_uni_w_hv16_8_end_neon
- ldp q16, q1, [sp]
- add sp, sp, x10
- ldp q17, q2, [sp]
- add sp, sp, x10
- ldp q18, q3, [sp]
- add sp, sp, x10
- ldp q19, q4, [sp]
- add sp, sp, x10
- ldp q20, q5, [sp]
- add sp, sp, x10
- ldp q21, q6, [sp]
- add sp, sp, x10
- ldp q22, q7, [sp]
- add sp, sp, x10
-1:
- ldp q23, q31, [sp]
- add sp, sp, x10
- QPEL_FILTER_H v24, v16, v17, v18, v19, v20, v21, v22, v23
- QPEL_FILTER_H2 v25, v16, v17, v18, v19, v20, v21, v22, v23
- QPEL_FILTER_H v26, v1, v2, v3, v4, v5, v6, v7, v31
- QPEL_FILTER_H2 v27, v1, v2, v3, v4, v5, v6, v7, v31
- QPEL_UNI_W_HV_16
- subs w22, w22, #1
- b.eq 2f
-
- ldp q16, q1, [sp]
- add sp, sp, x10
- QPEL_FILTER_H v24, v17, v18, v19, v20, v21, v22, v23, v16
- QPEL_FILTER_H2 v25, v17, v18, v19, v20, v21, v22, v23, v16
- QPEL_FILTER_H v26, v2, v3, v4, v5, v6, v7, v31, v1
- QPEL_FILTER_H2 v27, v2, v3, v4, v5, v6, v7, v31, v1
- QPEL_UNI_W_HV_16
- subs w22, w22, #1
- b.eq 2f
-
- ldp q17, q2, [sp]
- add sp, sp, x10
- QPEL_FILTER_H v24, v18, v19, v20, v21, v22, v23, v16, v17
- QPEL_FILTER_H2 v25, v18, v19, v20, v21, v22, v23, v16, v17
- QPEL_FILTER_H v26, v3, v4, v5, v6, v7, v31, v1, v2
- QPEL_FILTER_H2 v27, v3, v4, v5, v6, v7, v31, v1, v2
- QPEL_UNI_W_HV_16
- subs w22, w22, #1
- b.eq 2f
-
- ldp q18, q3, [sp]
- add sp, sp, x10
- QPEL_FILTER_H v24, v19, v20, v21, v22, v23, v16, v17, v18
- QPEL_FILTER_H2 v25, v19, v20, v21, v22, v23, v16, v17, v18
- QPEL_FILTER_H v26, v4, v5, v6, v7, v31, v1, v2, v3
- QPEL_FILTER_H2 v27, v4, v5, v6, v7, v31, v1, v2, v3
- QPEL_UNI_W_HV_16
- subs w22, w22, #1
- b.eq 2f
-
- ldp q19, q4, [sp]
- add sp, sp, x10
- QPEL_FILTER_H v24, v20, v21, v22, v23, v16, v17, v18, v19
- QPEL_FILTER_H2 v25, v20, v21, v22, v23, v16, v17, v18, v19
- QPEL_FILTER_H v26, v5, v6, v7, v31, v1, v2, v3, v4
- QPEL_FILTER_H2 v27, v5, v6, v7, v31, v1, v2, v3, v4
- QPEL_UNI_W_HV_16
- subs w22, w22, #1
- b.eq 2f
-
- ldp q20, q5, [sp]
- add sp, sp, x10
- QPEL_FILTER_H v24, v21, v22, v23, v16, v17, v18, v19, v20
- QPEL_FILTER_H2 v25, v21, v22, v23, v16, v17, v18, v19, v20
- QPEL_FILTER_H v26, v6, v7, v31, v1, v2, v3, v4, v5
- QPEL_FILTER_H2 v27, v6, v7, v31, v1, v2, v3, v4, v5
- QPEL_UNI_W_HV_16
- subs w22, w22, #1
- b.eq 2f
-
- ldp q21, q6, [sp]
- add sp, sp, x10
- QPEL_FILTER_H v24, v22, v23, v16, v17, v18, v19, v20, v21
- QPEL_FILTER_H2 v25, v22, v23, v16, v17, v18, v19, v20, v21
- QPEL_FILTER_H v26, v7, v31, v1, v2, v3, v4, v5, v6
- QPEL_FILTER_H2 v27, v7, v31, v1, v2, v3, v4, v5, v6
- QPEL_UNI_W_HV_16
- subs w22, w22, #1
- b.eq 2f
-
- ldp q22, q7, [sp]
- add sp, sp, x10
- QPEL_FILTER_H v24, v23, v16, v17, v18, v19, v20, v21, v22
- QPEL_FILTER_H2 v25, v23, v16, v17, v18, v19, v20, v21, v22
- QPEL_FILTER_H v26, v31, v1, v2, v3, v4, v5, v6, v7
- QPEL_FILTER_H2 v27, v31, v1, v2, v3, v4, v5, v6, v7
- QPEL_UNI_W_HV_16
- subs w22, w22, #1
- b.hi 1b
-
-2:
- QPEL_UNI_W_HV_END
- ret
-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_hv32_8_end_neon
-endfunc
-
-function hevc_put_hevc_qpel_uni_w_hv32_8_end_neon
- mov x11, sp
- mov w12, w22
- mov x13, x20
- mov x14, sp
-3:
- ldp q16, q1, [x11]
- add x11, x11, x10
- ldp q17, q2, [x11]
- add x11, x11, x10
- ldp q18, q3, [x11]
- add x11, x11, x10
- ldp q19, q4, [x11]
- add x11, x11, x10
- ldp q20, q5, [x11]
- add x11, x11, x10
- ldp q21, q6, [x11]
- add x11, x11, x10
- ldp q22, q7, [x11]
- add x11, x11, x10
-1:
- ldp q23, q31, [x11]
- add x11, x11, x10
- QPEL_FILTER_H v24, v16, v17, v18, v19, v20, v21, v22, v23
- QPEL_FILTER_H2 v25, v16, v17, v18, v19, v20, v21, v22, v23
- QPEL_FILTER_H v26, v1, v2, v3, v4, v5, v6, v7, v31
- QPEL_FILTER_H2 v27, v1, v2, v3, v4, v5, v6, v7, v31
- QPEL_UNI_W_HV_16
- subs w22, w22, #1
- b.eq 2f
-
- ldp q16, q1, [x11]
- add x11, x11, x10
- QPEL_FILTER_H v24, v17, v18, v19, v20, v21, v22, v23, v16
- QPEL_FILTER_H2 v25, v17, v18, v19, v20, v21, v22, v23, v16
- QPEL_FILTER_H v26, v2, v3, v4, v5, v6, v7, v31, v1
- QPEL_FILTER_H2 v27, v2, v3, v4, v5, v6, v7, v31, v1
- QPEL_UNI_W_HV_16
- subs w22, w22, #1
- b.eq 2f
-
- ldp q17, q2, [x11]
- add x11, x11, x10
- QPEL_FILTER_H v24, v18, v19, v20, v21, v22, v23, v16, v17
- QPEL_FILTER_H2 v25, v18, v19, v20, v21, v22, v23, v16, v17
- QPEL_FILTER_H v26, v3, v4, v5, v6, v7, v31, v1, v2
- QPEL_FILTER_H2 v27, v3, v4, v5, v6, v7, v31, v1, v2
- QPEL_UNI_W_HV_16
- subs w22, w22, #1
- b.eq 2f
-
- ldp q18, q3, [x11]
- add x11, x11, x10
- QPEL_FILTER_H v24, v19, v20, v21, v22, v23, v16, v17, v18
- QPEL_FILTER_H2 v25, v19, v20, v21, v22, v23, v16, v17, v18
- QPEL_FILTER_H v26, v4, v5, v6, v7, v31, v1, v2, v3
- QPEL_FILTER_H2 v27, v4, v5, v6, v7, v31, v1, v2, v3
- QPEL_UNI_W_HV_16
- subs w22, w22, #1
- b.eq 2f
-
- ldp q19, q4, [x11]
- add x11, x11, x10
- QPEL_FILTER_H v24, v20, v21, v22, v23, v16, v17, v18, v19
- QPEL_FILTER_H2 v25, v20, v21, v22, v23, v16, v17, v18, v19
- QPEL_FILTER_H v26, v5, v6, v7, v31, v1, v2, v3, v4
- QPEL_FILTER_H2 v27, v5, v6, v7, v31, v1, v2, v3, v4
- QPEL_UNI_W_HV_16
- subs w22, w22, #1
- b.eq 2f
-
- ldp q20, q5, [x11]
- add x11, x11, x10
- QPEL_FILTER_H v24, v21, v22, v23, v16, v17, v18, v19, v20
- QPEL_FILTER_H2 v25, v21, v22, v23, v16, v17, v18, v19, v20
- QPEL_FILTER_H v26, v6, v7, v31, v1, v2, v3, v4, v5
- QPEL_FILTER_H2 v27, v6, v7, v31, v1, v2, v3, v4, v5
- QPEL_UNI_W_HV_16
- subs w22, w22, #1
- b.eq 2f
-
- ldp q21, q6, [x11]
- add x11, x11, x10
- QPEL_FILTER_H v24, v22, v23, v16, v17, v18, v19, v20, v21
- QPEL_FILTER_H2 v25, v22, v23, v16, v17, v18, v19, v20, v21
- QPEL_FILTER_H v26, v7, v31, v1, v2, v3, v4, v5, v6
- QPEL_FILTER_H2 v27, v7, v31, v1, v2, v3, v4, v5, v6
- QPEL_UNI_W_HV_16
- subs w22, w22, #1
- b.eq 2f
-
- ldp q22, q7, [x11]
- add x11, x11, x10
- QPEL_FILTER_H v24, v23, v16, v17, v18, v19, v20, v21, v22
- QPEL_FILTER_H2 v25, v23, v16, v17, v18, v19, v20, v21, v22
- QPEL_FILTER_H v26, v31, v1, v2, v3, v4, v5, v6, v7
- QPEL_FILTER_H2 v27, v31, v1, v2, v3, v4, v5, v6, v7
- QPEL_UNI_W_HV_16
- subs w22, w22, #1
- b.hi 1b
-2:
- subs w27, w27, #16
- add x11, x14, #32
- add x20, x13, #16
- mov w22, w12
- mov x14, x11
- mov x13, x20
- b.hi 3b
- QPEL_UNI_W_HV_END
- ret
+ 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_hv64_8_end_neon
+ b hevc_put_hevc_qpel_uni_w_hv16_8_end_neon
endfunc
-function hevc_put_hevc_qpel_uni_w_hv64_8_end_neon
+function hevc_put_hevc_qpel_uni_w_hv16_8_end_neon
mov x11, sp
mov w12, w22
mov x13, x20
--
2.39.3 (Apple Git-146)
More information about the ffmpeg-devel
mailing list