Since there is no 8x16, I changed m8 to m4, and updated it in the reply
flow gg <hlefthl...@gmail.com> 于2024年4月30日周二 08:26写道：
> Hi, I initially used a loop, but according to libavcodec/blockdsp.h,
>
> the maximum is 8x16 = 128 bytes, so using ff_get_rv_vlenb() >= 16 and m8
> does not require a loop.
>
> ```
> /* add and put pixel (decoding)
> * Block sizes for op_pixels_func are 8x4,8x8 16x8 16x16.
> * h for op_pixels_func is limited to { width / 2, width },
> * but never larger than 16 and never smaller than 4. */
> typedef void (*op_fill_func)(uint8_t *block /* align width (8 or 16) */,
> uint8_t value, ptrdiff_t line_size, int h);
> ```
>
> Rémi Denis-Courmont <r...@remlab.net> 于2024年4月30日周二 01:31写道：
>
>> Le maanantaina 29. huhtikuuta 2024, 10.09.41 EEST flow gg a écrit :
>> >
>>
>> Are you sure that this works with all vector lengths?
>> The block8 code looks odd.
>>
>> --
>> レミ・デニ-クールモン
>> http://www.remlab.net/
>> _______________________________________________
>> ffmpeg-devel mailing list
>> ffmpeg-devel@ffmpeg.org
>> https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
>>
>> To unsubscribe, visit link above, or email
>> ffmpeg-devel-requ...@ffmpeg.org with subject "unsubscribe".
>>
>
From 38068cd4c770b24ac494bddab6c3d19149d2f5cb Mon Sep 17 00:00:00 2001
From: sunyuechi <sunyue...@iscas.ac.cn>
Date: Wed, 6 Mar 2024 12:46:03 +0800
Subject: [PATCH 2/2] lavc/blockdsp: R-V V fill_block
C908:
blockdsp.fill_block_tab[0]_c: 549.7
blockdsp.fill_block_tab[0]_rvv_i64: 48.2
blockdsp.fill_block_tab[1]_c: 77.0
blockdsp.fill_block_tab[1]_rvv_i64: 19.7
---
libavcodec/riscv/blockdsp_init.c | 6 ++++++
libavcodec/riscv/blockdsp_rvv.S | 21 +++++++++++++++++++++
2 files changed, 27 insertions(+)
diff --git a/libavcodec/riscv/blockdsp_init.c b/libavcodec/riscv/blockdsp_init.c
index 59b2f9d47b..42c8e87fa7 100644
--- a/libavcodec/riscv/blockdsp_init.c
+++ b/libavcodec/riscv/blockdsp_init.c
@@ -27,6 +27,10 @@
void ff_clear_block_rvv(int16_t *block);
void ff_clear_blocks_rvv(int16_t *block);
+void ff_fill_block16_rvv(uint8_t *block, uint8_t value, ptrdiff_t line_size,
+ int h);
+void ff_fill_block8_rvv(uint8_t *block, uint8_t value, ptrdiff_t line_size,
+ int h);
av_cold void ff_blockdsp_init_riscv(BlockDSPContext *c)
{
@@ -36,6 +40,8 @@ av_cold void ff_blockdsp_init_riscv(BlockDSPContext *c)
if (flags & AV_CPU_FLAG_RVV_I64 && ff_get_rv_vlenb() >= 16) {
c->clear_block = ff_clear_block_rvv;
c->clear_blocks = ff_clear_blocks_rvv;
+ c->fill_block_tab[0] = ff_fill_block16_rvv;
+ c->fill_block_tab[1] = ff_fill_block8_rvv;
}
#endif
}
diff --git a/libavcodec/riscv/blockdsp_rvv.S b/libavcodec/riscv/blockdsp_rvv.S
index 8bb00bb467..18ab17da00 100644
--- a/libavcodec/riscv/blockdsp_rvv.S
+++ b/libavcodec/riscv/blockdsp_rvv.S
@@ -40,3 +40,24 @@ func ff_clear_blocks_rvv, zve64x
ret
endfunc
+
+func ff_fill_block16_rvv, zve32x
+ vsetivli t0, 16, e8, m1, ta, ma
+ vmv.v.x v8, a1
+1:
+ addi a3, a3, -1
+ vse8.v v8, (a0)
+ add a0, a0, a2
+ bnez a3, 1b
+
+ ret
+endfunc
+
+func ff_fill_block8_rvv, zve64x
+ vsetvli t0, zero, e8, m4, ta, ma
+ vmv.v.x v8, a1
+ vsetvli t0, a3, e64, m4, ta, ma
+ vsse64.v v8, (a0), a2
+
+ ret
+endfunc
--
2.44.0
_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
To unsubscribe, visit link above, or email
ffmpeg-devel-requ...@ffmpeg.org with subject "unsubscribe".
