[FFmpeg-devel] [PATCH 2/2] lavc/rv40dsp: fix RISC-V chroma_mc
uk7b at foxmail.com
uk7b at foxmail.com
Thu Dec 5 06:29:01 EET 2024
From: sunyuechi <sunyuechi at iscas.ac.cn>
---
libavcodec/riscv/rv40dsp_rvv.S | 116 ++++++++++++++++++++++-----------
1 file changed, 78 insertions(+), 38 deletions(-)
diff --git a/libavcodec/riscv/rv40dsp_rvv.S b/libavcodec/riscv/rv40dsp_rvv.S
index ca431eb8ab..d4beb7f1e9 100644
--- a/libavcodec/riscv/rv40dsp_rvv.S
+++ b/libavcodec/riscv/rv40dsp_rvv.S
@@ -20,15 +20,30 @@
#include "libavutil/riscv/asm.S"
-.macro manual_avg dst src1 src2
- vadd.vv \dst, \src1, \src2
- vadd.vi \dst, \dst, 1
- vsrl.vi \dst, \dst, 1
-.endm
+const rv40_bias
+ .byte 0, 16, 32, 16
+ .byte 32, 28, 32, 28
+ .byte 0, 32, 16, 32
+ .byte 32, 28, 32, 28
+endconst
.macro do_chroma_mc type unroll
- csrwi vxrm, 2
+ csrwi vxrm, 0
+ addi sp, sp, -16
+#if __riscv_xlen == 32
+ sw s2, (sp)
+#elif __riscv_xlen == 64
+ sd s2, (sp)
+#else
+ sq s2, (sp)
+#endif
+ lla t4, rv40_bias
+ srli t5, a5, 1
+ sh2add t4, t5, t4
+ srli t5, a4, 1
+ add t5, t4, t5
slli t2, a5, 3
+ lb s2, (t5)
mul t1, a5, a4
sh3add a5, a4, t2
slli a4, a4, 3
@@ -80,17 +95,19 @@
vwmulu.vx v12, v14, a6
vwmaccu.vx v10, t1, v15
vwmaccu.vx v12, a7, v15
- vnclipu.wi v15, v8, 6
+ vwaddu.wx v20, v8, s2
+ vnsrl.wi v15, v20, 6
.ifc \type,avg
vle8.v v9, (a0)
- manual_avg v15, v15, v9
+ vaaddu.vv v15, v15, v9
.endif
vse8.v v15, (a0)
add a0, a0, a2
- vnclipu.wi v8, v10, 6
+ vwaddu.wx v20, v10, s2
+ vnsrl.wi v8, v20, 6
.ifc \type,avg
vle8.v v9, (a0)
- manual_avg v8, v8, v9
+ vaaddu.vv v8, v8, v9
.endif
add t4, t4, t3
vse8.v v8, (a0)
@@ -115,17 +132,19 @@
vslide1down.vx v14, v14, t5
vsetvli zero, t6, e8, m1, ta, ma
vwmaccu.vx v16, t1, v14
- vnclipu.wi v8, v12, 6
+ vwaddu.wx v20, v12, s2
+ vnsrl.wi v8, v20, 6
.ifc \type,avg
vle8.v v9, (a0)
- manual_avg v8, v8, v9
+ vaaddu.vv v8, v8, v9
.endif
vse8.v v8, (a0)
add a0, a0, a2
- vnclipu.wi v8, v16, 6
+ vwaddu.wx v20, v16, s2
+ vnsrl.wi v8, v20, 6
.ifc \type,avg
vle8.v v9, (a0)
- manual_avg v8, v8, v9
+ vaaddu.vv v8, v8, v9
.endif
vse8.v v8, (a0)
add a0, a0, a2
@@ -159,18 +178,20 @@
vwmaccu.vx v10, t0, v8
add a4, a4, a7
vwmaccu.vx v12, t0, v9
- vnclipu.wi v15, v10, 6
+ vwaddu.wx v20, v10, s2
+ vnsrl.wi v15, v20, 6
vwmulu.vx v10, v9, a6
- vnclipu.wi v9, v12, 6
+ vwaddu.wx v20, v12, s2
+ vnsrl.wi v9, v20, 6
.ifc \type,avg
vle8.v v16, (a0)
- manual_avg v15, v15, v16
+ vaaddu.vv v15, v15, v16
.endif
vse8.v v15, (a0)
add a0, a0, a2
.ifc \type,avg
vle8.v v16, (a0)
- manual_avg v9, v9, v16
+ vaaddu.vv v9, v9, v16
.endif
vse8.v v9, (a0)
add a0, a0, a2
@@ -179,18 +200,20 @@
vle8.v v14, (a5)
vwmaccu.vx v10, t0, v8
vwmulu.vx v12, v8, a6
- vnclipu.wi v8, v10, 6
+ vwaddu.wx v20, v10, s2
+ vnsrl.wi v8, v20, 6
vwmaccu.vx v12, t0, v14
.ifc \type,avg
vle8.v v16, (a0)
- manual_avg v8, v8, v16
+ vaaddu.vv v8, v8, v16
.endif
vse8.v v8, (a0)
add a0, a0, a2
- vnclipu.wi v8, v12, 6
+ vwaddu.wx v20, v12, s2
+ vnsrl.wi v8, v20, 6
.ifc \type,avg
vle8.v v16, (a0)
- manual_avg v8, v8, v16
+ vaaddu.vv v8, v8, v16
.endif
vse8.v v8, (a0)
add a0, a0, a2
@@ -226,17 +249,19 @@
vsetvli zero, t6, e8, m1, ta, ma
vwmulu.vx v12, v8, a6
vwmaccu.vx v12, a7, v9
- vnclipu.wi v16, v10, 6
+ vwaddu.wx v20, v10, s2
+ vnsrl.wi v16, v20, 6
.ifc \type,avg
vle8.v v18, (a0)
- manual_avg v16, v16, v18
+ vaaddu.vv v16, v16, v18
.endif
vse8.v v16, (a0)
add a0, a0, a2
- vnclipu.wi v10, v12, 6
+ vwaddu.wx v20, v12, s2
+ vnsrl.wi v10, v20, 6
.ifc \type,avg
vle8.v v18, (a0)
- manual_avg v10, v10, v18
+ vaaddu.vv v10, v10, v18
.endif
add a4, a4, t1
vse8.v v10, (a0)
@@ -254,18 +279,20 @@
vslide1down.vx v9, v8, t5
vsetvli zero, t6, e8, m1, ta, ma
vwmulu.vx v12, v8, a6
- vnclipu.wi v8, v14, 6
+ vwaddu.wx v20, v14, s2
+ vnsrl.wi v8, v20, 6
vwmaccu.vx v12, a7, v9
.ifc \type,avg
vle8.v v18, (a0)
- manual_avg v8, v8, v18
+ vaaddu.vv v8, v8, v18
.endif
vse8.v v8, (a0)
add a0, a0, a2
- vnclipu.wi v8, v12, 6
+ vwaddu.wx v20, v12, s2
+ vnsrl.wi v8, v20, 6
.ifc \type,avg
vle8.v v18, (a0)
- manual_avg v8, v8, v18
+ vaaddu.vv v8, v8, v18
.endif
vse8.v v8, (a0)
add a0, a0, a2
@@ -293,18 +320,20 @@
vwmulu.vx v10, v8, a6
vle8.v v8, (t0)
add t0, t1, a2
- vnclipu.wi v13, v10, 6
+ vwaddu.wx v20, v10, s2
+ vnsrl.wi v13, v20, 6
vwmulu.vx v10, v8, a6
.ifc \type,avg
vle8.v v18, (a5)
- manual_avg v13, v13, v18
+ vaaddu.vv v13, v13, v18
.endif
vse8.v v13, (a5)
add a5, a5, a2
- vnclipu.wi v8, v10, 6
+ vwaddu.wx v20, v10, s2
+ vnsrl.wi v8, v20, 6
.ifc \type,avg
vle8.v v18, (a5)
- manual_avg v8, v8, v18
+ vaaddu.vv v8, v8, v18
.endif
vse8.v v8, (a5)
add a5, a5, a2
@@ -312,23 +341,34 @@
vle8.v v9, (t1)
vle8.v v12, (t0)
vwmulu.vx v10, v9, a6
- vnclipu.wi v8, v10, 6
+ vwaddu.wx v20, v10, s2
+ vnsrl.wi v8, v20, 6
vwmulu.vx v10, v12, a6
.ifc \type,avg
vle8.v v18, (a5)
- manual_avg v8, v8, v18
+ vaaddu.vv v8, v8, v18
.endif
vse8.v v8, (a5)
add a5, a5, a2
- vnclipu.wi v8, v10, 6
+ vwaddu.wx v20, v10, s2
+ vnsrl.wi v8, v20, 6
.ifc \type,avg
vle8.v v18, (a5)
- manual_avg v8, v8, v18
+ vaaddu.vv v8, v8, v18
.endif
vse8.v v8, (a5)
.endif
blt t2, a3, 7b
8:
+#if __riscv_xlen == 32
+ lw s2, (sp)
+#elif __riscv_xlen == 64
+ ld s2, (sp)
+#else
+ lq s2, (sp)
+#endif
+ addi sp, sp, 16
+
ret
.endm
--
2.47.1
More information about the ffmpeg-devel
mailing list