History

lavc/huffyuvdsp: optimise RVV vtype for add_hfyu_left_pred_bgr32

T-Head C908: add_hfyu_left_pred_bgr32_c: 237.5 add_hfyu_left_pred_bgr32_rvv_i32: 173.5 (before) add_hfyu_left_pred_bgr32_rvv_i32: 110.0 (after)

Rémi Denis-Courmont committed 2 years ago

Commit 463c5731 parent 233066e2 files · +6 −3Browse files

Showing the changes to libavcodec (2 of 2 files). Show all

Unified · Split

2 files
  1. libavcodec/riscv/huffyuvdsp_init.c +2 −1
  2. libavcodec/riscv/huffyuvdsp_rvv.S +4 −2
libavcodec/riscv/huffyuvdsp_init.c+2−1
@@ -35,7 +35,8 @@ av_cold void ff_huffyuvdsp_init_riscv(HuffYUVDSPContext *c, · 34 unmodified lines
3535
3636 if ((flags & AV_CPU_FLAG_RVV_I32) && (flags & AV_CPU_FLAG_RVB_ADDR)) {
3737 c->add_int16 = ff_add_int16_rvv;
38− c->add_hfyu_left_pred_bgr32 = ff_add_hfyu_left_pred_bgr32_rvv;
38+ if (flags & AV_CPU_FLAG_RVB_BASIC)
39+ c->add_hfyu_left_pred_bgr32 = ff_add_hfyu_left_pred_bgr32_rvv;
3940 }
4041 #endif
4142 }
libavcodec/riscv/huffyuvdsp_rvv.S+4−2
@@ -36,8 +36,10 @@ func ff_add_int16_rvv, zve32x · 35 unmodified lines
3636 ret
3737 endfunc
3838
39−func ff_add_hfyu_left_pred_bgr32_rvv, zve32x
40− vsetivli zero, 4, e8, m1, ta, ma
39+func ff_add_hfyu_left_pred_bgr32_rvv, zve32x, zbb
40+ vtype_ivli t1, 4, e8, ta, ma
41+ li t0, 4
42+ vsetvl zero, t0, t1
4143 vle8.v v8, (a3)
4244 sh2add a2, a2, a1
4345 1:

Keyboard shortcuts

General

Show keyboard shortcuts
?
Focus the current search
/

Issues and pull requests

Open filters
f

Issues, pull requests and Inbox

Select next item
j↓
Select previous item
k↑
Open selected item
Enter
Dismiss filters or clear selection
Esc

Repository code

Go to file
t