History

lavc/idctdsp: improve R-V V add_pixels_clamped

Rémi Denis-Courmont committed 3 years ago

Commit d48810f1 parent 600c6f11 file · +14 −14Browse files

Showing the changes to libavcodec (1 of 1 file). Show all

Unified · Split

libavcodec/riscv/idctdsp_rvv.S+14−14
@@ -23,7 +23,6 @@ · 22 unmodified lines
23func ff_put_pixels_clamped_rvv, zve32x23func ff_put_pixels_clamped_rvv, zve32x
24 vsetivli zero, 8, e16, m1, ta, ma24 vsetivli zero, 8, e16, m1, ta, ma
25 vlseg8e16.v v24, (a0)25 vlseg8e16.v v24, (a0)
261:
27 /* RVV only has signed-signed and unsigned-unsigned clipping.26 /* RVV only has signed-signed and unsigned-unsigned clipping.
28 * We need two steps for signed-to-unsigned clipping. */27 * We need two steps for signed-to-unsigned clipping. */
29 vsetvli t0, zero, e16, m8, ta, ma28 vsetvli t0, zero, e16, m8, ta, ma
@@ -54,17 +53,18 @@ func ff_put_signed_pixels_clamped_rvv, zve64x · 24 unmodified lines
54 ret53 ret
55endfunc54endfunc
56 55
57func ff_add_pixels_clamped_rvv, zve32x56func ff_add_pixels_clamped_rvv, zve64x
58 vsetivli zero, 8, e8, mf2, ta, ma57 vsetivli zero, 8, e8, mf2, ta, ma
59 vlseg8e16.v v24, (a0)58 li t0, 8 * 8
60 vlsseg8e8.v v16, (a1), a259 vlse64.v v16, (a1), a2
61 vwaddu.wv v24, v24, v1660 vsetvli zero, t0, e8, m4, ta, ma
62 vwaddu.wv v25, v25, v1761 vle16.v v24, (a0)
63 vwaddu.wv v26, v26, v1862 vwaddu.wv v24, v24, v16
64 vwaddu.wv v27, v27, v1963 vsetvli zero, zero, e16, m8, ta, ma
65 vwaddu.wv v28, v28, v2064 vmax.vx v24, v24, zero
66 vwaddu.wv v29, v29, v2165 vsetvli zero, zero, e8, m4, ta, ma
67 vwaddu.wv v30, v30, v2266 vnclipu.wi v16, v24, 0
68 vwaddu.wv v31, v31, v2367 vsetivli zero, 8, e8, mf2, ta, ma
69 j 1b68 vsse64.v v16, (a1), a2
69 ret
70endfunc70endfunc

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