diff --git a/libavcodec/riscv/vc1dsp_rvv.S b/libavcodec/riscv/vc1dsp_rvv.S index 548ef9d3bf..f9b59688ae 100644 --- a/libavcodec/riscv/vc1dsp_rvv.S +++ b/libavcodec/riscv/vc1dsp_rvv.S @@ -38,18 +38,20 @@ func ff_vc1_inv_trans_\cols\()x\rows\()_dc_rvv, zve64x, zba .endif addi t2, t2, 64 srai t2, t2, 7 -.if \rows * \cols == 64 - vsetvli zero, t0, e16, m8, ta, ma -.elseif \rows * \cols == 32 - vsetvli zero, t0, e16, m4, ta, ma +.if \rows * \cols >= 32 + vsetvli zero, t0, e8, m\mat_lmul, ta, ma .else - vsetivli zero, \rows * \cols, e16, m2, ta, ma + vsetivli zero, \rows * \cols, e8, m\mat_lmul, ta, ma .endif - vzext.vf2 v8, v0 - vadd.vx v8, v8, t2 - vmax.vx v8, v8, zero - vsetvli zero, zero, e8, m\mat_lmul, ta, ma - vnclipu.wi v0, v8, 0 + bgez t2, 1f + + neg t2, t2 + vssubu.vx v0, v0, t2 + vsetivli zero, \rows, e8, m\row_lmul, ta, ma + vsse\w\().v v0, (a0), a1 + ret +1: + vsaddu.vx v0, v0, t2 vsetivli zero, \rows, e8, m\row_lmul, ta, ma vsse\w\().v v0, (a0), a1 ret