Lines Matching refs:v16
69 ld1 {v16.8B}, [x0], #8 // srcp[filterPos[2] + {0..7}]
73 uxtl v16.8H, v16.8B // unpack part 3 to 16-bit
74 smlal v2.4S, v16.4H, v17.4H // v2 accumulates srcp[filterPos[2] + {0..3}] * filter[{0..3}]
75 smlal2 v2.4S, v16.8H, v17.8H // v2 accumulates srcp[filterPos[2] + {4..7}] * filter[{4..7}]
107 // v16-v19 src values (8 bit) 8B
141 ld4 {v16.8B, v17.8B, v18.8B, v19.8B}, [sp] // transpose 8 bytes each from src into 4 registers
157 uxtl v16.8H, v16.8B // unsigned extend long, covert src data to 16-bit
166 smlal v0.4S, v1.4H, v16.4H // multiply accumulate inner loop j = 0, idx = 0..3
175 smlal2 v5.4S, v1.8H, v16.8H // multiply accumulate inner loop j = 0, idx = 4..7
192 ld4 {v16.8B, v17.8B, v18.8B, v19.8B}, [sp]
198 uxtl v16.8H, v16.8B // unsigned extend long, covert src data to 16-bit
203 smlal v0.4S, v1.4H, v16.4H // multiply accumulate inner loop j = 0, idx = 0..3
208 smlal2 v5.4S, v1.8H, v16.8H // multiply accumulate inner loop j = 0, idx = 4..7