/external/XNNPACK/src/f32-prelu/gen/ |
D | avx512f-2x32.c | 61 …const __m512 vacc0x0123456789ABCDEF = _mm512_mask_mul_ps(vi0x0123456789ABCDEF, vsign0x0123456789AB… in xnn_f32_prelu_ukernel__avx512f_2x32() 63 …const __m512 vacc0xGHIJKLMNOPQRSTUV = _mm512_mask_mul_ps(vi0xGHIJKLMNOPQRSTUV, vsign0xGHIJKLMNOPQR… in xnn_f32_prelu_ukernel__avx512f_2x32() 65 …const __m512 vacc1x0123456789ABCDEF = _mm512_mask_mul_ps(vi1x0123456789ABCDEF, vsign1x0123456789AB… in xnn_f32_prelu_ukernel__avx512f_2x32() 67 …const __m512 vacc1xGHIJKLMNOPQRSTUV = _mm512_mask_mul_ps(vi1xGHIJKLMNOPQRSTUV, vsign1xGHIJKLMNOPQR… in xnn_f32_prelu_ukernel__avx512f_2x32() 86 const __m512 vacc0 = _mm512_mask_mul_ps(vi0, vsign0, vi0, vw); in xnn_f32_prelu_ukernel__avx512f_2x32() 88 const __m512 vacc1 = _mm512_mask_mul_ps(vi1, vsign1, vi1, vw); in xnn_f32_prelu_ukernel__avx512f_2x32() 109 const __m512 vacc0 = _mm512_mask_mul_ps(vi0, vsign0, vi0, vw); in xnn_f32_prelu_ukernel__avx512f_2x32() 111 const __m512 vacc1 = _mm512_mask_mul_ps(vi1, vsign1, vi1, vw); in xnn_f32_prelu_ukernel__avx512f_2x32()
|
D | avx512f-2x16.c | 58 …const __m512 vacc0x0123456789ABCDEF = _mm512_mask_mul_ps(vi0x0123456789ABCDEF, vsign0x0123456789AB… in xnn_f32_prelu_ukernel__avx512f_2x16() 60 …const __m512 vacc1x0123456789ABCDEF = _mm512_mask_mul_ps(vi1x0123456789ABCDEF, vsign1x0123456789AB… in xnn_f32_prelu_ukernel__avx512f_2x16() 81 const __m512 vacc0 = _mm512_mask_mul_ps(vi0, vsign0, vi0, vw); in xnn_f32_prelu_ukernel__avx512f_2x16() 83 const __m512 vacc1 = _mm512_mask_mul_ps(vi1, vsign1, vi1, vw); in xnn_f32_prelu_ukernel__avx512f_2x16()
|
/external/XNNPACK/src/f32-vlrelu/gen/ |
D | vlrelu-avx512f-x32.c | 39 …vacc0123456789ABCDEF = _mm512_mask_mul_ps(vacc0123456789ABCDEF, vsign0123456789ABCDEF, vacc0123456… in xnn_f32_vlrelu_ukernel__avx512f_x32() 40 …vaccGHIJKLMNOPQRSTUV = _mm512_mask_mul_ps(vaccGHIJKLMNOPQRSTUV, vsignGHIJKLMNOPQRSTUV, vaccGHIJKLM… in xnn_f32_vlrelu_ukernel__avx512f_x32() 50 vacc = _mm512_mask_mul_ps(vacc, vsign, vacc, vslope); in xnn_f32_vlrelu_ukernel__avx512f_x32() 63 vacc = _mm512_mask_mul_ps(vacc, vsign, vacc, vslope); in xnn_f32_vlrelu_ukernel__avx512f_x32()
|
D | vlrelu-avx512f-x16.c | 37 …vacc0123456789ABCDEF = _mm512_mask_mul_ps(vacc0123456789ABCDEF, vsign0123456789ABCDEF, vacc0123456… in xnn_f32_vlrelu_ukernel__avx512f_x16() 51 vacc = _mm512_mask_mul_ps(vacc, vsign, vacc, vslope); in xnn_f32_vlrelu_ukernel__avx512f_x16()
|
/external/XNNPACK/src/f32-velu/gen/ |
D | velu-avx512f-rr1-lut16-p3-perm-x128.c | 176 vy0 = _mm512_mask_mul_ps(vy0, vsign0, vx0, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x128() 177 vy1 = _mm512_mask_mul_ps(vy1, vsign1, vx1, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x128() 178 vy2 = _mm512_mask_mul_ps(vy2, vsign2, vx2, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x128() 179 vy3 = _mm512_mask_mul_ps(vy3, vsign3, vx3, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x128() 180 vy4 = _mm512_mask_mul_ps(vy4, vsign4, vx4, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x128() 181 vy5 = _mm512_mask_mul_ps(vy5, vsign5, vx5, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x128() 182 vy6 = _mm512_mask_mul_ps(vy6, vsign6, vx6, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x128() 183 vy7 = _mm512_mask_mul_ps(vy7, vsign7, vx7, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x128() 218 vy = _mm512_mask_mul_ps(vy, vsign, vx, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x128() 251 vy = _mm512_mask_mul_ps(vy, vsign, vx, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x128()
|
D | velu-avx512f-rr1-lut16-p3-perm-x112.c | 161 vy0 = _mm512_mask_mul_ps(vy0, vsign0, vx0, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x112() 162 vy1 = _mm512_mask_mul_ps(vy1, vsign1, vx1, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x112() 163 vy2 = _mm512_mask_mul_ps(vy2, vsign2, vx2, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x112() 164 vy3 = _mm512_mask_mul_ps(vy3, vsign3, vx3, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x112() 165 vy4 = _mm512_mask_mul_ps(vy4, vsign4, vx4, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x112() 166 vy5 = _mm512_mask_mul_ps(vy5, vsign5, vx5, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x112() 167 vy6 = _mm512_mask_mul_ps(vy6, vsign6, vx6, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x112() 201 vy = _mm512_mask_mul_ps(vy, vsign, vx, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x112() 234 vy = _mm512_mask_mul_ps(vy, vsign, vx, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x112()
|
D | velu-avx512f-rr1-p6-x128.c | 186 vy0 = _mm512_mask_mul_ps(vy0, vsign0, vx0, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x128() 187 vy1 = _mm512_mask_mul_ps(vy1, vsign1, vx1, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x128() 188 vy2 = _mm512_mask_mul_ps(vy2, vsign2, vx2, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x128() 189 vy3 = _mm512_mask_mul_ps(vy3, vsign3, vx3, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x128() 190 vy4 = _mm512_mask_mul_ps(vy4, vsign4, vx4, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x128() 191 vy5 = _mm512_mask_mul_ps(vy5, vsign5, vx5, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x128() 192 vy6 = _mm512_mask_mul_ps(vy6, vsign6, vx6, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x128() 193 vy7 = _mm512_mask_mul_ps(vy7, vsign7, vx7, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x128() 229 vy = _mm512_mask_mul_ps(vy, vsign, vx, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x128() 263 vy = _mm512_mask_mul_ps(vy, vsign, vx, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x128()
|
D | velu-avx512f-rr1-lut16-p3-perm-x80.c | 131 vy0 = _mm512_mask_mul_ps(vy0, vsign0, vx0, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x80() 132 vy1 = _mm512_mask_mul_ps(vy1, vsign1, vx1, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x80() 133 vy2 = _mm512_mask_mul_ps(vy2, vsign2, vx2, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x80() 134 vy3 = _mm512_mask_mul_ps(vy3, vsign3, vx3, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x80() 135 vy4 = _mm512_mask_mul_ps(vy4, vsign4, vx4, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x80() 167 vy = _mm512_mask_mul_ps(vy, vsign, vx, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x80() 200 vy = _mm512_mask_mul_ps(vy, vsign, vx, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x80()
|
D | velu-avx512f-rr1-lut16-p3-perm-x96.c | 146 vy0 = _mm512_mask_mul_ps(vy0, vsign0, vx0, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x96() 147 vy1 = _mm512_mask_mul_ps(vy1, vsign1, vx1, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x96() 148 vy2 = _mm512_mask_mul_ps(vy2, vsign2, vx2, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x96() 149 vy3 = _mm512_mask_mul_ps(vy3, vsign3, vx3, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x96() 150 vy4 = _mm512_mask_mul_ps(vy4, vsign4, vx4, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x96() 151 vy5 = _mm512_mask_mul_ps(vy5, vsign5, vx5, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x96() 184 vy = _mm512_mask_mul_ps(vy, vsign, vx, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x96() 217 vy = _mm512_mask_mul_ps(vy, vsign, vx, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x96()
|
D | velu-avx512f-rr1-p6-x96.c | 154 vy0 = _mm512_mask_mul_ps(vy0, vsign0, vx0, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x96() 155 vy1 = _mm512_mask_mul_ps(vy1, vsign1, vx1, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x96() 156 vy2 = _mm512_mask_mul_ps(vy2, vsign2, vx2, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x96() 157 vy3 = _mm512_mask_mul_ps(vy3, vsign3, vx3, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x96() 158 vy4 = _mm512_mask_mul_ps(vy4, vsign4, vx4, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x96() 159 vy5 = _mm512_mask_mul_ps(vy5, vsign5, vx5, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x96() 193 vy = _mm512_mask_mul_ps(vy, vsign, vx, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x96() 227 vy = _mm512_mask_mul_ps(vy, vsign, vx, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x96()
|
D | velu-avx512f-rr1-p6-x112.c | 170 vy0 = _mm512_mask_mul_ps(vy0, vsign0, vx0, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x112() 171 vy1 = _mm512_mask_mul_ps(vy1, vsign1, vx1, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x112() 172 vy2 = _mm512_mask_mul_ps(vy2, vsign2, vx2, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x112() 173 vy3 = _mm512_mask_mul_ps(vy3, vsign3, vx3, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x112() 174 vy4 = _mm512_mask_mul_ps(vy4, vsign4, vx4, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x112() 175 vy5 = _mm512_mask_mul_ps(vy5, vsign5, vx5, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x112() 176 vy6 = _mm512_mask_mul_ps(vy6, vsign6, vx6, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x112() 211 vy = _mm512_mask_mul_ps(vy, vsign, vx, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x112() 245 vy = _mm512_mask_mul_ps(vy, vsign, vx, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x112()
|
D | velu-avx512f-rr1-p6-x80.c | 138 vy0 = _mm512_mask_mul_ps(vy0, vsign0, vx0, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x80() 139 vy1 = _mm512_mask_mul_ps(vy1, vsign1, vx1, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x80() 140 vy2 = _mm512_mask_mul_ps(vy2, vsign2, vx2, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x80() 141 vy3 = _mm512_mask_mul_ps(vy3, vsign3, vx3, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x80() 142 vy4 = _mm512_mask_mul_ps(vy4, vsign4, vx4, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x80() 175 vy = _mm512_mask_mul_ps(vy, vsign, vx, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x80() 209 vy = _mm512_mask_mul_ps(vy, vsign, vx, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x80()
|
D | velu-avx512f-rr1-p6-x64.c | 122 vy0 = _mm512_mask_mul_ps(vy0, vsign0, vx0, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x64() 123 vy1 = _mm512_mask_mul_ps(vy1, vsign1, vx1, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x64() 124 vy2 = _mm512_mask_mul_ps(vy2, vsign2, vx2, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x64() 125 vy3 = _mm512_mask_mul_ps(vy3, vsign3, vx3, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x64() 157 vy = _mm512_mask_mul_ps(vy, vsign, vx, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x64() 191 vy = _mm512_mask_mul_ps(vy, vsign, vx, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x64()
|
D | velu-avx512f-rr1-lut16-p3-perm-x64.c | 116 vy0 = _mm512_mask_mul_ps(vy0, vsign0, vx0, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x64() 117 vy1 = _mm512_mask_mul_ps(vy1, vsign1, vx1, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x64() 118 vy2 = _mm512_mask_mul_ps(vy2, vsign2, vx2, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x64() 119 vy3 = _mm512_mask_mul_ps(vy3, vsign3, vx3, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x64() 150 vy = _mm512_mask_mul_ps(vy, vsign, vx, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x64() 183 vy = _mm512_mask_mul_ps(vy, vsign, vx, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x64()
|
D | velu-avx512f-rr1-lut16-p3-perm-x48.c | 101 vy0 = _mm512_mask_mul_ps(vy0, vsign0, vx0, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x48() 102 vy1 = _mm512_mask_mul_ps(vy1, vsign1, vx1, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x48() 103 vy2 = _mm512_mask_mul_ps(vy2, vsign2, vx2, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x48() 133 vy = _mm512_mask_mul_ps(vy, vsign, vx, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x48() 166 vy = _mm512_mask_mul_ps(vy, vsign, vx, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x48()
|
D | velu-avx512f-rr1-p6-x48.c | 106 vy0 = _mm512_mask_mul_ps(vy0, vsign0, vx0, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x48() 107 vy1 = _mm512_mask_mul_ps(vy1, vsign1, vx1, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x48() 108 vy2 = _mm512_mask_mul_ps(vy2, vsign2, vx2, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x48() 139 vy = _mm512_mask_mul_ps(vy, vsign, vx, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x48() 173 vy = _mm512_mask_mul_ps(vy, vsign, vx, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x48()
|
D | velu-avx512f-rr1-lut16-p3-perm-x32.c | 86 vy0 = _mm512_mask_mul_ps(vy0, vsign0, vx0, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x32() 87 vy1 = _mm512_mask_mul_ps(vy1, vsign1, vx1, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x32() 116 vy = _mm512_mask_mul_ps(vy, vsign, vx, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x32() 149 vy = _mm512_mask_mul_ps(vy, vsign, vx, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x32()
|
D | velu-avx512f-rr1-p6-x32.c | 90 vy0 = _mm512_mask_mul_ps(vy0, vsign0, vx0, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x32() 91 vy1 = _mm512_mask_mul_ps(vy1, vsign1, vx1, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x32() 121 vy = _mm512_mask_mul_ps(vy, vsign, vx, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x32() 155 vy = _mm512_mask_mul_ps(vy, vsign, vx, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x32()
|
D | velu-avx512f-rr1-lut16-p3-perm-x16.c | 65 vy = _mm512_mask_mul_ps(vy, vsign, vx, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x16() 98 vy = _mm512_mask_mul_ps(vy, vsign, vx, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x16()
|
D | velu-avx512f-rr1-p6-x16.c | 66 vy = _mm512_mask_mul_ps(vy, vsign, vx, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x16() 100 vy = _mm512_mask_mul_ps(vy, vsign, vx, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x16()
|
/external/XNNPACK/src/f32-vlrelu/ |
D | avx512f.c.in | 40 …vacc${ABC[N:N+16]} = _mm512_mask_mul_ps(vacc${ABC[N:N+16]}, vsign${ABC[N:N+16]}, vacc${ABC[N:N+16]… 52 vacc = _mm512_mask_mul_ps(vacc, vsign, vacc, vslope); 65 vacc = _mm512_mask_mul_ps(vacc, vsign, vacc, vslope);
|
/external/XNNPACK/src/f32-prelu/ |
D | avx512f.c.in | 70 …const __m512 vacc${M}x${ABC[C:C+16]} = _mm512_mask_mul_ps(vi${M}x${ABC[C:C+16]}, vsign${M}x${ABC[C… 89 const __m512 vacc${M} = _mm512_mask_mul_ps(vi${M}, vsign${M}, vi${M}, vw); 109 const __m512 vacc${M} = _mm512_mask_mul_ps(vi${M}, vsign${M}, vi${M}, vw);
|
/external/XNNPACK/src/f32-velu/ |
D | avx512f-rr1-lut16-p3-perm.c.in | 84 vy${N} = _mm512_mask_mul_ps(vy${N}, vsign${N}, vx${N}, vbeta); 114 vy = _mm512_mask_mul_ps(vy, vsign, vx, vbeta); 147 vy = _mm512_mask_mul_ps(vy, vsign, vx, vbeta);
|
D | avx512f-rr1-p6.c.in | 89 vy${N} = _mm512_mask_mul_ps(vy${N}, vsign${N}, vx${N}, vbeta); 120 vy = _mm512_mask_mul_ps(vy, vsign, vx, vbeta); 154 vy = _mm512_mask_mul_ps(vy, vsign, vx, vbeta);
|
/external/XNNPACK/src/math/ |
D | exp-avx512f-rr2-lut32-p2-perm2.c | 104 vf = _mm512_mask_mul_ps(vplus_inf, vinvof, vso, vf); in xnn_math_f32_exp__avx512f_rr2_lut32_p2_perm2()
|