/external/XNNPACK/src/f32-velu/gen/ |
D | velu-avx512f-rr1-lut16-p3-perm-x48.c | 99 const __mmask16 vsign2 = _mm512_cmp_ps_mask(vx2, vzero, _CMP_NLT_US); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x48() local 103 vy2 = _mm512_mask_mul_ps(vy2, vsign2, vx2, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x48()
|
D | velu-avx512f-rr1-p6-x48.c | 104 const __mmask16 vsign2 = _mm512_cmp_ps_mask(vx2, vzero, _CMP_NLT_US); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x48() local 108 vy2 = _mm512_mask_mul_ps(vy2, vsign2, vx2, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x48()
|
D | velu-avx512f-rr1-p6-x64.c | 118 const __mmask16 vsign2 = _mm512_cmp_ps_mask(vx2, vzero, _CMP_NLT_US); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x64() local 124 vy2 = _mm512_mask_mul_ps(vy2, vsign2, vx2, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x64()
|
D | velu-avx512f-rr1-lut16-p3-perm-x64.c | 112 const __mmask16 vsign2 = _mm512_cmp_ps_mask(vx2, vzero, _CMP_NLT_US); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x64() local 118 vy2 = _mm512_mask_mul_ps(vy2, vsign2, vx2, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x64()
|
D | velu-avx512f-rr1-lut16-p3-perm-x80.c | 125 const __mmask16 vsign2 = _mm512_cmp_ps_mask(vx2, vzero, _CMP_NLT_US); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x80() local 133 vy2 = _mm512_mask_mul_ps(vy2, vsign2, vx2, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x80()
|
D | velu-avx512f-rr1-p6-x80.c | 132 const __mmask16 vsign2 = _mm512_cmp_ps_mask(vx2, vzero, _CMP_NLT_US); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x80() local 140 vy2 = _mm512_mask_mul_ps(vy2, vsign2, vx2, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x80()
|
D | velu-avx512f-rr1-lut16-p3-perm-x96.c | 138 const __mmask16 vsign2 = _mm512_cmp_ps_mask(vx2, vzero, _CMP_NLT_US); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x96() local 148 vy2 = _mm512_mask_mul_ps(vy2, vsign2, vx2, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x96()
|
D | velu-avx512f-rr1-p6-x96.c | 146 const __mmask16 vsign2 = _mm512_cmp_ps_mask(vx2, vzero, _CMP_NLT_US); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x96() local 156 vy2 = _mm512_mask_mul_ps(vy2, vsign2, vx2, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x96()
|
D | velu-avx512f-rr1-lut16-p3-perm-x112.c | 151 const __mmask16 vsign2 = _mm512_cmp_ps_mask(vx2, vzero, _CMP_NLT_US); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x112() local 163 vy2 = _mm512_mask_mul_ps(vy2, vsign2, vx2, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x112()
|
D | velu-avx512f-rr1-p6-x112.c | 160 const __mmask16 vsign2 = _mm512_cmp_ps_mask(vx2, vzero, _CMP_NLT_US); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x112() local 172 vy2 = _mm512_mask_mul_ps(vy2, vsign2, vx2, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x112()
|
D | velu-avx512f-rr1-lut16-p3-perm-x128.c | 164 const __mmask16 vsign2 = _mm512_cmp_ps_mask(vx2, vzero, _CMP_NLT_US); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x128() local 178 vy2 = _mm512_mask_mul_ps(vy2, vsign2, vx2, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x128()
|
D | velu-avx512f-rr1-p6-x128.c | 174 const __mmask16 vsign2 = _mm512_cmp_ps_mask(vx2, vzero, _CMP_NLT_US); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x128() local 188 vy2 = _mm512_mask_mul_ps(vy2, vsign2, vx2, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x128()
|