/external/XNNPACK/src/f32-prelu/gen/ |
D | avx512f-2x32.c | 85 const __mmask16 vsign0 = _mm512_cmp_ps_mask(vi0, vzero, _CMP_LT_OQ); in xnn_f32_prelu_ukernel__avx512f_2x32() local 86 const __m512 vacc0 = _mm512_mask_mul_ps(vi0, vsign0, vi0, vw); in xnn_f32_prelu_ukernel__avx512f_2x32() 108 const __mmask16 vsign0 = _mm512_cmp_ps_mask(vi0, vzero, _CMP_LT_OQ); in xnn_f32_prelu_ukernel__avx512f_2x32() local 109 const __m512 vacc0 = _mm512_mask_mul_ps(vi0, vsign0, vi0, vw); in xnn_f32_prelu_ukernel__avx512f_2x32()
|
D | avx512f-2x16.c | 80 const __mmask16 vsign0 = _mm512_cmp_ps_mask(vi0, vzero, _CMP_LT_OQ); in xnn_f32_prelu_ukernel__avx512f_2x16() local 81 const __m512 vacc0 = _mm512_mask_mul_ps(vi0, vsign0, vi0, vw); in xnn_f32_prelu_ukernel__avx512f_2x16()
|
/external/XNNPACK/src/f32-velu/gen/ |
D | velu-avx512f-rr1-lut16-p3-perm-x32.c | 82 const __mmask16 vsign0 = _mm512_cmp_ps_mask(vx0, vzero, _CMP_NLT_US); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x32() local 86 vy0 = _mm512_mask_mul_ps(vy0, vsign0, vx0, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x32()
|
D | velu-avx512f-rr1-p6-x32.c | 86 const __mmask16 vsign0 = _mm512_cmp_ps_mask(vx0, vzero, _CMP_NLT_US); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x32() local 90 vy0 = _mm512_mask_mul_ps(vy0, vsign0, vx0, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x32()
|
D | velu-avx512f-rr1-lut16-p3-perm-x48.c | 95 const __mmask16 vsign0 = _mm512_cmp_ps_mask(vx0, vzero, _CMP_NLT_US); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x48() local 101 vy0 = _mm512_mask_mul_ps(vy0, vsign0, vx0, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x48()
|
D | velu-avx512f-rr1-p6-x48.c | 100 const __mmask16 vsign0 = _mm512_cmp_ps_mask(vx0, vzero, _CMP_NLT_US); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x48() local 106 vy0 = _mm512_mask_mul_ps(vy0, vsign0, vx0, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x48()
|
D | velu-avx512f-rr1-p6-x64.c | 114 const __mmask16 vsign0 = _mm512_cmp_ps_mask(vx0, vzero, _CMP_NLT_US); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x64() local 122 vy0 = _mm512_mask_mul_ps(vy0, vsign0, vx0, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x64()
|
D | velu-avx512f-rr1-lut16-p3-perm-x64.c | 108 const __mmask16 vsign0 = _mm512_cmp_ps_mask(vx0, vzero, _CMP_NLT_US); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x64() local 116 vy0 = _mm512_mask_mul_ps(vy0, vsign0, vx0, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x64()
|
D | velu-avx512f-rr1-lut16-p3-perm-x80.c | 121 const __mmask16 vsign0 = _mm512_cmp_ps_mask(vx0, vzero, _CMP_NLT_US); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x80() local 131 vy0 = _mm512_mask_mul_ps(vy0, vsign0, vx0, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x80()
|
D | velu-avx512f-rr1-p6-x80.c | 128 const __mmask16 vsign0 = _mm512_cmp_ps_mask(vx0, vzero, _CMP_NLT_US); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x80() local 138 vy0 = _mm512_mask_mul_ps(vy0, vsign0, vx0, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x80()
|
D | velu-avx512f-rr1-lut16-p3-perm-x96.c | 134 const __mmask16 vsign0 = _mm512_cmp_ps_mask(vx0, vzero, _CMP_NLT_US); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x96() local 146 vy0 = _mm512_mask_mul_ps(vy0, vsign0, vx0, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x96()
|
D | velu-avx512f-rr1-p6-x96.c | 142 const __mmask16 vsign0 = _mm512_cmp_ps_mask(vx0, vzero, _CMP_NLT_US); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x96() local 154 vy0 = _mm512_mask_mul_ps(vy0, vsign0, vx0, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x96()
|
D | velu-avx512f-rr1-lut16-p3-perm-x112.c | 147 const __mmask16 vsign0 = _mm512_cmp_ps_mask(vx0, vzero, _CMP_NLT_US); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x112() local 161 vy0 = _mm512_mask_mul_ps(vy0, vsign0, vx0, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x112()
|
D | velu-avx512f-rr1-p6-x112.c | 156 const __mmask16 vsign0 = _mm512_cmp_ps_mask(vx0, vzero, _CMP_NLT_US); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x112() local 170 vy0 = _mm512_mask_mul_ps(vy0, vsign0, vx0, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x112()
|
D | velu-avx512f-rr1-lut16-p3-perm-x128.c | 160 const __mmask16 vsign0 = _mm512_cmp_ps_mask(vx0, vzero, _CMP_NLT_US); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x128() local 176 vy0 = _mm512_mask_mul_ps(vy0, vsign0, vx0, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x128()
|
D | velu-avx512f-rr1-p6-x128.c | 170 const __mmask16 vsign0 = _mm512_cmp_ps_mask(vx0, vzero, _CMP_NLT_US); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x128() local 186 vy0 = _mm512_mask_mul_ps(vy0, vsign0, vx0, vbeta); in xnn_f32_velu_ukernel__avx512f_rr1_p6_x128()
|