Home
last modified time | relevance | path

Searched refs:_mm256_or_ps (Results 1 – 25 of 43) sorted by relevance

12

/external/XNNPACK/src/f32-sigmoid/gen/
Davx2-rr1-p5-div-x80.c63 const __m256 vz0 = _mm256_or_ps(vx0, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x80()
64 const __m256 vz1 = _mm256_or_ps(vx1, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x80()
65 const __m256 vz2 = _mm256_or_ps(vx2, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x80()
66 const __m256 vz3 = _mm256_or_ps(vx3, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x80()
67 const __m256 vz4 = _mm256_or_ps(vx4, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x80()
68 const __m256 vz5 = _mm256_or_ps(vx5, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x80()
69 const __m256 vz6 = _mm256_or_ps(vx6, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x80()
70 const __m256 vz7 = _mm256_or_ps(vx7, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x80()
71 const __m256 vz8 = _mm256_or_ps(vx8, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x80()
72 const __m256 vz9 = _mm256_or_ps(vx9, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x80()
[all …]
Davx2-rr1-p5-div-x64.c61 const __m256 vz0 = _mm256_or_ps(vx0, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x64()
62 const __m256 vz1 = _mm256_or_ps(vx1, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x64()
63 const __m256 vz2 = _mm256_or_ps(vx2, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x64()
64 const __m256 vz3 = _mm256_or_ps(vx3, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x64()
65 const __m256 vz4 = _mm256_or_ps(vx4, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x64()
66 const __m256 vz5 = _mm256_or_ps(vx5, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x64()
67 const __m256 vz6 = _mm256_or_ps(vx6, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x64()
68 const __m256 vz7 = _mm256_or_ps(vx7, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x64()
237 const __m256 vz = _mm256_or_ps(vx, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x64()
300 const __m256 vz = _mm256_or_ps(vx, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x64()
Davx2-rr1-p5-div-x72.c62 const __m256 vz0 = _mm256_or_ps(vx0, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x72()
63 const __m256 vz1 = _mm256_or_ps(vx1, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x72()
64 const __m256 vz2 = _mm256_or_ps(vx2, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x72()
65 const __m256 vz3 = _mm256_or_ps(vx3, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x72()
66 const __m256 vz4 = _mm256_or_ps(vx4, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x72()
67 const __m256 vz5 = _mm256_or_ps(vx5, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x72()
68 const __m256 vz6 = _mm256_or_ps(vx6, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x72()
69 const __m256 vz7 = _mm256_or_ps(vx7, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x72()
70 const __m256 vz8 = _mm256_or_ps(vx8, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x72()
254 const __m256 vz = _mm256_or_ps(vx, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x72()
[all …]
Davx2-rr1-p5-nr1fma-x80.c63 const __m256 vz0 = _mm256_or_ps(vx0, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x80()
64 const __m256 vz1 = _mm256_or_ps(vx1, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x80()
65 const __m256 vz2 = _mm256_or_ps(vx2, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x80()
66 const __m256 vz3 = _mm256_or_ps(vx3, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x80()
67 const __m256 vz4 = _mm256_or_ps(vx4, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x80()
68 const __m256 vz5 = _mm256_or_ps(vx5, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x80()
69 const __m256 vz6 = _mm256_or_ps(vx6, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x80()
70 const __m256 vz7 = _mm256_or_ps(vx7, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x80()
71 const __m256 vz8 = _mm256_or_ps(vx8, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x80()
72 const __m256 vz9 = _mm256_or_ps(vx9, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x80()
[all …]
Davx2-rr1-p5-div-x56.c60 const __m256 vz0 = _mm256_or_ps(vx0, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x56()
61 const __m256 vz1 = _mm256_or_ps(vx1, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x56()
62 const __m256 vz2 = _mm256_or_ps(vx2, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x56()
63 const __m256 vz3 = _mm256_or_ps(vx3, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x56()
64 const __m256 vz4 = _mm256_or_ps(vx4, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x56()
65 const __m256 vz5 = _mm256_or_ps(vx5, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x56()
66 const __m256 vz6 = _mm256_or_ps(vx6, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x56()
220 const __m256 vz = _mm256_or_ps(vx, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x56()
283 const __m256 vz = _mm256_or_ps(vx, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x56()
Davx2-rr1-p5-nr2fma-x80.c63 const __m256 vz0 = _mm256_or_ps(vx0, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x80()
64 const __m256 vz1 = _mm256_or_ps(vx1, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x80()
65 const __m256 vz2 = _mm256_or_ps(vx2, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x80()
66 const __m256 vz3 = _mm256_or_ps(vx3, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x80()
67 const __m256 vz4 = _mm256_or_ps(vx4, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x80()
68 const __m256 vz5 = _mm256_or_ps(vx5, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x80()
69 const __m256 vz6 = _mm256_or_ps(vx6, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x80()
70 const __m256 vz7 = _mm256_or_ps(vx7, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x80()
71 const __m256 vz8 = _mm256_or_ps(vx8, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x80()
72 const __m256 vz9 = _mm256_or_ps(vx9, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x80()
[all …]
Davx2-rr1-p5-nr1fma-x72.c62 const __m256 vz0 = _mm256_or_ps(vx0, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x72()
63 const __m256 vz1 = _mm256_or_ps(vx1, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x72()
64 const __m256 vz2 = _mm256_or_ps(vx2, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x72()
65 const __m256 vz3 = _mm256_or_ps(vx3, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x72()
66 const __m256 vz4 = _mm256_or_ps(vx4, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x72()
67 const __m256 vz5 = _mm256_or_ps(vx5, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x72()
68 const __m256 vz6 = _mm256_or_ps(vx6, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x72()
69 const __m256 vz7 = _mm256_or_ps(vx7, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x72()
70 const __m256 vz8 = _mm256_or_ps(vx8, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x72()
278 const __m256 vz = _mm256_or_ps(vx, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x72()
[all …]
Davx2-rr1-p5-nr2fma-x72.c62 const __m256 vz0 = _mm256_or_ps(vx0, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x72()
63 const __m256 vz1 = _mm256_or_ps(vx1, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x72()
64 const __m256 vz2 = _mm256_or_ps(vx2, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x72()
65 const __m256 vz3 = _mm256_or_ps(vx3, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x72()
66 const __m256 vz4 = _mm256_or_ps(vx4, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x72()
67 const __m256 vz5 = _mm256_or_ps(vx5, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x72()
68 const __m256 vz6 = _mm256_or_ps(vx6, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x72()
69 const __m256 vz7 = _mm256_or_ps(vx7, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x72()
70 const __m256 vz8 = _mm256_or_ps(vx8, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x72()
287 const __m256 vz = _mm256_or_ps(vx, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x72()
[all …]
Davx2-rr1-p5-nr1fma-x64.c61 const __m256 vz0 = _mm256_or_ps(vx0, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x64()
62 const __m256 vz1 = _mm256_or_ps(vx1, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x64()
63 const __m256 vz2 = _mm256_or_ps(vx2, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x64()
64 const __m256 vz3 = _mm256_or_ps(vx3, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x64()
65 const __m256 vz4 = _mm256_or_ps(vx4, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x64()
66 const __m256 vz5 = _mm256_or_ps(vx5, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x64()
67 const __m256 vz6 = _mm256_or_ps(vx6, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x64()
68 const __m256 vz7 = _mm256_or_ps(vx7, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x64()
259 const __m256 vz = _mm256_or_ps(vx, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x64()
328 const __m256 vz = _mm256_or_ps(vx, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x64()
Davx2-rr1-p5-div-x48.c59 const __m256 vz0 = _mm256_or_ps(vx0, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x48()
60 const __m256 vz1 = _mm256_or_ps(vx1, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x48()
61 const __m256 vz2 = _mm256_or_ps(vx2, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x48()
62 const __m256 vz3 = _mm256_or_ps(vx3, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x48()
63 const __m256 vz4 = _mm256_or_ps(vx4, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x48()
64 const __m256 vz5 = _mm256_or_ps(vx5, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x48()
203 const __m256 vz = _mm256_or_ps(vx, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x48()
266 const __m256 vz = _mm256_or_ps(vx, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x48()
Davx2-rr1-p5-div-x40.c58 const __m256 vz0 = _mm256_or_ps(vx0, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x40()
59 const __m256 vz1 = _mm256_or_ps(vx1, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x40()
60 const __m256 vz2 = _mm256_or_ps(vx2, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x40()
61 const __m256 vz3 = _mm256_or_ps(vx3, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x40()
62 const __m256 vz4 = _mm256_or_ps(vx4, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x40()
186 const __m256 vz = _mm256_or_ps(vx, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x40()
249 const __m256 vz = _mm256_or_ps(vx, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x40()
Davx2-rr1-p5-nr1fma-x56.c60 const __m256 vz0 = _mm256_or_ps(vx0, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x56()
61 const __m256 vz1 = _mm256_or_ps(vx1, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x56()
62 const __m256 vz2 = _mm256_or_ps(vx2, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x56()
63 const __m256 vz3 = _mm256_or_ps(vx3, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x56()
64 const __m256 vz4 = _mm256_or_ps(vx4, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x56()
65 const __m256 vz5 = _mm256_or_ps(vx5, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x56()
66 const __m256 vz6 = _mm256_or_ps(vx6, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x56()
240 const __m256 vz = _mm256_or_ps(vx, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x56()
309 const __m256 vz = _mm256_or_ps(vx, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x56()
Davx2-rr1-p5-nr1fma-x48.c59 const __m256 vz0 = _mm256_or_ps(vx0, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x48()
60 const __m256 vz1 = _mm256_or_ps(vx1, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x48()
61 const __m256 vz2 = _mm256_or_ps(vx2, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x48()
62 const __m256 vz3 = _mm256_or_ps(vx3, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x48()
63 const __m256 vz4 = _mm256_or_ps(vx4, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x48()
64 const __m256 vz5 = _mm256_or_ps(vx5, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x48()
221 const __m256 vz = _mm256_or_ps(vx, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x48()
290 const __m256 vz = _mm256_or_ps(vx, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x48()
Davx2-rr1-p5-div-x32.c57 const __m256 vz0 = _mm256_or_ps(vx0, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x32()
58 const __m256 vz1 = _mm256_or_ps(vx1, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x32()
59 const __m256 vz2 = _mm256_or_ps(vx2, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x32()
60 const __m256 vz3 = _mm256_or_ps(vx3, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x32()
169 const __m256 vz = _mm256_or_ps(vx, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x32()
232 const __m256 vz = _mm256_or_ps(vx, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x32()
Davx2-rr1-p5-nr2fma-x64.c61 const __m256 vz0 = _mm256_or_ps(vx0, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x64()
62 const __m256 vz1 = _mm256_or_ps(vx1, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x64()
63 const __m256 vz2 = _mm256_or_ps(vx2, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x64()
64 const __m256 vz3 = _mm256_or_ps(vx3, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x64()
65 const __m256 vz4 = _mm256_or_ps(vx4, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x64()
66 const __m256 vz5 = _mm256_or_ps(vx5, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x64()
67 const __m256 vz6 = _mm256_or_ps(vx6, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x64()
68 const __m256 vz7 = _mm256_or_ps(vx7, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x64()
267 const __m256 vz = _mm256_or_ps(vx, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x64()
337 const __m256 vz = _mm256_or_ps(vx, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x64()
Davx2-rr1-p5-nr2fma-x56.c60 const __m256 vz0 = _mm256_or_ps(vx0, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x56()
61 const __m256 vz1 = _mm256_or_ps(vx1, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x56()
62 const __m256 vz2 = _mm256_or_ps(vx2, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x56()
63 const __m256 vz3 = _mm256_or_ps(vx3, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x56()
64 const __m256 vz4 = _mm256_or_ps(vx4, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x56()
65 const __m256 vz5 = _mm256_or_ps(vx5, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x56()
66 const __m256 vz6 = _mm256_or_ps(vx6, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x56()
247 const __m256 vz = _mm256_or_ps(vx, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x56()
317 const __m256 vz = _mm256_or_ps(vx, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x56()
Davx2-rr1-p5-nr2fma-x48.c59 const __m256 vz0 = _mm256_or_ps(vx0, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x48()
60 const __m256 vz1 = _mm256_or_ps(vx1, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x48()
61 const __m256 vz2 = _mm256_or_ps(vx2, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x48()
62 const __m256 vz3 = _mm256_or_ps(vx3, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x48()
63 const __m256 vz4 = _mm256_or_ps(vx4, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x48()
64 const __m256 vz5 = _mm256_or_ps(vx5, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x48()
227 const __m256 vz = _mm256_or_ps(vx, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x48()
297 const __m256 vz = _mm256_or_ps(vx, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x48()
Davx2-rr1-p5-nr2fma-x40.c58 const __m256 vz0 = _mm256_or_ps(vx0, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x40()
59 const __m256 vz1 = _mm256_or_ps(vx1, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x40()
60 const __m256 vz2 = _mm256_or_ps(vx2, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x40()
61 const __m256 vz3 = _mm256_or_ps(vx3, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x40()
62 const __m256 vz4 = _mm256_or_ps(vx4, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x40()
207 const __m256 vz = _mm256_or_ps(vx, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x40()
277 const __m256 vz = _mm256_or_ps(vx, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x40()
Davx2-rr1-p5-nr1fma-x40.c58 const __m256 vz0 = _mm256_or_ps(vx0, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x40()
59 const __m256 vz1 = _mm256_or_ps(vx1, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x40()
60 const __m256 vz2 = _mm256_or_ps(vx2, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x40()
61 const __m256 vz3 = _mm256_or_ps(vx3, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x40()
62 const __m256 vz4 = _mm256_or_ps(vx4, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x40()
202 const __m256 vz = _mm256_or_ps(vx, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x40()
271 const __m256 vz = _mm256_or_ps(vx, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x40()
Davx2-rr1-p5-div-x24.c56 const __m256 vz0 = _mm256_or_ps(vx0, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x24()
57 const __m256 vz1 = _mm256_or_ps(vx1, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x24()
58 const __m256 vz2 = _mm256_or_ps(vx2, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x24()
152 const __m256 vz = _mm256_or_ps(vx, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x24()
215 const __m256 vz = _mm256_or_ps(vx, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x24()
Davx2-rr1-p5-nr1fma-x32.c57 const __m256 vz0 = _mm256_or_ps(vx0, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x32()
58 const __m256 vz1 = _mm256_or_ps(vx1, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x32()
59 const __m256 vz2 = _mm256_or_ps(vx2, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x32()
60 const __m256 vz3 = _mm256_or_ps(vx3, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x32()
183 const __m256 vz = _mm256_or_ps(vx, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x32()
252 const __m256 vz = _mm256_or_ps(vx, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x32()
Davx2-rr1-p5-nr1fma-x24.c56 const __m256 vz0 = _mm256_or_ps(vx0, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x24()
57 const __m256 vz1 = _mm256_or_ps(vx1, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x24()
58 const __m256 vz2 = _mm256_or_ps(vx2, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x24()
164 const __m256 vz = _mm256_or_ps(vx, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x24()
233 const __m256 vz = _mm256_or_ps(vx, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x24()
Davx2-rr1-p5-nr2fma-x32.c57 const __m256 vz0 = _mm256_or_ps(vx0, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x32()
58 const __m256 vz1 = _mm256_or_ps(vx1, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x32()
59 const __m256 vz2 = _mm256_or_ps(vx2, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x32()
60 const __m256 vz3 = _mm256_or_ps(vx3, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x32()
187 const __m256 vz = _mm256_or_ps(vx, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x32()
257 const __m256 vz = _mm256_or_ps(vx, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x32()
Davx2-rr1-p5-nr2fma-x24.c56 const __m256 vz0 = _mm256_or_ps(vx0, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x24()
57 const __m256 vz1 = _mm256_or_ps(vx1, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x24()
58 const __m256 vz2 = _mm256_or_ps(vx2, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x24()
167 const __m256 vz = _mm256_or_ps(vx, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x24()
237 const __m256 vz = _mm256_or_ps(vx, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x24()
Davx2-rr1-p5-div-x16.c55 const __m256 vz0 = _mm256_or_ps(vx0, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x16()
56 const __m256 vz1 = _mm256_or_ps(vx1, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x16()
135 const __m256 vz = _mm256_or_ps(vx, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x16()
198 const __m256 vz = _mm256_or_ps(vx, vsign_mask); in xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x16()

12