|
4 | 4 |
|
5 | 5 | | Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) | |
6 | 6 | |---------|---------------|----------------|------------| |
7 | | -| 100000 | 0.110 | 0.515 | 4.68x | |
| 7 | +| 100000 | 0.080 | 0.511 | 6.39x | |
8 | 8 |
|
9 | 9 | #### float256 Subtraction |
10 | 10 |
|
11 | 11 | | Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) | |
12 | 12 | |---------|---------------|----------------|------------| |
13 | | -| 100000 | 0.110 | 0.523 | 4.75x | |
| 13 | +| 100000 | 0.080 | 0.523 | 6.54x | |
14 | 14 |
|
15 | 15 | #### float256 Multiplication |
16 | 16 |
|
17 | 17 | | Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) | |
18 | 18 | |---------|---------------|----------------|------------| |
19 | | -| 100000 | 0.111 | 0.860 | 7.75x | |
| 19 | +| 100000 | 0.080 | 0.581 | 7.26x | |
20 | 20 |
|
21 | 21 | #### float256 Division |
22 | 22 |
|
23 | 23 | | Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) | |
24 | 24 | |---------|---------------|----------------|------------| |
25 | | -| 100000 | 0.113 | 0.769 | 6.81x | |
| 25 | +| 100000 | 0.110 | 0.768 | 6.98x | |
26 | 26 |
|
27 | 27 | #### double256 Addition |
28 | 28 |
|
29 | 29 | | Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) | |
30 | 30 | |---------|---------------|----------------|------------| |
31 | | -| 100000 | 0.115 | 0.261 | 2.27x | |
| 31 | +| 100000 | 0.080 | 0.262 | 3.27x | |
32 | 32 |
|
33 | 33 | #### double256 Subtraction |
34 | 34 |
|
35 | 35 | | Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) | |
36 | 36 | |---------|---------------|----------------|------------| |
37 | | -| 100000 | 0.107 | 0.273 | 2.55x | |
| 37 | +| 100000 | 0.081 | 0.272 | 3.36x | |
38 | 38 |
|
39 | 39 | #### double256 Multiplication |
40 | 40 |
|
41 | 41 | | Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) | |
42 | 42 | |---------|---------------|----------------|------------| |
43 | | -| 100000 | 0.110 | 0.336 | 3.05x | |
| 43 | +| 100000 | 0.080 | 0.337 | 4.21x | |
44 | 44 |
|
45 | 45 | #### double256 Division |
46 | 46 |
|
47 | 47 | | Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) | |
48 | 48 | |---------|---------------|----------------|------------| |
49 | | -| 100000 | 0.141 | 0.565 | 4.01x | |
| 49 | +| 100000 | 0.141 | 0.564 | 4.00x | |
50 | 50 |
|
51 | 51 | #### int128_with_int32 t_Addition |
52 | 52 |
|
53 | 53 | | Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) | |
54 | 54 | |---------|---------------|----------------|------------| |
55 | | -| 1000000 | 0.900 | 2.560 | 2.84x | |
| 55 | +| 1000000 | 0.891 | 2.560 | 2.87x | |
56 | 56 |
|
57 | 57 | #### int128_with_int32 t_Subtraction |
58 | 58 |
|
59 | 59 | | Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) | |
60 | 60 | |---------|---------------|----------------|------------| |
61 | | -| 1000000 | 0.954 | 2.590 | 2.71x | |
| 61 | +| 1000000 | 0.977 | 2.560 | 2.62x | |
62 | 62 |
|
63 | 63 | #### int128_with_int32 t_Multiplication |
64 | 64 |
|
65 | 65 | | Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) | |
66 | 66 | |---------|---------------|----------------|------------| |
67 | | -| 100000 | 0.076 | 0.268 | 3.53x | |
| 67 | +| 100000 | 0.075 | 0.270 | 3.60x | |
68 | 68 |
|
69 | 69 | #### int128_with_int16 t_Addition |
70 | 70 |
|
71 | 71 | | Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) | |
72 | 72 | |---------|---------------|----------------|------------| |
73 | | -| 100000 | 0.074 | 0.515 | 6.96x | |
| 73 | +| 100000 | 0.074 | 0.514 | 6.95x | |
74 | 74 |
|
75 | 75 | #### int128_with_int16 t_Subtraction |
76 | 76 |
|
77 | 77 | | Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) | |
78 | 78 | |---------|---------------|----------------|------------| |
79 | | -| 100000 | 0.075 | 0.514 | 6.85x | |
| 79 | +| 100000 | 0.075 | 0.516 | 6.88x | |
80 | 80 |
|
81 | 81 | #### int128_with_int16 t_Multiplication |
82 | 82 |
|
83 | 83 | | Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) | |
84 | 84 | |---------|---------------|----------------|------------| |
85 | | -| 100000 | 0.074 | 0.644 | 8.70x | |
| 85 | +| 100000 | 0.073 | 0.617 | 8.45x | |
86 | 86 |
|
87 | 87 | #### int128_with_int8 t_Addition |
88 | 88 |
|
89 | 89 | | Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) | |
90 | 90 | |---------|---------------|----------------|------------| |
91 | | -| 100000 | 0.068 | 1.030 | 15.15x | |
| 91 | +| 100000 | 0.067 | 1.030 | 15.37x | |
92 | 92 |
|
93 | 93 | #### int128_with_int8 t_Subtraction |
94 | 94 |
|
95 | 95 | | Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) | |
96 | 96 | |---------|---------------|----------------|------------| |
97 | | -| 100000 | 0.063 | 1.060 | 16.83x | |
| 97 | +| 100000 | 0.061 | 1.040 | 17.05x | |
98 | 98 |
|
99 | 99 | #### int256_with_int32 t_Addition |
100 | 100 |
|
101 | 101 | | Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) | |
102 | 102 | |---------|---------------|----------------|------------| |
103 | | -| 100000 | 0.111 | 0.518 | 4.67x | |
| 103 | +| 100000 | 0.080 | 0.506 | 6.33x | |
104 | 104 |
|
105 | 105 | #### int256_with_int32 t_Subtraction |
106 | 106 |
|
107 | 107 | | Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) | |
108 | 108 | |---------|---------------|----------------|------------| |
109 | | -| 100000 | 0.112 | 0.518 | 4.62x | |
| 109 | +| 100000 | 0.080 | 0.506 | 6.33x | |
110 | 110 |
|
111 | 111 | #### int256_with_int32 t_Multiplication |
112 | 112 |
|
113 | 113 | | Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) | |
114 | 114 | |---------|---------------|----------------|------------| |
115 | | -| 100000 | 0.111 | 0.549 | 4.95x | |
| 115 | +| 100000 | 0.080 | 0.533 | 6.66x | |
116 | 116 |
|
117 | 117 | #### int256_with_int16 t_Addition |
118 | 118 |
|
119 | 119 | | Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) | |
120 | 120 | |---------|---------------|----------------|------------| |
121 | | -| 100000 | 0.113 | 1.050 | 9.29x | |
| 121 | +| 100000 | 0.080 | 1.020 | 12.75x | |
122 | 122 |
|
123 | 123 | #### int256_with_int16 t_Subtraction |
124 | 124 |
|
125 | 125 | | Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) | |
126 | 126 | |---------|---------------|----------------|------------| |
127 | | -| 100000 | 0.109 | 1.050 | 9.63x | |
| 127 | +| 100000 | 0.080 | 1.020 | 12.75x | |
128 | 128 |
|
129 | 129 | #### int256_with_int16 t_Multiplication |
130 | 130 |
|
131 | 131 | | Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) | |
132 | 132 | |---------|---------------|----------------|------------| |
133 | | -| 100000 | 0.111 | 1.190 | 10.72x | |
| 133 | +| 100000 | 0.080 | 1.160 | 14.50x | |
134 | 134 |
|
135 | 135 | #### int256_with_int8 t_Addition |
136 | 136 |
|
137 | 137 | | Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) | |
138 | 138 | |---------|---------------|----------------|------------| |
139 | | -| 100000 | 0.110 | 2.230 | 20.27x | |
| 139 | +| 100000 | 0.080 | 2.210 | 27.62x | |
140 | 140 |
|
141 | 141 | #### int256_with_int8 t_Subtraction |
142 | 142 |
|
143 | 143 | | Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) | |
144 | 144 | |---------|---------------|----------------|------------| |
145 | | -| 100000 | 0.111 | 2.230 | 20.09x | |
| 145 | +| 100000 | 0.080 | 2.200 | 27.50x | |
146 | 146 |
|
0 commit comments