|
4 | 4 |
|
5 | 5 | | Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) | |
6 | 6 | |---------|---------------|----------------|------------| |
7 | | -| 100000 | 0.107 | 0.510 | 4.77x | |
| 7 | +| 100000 | 0.081 | 0.507 | 6.26x | |
8 | 8 |
|
9 | 9 | #### float256 Subtraction |
10 | 10 |
|
11 | 11 | | Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) | |
12 | 12 | |---------|---------------|----------------|------------| |
13 | | -| 100000 | 0.106 | 0.506 | 4.77x | |
| 13 | +| 100000 | 0.081 | 0.505 | 6.23x | |
14 | 14 |
|
15 | 15 | #### float256 Multiplication |
16 | 16 |
|
17 | 17 | | Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) | |
18 | 18 | |---------|---------------|----------------|------------| |
19 | | -| 100000 | 0.107 | 0.754 | 7.05x | |
| 19 | +| 100000 | 0.082 | 0.717 | 8.74x | |
20 | 20 |
|
21 | 21 | #### float256 Division |
22 | 22 |
|
23 | 23 | | Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) | |
24 | 24 | |---------|---------------|----------------|------------| |
25 | | -| 100000 | 0.111 | 0.784 | 7.06x | |
| 25 | +| 100000 | 0.104 | 0.806 | 7.75x | |
26 | 26 |
|
27 | 27 | #### double256 Addition |
28 | 28 |
|
29 | 29 | | Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) | |
30 | 30 | |---------|---------------|----------------|------------| |
31 | | -| 100000 | 0.106 | 0.265 | 2.50x | |
| 31 | +| 100000 | 0.084 | 0.257 | 3.06x | |
32 | 32 |
|
33 | 33 | #### double256 Subtraction |
34 | 34 |
|
35 | 35 | | Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) | |
36 | 36 | |---------|---------------|----------------|------------| |
37 | | -| 100000 | 0.106 | 0.287 | 2.71x | |
| 37 | +| 100000 | 0.081 | 0.278 | 3.43x | |
38 | 38 |
|
39 | 39 | #### double256 Multiplication |
40 | 40 |
|
41 | 41 | | Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) | |
42 | 42 | |---------|---------------|----------------|------------| |
43 | | -| 100000 | 0.108 | 0.366 | 3.39x | |
| 43 | +| 100000 | 0.087 | 0.378 | 4.34x | |
44 | 44 |
|
45 | 45 | #### double256 Division |
46 | 46 |
|
47 | 47 | | Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) | |
48 | 48 | |---------|---------------|----------------|------------| |
49 | | -| 100000 | 0.143 | 0.562 | 3.93x | |
| 49 | +| 100000 | 0.143 | 0.561 | 3.92x | |
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 | 0.986 | 2.570 | 2.61x | |
| 55 | +| 1000000 | 1.010 | 2.580 | 2.55x | |
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 | 0.960 | 2.560 | 2.67x | |
| 61 | +| 1000000 | 1.000 | 2.580 | 2.58x | |
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 | 0.075 | 0.259 | 3.45x | |
| 67 | +| 100000 | 0.075 | 0.254 | 3.39x | |
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 | 0.076 | 0.510 | 6.71x | |
| 73 | +| 100000 | 0.075 | 0.509 | 6.79x | |
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 | 0.510 | 6.80x | |
| 79 | +| 100000 | 0.080 | 0.510 | 6.38x | |
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 | 0.077 | 0.680 | 8.83x | |
| 85 | +| 100000 | 0.075 | 0.680 | 9.07x | |
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 | 0.061 | 1.100 | 18.03x | |
| 91 | +| 100000 | 0.060 | 1.100 | 18.33x | |
92 | 92 |
|
93 | 93 | #### int128_with_int8 t_Subtraction |
94 | 94 |
|
|
100 | 100 |
|
101 | 101 | | Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) | |
102 | 102 | |---------|---------------|----------------|------------| |
103 | | -| 100000 | 0.109 | 0.511 | 4.69x | |
| 103 | +| 100000 | 0.088 | 0.508 | 5.77x | |
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 | 0.108 | 0.506 | 4.69x | |
| 109 | +| 100000 | 0.089 | 0.505 | 5.67x | |
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 | 0.108 | 0.590 | 5.46x | |
| 115 | +| 100000 | 0.088 | 0.572 | 6.50x | |
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 | 0.107 | 1.040 | 9.72x | |
| 121 | +| 100000 | 0.087 | 1.030 | 11.84x | |
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 | 0.107 | 1.040 | 9.72x | |
| 127 | +| 100000 | 0.086 | 1.030 | 11.98x | |
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 | 0.110 | 1.400 | 12.73x | |
| 133 | +| 100000 | 0.088 | 1.410 | 16.02x | |
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 | 0.107 | 2.160 | 20.19x | |
| 139 | +| 100000 | 0.085 | 2.160 | 25.41x | |
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 | 0.106 | 2.160 | 20.38x | |
| 145 | +| 100000 | 0.082 | 2.160 | 26.34x | |
146 | 146 |
|
0 commit comments