Skip to content

Commit 44da550

Browse files
committed
Add plots too...
1 parent b559793 commit 44da550

3 files changed

Lines changed: 146 additions & 0 deletions

File tree

743 KB
Loading
660 KB
Loading
Lines changed: 146 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,146 @@
1+
# SIMD Performance Comparison Summary
2+
3+
#### float256 Addition
4+
5+
| Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) |
6+
|---------|---------------|----------------|------------|
7+
| 100000 | 0.069 | 0.460 | 6.67x |
8+
9+
#### float256 Subtraction
10+
11+
| Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) |
12+
|---------|---------------|----------------|------------|
13+
| 100000 | 0.069 | 0.471 | 6.83x |
14+
15+
#### float256 Multiplication
16+
17+
| Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) |
18+
|---------|---------------|----------------|------------|
19+
| 100000 | 0.070 | 0.572 | 8.17x |
20+
21+
#### float256 Division
22+
23+
| Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) |
24+
|---------|---------------|----------------|------------|
25+
| 100000 | 0.096 | 0.664 | 6.92x |
26+
27+
#### double256 Addition
28+
29+
| Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) |
30+
|---------|---------------|----------------|------------|
31+
| 100000 | 0.071 | 0.240 | 3.38x |
32+
33+
#### double256 Subtraction
34+
35+
| Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) |
36+
|---------|---------------|----------------|------------|
37+
| 100000 | 0.074 | 0.245 | 3.31x |
38+
39+
#### double256 Multiplication
40+
41+
| Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) |
42+
|---------|---------------|----------------|------------|
43+
| 100000 | 0.075 | 0.330 | 4.40x |
44+
45+
#### double256 Division
46+
47+
| Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) |
48+
|---------|---------------|----------------|------------|
49+
| 100000 | 0.118 | 0.467 | 3.96x |
50+
51+
#### int128_with_int32 t_Addition
52+
53+
| Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) |
54+
|---------|---------------|----------------|------------|
55+
| 1000000 | 2.480 | 3.050 | 1.23x |
56+
57+
#### int128_with_int32 t_Subtraction
58+
59+
| Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) |
60+
|---------|---------------|----------------|------------|
61+
| 1000000 | 2.340 | 3.110 | 1.33x |
62+
63+
#### int128_with_int32 t_Multiplication
64+
65+
| Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) |
66+
|---------|---------------|----------------|------------|
67+
| 100000 | 0.070 | 0.274 | 3.91x |
68+
69+
#### int128_with_int16 t_Addition
70+
71+
| Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) |
72+
|---------|---------------|----------------|------------|
73+
| 100000 | 0.072 | 0.473 | 6.57x |
74+
75+
#### int128_with_int16 t_Subtraction
76+
77+
| Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) |
78+
|---------|---------------|----------------|------------|
79+
| 100000 | 0.069 | 0.545 | 7.90x |
80+
81+
#### int128_with_int16 t_Multiplication
82+
83+
| Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) |
84+
|---------|---------------|----------------|------------|
85+
| 100000 | 0.073 | 0.559 | 7.66x |
86+
87+
#### int128_with_int8 t_Addition
88+
89+
| Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) |
90+
|---------|---------------|----------------|------------|
91+
| 100000 | 0.061 | 0.975 | 15.98x |
92+
93+
#### int128_with_int8 t_Subtraction
94+
95+
| Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) |
96+
|---------|---------------|----------------|------------|
97+
| 100000 | 0.059 | 1.090 | 18.47x |
98+
99+
#### int256_with_int32 t_Addition
100+
101+
| Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) |
102+
|---------|---------------|----------------|------------|
103+
| 100000 | 0.091 | 0.503 | 5.53x |
104+
105+
#### int256_with_int32 t_Subtraction
106+
107+
| Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) |
108+
|---------|---------------|----------------|------------|
109+
| 100000 | 0.084 | 0.500 | 5.95x |
110+
111+
#### int256_with_int32 t_Multiplication
112+
113+
| Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) |
114+
|---------|---------------|----------------|------------|
115+
| 100000 | 0.080 | 0.532 | 6.65x |
116+
117+
#### int256_with_int16 t_Addition
118+
119+
| Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) |
120+
|---------|---------------|----------------|------------|
121+
| 100000 | 0.074 | 1.060 | 14.32x |
122+
123+
#### int256_with_int16 t_Subtraction
124+
125+
| Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) |
126+
|---------|---------------|----------------|------------|
127+
| 100000 | 0.075 | 0.905 | 12.07x |
128+
129+
#### int256_with_int16 t_Multiplication
130+
131+
| Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) |
132+
|---------|---------------|----------------|------------|
133+
| 100000 | 0.079 | 1.130 | 14.30x |
134+
135+
#### int256_with_int8 t_Addition
136+
137+
| Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) |
138+
|---------|---------------|----------------|------------|
139+
| 100000 | 0.083 | 1.780 | 21.45x |
140+
141+
#### int256_with_int8 t_Subtraction
142+
143+
| Variant | SIMD Time (ms) | Plain Time (ms) | Speedup (x) |
144+
|---------|---------------|----------------|------------|
145+
| 100000 | 0.070 | 2.150 | 30.71x |
146+

0 commit comments

Comments
 (0)