A nice talk from Chandler Carruth at cppcon last year:
Which features this nice table which helps to highlight why data structures are so important.
| ns | ms | Notes | |
| One cycle on a 3 GHz processor | 1 | ||
| L1 cache reference | 0.5 | ||
| Branch mispredict | 5 | ||
| L2 cache reference | 7 | 14x L1 cache | |
| Mutex lock/unlock | 25 | ||
| Main memory reference | 100 | 20x L2, 200x L1 | |
| Compress 1K bytes with Snappy | 3,000 | ||
| Send 1K bytes over 1 Gbps network | 10,000 | 0.01 | |
| Read 4K randomly from SSD* | 150,000 | 0.15 | |
| Read 1 MB sequentially from memory | 250,000 | 0.25 | |
| Round trip within same datacenter | 500,000 | 0.5 | |
| Read 1 MB sequentially from SSD* | 1,000,000 | 1 | 4X memory |
| Disk seek | 10,000,000 | 10 | 20x datacenter RT |
| Read 1 MB sequentially from disk | 20,000,000 | 20 | 80x memory, 20X SSD |
| Send packet CA->Netherlands->CA | 150,000,000 | 150 |
Good hash table design : 00:49:00