Teensy 4.0 vs Feather M4
Cortex-M7 (i.MX RT1062) at 600 MHz against Cortex-M4F (SAMD51) at 120 MHz, on real hardware, same C kernels, clocks verified.
Teensy 4.0
Cortex-M7 (i.MX RT1062)
- Family
- Arm Cortex-M
- Board
- Teensy 4.0
- Clock
- 600 MHz
- float / double
- 32-bit / 64-bit
Feather M4
Cortex-M4F (SAMD51)
- Family
- Arm Cortex-M
- Board
- Feather M4 Express
- Clock
- 120 MHz
- float / double
- 32-bit / 64-bit
Typical gap
9.28×
Teensy 4.0 faster, geometric mean of 30 cells
Biggest win for Teensy 4.0
46.8×
double add
Closest cell
5.62×
uint32_t modulo
Clock for clock
1.86×
Teensy 4.0 needs fewer cycles per op (5.00× clock gap)
Operation by operation
Every cell
How many times faster Teensy 4.0 is than Feather M4, operations per second. Blue: Teensy 4.0 ahead. Orange: Feather M4 ahead.
| Add | Subtract | Multiply | Divide | Modulo | |
|---|---|---|---|---|---|
| uint8_t | 8.62× 77.4 M/s · 8.98 M/s | 8.38× 75.3 M/s · 8.98 M/s | 8.38× 75.3 M/s · 8.98 M/s | 7.46× 52.3 M/s · 7.01 M/s | 7.28× 46.3 M/s · 6.36 M/s |
| uint16_t | 8.38× 75.3 M/s · 8.98 M/s | 8.35× 75 M/s · 8.98 M/s | 7.64× 68.6 M/s · 8.98 M/s | 6.78× 41.5 M/s · 6.12 M/s | 6.99× 37.5 M/s · 5.36 M/s |
| uint32_t | 8.52× 82.8 M/s · 9.71 M/s | 8.83× 85.7 M/s · 9.71 M/s | 7.06× 68.6 M/s · 9.71 M/s | 6.02× 39.3 M/s · 6.53 M/s | 5.62× 34.8 M/s · 6.19 M/s |
| uint64_t | 10.2× 63.2 M/s · 6.19 M/s | 10.2× 63.2 M/s · 6.19 M/s | 7.79× 43.7 M/s · 5.61 M/s | 6.26× 5.54 M/s · 885 k/s | 6.26× 5.54 M/s · 885 k/s |
| float | 8.66× 77.7 M/s · 8.98 M/s | 8.66× 77.7 M/s · 8.98 M/s | 8.66× 77.7 M/s · 8.98 M/s | 5.71× 27 M/s · 4.73 M/s | 7.70× 6.67 M/s · 866 k/s |
| double | 46.8× 56 M/s · 1.2 M/s | 45.9× 54.7 M/s · 1.19 M/s | 25.7× 43.7 M/s · 1.7 M/s | 12.5× 15.7 M/s · 1.26 M/s | 11.4× 4.84 M/s · 425 k/s |