Feather M4 vs MSP430FR2433
Cortex-M4F (SAMD51) at 120 MHz against MSP430FRx (MSP430FR2433) at 15.99 MHz, on real hardware, same C kernels, clocks verified.
Feather M4
Cortex-M4F (SAMD51)
- Family
- Arm Cortex-M
- Board
- Feather M4 Express
- Clock
- 120 MHz
- float / double
- 32-bit / 64-bit
MSP430FR2433
MSP430FRx (MSP430FR2433)
- Family
- MSP430
- Board
- MSP-EXP430FR2433 LaunchPad
- Clock
- 15.99 MHz
- float / double
- 32-bit / 64-bit
Typical gap
93.7×
Feather M4 faster, geometric mean of 30 cells
Biggest win for Feather M4
1,808×
double multiply
Closest cell
13.9×
uint16_t add
Clock for clock
12.5×
Feather M4 needs fewer cycles per op (7.50× clock gap)
Operation by operation
Every cell
How many times faster Feather M4 is than MSP430FR2433, operations per second. Blue: Feather M4 ahead. Orange: MSP430FR2433 ahead.
| Add | Subtract | Multiply | Divide | Modulo | |
|---|---|---|---|---|---|
| uint8_t | 14.5× 8.98 M/s · 621 k/s | 15.0× 8.98 M/s · 598 k/s | 31.0× 8.98 M/s · 290 k/s | 81.1× 7.01 M/s · 86.4 k/s | 74.0× 6.36 M/s · 86 k/s |
| uint16_t | 13.9× 8.98 M/s · 646 k/s | 14.4× 8.98 M/s · 622 k/s | 29.1× 8.98 M/s · 309 k/s | 90.9× 6.12 M/s · 67.3 k/s | 80.1× 5.36 M/s · 67 k/s |
| uint32_t | 26.2× 9.71 M/s · 370 k/s | 24.4× 9.71 M/s · 397 k/s | 46.3× 9.71 M/s · 210 k/s | 283× 6.53 M/s · 23.1 k/s | 269× 6.19 M/s · 23 k/s |
| uint64_t | 41.1× 6.19 M/s · 151 k/s | 45.2× 6.19 M/s · 137 k/s | 59.5× 5.61 M/s · 94.3 k/s | 218× 885 k/s · 4.06 k/s | 174× 885 k/s · 5.1 k/s |
| float | 534× 8.98 M/s · 16.8 k/s | 553× 8.98 M/s · 16.2 k/s | 1,534× 8.98 M/s · 5.85 k/s | 405× 4.73 M/s · 11.7 k/s | 40.8× 866 k/s · 21.3 k/s |
| double | 146× 1.2 M/s · 8.18 k/s | 153× 1.19 M/s · 7.8 k/s | 1,808× 1.7 M/s · 942 /s | 601× 1.26 M/s · 2.1 k/s | 48.4× 425 k/s · 8.79 k/s |