Pi Pico 2W (RISC-V) vs Feather M4
Hazard3 RV32IMAC (RP2350) at 150 MHz against Cortex-M4F (SAMD51) at 120 MHz, on real hardware, same C kernels, clocks verified.
Pi Pico 2W (RISC-V)
Hazard3 RV32IMAC (RP2350)
- Family
- RISC-V
- Board
- Pi Pico 2W (RISC-V)
- Clock
- 150 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
1.19×
Feather M4 faster, geometric mean of 30 cells
Biggest win for Pi Pico 2W (RISC-V)
1.72×
double modulo
Biggest win for Feather M4
6.24×
float divide
Clock for clock
1.48×
Feather M4 needs fewer cycles per op (1.25× clock gap)
Operation by operation
Every cell
How many times faster Pi Pico 2W (RISC-V) is than Feather M4, operations per second. Blue: Pi Pico 2W (RISC-V) ahead. Orange: Feather M4 ahead.
| Add | Subtract | Multiply | Divide | Modulo | |
|---|---|---|---|---|---|
| uint8_t | 1.36× 12.2 M/s · 8.98 M/s | 1.48× 13.3 M/s · 8.98 M/s | 1.48× 13.3 M/s · 8.98 M/s | 1/1.32× 5.3 M/s · 7.01 M/s | 1/1.20× 5.3 M/s · 6.36 M/s |
| uint16_t | 1.26× 11.3 M/s · 8.98 M/s | 1.26× 11.3 M/s · 8.98 M/s | 1.17× 10.5 M/s · 8.98 M/s | 1/1.24× 4.94 M/s · 6.12 M/s | 1/1.12× 4.79 M/s · 5.36 M/s |
| uint32_t | 1.26× 12.2 M/s · 9.71 M/s | 1.16× 11.3 M/s · 9.71 M/s | 1.16× 11.3 M/s · 9.71 M/s | 1/1.32× 4.94 M/s · 6.53 M/s | 1/1.25× 4.94 M/s · 6.19 M/s |
| uint64_t | 1.32× 8.2 M/s · 6.19 M/s | 1.32× 8.2 M/s · 6.19 M/s | 1.32× 7.39 M/s · 5.61 M/s | 1/1.08× 822 k/s · 885 k/s | 1/1.11× 794 k/s · 885 k/s |
| float | 1/3.69× 2.43 M/s · 8.98 M/s | 1/3.69× 2.43 M/s · 8.98 M/s | 1/3.02× 2.98 M/s · 8.98 M/s | 1/6.24× 758 k/s · 4.73 M/s | 1.32× 1.14 M/s · 866 k/s |
| double | 1.01× 1.21 M/s · 1.2 M/s | 1.04× 1.24 M/s · 1.19 M/s | 1/2.51× 678 k/s · 1.7 M/s | 1/3.20× 394 k/s · 1.26 M/s | 1.72× 731 k/s · 425 k/s |