Thing Done

← The fleet

Feather M4 vs Nucleo G474RE

Cortex-M4F (SAMD51) at 120 MHz against Cortex-M4F (STM32G474) at 170 MHz, on real hardware, same C kernels, clocks verified.

Feather M4 Express

Feather M4

Cortex-M4F (SAMD51)
Family
Arm Cortex-M
Board
Feather M4 Express
Clock
120 MHz
float / double
32-bit / 64-bit
Nucleo G474RE

Nucleo G474RE

Cortex-M4F (STM32G474)
Family
Arm Cortex-M
Board
Nucleo G474RE
Clock
170 MHz
float / double
32-bit / 64-bit
Typical gap
1.32×
Nucleo G474RE faster, geometric mean of 30 cells
Biggest win for Feather M4
0.84×
uint64_t multiply
Biggest win for Nucleo G474RE
1.62×
double modulo
Clock for clock
1.07×
Feather M4 needs fewer cycles per op (1.42× clock gap)

Operation by operation

Every cell

How many times faster Feather M4 is than Nucleo G474RE, operations per second. Blue: Feather M4 ahead. Orange: Nucleo G474RE ahead.

AddSubtractMultiplyDivideModulo
uint8_t 1/1.31× 8.98 M/s · 11.7 M/s 1/1.31× 8.98 M/s · 11.7 M/s 1/1.31× 8.98 M/s · 11.7 M/s 1/1.28× 7.01 M/s · 8.96 M/s 1/1.27× 6.36 M/s · 8.1 M/s
uint16_t 1/1.31× 8.98 M/s · 11.7 M/s 1/1.31× 8.98 M/s · 11.7 M/s 1/1.31× 8.98 M/s · 11.7 M/s 1/1.34× 6.12 M/s · 8.2 M/s 1/1.41× 5.36 M/s · 7.56 M/s
uint32_t 1/1.30× 9.71 M/s · 12.6 M/s 1/1.30× 9.71 M/s · 12.6 M/s 1/1.30× 9.71 M/s · 12.6 M/s 1/1.34× 6.53 M/s · 8.73 M/s 1/1.34× 6.19 M/s · 8.3 M/s
uint64_t 1/1.22× 6.19 M/s · 7.56 M/s 1/1.22× 6.19 M/s · 7.56 M/s 1/1.19× 5.61 M/s · 6.67 M/s 1/1.31× 885 k/s · 1.16 M/s 1/1.31× 885 k/s · 1.16 M/s
float 1/1.31× 8.98 M/s · 11.7 M/s 1/1.31× 8.98 M/s · 11.7 M/s 1/1.31× 8.98 M/s · 11.7 M/s 1/1.36× 4.73 M/s · 6.42 M/s 1/1.55× 866 k/s · 1.34 M/s
double 1/1.32× 1.2 M/s · 1.58 M/s 1/1.32× 1.19 M/s · 1.58 M/s 1/1.30× 1.7 M/s · 2.22 M/s 1/1.33× 1.26 M/s · 1.67 M/s 1/1.62× 425 k/s · 688 k/s

Where they sit in the fleet

Keep comparing

Swap sides