Thing Done

← The fleet

PIC18F57Q84 vs Feather M4

PIC18F (PIC18F57Q84) at 64 MHz against Cortex-M4F (SAMD51) at 120 MHz, on real hardware, same C kernels, clocks verified.

PIC18F57Q84 Curiosity Nano

PIC18F57Q84

PIC18F (PIC18F57Q84)
Family
PIC / dsPIC
Board
PIC18F57Q84 Curiosity Nano
Clock
64 MHz
float / double
32-bit / 32-bit
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
Typical gap
70.2×
Feather M4 faster, geometric mean of 25 cells
Biggest win for PIC18F57Q84
0.06×
uint8_t add
Biggest win for Feather M4
464×
float divide
Clock for clock
37.5×
Feather M4 needs fewer cycles per op (1.88× clock gap)

Operation by operation

Every cell

How many times faster PIC18F57Q84 is than Feather M4, operations per second. Blue: PIC18F57Q84 ahead. Orange: Feather M4 ahead.

AddSubtractMultiplyDivideModulo
uint8_t 1/16.7× 538 k/s · 8.98 M/s 1/17.8× 504 k/s · 8.98 M/s 1/17.3× 520 k/s · 8.98 M/s 1/51.8× 135 k/s · 7.01 M/s 1/59.9× 106 k/s · 6.36 M/s
uint16_t 1/27.4× 328 k/s · 8.98 M/s 1/27.4× 328 k/s · 8.98 M/s 1/31.3× 287 k/s · 8.98 M/s 1/98.4× 62.1 k/s · 6.12 M/s 1/76.0× 70.6 k/s · 5.36 M/s
uint32_t 1/40.5× 240 k/s · 9.71 M/s 1/40.5× 240 k/s · 9.71 M/s 1/414× 23.5 k/s · 9.71 M/s 1/267× 24.5 k/s · 6.53 M/s 1/216× 28.6 k/s · 6.19 M/s
uint64_t not measurednot measurednot measurednot measurednot measured
float 1/240× 37.4 k/s · 8.98 M/s 1/283× 31.7 k/s · 8.98 M/s 1/398× 22.6 k/s · 8.98 M/s 1/464× 10.2 k/s · 4.73 M/s 1/43.8× 19.8 k/s · 866 k/s
double 1/32.0× 37.4 k/s · 1.2 M/s 1/37.6× 31.7 k/s · 1.19 M/s 1/75.5× 22.6 k/s · 1.7 M/s 1/123× 10.2 k/s · 1.26 M/s 1/21.5× 19.8 k/s · 425 k/s

Where they sit in the fleet

Keep comparing

Swap sides