Thing Done

← The fleet

Teensy 4.0

Cortex-M7 (i.MX RT1062) · Arm Cortex-M · 600 MHz

Teensy 4.0
Board
Teensy 4.0
Core
Cortex-M7 (i.MX RT1062)
Clock
600 MHz
float / double
32-bit / 64-bit
uint8_t add
77.4 M/s
rank 1 of 16 · 12.9 ns
uint32_t add
82.8 M/s
rank 1 of 16 · 12.1 ns
uint32_t divide
39.3 M/s
rank 1 of 16 · 25.4 ns
float multiply
77.7 M/s
rank 1 of 16 · 12.9 ns
Cycles per uint32 add
7.25 cycles
rank 1 of 16 — the clock-independent number

What every operation costs

Every numeric type, all five operations, as clock cycles per operation: the shape of this part's cost independent of its clock. The bars are the story of where it falls off a cliff — divide, 64-bit, floating point.

The same cells as nanoseconds per operation, median of three samples. Darker is slower; the small number is this board's rank in the fleet for that cell (1 = fastest of 16).

AddSubtractMultiplyDivideModulo
uint8_t 12.9 ns #1 of 16 13.3 ns #1 of 16 13.3 ns #1 of 16 19.1 ns #1 of 16 21.6 ns #1 of 16
uint16_t 13.3 ns #1 of 16 13.3 ns #1 of 16 14.6 ns #1 of 16 24.1 ns #1 of 16 26.7 ns #1 of 16
uint32_t 12.1 ns #1 of 16 11.7 ns #1 of 16 14.6 ns #1 of 16 25.4 ns #1 of 16 28.7 ns #1 of 16
uint64_t 15.8 ns #1 of 14 15.8 ns #1 of 14 22.9 ns #1 of 14 180 ns #1 of 14 180 ns #1 of 14
float 12.9 ns #1 of 16 12.9 ns #1 of 16 12.9 ns #1 of 16 37 ns #1 of 16 150 ns #1 of 16
double 17.9 ns #1 of 16 18.3 ns #1 of 16 22.9 ns #1 of 16 63.8 ns #1 of 16 207 ns #1 of 16

In the fleet

Head to head