ESP32

Xtensa LX6 (ESP32) · Xtensa · 240 MHz

Board: ESP32
Core: Xtensa LX6 (ESP32)
Clock: 240 MHz
float / double: 32-bit / 64-bit

uint8_t add

11.4 M/s

rank 9 of 16 · 87.4 ns

uint32_t add

12 M/s

rank 7 of 16 · 83.3 ns

uint32_t divide

10 M/s

rank 3 of 16 · 100 ns

float multiply

12 M/s

rank 4 of 16 · 83.4 ns

Cycles per uint32 add

20.0 cycles

rank 11 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).

	Add	Subtract	Multiply	Divide	Modulo
uint8_t	87.4 ns #9 of 16	87.4 ns #9 of 16	87.6 ns #8 of 16	95.8 ns #3 of 16	100 ns #3 of 16
uint16_t	87.4 ns #6 of 16	87.4 ns #6 of 16	87.4 ns #6 of 16	107 ns #3 of 16	111 ns #3 of 16
uint32_t	83.3 ns #7 of 16	83.3 ns #5 of 16	83.3 ns #6 of 16	100 ns #3 of 16	104 ns #3 of 16
uint64_t	142 ns #8 of 14	144 ns #8 of 14	209 ns #9 of 14	572 ns #4 of 14	592 ns #4 of 14
float	83.4 ns #4 of 16	83.4 ns #4 of 16	83.4 ns #4 of 16	263 ns #6 of 16	578 ns #5 of 16
double	338 ns #5 of 16	373 ns #5 of 16	536 ns #6 of 16	2.18 µs #9 of 16	904 ns #5 of 16

ESP32

What every operation costs

In the fleet

Head to head