ESP32-S3 vs Pi Pico 2W (RISC-V)
Xtensa LX7 (ESP32-S3) at 240 MHz against Hazard3 RV32IMAC (RP2350) at 150 MHz, on real hardware, same C kernels, clocks verified.
ESP32-S3
Xtensa LX7 (ESP32-S3)
- Family
- Xtensa
- Board
- ESP32-S3 DevKit
- Clock
- 240 MHz
- float / double
- 32-bit / 64-bit
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
Typical gap
1.75×
ESP32-S3 faster, geometric mean of 30 cells
Biggest win for ESP32-S3
5.21×
float add
Biggest win for Pi Pico 2W (RISC-V)
1.36×
uint64_t multiply
Clock for clock
1.10×
ESP32-S3 needs fewer cycles per op (1.60× clock gap)
Operation by operation
Every cell
How many times faster ESP32-S3 is than Pi Pico 2W (RISC-V), operations per second. Blue: ESP32-S3 ahead. Orange: Pi Pico 2W (RISC-V) ahead.
| Add | Subtract | Multiply | Divide | Modulo | |
|---|---|---|---|---|---|
| uint8_t | 1.04× 12.7 M/s · 12.2 M/s | 1/1.05× 12.7 M/s · 13.3 M/s | 1/1.05× 12.7 M/s · 13.3 M/s | 2.17× 11.5 M/s · 5.3 M/s | 2.07× 10.9 M/s · 5.3 M/s |
| uint16_t | 1.12× 12.7 M/s · 11.3 M/s | 1.12× 12.7 M/s · 11.3 M/s | 1.21× 12.7 M/s · 10.5 M/s | 2.05× 10.1 M/s · 4.94 M/s | 2.03× 9.72 M/s · 4.79 M/s |
| uint32_t | 1.10× 13.4 M/s · 12.2 M/s | 1.19× 13.4 M/s · 11.3 M/s | 1.19× 13.4 M/s · 11.3 M/s | 2.21× 11 M/s · 4.94 M/s | 2.12× 10.5 M/s · 4.94 M/s |
| uint64_t | 1/1.04× 7.87 M/s · 8.2 M/s | 1/1.05× 7.81 M/s · 8.2 M/s | 1/1.36× 5.45 M/s · 7.39 M/s | 2.19× 1.8 M/s · 822 k/s | 2.19× 1.74 M/s · 794 k/s |
| float | 5.21× 12.7 M/s · 2.43 M/s | 5.21× 12.7 M/s · 2.43 M/s | 4.26× 12.7 M/s · 2.98 M/s | 4.59× 3.48 M/s · 758 k/s | 1.71× 1.95 M/s · 1.14 M/s |
| double | 2.51× 3.04 M/s · 1.21 M/s | 2.24× 2.79 M/s · 1.24 M/s | 2.95× 2 M/s · 678 k/s | 1.31× 516 k/s · 394 k/s | 1.67× 1.22 M/s · 731 k/s |