Performance

Performance and memory

Test date: 4/13/2020

X86 platform:

CPU：Intel(R) Core(TM) i7-7700 CPU @ 3.60GHz
OS ：ubuntu 18.04
Compiler：gcc version 7.4.0 (Ubuntu 7.4.0-1ubuntu1~18.04.1), flag: O3

performance comparison:

workload	wamr-aot / wasm3	wasm3 / wamr-interpreter	wamr-aot / GCC(O3)	wamr interpreters (fast/classic)
matrix	7.8	1.12	0.33	2.3
gimli	9.3	1.03	0.87	2.7
CoreMark	6.0	1.33	0.52	2.5

Note：

• WAMR provides two interpreters - the fast version for advanced performance and and the classic version smaller footprint respectively.
• Workload CoreMark is measured by its reported scores, and other workloads matrix and gimli are measured by the execution time.

ARMV7 Cortex-M7:

Board: nucleo_f767zi (ARMV7 Cortex-M7)
OS : Zephyr
Compiler: arm-zephyr-eabi-gcc (crosstool-NG 1.24.0.37-3f461da-dirty) 9.2.0, Os

performance comparison:

workload	wamr-aot/wasm3	wasm3/wamr-interpreter	wamr interpreters (fast/classic)
matrix	24.3	1.09	1.75
gimli	20.8	1.08	2.06
seqhash	10.2	1.15	1.46

Memory consumption

workload: CoreMark
measurement tool: valgrind/massif

WASM interpreter	Peak memory usage
WAMR classic	288KB
WAMR fast	363KB
wasm3	522KB

WASM application binary size

Compilation option: -Os

Workload	GCC compiled native binary (KB)	Wasm bytecode (KB)	iwasm-aot module (KB)**
coremark	23120	10479	24496
base64	10224	6284	7236
gimli	10224	905	2240

Misc.

The page is also a response to the data published by wasm3 at https://github.com/wasm3/wasm3/blob/master/docs/Performance.md.

Some background of the performance comparison between WAMR and wasm3:

https://github.com/bytecodealliance/wasm-micro-runtime/issues/134