Commit Graph

10 Commits

Author SHA1 Message Date
Crypt Keeper
e31856d360 updates external tool versions (#1498)
Signed-off-by: Adrian Cole <adrian@tetrate.io>
2023-06-02 15:53:29 +08:00
Crypt Keeper
8c7e0caead updates benchmark library versions (#1486)
Signed-off-by: Adrian Cole <adrian@tetrate.io>
2023-05-20 06:41:02 +02:00
Crypt Keeper
e55ac9b5e9 benchmark: bumps vs tests wasmtime and wasmedge to latest (#1097)
Signed-off-by: Adrian Cole <adrian@tetrate.io>
2023-02-03 11:27:05 +02:00
Crypt Keeper
d3c5e8655f Adds benchmarks from lib sodium (#948)
This adds benchmarks from lib sodium, but the results are hard to interpret. We may need to recompile them using zig so that we can export a function instead of using WASI to do it. Right now, we can't really see performance of functions because other runtimes aren't designed to re-instantiate like ours.

This only compares against wasmtime as that's the only runtime besides
ours that is safe to re-instantiate.

Signed-off-by: Adrian Cole <adrian@tetrate.io>
2022-12-21 09:17:13 +08:00
Crypt Keeper
126bd9050d Removes context parameter from instruction-scoped operations (#923)
We originally had a `context.Context` for anything that might be
traced, but it turned out to be only useful for lifecycle and host functions.

For instruction-scoped aspects like memory updates, a context parameter is too
fine-grained and also invisible in practice. For example, most users will use
the compiler engine, and its memory, global or table access will never use go's
context.

Signed-off-by: Adrian Cole <adrian@tetrate.io>
2022-12-14 16:08:07 +09:00
Crypt Keeper
d108ce4c43 Restores ability to define host functions w/o context via reflection (#832)
This restores the ability to leave out the initial context parameter
when defining functions with reflection. This is important because some
projects are porting from a different library to wazero, and all the
alternatives are not contextualized.

For example, this project is porting envoy host functions, and the
original definitions (in mosn) don't have a context parameter. By being
lenient, they can migrate easier.

See 6b813482b6/pkg/proxywasm/wazero/imports_v1.go

Signed-off-by: Adrian Cole <adrian@tetrate.io>
2022-10-28 12:44:12 -07:00
Takeshi Yoneda
62520e4ea8 vs: adds the benchmark on i32/i64 load/store insts (#766)
Signed-off-by: Takeshi Yoneda <takeshi@tetrate.io>
2022-08-26 07:32:05 +09:00
Takeshi Yoneda
50cef32ae0 vs: adds the benchmark to see the cost of host function calls (#756)
This adds the new vs target to measure the cost of host function calls.
Notably, I can see that wazero is roughly 2x to 4x times faster than CGO-based
runtimes in terms of host call boundary crossing. One implication here is that
we can just focus on the native code generation rather than how to organize the
Go function calls. For example, it's not prioritized to call Go functions directly
from the native code.

Signed-off-by: Takeshi Yoneda <takeshi@tetrate.io>
2022-08-22 16:53:58 +09:00
Matt Turner
7d071a45d7 Enable comparative benchmark builds on darwin/aarch64 (ie Apple Silicon) (#746)
Enable for Wasmer, as confirmed that the version we use has arm64 support.
Enable for Wasmtime after bumping to a version which supports arm64.
Don't enable for wasm-edge as they don't support arm64/darwin.
2022-08-17 07:33:40 +08:00
Crypt Keeper
0a39438138 benchmark: Adds allocation benchmark and splits runtimes (#507)
Signed-off-by: Adrian Cole <adrian@tetrate.io>
2022-04-26 13:44:50 +08:00