Enhance the statistic of wasm function execution time, or the performance
profiling feature:
- Add os_time_thread_cputime_us() to get the cputime of a thread,
and use it to calculate the execution time of a wasm function
- Support the statistic of the children execution time of a function,
and dump it in wasm_runtime_dump_perf_profiling
- Expose two APIs:
wasm_runtime_sum_wasm_exec_time
wasm_runtime_get_wasm_func_exec_time
And rename os_time_get_boot_microsecond to os_time_get_boot_us.
The wamrc execution errors were skipped in the runtest.py due to `sys.exit(1)`
was caught by upper try-catch sentence and ignored with ret_code 0 returned.
This PR fixed this script issue and fixed the related wamrc/GC issues found.
Currently, `data.drop` instruction is implemented by directly modifying the
underlying module. It breaks use cases where you have multiple instances
sharing a single loaded module. `elem.drop` has the same problem too.
This PR fixes the issue by keeping track of which data/elem segments have
been dropped by using bitmaps for each module instances separately, and
add a sample to demonstrate the issue and make the CI run it.
Also add a missing check of dropped elements to the fast-jit `table.init`.
Fixes: https://github.com/bytecodealliance/wasm-micro-runtime/issues/2735
Fixes: https://github.com/bytecodealliance/wasm-micro-runtime/issues/2772
When labels-as-values is enabled in a target which doesn't support
unaligned address access, 16-bit offset is used to store the relative
offset between two opcode labels. But it is a little small and the loader
may report "pre-compiled label offset out of range" error.
Emitting 32-bit data instead to resolve the issue: emit label address in
32-bit target and emit 32-bit relative offset in 64-bit target.
See also:
https://github.com/bytecodealliance/wasm-micro-runtime/issues/2635
This PR implements the WebAssembly stringref proposal:
https://github.com/WebAssembly/stringref
It adds cmake variable `WAMR_BUILD_STRINGREF` to build the feature,
which will enable GC automatically.
The stringref contains two parts:
- `part 1`: add new ref types in WasmGC, add opcode processing in loader and interpreter
- `part 2`: add a library for string representation/encoding/decoding and so on
To reduce the code size introduced to WAMR, this PR only includes `part 1`,
`part 2` can be provided by embedder, they may use their own implementation,
e.g., Wasmnizer-ts uses JSString from QuickJS to implement stringref:
https://github.com/intel/Wasmnizer-ts/blob/main/runtime-library/stringref/stringref_qjs.c
We will submit another PR of `part 2` and make it as a sample rather than WAMR core part.
Signed-off-by: Su Yihan <yihan.su@intel.com>
Co-authored-by: Xu Jun <jun1.xu@intel.com>
Avoid the stack traces getting mixed up together when multi-threading is enabled
by using exception_lock/unlock in dumping the call stacks.
And remove duplicated call stack dump in wasm_application.c.
Also update coding guideline CI to fix the clang-format-12 not found issue.
- Inherit shared memory from the parent instance, instead of
trying to look it up by the underlying module. The old method
works correctly only when every cluster uses different module.
- Use reference count in WASMMemoryInstance/AOTMemoryInstance
to mark whether the memory is shared or not
- Retire WASMSharedMemNode
- For atomic opcode implementations in the interpreters, use
a global lock for now
- Update the internal API users
(wasi-threads, lib-pthread, wasm_runtime_spawn_thread)
Fixes https://github.com/bytecodealliance/wasm-micro-runtime/issues/1962
We have observed a significant performance degradation after merging
https://github.com/bytecodealliance/wasm-micro-runtime/pull/1991
Instead of protecting suspend flags with a mutex, we implement the flags
as atomic variable and only use mutex when atomics are not available
on a given platform.
Allow to use `cmake -DWAMR_CONFIGURABLE_BOUNDS_CHECKS=1` to
build iwasm, and then run `iwasm --disable-bounds-checks` to disable the
memory access boundary checks.
And add two APIs:
`wasm_runtime_set_bounds_checks` and `wasm_runtime_is_bounds_checks_enabled`
Segue is an optimization technology which uses x86 segment register to store
the WebAssembly linear memory base address, so as to remove most of the cost
of SFI (Software-based Fault Isolation) base addition and free up a general
purpose register, by this way it may:
- Improve the performance of JIT/AOT
- Reduce the footprint of JIT/AOT, the JIT/AOT code generated is smaller
- Reduce the compilation time of JIT/AOT
This PR uses the x86-64 GS segment register to apply the optimization, currently
it supports linux and linux-sgx platforms on x86-64 target. By default it is disabled,
developer can use the option below to enable it for wamrc and iwasm(with LLVM
JIT enabled):
```bash
wamrc --enable-segue=[<flags>] -o output_file wasm_file
iwasm --enable-segue=[<flags>] wasm_file [args...]
```
`flags` can be:
i32.load, i64.load, f32.load, f64.load, v128.load,
i32.store, i64.store, f32.store, f64.store, v128.store
Use comma to separate them, e.g. `--enable-segue=i32.load,i64.store`,
and `--enable-segue` means all flags are added.
Acknowledgement:
Many thanks to Intel Labs, UC San Diego and UT Austin teams for introducing this
technology and the great support and guidance!
Signed-off-by: Wenyong Huang <wenyong.huang@intel.com>
Co-authored-by: Vahldiek-oberwagner, Anjo Lucas <anjo.lucas.vahldiek-oberwagner@intel.com>
Load memory data size in each time memory access boundary check in
multi-threading mode since it may be changed by other threads when
memory growing.
And use `memory->memory_data_size` instead of
`memory->num_bytes_per_page * memory->cur_page_count` to refine
the code.
Use the shared memory's shared_mem_lock to lock the whole atomic.wait and
atomic.notify processes, and use it for os_cond_reltimedwait and os_cond_notify,
so as to make the whole processes actual atomic operations:
the original implementation accesses the wait address with shared_mem_lock
and uses wait_node->wait_lock for os_cond_reltimedwait, which is not an atomic
operation.
And remove the unnecessary wait_map_lock and wait_lock, since the whole
processes are already locked by shared_mem_lock.
