1499 Commits

Author	SHA1	Message	Date
Joe Polny	4b42cfdbce	fix: remove stack size check from exec_env_check (#4688) ... As per [this blogpost](https://bytecodealliance.github.io/wamr.dev/blog/understand-the-wamr-stacks/) WAMR does not require a WASM stack in AoT/JIT mode, but `wasm_runtime_exec_env_check` still always expects the size to be > 0	2025-11-05 08:10:02 +08:00
Joe Polny	238f45dddc	docs: clarify that * in signatures does address conversion (#4681) ... docs: clarify that * and $ in signatures does address conversion It was non-obvious that `*` means the runtime does the app to native conversion automatically. With the current docstring, one might assume that the runtime only does boundary checks and not address conversion. Under this assumption, passing the already-native address to `wasm_runtime_addr_app_to_native` will lead to unexpected behavior	2025-10-31 15:41:35 +08:00
YAMAMOTO Takashi	3b8b265f1f	Pass InstantiationArgs2 down to aot_instantiate/wasm_instantiate (#4594) ... This is a preparation for https://github.com/bytecodealliance/wasm-micro-runtime/issues/4364 No functional changes are intended.	2025-10-23 15:57:50 +08:00
Xenia Lu	4c371e655a	fix: false OOB in array.fill for interp (#4645) ... * cherry-pick gc spec test case * Fix false OOB in array.fill	2025-10-23 13:15:42 +08:00
Liu Jia	0ecaf8c7da	add validation of dynamic_offset (#4563) ... * add check_dynamic_offset_pop	2025-10-23 11:27:30 +08:00
Xenia Lu	3bf08a0eda	loader: fix block/loop ref params type checking (#4647) ... * loader: fix block/loop ref params type checking	2025-10-16 10:20:50 +08:00
Xenia Lu	d25fdc3709	fix: typo in AOT stack dump with GC (#4657)	2025-10-16 10:20:16 +08:00
liang.he	826ae6eb01	Prevent BuildPhi from encountering a null llvm_entry_block (#4663) ... There is a scenario where `aot_compile_op_block()` does not prepare a block for `if`. As a result, the return value of `LLVMBuildPhi()` in `push_aot_block_to_stack_and_pass_params()` will be dangling, leading to a memory leak as it cannot be released.	2025-10-16 10:19:44 +08:00
Liu Jia	d7b6bc5aca	Add a watchdog to prevent the similar crash in AOT mode (#4625)	2025-10-12 20:18:25 +08:00
Aiden Grossman	df908048de	Switch from deprecated overload of createTargetMachine (#4650) ... The overload accepting the string version of a triple will be removed soon, so switch over to the one that accepts a triple object. https://github.com/llvm/llvm-project/pull/161053	2025-10-09 13:33:11 +08:00
Hiroshi Hatake	1b9542830e	Implement invokeNative asm code for armasm64 assembler on ARM64 Windows (#4636) ... * Implement invokeNative asm code for armasm64 assembler on ARM64 Windows * Use more solid wrapper for armasm64 executable Signed-off-by: Hiroshi Hatake <cosmo0920.oucc@gmail.com>	2025-10-09 12:09:00 +08:00
Zhenwei Jin	74cdf0b8c1	Add import functions callback (#4606) ... Signed-off-by: zhenweijin <zhenwei.jin@intel.com>	2025-10-09 12:04:29 +08:00
Liu Jia	326eeec615	Add new cases in ARC relocation of AOT (#4653) ... * add new case for arc relocation. R_ARC_S21H_PCREL, R_ARC_S21W_PCREL	2025-10-09 11:35:12 +08:00
James Marsh	5ba1b331c3	Add missing condition for V128 in WASM_OP_TEE_LOCAL	2025-09-24 13:29:15 +01:00
Liu Jia	95f506a6e7	Merge commit from fork ... * fix overflow in check_bulk_memory_overflow * add comment	2025-09-15 15:19:51 +08:00
Zhenwei Jin	e6fe6060e4	add micro AMR_BUILD_LIME1 to enable minimal lime1 feature set (#4571) ... Signed-off-by: zhenweijin <zhenwei.jin@intel.com>	2025-09-14 14:08:27 +08:00
YAMAMOTO Takashi	5e779b3d7b	libc-wasi: add missing pointer validations to socket functions (#4611) ... cf. https://github.com/bytecodealliance/wasm-micro-runtime/issues/4463 the fix for sock_addr_resolve is incomplete. cf. https://github.com/bytecodealliance/wasm-micro-runtime/issues/4610	2025-09-14 14:02:48 +08:00
YAMAMOTO Takashi	4f86468670	wasi-nn: retire is_model_loaded flag (#4613) ... this flag doesn't make much sense anymore because: - backends validate given graph/ctx by themselves - some of them support loading multiple models for a context	2025-09-14 14:01:55 +08:00
liang.he	ad21524573	fix: few CI errors caused by recently enabled compilation flags (#4620) ... - add missing warning for incompatible pointer types in CMake configuration - fix a shadow warning	2025-09-12 16:00:23 +08:00
TianlongLiang	d7afa4c0cf	Enable -Wdouble-promotion by default and fix related warnings (#4603) ... - fix float to double implicit conversion - add isnanf and signbitf macros, map them to existing double version when float versions are absent - enable -Wdouble-promotion by default - define isnan as macro for platform use core\sahred\platform\common\math.c	2025-09-12 08:44:42 +08:00
Lukas Döllerer	0d3b5caff0	Add support for metadata.code.branch_hint section (#4460) ... Add support for metadata.code.branch_hint section	2025-09-12 08:42:48 +08:00
liang.he	e2cf59cc26	Fix an undefined reference problem (#4612) ... The issue was previously covered by WAMR_BUILD_LIBC_BUILTIN and WAMR_BUILD_LIBC_WASI. Reproduced by ``` $ cmake -S . -B build -DWAMR_BUILD_SHARE_HEAP=1 -DWAMR_BUILD_LIBC_BUILTIN=0 -DWAMR_BUILD_LIBC_WASI=0 $ cmake --build build ```	2025-09-11 06:32:15 +08:00
YAMAMOTO Takashi	7263a04e43	wasi-nn: add a missing address validation for get_output (#4535) ... cf. https://github.com/bytecodealliance/wasm-micro-runtime/issues/4533	2025-09-11 06:31:22 +08:00
YAMAMOTO Takashi	6253bd1b52	Reduce the code duplication a bit (#4596) ... This is a preparation for https://github.com/bytecodealliance/wasm-micro-runtime/issues/4364 No functional changes are intended.	2025-09-04 10:58:09 +08:00
Zhenwei Jin	d55852d992	fix potential overflow in memory size calculation (#4549) ... Signed-off-by: zhenweijin <zhenwei.jin@intel.com>	2025-09-02 08:33:06 +08:00
liang.he	9cb1cc4af6	fix: cast file descriptor to size_t for comparison in fd_prestats functions (#4582) ... ``` comparison of integer expressions of different signedness: ‘__wasi_fd_t’ {aka ‘int’} and ‘size_t’ {aka ‘long unsigned int’} [-Werror=sign-compare] 288 | if (fd >= pt->size) ```	2025-08-27 07:15:08 +08:00
liang.he	0b97d0cb14	Merge dev/zephyr_file_socket into main (#4347) ... zephyr: Enable WASI support for file system and sockets on zephyr (#3633) This work also implements the WASI support on Zephyr. * Added os_is_* methods for stdin/stdout/stderr. Fixed issues in os_renameat * Zephyr platform fixes for WASI sockets Addressed numerous of build warnings on Zephyr * Updated `os_writev` to use `fwrite` for STDOUT/STDERR * Temporarily reverted change to `writev` to work around an issue. * Fixes: fstat, fstatat, and unlink * Add initial support for directories in os_openat. Partial implementation — just avoids a hard fault. * Directory support WIP. readdir works but I think we have a memory leak somewhere * Fix: always use standard stream fds. Fix unlinkat and renameat. fd 0, 1, and 2 will always be supplied for standard streams. Unlinkat and renameat work exclusively based on supplied paths. * Fix: use macro for free() * Added a temporary workaround for issue identified in PR#4377 * Fixed reference to file descriptor and cleaned up dead/commented code. Note that some comments haven't been addressed and will be fixed in the further patches. Signed-off-by: Stephen Berard <stephen.berard@outlook.com> Co-authored-by: Lucas Abad <149054121+lucasAbadFr@users.noreply.github.com> Co-authored-by: Stephen Berard <srberard@users.noreply.github.com> Co-authored-by: Dan Kouba <dan@atym.io>	2025-08-25 16:55:23 +08:00
Marcin Kolny	58fae578e7	Merge pull request #4568 from yamt/nn-51 ... core/iwasm/libraries/wasi-nn/test/build.sh: set -e	2025-08-20 20:53:35 +02:00
James Marsh	9ee44bf2d0	Add Android macro check for indirect mode	2025-08-20 13:13:56 +01:00
YAMAMOTO Takashi	735b510437	core/iwasm/libraries/wasi-nn/test/build.sh: set -e	2025-08-19 14:58:27 +09:00
Liu Jia	b0dae624a1	add comments about AOT crash when calling unlinked import func (#4559)	2025-08-19 08:53:51 +08:00
Zhenwei Jin	be3f1f88fe	remove duplicate parent type index validation (#4556) ... Signed-off-by: zhenweijin <zhenwei.jin@intel.com>	2025-08-19 08:53:44 +08:00
Zhenwei Jin	ab2ff4a56d	add rec idx and rec count validation in aot loader (#4555) ... Signed-off-by: zhenweijin <zhenwei.jin@intel.com>	2025-08-19 08:53:37 +08:00
YAMAMOTO Takashi	c661592edd	wasi_nn_onnx.cpp: fix debug build (#4564)	2025-08-19 08:23:00 +08:00
dongsheng28849455	14ced7c86c	Add onnxruntime as wasi-nn backend (#4485) ... * Add onnxruntime as wasi-nn backend * remove global context * put checks under the lock * tensor type will not support legacy wasi-nn abi * Manually set the imported target with name space	2025-08-15 09:48:37 +08:00
Liu Jia	cbb6d03337	add validtion for parent_type_idx (#4550)	2025-08-13 11:05:06 +08:00
Zhenwei Jin	feecaf602e	add bounds checking to prevent ref_type_map_count (#4548) ... Signed-off-by: zhenweijin <zhenwei.jin@intel.com>	2025-08-13 08:17:42 +08:00
YAMAMOTO Takashi	bbf571e5af	wasi_socket_ext.c: fix a typo in a comment (#4552)	2025-08-13 08:14:58 +08:00
TianlongLiang	d95b0e3d46	add new relocation type (#4500)	2025-08-11 15:09:33 +08:00
Zhenwei Jin	2d05aece1a	add validation for struct field type (#4536)	2025-08-11 15:07:15 +08:00
YAMAMOTO Takashi	6b51c61f5e	wasi-nn: fix set_input memory address validation for the legacy abi (#4534) ... cf. https://github.com/bytecodealliance/wasm-micro-runtime/issues/3223	2025-08-06 10:40:56 +08:00
YAMAMOTO Takashi	5b63f3526d	core/iwasm/libraries/lib-socket/test/nslookup.c: use gai_strerror (#4532)	2025-08-05 08:39:35 +08:00
YAMAMOTO Takashi	29d465b44e	wasi_nn_tensorflowlite.cpp: make this compatible with wasmedge (#4517) ... for wasi_ephemeral_nn, * implement u8 input * stop dealing with quantization. * wasi-nn doesn't have a concept of quantization or pre/post-processing. i can't think of any ways to make the backend perform zero-point/scale processing without risking to break other applications. * there seems to be applications which just use u8 inputs/outputs for a quantized model. (see [1] for an example.) for certain kinds of inputs/outputs, it usually just works. this commit keeps the legacy wasi_nn logic intact for now. tested with [1] with [2] applied. WAMR with this patch: ``` Read graph weights, size in bytes: 3561598 [wasi_nn.c:297 WARNING] load_by_name_with_config() not found [wasi_nn_tensorflowlite.cpp:272 WARNING] Default encoding is CPU. Loaded graph into wasi-nn with ID: Graph#0 Read input tensor, size in bytes: 150528 1.) [166](198)Aix galericulata 2.) [34](1)Gallus gallus domesticus 3.) [158](1)Coccothraustes coccothraustes 4.) [778](1)Sitta europaea 5.) [819](1)Anas platyrhynchos ``` wasmedge: ``` Read graph weights, size in bytes: 3561598 Loaded graph into wasi-nn with ID: Graph#0 Read input tensor, size in bytes: 150528 1.) [166](198)Aix galericulata 2.) [34](1)Gallus gallus domesticus 3.) [158](1)Coccothraustes coccothraustes 4.) [778](1)Sitta europaea 5.) [819](1)Anas platyrhynchos ``` and "Aix galericulata" seems like a reasonable classification of the image to my eyes. [1] 67f174bab5/tflite-birds_v1-image [2] https://github.com/second-state/WasmEdge-WASINN-examples/pull/204 Related: https://github.com/bytecodealliance/wasm-micro-runtime/issues/3555 https://github.com/bytecodealliance/wasm-micro-runtime/issues/2611	2025-08-01 14:31:02 +08:00
Jaco Kroon	272a41dc80	Avoid executable stack by marking that it's not required. (#4418) ... Also refer to: https://github.com/fluent/fluent-bit/issues/10513 Signed-off-by: Jaco Kroon <jaco@uls.co.za>	2025-08-01 14:30:39 +08:00
Zhenwei Jin	378320b886	loader: add type index checking (#4521)	2025-08-01 08:58:26 +08:00
Zhenwei Jin	33eff933c0	add validation for rec indices in aot loader (#4520)	2025-08-01 08:45:57 +08:00
Zhenwei Jin	aad1866260	add validation for recursive type count in loader (#4522)	2025-07-31 16:19:08 +08:00
YAMAMOTO Takashi	a0de8c7b7d	wasi-nn: fix buffer overruns in load_by_name/load_by_name_with_config (#4491) ... also, ensure NUL terminations here to simplify backend implementations. (note that, although names with '\0' in the middle are usually valid in wasm, wamr doesn't support them in general. we might revisit this later.) also, add a missing address validation in load_by_name_with_config. cf. https://github.com/bytecodealliance/wasm-micro-runtime/issues/4487	2025-07-30 10:27:20 +08:00
TianlongLiang	b322e297c6	Add CLI option for iwasm to create and attach shared heap to wasm app (#4499)	2025-07-29 11:13:23 +08:00
YAMAMOTO Takashi	f34d28cfbc	lib-socket: implement gai_strerror (#4508) ... cf. https://pubs.opengroup.org/onlinepubs/9799919799/functions/gai_strerror.html	2025-07-29 11:12:27 +08:00
YAMAMOTO Takashi	d298a66d38	bump AOT_CURRENT_VERSION for extended-const (#4511) ... cf. https://github.com/bytecodealliance/wasm-micro-runtime/issues/4504	2025-07-27 14:39:35 +08:00
liang.he	121232a995	Merge commit from fork ... If `--addr-pool=1.2.3.4`, the runtime will return an error. The value must be in the form of ADDRESS/MASK.	2025-07-27 14:38:56 +08:00
YAMAMOTO Takashi	a780ffdc43	lib-socket: make getaddrinfo return EAI_ values (#4498) ... cf. https://github.com/bytecodealliance/wasm-micro-runtime/issues/4464	2025-07-21 09:21:31 +08:00
YAMAMOTO Takashi	e4d2673a7c	wasi-nn: add a comment on load_by_name_with_config (#4492) ... this api has been introduced by https://github.com/bytecodealliance/wasm-micro-runtime/pull/3709 in which i couldn't find any explanations. this comment is my best guess.	2025-07-17 09:50:49 +08:00
Liu Jia	704aa3e7e5	modify macro related to simde when WASM_OP_SELECT_128 (#4461) ... * remove macro of fast interpreter when WASM_OP_SELECT_128 * Modified some macros related to SIMDE	2025-07-17 08:04:41 +08:00
YAMAMOTO Takashi	db942f3aaf	wasi_socket_ext.c: fix error reporting ... do not return __WASI_ERRNO_xxx error code where 0/-1 is more appropriate. most of them were not harmful because the value of __WASI_ERRNO_SUCCESS is 0. the one with __WASI_ERRNO_NOPROTOOPT in socket() is a user-visible bug. tested with wamr-wasi-extensions/samples/socket-tcp-udp. cf. https://github.com/bytecodealliance/wasm-micro-runtime/issues/4474	2025-07-15 09:23:46 +02:00
YAMAMOTO Takashi	2a952b371a	wasi_socket_ext.c: fix the number of getaddrinfo results (#4466) ... the case of zero results was especially broken.	2025-07-14 13:12:32 +08:00
YAMAMOTO Takashi	53feadc2b0	lib-socket: implement getsockopt(SOL_SOCKET,SO_TYPE) (#4458) ... cf. https://github.com/bytecodealliance/wasm-micro-runtime/issues/4456	2025-07-14 13:06:33 +08:00
YAMAMOTO Takashi	5d48cfdbc0	introduce wasm_runtime_instantiate_ex2 (#4444) ... * introduce wasm_runtime_instantiate_ex2 at this point, just a slightly inefficiant functionality equivalent of wasm_runtime_instantiate_ex. however, unlike wasm_runtime_instantiate_ex, this one is designed to be extendable without breaking the user-visible ABI. because the definition of InstantiationArgs2 is not exposed to users, we can safely add new members to it. this commit also makes wasm_runtime_instantiate_ex a wrapper of wasm_runtime_instantiate_ex2. if this goes well, maybe it's a good idea to apply a similar pattern to RuntimeInitArgs, LoadArgs, SharedHeapInitArgs, etc. i started with InstantiationArgs just because i happen to have a need to extend it for wasi-nn. cf. https://github.com/bytecodealliance/wasm-micro-runtime/issues/4364 https://github.com/bytecodealliance/wasm-micro-runtime/issues/4331 * product-mini/platforms/posix: use wasm_runtime_instantiate_ex2	2025-07-14 13:06:23 +08:00
Zhenwei Jin	65d3ffa7a4	add validation for recursive type count in loader (#4440)	2025-07-14 13:06:08 +08:00
Zhenwei Jin	9e92f5ebe1	fix a wamrc debug mode compile issue (#4470)	2025-07-10 08:29:31 +08:00
YAMAMOTO Takashi	56f87b7ee9	wasi-nn: do not pretend to support legacy abi in openvino and llamacpp (#4468) ... as tested by core/iwasm/libraries/wasi-nn/test/test_tensorflow.c, the legacy "wasi_nn" abi uses the number of fp32 for get_output. because these backends don't implement the abi, bail out explicitly in build time. cf. https://github.com/bytecodealliance/wasm-micro-runtime/issues/4376	2025-07-10 08:28:08 +08:00
YAMAMOTO Takashi	933e49df18	appease a few compiler warnings (-Wstrict-prototypes) (#4465)	2025-07-10 08:28:00 +08:00
Liu Jia	903a5c1f8c	improve logic of heap_type validation when ref.null (#4372) ... * Follow-up to PR #4300: prevent potential overflow PR #4300 introduced the rationale for validating heap_type. This patch moves the validation before the computation of type1 to prevent potential overflow.	2025-07-10 08:27:11 +08:00
YAMAMOTO Takashi	fbd27e5e03	wasi_nn_llamacpp.c: explicitly reject unimplemented input index (#4446) ... note: wasmedge seems to accept index 1 for metadata. we don't implement it.	2025-07-09 10:35:46 +08:00
YAMAMOTO Takashi	0eceed2ba9	wasi: avoid user-triggerable 0-sized allocations (#4452) ... might fix https://github.com/bytecodealliance/wasm-micro-runtime/issues/4451	2025-07-08 09:25:50 +08:00
TianlongLiang	7d05dbc988	Support extended constant expressions (#4432) ... * implement extended const expr (#4318) * add a toggle to enable extended const on wamrc (#4412)	2025-07-07 13:34:02 +08:00
TianlongLiang	8a55a1e7a1	Shared heap enhancements for Interpreter and AOT (#4400) ... Propose two enhancements: - Shared heap created from preallocated memory buffer: The user can create a shared heap from a pre-allocated buffer and see that memory region as one large chunk; there's no need to dynamically manage it(malloc/free). The user needs to make sure the native address and size of that memory region are valid. - Introduce shared heap chain: The user can create a shared heap chain, from the wasm app point of view, it's still a continuous memory region in wasm app's point of view while in the native it can consist of multiple shared heaps (each of which is a continuous memory region). For example, one 500MB shared heap 1 and one 500 MB shared heap 2 form a chain, in Wasm's point of view, it's one 1GB shared heap. After these enhancements, the data sharing between wasm apps, and between hosts can be more efficient and flexible. Admittedly shared heap management can be more complex for users, but it's similar to the zero-overhead principle. No overhead will be imposed for the users who don't use the shared heap enhancement or don't use the shared heap at all.	2025-07-04 10:44:51 +08:00
YAMAMOTO Takashi	ee056d8076	wasi_nn_llamacpp.c: validate input tensor type/dimensions (#4442)	2025-07-03 10:17:19 +08:00
YAMAMOTO Takashi	da6019f749	wasi_nn_llamacpp.c: reject invalid graph and execution context (#4422) ... * return valid graph and execution context instead of using stack garbage. (always 0 for now because we don't implement multiple graph/context for this backend.) * validate user-given graph and execution context values. reject invalid ones.	2025-07-01 19:31:00 +08:00
YAMAMOTO Takashi	ebf1404ad1	wasi_nn_openvino.c: avoid self-assignment warning (#4434)	2025-07-01 19:19:36 +08:00
liang.he	c7148a6823	Fix potential integer overflow issues (#4429) ... It is reported as "Multiplication result converted to larger type". And "Multiplication result may overflow 'Type A' before it is converted to 'Type B'." Type A is a larger type than Type B. Since the conversion applies after the multiplication, arithmetic overflow may still occur. > The rule flags every multiplication of two non-constant integer expressions > that is (explicitly or implicitly) converted to a larger integer type. The > conversion is an indication that the expression would produce a result that > would be too large to fit in the smaller integer type.	2025-07-01 13:39:30 +08:00
YAMAMOTO Takashi	38fe056cc6	wasi-nn: reduce code duplication a bit (#4433)	2025-07-01 10:37:12 +08:00
liang.he	430cc5e5ef	Refactor AOTObjectData definition to use a forward declaration (#4428) ... > core/iwasm/compilation/aot_emit_aot_file.c:85:3: error: redefinition of typedef 'AOTObjectData' is a C11 feature	2025-07-01 10:10:11 +08:00
Zhenwei Jin	0127eafbe5	loader: fix a potential overflow issue (#4427)	2025-06-30 12:57:57 +08:00
YAMAMOTO Takashi	7a6a6a39e9	wasi_nn_openvino.c: fix a debug build (#4416) ... after "wasi_nn_openvino.c: implement multiple models per instance" change. (https://github.com/bytecodealliance/wasm-micro-runtime/pull/4380)	2025-06-30 12:57:44 +08:00
liang.he	0641dd1506	Fix few shadow warnings (#4409) ... - declaration of ‘memidx’ shadows a previous local - declaration of ‘count’ shadows a previous local	2025-06-27 11:55:32 +08:00
YAMAMOTO Takashi	8ed89e2ab2	wasi_nn_llamacpp.c: remove an unused variable (#4415)	2025-06-27 11:55:08 +08:00
YAMAMOTO Takashi	d6876f1e9f	wasi_nn_llamacpp.c: fix buffer overruns in set_input (#4420) ... note: for some reasons, wasmedge seems to ignore type/dimensions for the input of ggml. some user code relies on it. cf. https://github.com/second-state/WasmEdge-WASINN-examples/issues/196 note: despite the comment in our code, the input doesn't seem nul-terminated.	2025-06-27 11:51:03 +08:00
YAMAMOTO Takashi	2372a472aa	wasi-nn: make the host use the wasi_ephemeral_nn version of tensor_data (#4411) ... the motivations: * make the actual input size available to the backends. (currently the backends have to make a guess from shape/type.) * make the host logic look a bit similar to wasi_ephemeral_nn. this is a backend api/abi change.	2025-06-27 07:41:42 +08:00
TianlongLiang	23799a2cb6	Collective fix (#4413) ... * Fix vector growth check and typos in core (#9) * Fix resource cleanup in memory and running modes tests (#10) * Add end of file empty line in wasm_running_modes_test.cc	2025-06-26 10:20:40 +08:00
YAMAMOTO Takashi	a7aae9d2cc	wasi_nn_llamacpp.c: make this compilable (#4403)	2025-06-26 07:05:45 +08:00
Liu Jia	535004dedc	Fix handling of non-nullable global_type during global import (#4408)	2025-06-26 06:59:57 +08:00
Zhenwei Jin	1e41519977	loader: add type index checking (#4402)	2025-06-24 20:38:39 +08:00
liang.he	e414a327a0	Refactor copy callstack feature (#4401) ... - Change `WAMR_ENABLE_COPY_CALLSTACK` to `WAMR_BUILD_COPY_CALL_STACK`, as `WAMR_BUILD` is the prefix for a command line option. - Change `WAMR_ENABLE_COPY_CALLSTACK` to `WASM_ENABLE_COPY_CALL_STACK`, as `WASM_ENABLE` is the prefix for a macro in the source code. - Change `CALLSTACK` to `CALL_STACK` to align with the existing `DUMP_CALL_STACK` feature. - Continue using `WASMCApiFrame` instead of `wasm_frame_t` outside of *wasm_c_api.xxx* to avoid a typedef redefinition warning, which is identified by Clang.	2025-06-24 20:38:30 +08:00
YAMAMOTO Takashi	8289452abb	wasi_nn_tensorflowlite.cpp: fix get_output return size (#4390) ... it should be byte size, not the number of (fp32) values. i'm ambivalent about how to deal with the compatibility for the legacy wamr-specific "wasi_nn". for now, i avoided changing it. (so that existing tests using the legacy abi, namely test_tensorflow.c and test_tensorflow_quantized.c, passes as they are.) if we have any users who still want to use the legacy abi, i suppose they consider the compatibility is more important than the consistency with other backends. cf. https://github.com/bytecodealliance/wasm-micro-runtime/issues/4376	2025-06-24 20:38:19 +08:00
YAMAMOTO Takashi	70c39bae77	wasi-nn: fix context lifetime issues (#4396) ... * wasi-nn: fix context lifetime issues use the module instance context api instead of trying to roll our own with a hashmap. this fixes context lifetime problems mentioned in https://github.com/bytecodealliance/wasm-micro-runtime/issues/4313. namely, * wasi-nn resources will be freed earlier now. before this change, they used to be kept until the runtime shutdown. (wasm_runtime_destroy) after this change, they will be freed together with the associated instances. * wasm_module_inst_t pointer uniqueness assumption (which is wrong after wasm_runtime_deinstantiate) was lifted. as a side effect, this change also makes a context shared among threads within a cluster. note that this is a user-visible api/abi breaking change. before this change, wasi-nn "handles" like wasi_ephemeral_nn_graph were thread-local. after this change, they are shared among threads within a cluster, similarly to wasi file descriptors. spec-wise, either behavior should be ok simply because wasi officially doesn't have threads yet. althogh i feel the latter semantics is more intuitive, if your application depends on the thread-local behavior, this change breaks your application. tested with wamr-wasi-extensions/samples/nn-cli, modified to call each wasi-nn operations on different threads. (if you are interested, you can find the modification at https://github.com/yamt/wasm-micro-runtime/tree/yamt-nn-wip-20250619.) cf. https://github.com/bytecodealliance/wasm-micro-runtime/issues/4313 https://github.com/bytecodealliance/wasm-micro-runtime/issues/2430 * runtime_lib.cmake: enable WAMR_BUILD_MODULE_INST_CONTEXT for wasi-nn as we do for wasi (WAMR_BUILD_LIBC_WASI)	2025-06-24 20:37:56 +08:00
YAMAMOTO Takashi	f449b79a31	wasi_nn_openvino.c: implement multiple models per instance (#4380) ... tested with two models: ``` --load-graph=id=graph1,file=public/license-plate-recognition-barrier-0007/FP32/license-plate-recognition-barrier-0007.xml,file=public/license-plate-recognition-barrier-0007/FP32/license-plate-recognition-barrier-0007.bin \ --load-graph=id=graph2,file=classify/model.xml,file=classify/model.bin \ --init-execution-context=id=exec1,graph-id=graph1 \ --init-execution-context=id=exec2,graph-id=graph2 \ --set-input=context-id=exec1,dim=1,dim=24,dim=94,dim=3,file=out.bin \ --set-input=context-id=exec2,file=classify/banana-3x224x224-bgr.bin,dim=1,dim=3,dim=224,dim=224 \ --compute=context-id=exec1 \ --compute=context-id=exec2 \ --get-output=context-id=exec1,file=exec1-result.bin \ --get-output=context-id=exec2,file=exec2-result.bin ``` a detailed HOWTO: https://github.com/bytecodealliance/wasm-micro-runtime/pull/4380#issuecomment-2986882718	2025-06-20 15:50:29 +08:00
YAMAMOTO Takashi	ea408ab6c0	wasi-nn: add minimum serialization on WASINNContext (#4387) ... currently this is not necessary because context (WASINNContext) is local to instance. (wasm_module_instance_t) i plan to make a context shared among instances in a cluster when fixing https://github.com/bytecodealliance/wasm-micro-runtime/issues/4313. this is a preparation for that direction. an obvious alternative is to tweak the module instance context APIs to allow declaring some kind of contexts instance-local. but i feel, in this particular case, it's more natural to make "wasi-nn handles" shared among threads within a "process". note that, spec-wise, how wasi-nn behaves wrt threads is not defined at all because wasi officially doesn't have threads yet. i suppose, at this point, that how wasi-nn interacts with wasi-threads is something we need to define by ourselves, especially when we are using an outdated wasi-nn version. with this change, if a thread attempts to access a context while another thread is using it, we simply make the operation fail with the "busy" error. this is intended for the mimimum serialization to avoid problems like crashes/leaks/etc. this is not intended to allow parallelism or such. no functional changes are intended at this point yet. cf. https://github.com/bytecodealliance/wasm-micro-runtime/issues/4313 https://github.com/bytecodealliance/wasm-micro-runtime/issues/2430	2025-06-20 09:48:55 +08:00
YAMAMOTO Takashi	71c07f3e4e	deprecate legacy WAMR-specific "wasi_nn" module (#4382) ... wasi_nn.h: deprecate legacy "wasi_nn" cf. https://github.com/bytecodealliance/wasm-micro-runtime/issues/4326	2025-06-19 14:32:26 +08:00
YAMAMOTO Takashi	aa53d648fa	wasi-nn: fix tensor_data abi for wasi_ephemeral_nn (#4379) ... it's "(list u8)" in the witx definition. the new definition matches both of our own host definition (struct tensor_wasm) and wasmtime. cf. https://github.com/bytecodealliance/wasm-micro-runtime/issues/4352	2025-06-19 14:18:36 +08:00
YAMAMOTO Takashi	a29f3943ef	core/iwasm/libraries/wasi-nn/test: use the correct version of keras (#4383)	2025-06-18 19:24:06 +08:00
YAMAMOTO Takashi	db7714f0f5	wasi_nn_tensorflowlite.cpp: reject non-fp32 input earlier (#4388) ... this backend assumes fp32 here and there. it's safer to reject unexpected inputs explicitly.	2025-06-18 19:08:57 +08:00
YAMAMOTO Takashi	4bf799c3af	core/iwasm/libraries/wasi-nn/test/build.sh: add a tip for intel mac (#4389) ... i keep forgetting this and had to re-investigate it at least twice. hopefully this can be helpful for others too.	2025-06-18 19:06:57 +08:00
YAMAMOTO Takashi	cba9001749	wasi-nn: don't try to deinit uninitialized backend (#4375) ... cf. https://github.com/bytecodealliance/wasm-micro-runtime/issues/4339	2025-06-17 17:40:53 +08:00
YAMAMOTO Takashi	c9b8c16088	wasi_nn_openvino.c: remove pre/postprocessing and layout assumptions (#4361) ... as wasi-nn doesn't have these concepts, the best we can do without risking breaking certain applications here is to pass through tensors as they are. this matches wasmtime's behavior. tested with: * wasmtime classification-example (with this change, this example fails on tensor size mismatch instead of implicitly resizing it.) * license-plate-recognition-barrier-0007, a converted version with non-fp32 output. [1] (with this change, this model outputs integers as expected.) [1] cd7ebe313b/models/public/license-plate-recognition-barrier-0007	2025-06-17 13:01:46 +08:00
Su Yihan	6dfb410869	send an empty/error reply from server (#4362) ... Signed-off-by: Su Yihan <yihan.su@intel.com>	2025-06-17 13:00:58 +08:00
YAMAMOTO Takashi	2f0750a6fe	wasi_nn_openvino.c: add a missing buffer overflow check in get_output (#4353) ... cf. https://github.com/bytecodealliance/wasm-micro-runtime/issues/4351	2025-06-17 11:17:00 +08:00
YAMAMOTO Takashi	20be1d33fe	wasi_ephemeral_nn.h: prefix identfiers to avoid too generic names (#4358)	2025-06-17 11:15:01 +08:00
YAMAMOTO Takashi	745da82cd6	wasi_nn_openvino.c: remove broken xml check (#4365) ... `xml.buf[xml.size]` check is broken because it accesses past the end of the buffer. anyway, openvino doesn't seem to care the NUL termination.	2025-06-17 11:02:36 +08:00