can not run getting_started_resnet tutorial with AMD Phoenix (PHX) platform (Ryzen 7 7840H)

[mattchai]

getting_started_resnet tutorial can run on AMD Strix point platform, but can not run on AMD Phoenix (PHX) platform.

[shivani-athavale]

Hi @mattchai, the getting_started_resnet tutorial should be able to run on PHX. The following steps need to be ensured:

1. Some environment variables are set for STX by default, they need to be set as following for PHX.

   set XLNX_VART_FIRMWARE=%RYZEN_AI_INSTALLATION_PATH%/voe-4.0-win_amd64/xclbins/phoenix/1x4.xclbin
   set XLNX_TARGET_NAME=AMD_AIE2_Nx4_Overlay

   The instructions are also available at https://ryzenai.docs.amd.com/en/latest/runtime_setup.html#npu-configurations

2. Make sure to delete the cache folder before every inference run. (It is named 'modelcachekey' and is created in the getting_started_resnet folder.)

[mattchai]

It can work after delete the cache folder, i will close this issue

[mattchai]

@shivani-athavale , still can't work on Hawk(HPT) (R9 8945HS) platform, error message as below, please help to check it, thanks.

(ryzen-ai-1.2.0) C:\getting_started_resnet>rmdir /s /q modelcachekey

(ryzen-ai-1.2.0) C:\getting_started_resnet>set XLNX_VART_FIRMWARE=%RYZEN_AI_INSTALLATION_PATH%/voe-4.0-win_amd64/xclbins/phoenix/1x4.xclbin

(ryzen-ai-1.2.0) C:\getting_started_resnet>set XLNX_TARGET_NAME=AMD_AIE2_Nx4_Overlay

(ryzen-ai-1.2.0) C:\getting_started_resnet>python predict.py --ep npu WARNING: Logging before InitGoogleLogging() is written to STDERR E20240925 01:51:43.794515 10400 xclbin_file.cpp:101] Failed to open xclbin C:\Windows\System32\AMD\%RYZEN_AI_INSTALLATION_PATH%/voe-4.0-win_amd64/xclbins/phoenix/1x4.xclbin E20240925 01:51:44.213496 10400 xclbin_file.cpp:101] Failed to open xclbin C:\Windows\System32\AMD\%RYZEN_AI_INSTALLATION_PATH%/voe-4.0-win_amd64/xclbins/phoenix/1x4.xclbin E20240925 01:51:52.526823 10400 xclbin_file.cpp:101] Failed to open xclbin C:\Windows\System32\AMD\%RYZEN_AI_INSTALLATION_PATH%/voe-4.0-winamd64/xclbins/phoenix/1x4.xclbin [Vitis AI EP] No. of Operators : CPU 2 NPU 398 [Vitis AI EP] No. of Subgraphs : CPU 1 NPU 1 Actually running on NPU 1 ← [ 0 ; 9 3 m 2 0 2 4 - 0 9 - 2 5 0 1 : 5 1 : 5 2 . 6 3 8 0 2 9 1 [ W : o n n x r u n t i m e : , s e s s i o n s t a t e . c c : 1 1 6 6 o n n x r u n t i m e : : V e r i f y E a c h N o d e I s A s s i g n e d T o A n E p ] S o m e n o d e s w e r e n o t a s s i g n e d t o t h e p r e f e r r e d e x e c u t i o n p r o v i d e r s w h i c h m a y o r m a y n o t h a v e a n n e g a t i v e i m p a c t o n p e r f o r m a n c e . e . g . O R T e x p l i c i t l y a s s i g n s s h a p e r e l a t e d o p s t o C P U t o i m p r o v e p e r f . ← [ m ← [ 0 ; 9 3 m 2 0 2 4 - 0 9 - 2 5 0 1 : 5 1 : 5 2 . 6 4 4 1 1 6 6 [ W : o n n x r u n t i m e : , s e s s i o n _ s t a t e . c c : 1 1 6 8 o n n x r u n t i m e : : V e r i f y E a c h N o d e I s A s s i g n e d T o A n E p ] R e r u n n i n g w i t h v e r b o s e o u t p u t o n a n o n - m i n i m a l b u i l d w i l l s h o w n o d e a s s i g n m e n t s . ← [ m F20240925 01:51:52.939664 10400 customop.cpp:368] -- Error: Failed to create GE handle: Error: No compatible xclbin file found. ← [ 1 ; 3 1 m 2 0 2 4 - 0 9 - 2 5 0 1 : 5 1 : 5 2 . 9 8 1 3 1 2 8 [ E : o n n x r u n t i m e : , i n f e r e n c e s e s s i o n . c c : 1 9 3 5 o n n x r u n t i m e : : I n f e r e n c e S e s s i o n : : I n i t i a l i z e : : < l a m b d a 2 a 0 e 0 9 6 4 6 3 d 5 3 c e b 1 6 5 4 2 7 f a 1 4 e 8 0 3 7 a > : : o p e r a t o r ( ) ] E x c e p t i o n d u r i n g i n i t i a l i z a t i o n : p u b l i c : v i r t u a l c d e c l g o o g l e : : p r o t o b u f : : S t r u c t : : ~ S t r u c t ( v o i d ) p t r 6 4 p u b l i c : v i r t u a l u n s i g n e d c h a r * p t r 6 4 c d e c l g o o g l e : : p r o t o b u f : : i n t e r n a l : : Z e r o F i e l d s B a s e : : I n t e r n a l S e r i a l i z e ( u n s i g n e d c h a r p t r 6 4 , c l a s s g o o g l e : : p r o t o b u f : : i o : : E p s C o p y O u t p u t S t r e a m p t r 6 4 ) c o n s t p t r 6 4 C x x F r a m e H a n d l e r 4 ( u n k n o w n ) R t l C a p t u r e C o n t e x t 2 p u b l i c : v o i d c d e c l v a i p c o r e : : D p u S u b g r a p h E n t r y P r o t o : : u n s a f e a r e n a s e t a l l o c a t e d t r y f u s e ( c l a s s v a i p c o r e : : T r y F u s e P r o t o * p t r 6 4 ) p t r 6 4 p u b l i c : v o i d c d e c l v a i p c o r e : : D p u S u b g r a p h E n t r y P r o t o : : u n s a f e a r e n a s e t a l l o c a t e d t r y f u s e ( c l a s s v a i p c o r e : : T r y F u s e P r o t o p t r 6 4 ) p t r 6 4 ( u n k n o w n ) P y I n i t o n n x r u n t i m e p y b i n d 1 1 s t a t e P y I n i t o n n x r u n t i m e p y b i n d 1 1 s t a t e P y I n i t o n n x r u n t i m e p y b i n d 1 1 s t a t e P y I n i t o n n x r u n t i m e p y b i n d 1 1 s t a t e P y I n i t o n n x r u n t i m e p y b i n d 1 1 s t a t e P y I n i t o n n x r u n t i m e p y b i n d 1 1 s t a t e P y I n i t o n n x r u n t i m e p y b i n d 1 1 s t a t e P y I n i t o n n x r u n t i m e p y b i n d 1 1 s t a t e P y I n i t o n n x r u n t i m e p y b i n d 1 1 s t a t e P y I n i t o n n x r u n t i m e p y b i n d 1 1 s t a t e p u b l i c : v o i d c d e c l p y b i n d 1 1 : : e r r o r a l r e a d y s e t : : d i s c a r d a s u n r a i s a b l e ( c l a s s p y b i n d 1 1 : : o b j e c t ) p t r 6 4 P y C F u n c t i o n G e t F l a g s P y O b j e c t M a k e T p C a l l P y M e t h o d S e l f P y O S U R a n d o m N o n b l o c k P y E v a l G e t F u n c D e s c P y E v a l E v a l F r a m e D e f a u l t P y E v a l E v a l F r a m e D e f a u l t P y F u n c t i o n V e c t o r c a l l P y O S U R a n d o m N o n b l o c k P y E v a l G e t F u n c D e s c P y E v a l E v a l F r a m e D e f a u l t P y E v a l E v a l F r a m e D e f a u l t P y F u n c t i o n V e c t o r c a l l ← [ m Traceback (most recent call last): File "C:\getting_started_resnet\predict.py", line 36, in session = ort.InferenceSession(model.SerializeToString(), providers=providers, File "C:\ProgramData\anaconda3\envs\ryzen-ai-1.2.0\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 419, in init self._create_inference_session(providers, provider_options, disabled_optimizers) File "C:\ProgramData\anaconda3\envs\ryzen-ai-1.2.0\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 483, in _create_inference_session sess.initialize_session(providers, provider_options, disabled_optimizers) onnxruntime.capi.onnxruntime_pybind11_state.RuntimeException: [ONNXRuntimeError] : 6 : RUNTIME_EXCEPTION : Exception during initialization: public: virtual cdecl google::protobuf::Struct::~Struct(void) ptr64 public: virtual unsigned char ptr64 cdecl google::protobuf::internal::ZeroFieldsBase::_InternalSerialize(unsigned char __ptr64,class google::protobuf::io::EpsCopyOutputStream ptr64)const ptr64 CxxFrameHandler4 (unknown) RtlCaptureContext2 public: void cdecl vaip_core::DpuSubgraphEntryProto::unsafe_arena_set_allocated_try_fuse(class vaip_core::TryFuseProto ptr64) ptr64 public: void __cdecl vaip_core::DpuSubgraphEntryProto::unsafe_arena_set_allocated_try_fuse(class vaip_core::TryFuseProto ptr64) ptr64 (unknown) PyInit_onnxruntime_pybind11_state PyInit_onnxruntime_pybind11_state PyInit_onnxruntime_pybind11_state PyInit_onnxruntime_pybind11_state PyInit_onnxruntime_pybind11_state PyInit_onnxruntime_pybind11_state PyInit_onnxruntime_pybind11_state PyInit_onnxruntime_pybind11_state PyInit_onnxruntime_pybind11_state PyInit_onnxruntime_pybind11_state public: void cdecl pybind11::error_already_set::discard_as_unraisable(class pybind11::object) ptr64 PyCFunction_GetFlags _PyObject_MakeTpCall PyMethod_Self _PyOS_URandomNonblock PyEval_GetFuncDesc _PyEval_EvalFrameDefault _PyEval_EvalFrameDefault _PyFunction_Vectorcall _PyOS_URandomNonblock PyEval_GetFuncDesc _PyEval_EvalFrameDefault _PyEval_EvalFrameDefault _PyFunction_Vectorcall

(ryzen-ai-1.2.0) C:\getting_started_resnet>

[shivani-athavale]

Hi @mattchai,

Can you try checking your %RYZEN_AI_INSTALLATION_PATH%?

As mentioned in the documentation at , RyzenAI should be installed at the path C:\Program Files\RyzenAI\1.2.0 by default.

In your error logs, the path is shown as: C:\Windows\System32\AMD%RYZEN_AI_INSTALLATION_PATH%. Maybe this path has been set wrong which is why the xclbin is not found.

You could try the installation steps and ensure the environment variables are set correctly.

[mattchai]

Hi @shivani-athavale, RyzenAI path is correct, I got the error during first time running, it can run without any error after the second attempt, thanks.

[uday610]

Closing this issue as it is resolved