[Tracker] All the issue related with ONNX model zoo models

[pdhirajkumarprasad]

We have enabled total 2325 models from ONNX model zoo. This issue is to track all the issues seen in the models.

Passing Summary

TOTAL TESTS = 2325	Stage	# Passing	% of Total	% of Attempted
Setup	2319	99.7.0%	99.7.0%
IREE Compilation	1910	82.1%	82.1%
Gold Inference	1910	82.1%	82.3%
IREE Inference Invocation	1825	78.4%	95.5%
Inference Comparison (PASS)	1268	54.5%	69.4%

Fail Summary

TOTAL TESTS = 2325	Stage	# Failed at Stage	% of Total
Setup	6	0.2%
IREE Compilation	409	17.5%
Gold Inference	0	0.0%
IREE Inference Invocation	95	4.0%
Inference Comparison	557	23.9%

CPU

#	issue type	issue no	#model impacted	list of model	assignee	status
1	failed to legalize operation 'arith.sitofp' that was explicitly marked illegal	151
2	failed to legalize operation 'torch.operator' that was explicitly marked illegal	56
3	'tensor.expand_shape' op expected dimension 1 of collapsed type to be static value of 9216	29
4	'linalg.fill' op unexpected result less than 0 at expression #1 in (d0, d1, d2, d3, d4) -> (d0, d1, d2, d3, d4)	6
5	'linalg.generic' op inferred input/output operand #2 has shape's dimension #3 to be 392, but found 4	14
6	One or more operations with large vector sizes (16384 bytes) were found	27
7	expected '>'	34
8	'func.func' op exceeded stack allocation limit of 32768 bytes for function. Got 33792 bytes	4
9	'vector.transfer_write' op inferred mask type ('vector<1x1x8xi1>') and mask operand type ('vector<1x8x1xi1>') don't match	9
10	failed to legalize operation 'torch.aten.nonzero'	8
11	expected type to be 'tensor<?x?x?xf32>' or a rank-reduced version. (size mismatch)	3
12	'tensor.cast' op operand type 'tensor<80x15130xf32>' and result type 'tensor<15130xf32>' are cast incompatibl	3
13	'tensor.reshape' op source and destination tensor should have the same number of elements	56