GitLab

The inaccuracy was caused by ONNX round requires nearest integer rounding for halway (0.5) cases.
std::round rounds away from zero, thus giving wrong results with halfway cases.
Replaced std::round with std::nearbyint which uses the correct rounding by default.

Fixes an issue that comes up for variable input slice with steps set manually in ONNX to default 1's.

Since opset version 18, the Split operator allows splitting into unevenly sized outputs when the split input is not present, and a num_outputs attribute has been introduced.

responses to some PR comments, new parsing tests, and removed an IF block that blocked a needed check

Added another check to a verify_onnx test.  Dynamic and static input versions with same attributes and inputs go through different code paths but should give same result.

comment cleanup, some test fixes, minor refactoring of parse_resize.  onnx_test still fails; needs to be updated with new instructions.

comment cleanup, some test fixes, minor refactoring of parse_resize.  onnx_test still fails; needs to be updated with new instructions.

Adds workarounds to avoid passing capture ops and scalar literals from quantization as arguments to ck_gemm.

* Update onnxruntime main 635d3faa3b3908d2806d009dc6872152cfcfcdda
* Update script for build_and_test_onnxrt.sh

Add support for the QLinearMatMul onnx operator

Makes ConstantOfShape work with a variable dimensions input

MIGraphX verification by default uses normalized RMS error as the basis for the verification.  This change adds some logic to allow migraphx to do "np.allclose" type of elementwise verification using atol and rtol.

Commit also includes changes to consistently pass "gold" or "expected" results as the second argument for "verify_range()" calls.  Default RMS tolerance inside driver is set to 0.001 which IMO is high for FP32 compared to what we had earlier. Need better defaults