migraphx-bot comments

Results 64 comments of


                                            migraphx-bot

Keep LayerNorm accumulator at FP32

| Test | Batch | Rate new d8422b | Rate old 3b3eca | Diff | Compare | |:-----------------------------|--------:|------------------------:|------------------------:|-------:|:------------------:| | torchvision-resnet50 | 64 | 2,957.76 | 2,950.34 | 0.25% | :white_check_mark:...

Keep LayerNorm accumulator at FP32

:x:bert-mrpc-onnx: ERROR - check error outputTraceback (most recent call last): File "/src/AMDMIGraphX/tools/accuracy/accuracy_checker.py", line 340, in main() File "/src/AMDMIGraphX/tools/accuracy/accuracy_checker.py", line 205, in main model = migraphx.parse_onnx(model_name, default_dim_value=batch)RuntimeError: /src/AMDMIGraphX/src/onnx/onnx_parser.cpp:264: parse_from: PARSE_FROM: Failed...

Random number range expansion for Perf tests

| Test | Batch | Rate new 97b181 | Rate old 2c4dd4 | Diff | Compare | |:-----------------------------|--------:|------------------------:|------------------------:|-------:|:------------------:| | torchvision-resnet50 | 64 | [1,743.59](https://github.com/ROCm/migraphx-reports/blob/main/performance_results/PRs/PR-2953/97b181/torchvision-resnet50.out) | [1,744.86](https://github.com/ROCm/migraphx-reports/blob/main/performance_results/develop/2c4dd4/torchvision-resnet50.out) | -0.07% | :white_check_mark:...

Random number range expansion for Perf tests

     :white_check_mark: bert-mrpc-onnx: PASSED: MIGraphX meets tolerance      :white_check_mark: bert-mrpc-tf: PASSED: MIGraphX meets tolerance      :white_check_mark: pytorch-examples-wlang-gru: PASSED: MIGraphX meets tolerance      :white_check_mark: pytorch-examples-wlang-lstm: PASSED: MIGraphX meets tolerance      :white_check_mark:...

Add support for GridSample operator

| Test | Batch | Rate new b6172d | Rate old 5fcf86 | Diff | Compare | |:-----------------------------|--------:|------------------------:|------------------------:|-------:|:------------------:| | torchvision-resnet50 | 64 | 1,751.55 | 1,751.74 | -0.01% | :white_check_mark:...

Add support for GridSample operator

Add support for the Einsum operator

| Test | Batch | Rate new 7140ae | Rate old dc028d | Diff | Compare | |:-----------------------------|--------:|------------------------:|------------------------:|--------:|:------------------:| | torchvision-resnet50 | 64 | 1,713.92 | 1,489.70 | 15.05% | :high_brightness:...

Add support for the Einsum operator

Add propagate_precision pass

| Test | Batch | Rate new 0f785b | Rate old 5ba023 | Diff | Compare | |:-----------------------------|--------:|------------------------:|------------------------:|-------:|:------------------:| | torchvision-resnet50 | 64 | 2,826.08 | 2,824.95 | 0.04% | :white_check_mark:...