migraphx-bot

icon company AMD

Results 124 comments of migraphx-bot

Enable MIGRAPHX_MLIR_TUNING_CFG generation when defined

| Test | Batch | Rate new 64c5a0 | Rate old a4acf4 | Diff | Compare | |:-----------------------------|--------:|------------------------:|------------------------:|-------:|:------------------:| | torchvision-resnet50 | 64 | [3,255.72](https://github.com/ROCm/migraphx-reports/blob/main/performance_results/PRs/PR-3616/64c5a0/torchvision-resnet50.out) | [3,239.15](https://github.com/ROCm/migraphx-reports/blob/main/performance_results/develop/a4acf4/torchvision-resnet50.out) | 0.51% | :white_check_mark:...

Enable MIGRAPHX_MLIR_TUNING_CFG generation when defined

     :white_check_mark: bert-mrpc-onnx: PASSED: MIGraphX meets tolerance :x:bert-mrpc-tf: ERROR - check error output2025-06-17 05:25:02.110042: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.To enable...

Enable BF16 Types for DLM Models in Examples

| Test | Batch | Rate new 035a83 | Rate old 0194f5 | Diff | Compare | |:-----------------------------|--------:|------------------------:|------------------------:|-------:|:------------------:| | torchvision-resnet50 | 64 | [3,256.68](https://github.com/ROCm/migraphx-reports/blob/main/performance_results/PRs/PR-3851/035a83/torchvision-resnet50.out) | [3,256.25](https://github.com/ROCm/migraphx-reports/blob/main/performance_results/develop/0194f5/torchvision-resnet50.out) | 0.01% | :white_check_mark:...

Enable BF16 Types for DLM Models in Examples

     :white_check_mark: bert-mrpc-onnx: PASSED: MIGraphX meets tolerance :x:bert-mrpc-tf: ERROR - check error output2025-04-25 20:30:34.247087: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.To enable...

[AI generated] AIMIGRAPHX-236 Updated Resize op to support linear mode

| Test | Batch | Rate new a184c4 | Rate old d80627 | Diff | Compare | |:-----------------------------|--------:|------------------------:|------------------------:|-------:|:------------------:| | torchvision-resnet50 | 64 | [3,117.45](https://github.com/ROCm/migraphx-reports/blob/main/performance_results/PRs/PR-4382/a184c4/torchvision-resnet50.out) | [3,114.58](https://github.com/ROCm/migraphx-reports/blob/main/performance_results/develop/d80627/torchvision-resnet50.out) | 0.09% | :white_check_mark:...

[AI generated] AIMIGRAPHX-236 Updated Resize op to support linear mode

     :white_check_mark: bert-mrpc-onnx: PASSED: MIGraphX meets tolerance :x:bert-mrpc-tf: ERROR - check error outputTraceback (most recent call last): File "/src/AMDMIGraphX/tools/accuracy/accuracy_checker.py", line 359, in main() File "/src/AMDMIGraphX/tools/accuracy/accuracy_checker.py", line 295, in main import...

Fix for Lower unsupported pooling sizes for the CPU to Reference backend #3177

| Test | Batch | Rate new b9fe91 | Rate old 0d07c2 | Diff | Compare | |:-----------------------------|--------:|------------------------:|------------------------:|-------:|:------------------:| | torchvision-resnet50 | 64 | [3,263.47](https://github.com/ROCm/migraphx-reports/blob/main/performance_results/PRs/PR-3468/b9fe91/torchvision-resnet50.out) | [3,260.52](https://github.com/ROCm/migraphx-reports/blob/main/performance_results/develop/0d07c2/torchvision-resnet50.out) | 0.09% | :white_check_mark:...

Fix for Lower unsupported pooling sizes for the CPU to Reference backend #3177

     :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:...

SparseAttention ONNX Contrib Op Implementation

| Test | Batch | Rate new 2ed947 | Rate old 8177ed | Diff | Compare | |:-----------------------------|--------:|------------------------:|------------------------:|-------:|:------------------:| | torchvision-resnet50 | 64 | [3,175.23](https://github.com/ROCm/migraphx-reports/blob/main/performance_results/PRs/PR-4275/2ed947/torchvision-resnet50.out) | [3,156.64](https://github.com/ROCm/migraphx-reports/blob/main/performance_results/develop/8177ed/torchvision-resnet50.out) | 0.59% | :white_check_mark:...

SparseAttention ONNX Contrib Op Implementation

     :white_check_mark: bert-mrpc-onnx: PASSED: MIGraphX meets tolerance :x:bert-mrpc-tf: ERROR - check error output2025-09-03 10:20:56.197188: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.To enable...