[rocm-libraries] ROCm/rocm-libraries#5114 (commit 59b8cb5)

[CK][CK Tile] Improvements for grouped conv fwd tile
 profiling (#5114)

## Motivation

Improve profiling for grouped convolution forward for better comparison
between CK and CK Tile
## Technical Details

- Include preprocessing time for ck tile
- Add flush cache for conv fwd profiler
- Switch configs to builder reflect
- Add KPerXdl deduce
- Add non-grouped ported instances

## Test Plan

test_grouped_convnd_fwd_tile

## Test Result

pass

## Submission Checklist

- [x] Look over the contributing guidelines at
https://github.com/ROCm/ROCm/blob/develop/CONTRIBUTING.md#pull-requests.

AICK-786

experimental/grouped_convolution_tile_instances/configs/create_configs.sh

@@ -68,7 +68,14 @@ mkdir -p forward/tests
 mkdir -p backward_weight/tests
 mkdir -p backward_data/tests
 
-# Do not change the existing fwd test configs
+# For FWD, generate new test configs by taking 20% of the profiler configs for each data type and layout
+for layout in nhwgc ndhwgc; do
+    for dtype in fp32 fp16 bf16; do
+        profiler_config="forward/profiler/${layout}_${dtype}.conf"
+        test_config="forward/tests/${layout}_${dtype}.conf"
+        awk 'NR % 5 == 0' $profiler_config > $test_config # 20% of lines in the profiler configs
+    done
+done
 
 # For BWD weight, generate new test configs by taking 20% of the profiler configs for each data type and layout
 for layout in nhwgc ndhwgc; do