[CK] Grouped Convolution Global Load/Store support (#7631)
## Motivation
Grouped Convolution Global Load/Store support to cover large tensor
cases.
## Technical Details
Utilize global load for grouped convolution forwad kernels. Update
Indexes to use int64.
## Test Plan
- test utils
- test conv kernels in next pr with instances
## Test Result
CI pending
## Submission Checklist
- [x] Look over the contributing guidelines at
https://github.com/ROCm/ROCm/blob/develop/CONTRIBUTING.md#pull-requests.
AICK-1255
---------
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
