Adjust the inductor workflow to ensure the macOS perf run gets uploaded
Pull Request resolved: pytorch#141999
Approved by: https://github.com/huydhn

After #135386 and #141999, MPS benchmark has been running for a while and the data has been uploaded correctly.  However, the dashboard is still using the old schema that requires the output CSV files to be named in a certain way for its query to work https://github.com/pytorch/test-infra/blob/main/torchci/clickhouse_queries/compilers_benchmark_performance/query.sql#L32-L40.  Specifically, the filename needs to be in the following format `inductor_${backend}_${suite}_${dtype}_${mode}_${device}_${target}.csv`.

The new schema gets away with all this hacky setup, but the dashboard hasn't been migrated to the new schema yet. So, this is a quick way to just get the data to show up first.

### Testing

https://github.com/pytorch/pytorch/actions/runs/12153886764
Pull Request resolved: #142034
Approved by: https://github.com/skotapati, https://github.com/malfet

Adjust the inductor workflow to ensure the macOS perf run gets uploaded
Pull Request resolved: pytorch#141999
Approved by: https://github.com/huydhn

After #135386 and #141999, MPS benchmark has been running for a while and the data has been uploaded correctly.  However, the dashboard is still using the old schema that requires the output CSV files to be named in a certain way for its query to work https://github.com/pytorch/test-infra/blob/main/torchci/clickhouse_queries/compilers_benchmark_performance/query.sql#L32-L40.  Specifically, the filename needs to be in the following format `inductor_${backend}_${suite}_${dtype}_${mode}_${device}_${target}.csv`.

The new schema gets away with all this hacky setup, but the dashboard hasn't been migrated to the new schema yet. So, this is a quick way to just get the data to show up first.

### Testing

https://github.com/pytorch/pytorch/actions/runs/12153886764
Pull Request resolved: #142034
Approved by: https://github.com/skotapati, https://github.com/malfet

…ockIdx.* * blockDim.*` code (#142010)

`grep` didn't surface any `blockIdx.z * blockDim.z` cases
```
git grep -l "int64_t.*=.*blockIdx.x \* blockDim.x.*" | xargs sed -i 's/int64_t \(.*\) = blockIdx.x \* blockDim.x + threadIdx.x;.*/int64_t \1 = ((int64_t) blockIdx.x) * blockDim.x + threadIdx.x;/g'
git grep -l "int64_t.*=.*blockIdx.x \* blockDim.x.*" | xargs sed -i 's/int64_t \(.*\) = threadIdx.x + blockIdx.x \* blockDim.x;.*/int64_t \1 = threadIdx.x + ((int64_t) blockIdx.x) * blockDim.x;/g'
git grep -l "int64_t.*=.*blockIdx.y \* blockDim.y.*" | xargs sed -i 's/int64_t \(.*\) = blockIdx.y \* blockDim.y + threadIdx.y;.*/int64_t \1 = ((int64_t) blockIdx.y) * blockDim.y + threadIdx.y;/g'
git grep -l "int64_t.*=.*blockIdx.y \* blockDim.y.*" | xargs sed -i 's/int64_t \(.*\) = threadIdx.y + blockIdx.y \* blockDim.y;.*/int64_t \1 = threadIdx.y + ((int64_t) blockIdx.y) * blockDim.y;/g'
git grep -l "int64_t.*=.*blockDim.x \* blockIdx.x.*" | xargs sed -i 's/int64_t \(.*\) = blockDim.x \* blockIdx.x + threadIdx.x;.*/int64_t \1 = ((int64_t) blockIdx.x) * blockDim.x + threadIdx.x;/g'
```

See also https://github.com/pytorch/pytorch/pull/141922/files#r1868262823 in #141999 141922

Pull Request resolved: #142010
Approved by: https://github.com/ngimel