Update on "[inductor] allow clone cse cache during vectorized indirec…

…t load"

Fix #123502

`swap_buffer` do not clone the `cse.cache` which will bring redundant computation.
We may able to clone the `cse.cache` if there is no cse value in the `expr`
```
auto tmp8 =
[&]
{
    __at_align__ std::array<int64_t, 16> tmpbuf;
    tmp7.store(tmpbuf.data());
    return tmpbuf;
}
()
;
//
// other codes
//
// also store tmp7 here (redundant tmp16)
auto tmp16 =
[&]
{
    __at_align__ std::array<int64_t, 16> tmpbuf;
    tmp7.store(tmpbuf.data());
    return tmpbuf;
}
()
;
```




cc voznesenskym penguinwu EikanWang jgong5 Guobing-Chen XiaobingSuper blzheng wenzhe-nrv jiayisunx peterbell10 ipiszy yf225 chenyang78 kadeng muchulee8 ColinPeppler amjames desertfire chauhang

[ghstack-poisoned]

.ci/docker/ci_commit_pins/triton-rocm.txt

@@ -1 +1 @@
-0a22a91d04c2b4a029a69a198eac390089c3e891
+bbe6246e37d8aa791c67daaf9d9d61b26c9ccfdc

.ci/docker/common/install_triton.sh

@@ -13,7 +13,7 @@ conda_reinstall() {
 }
 
 if [ -n "${ROCM_VERSION}" ]; then
-  TRITON_REPO="https://github.com/ROCmSoftwarePlatform/triton"
+  TRITON_REPO="https://github.com/openai/triton"
   TRITON_TEXT_FILE="triton-rocm"
 elif [ -n "${BASEKIT_VERSION}" ]; then
   TRITON_REPO="https://github.com/intel/intel-xpu-backend-for-triton"

.github/actions/download-build-artifacts/action.yml

@@ -25,7 +25,7 @@ runs:
         s3-bucket: ${{ inputs.s3-bucket }}
 
     - name: Download PyTorch Build Artifacts from GHA
-      if: inputs.use-gha
+      if: ${{ inputs.use-gha }}
       uses: actions/download-artifact@v3
       with:
         name: ${{ inputs.name }}