)]}'
{
  "commit": "df0db843401a3053e111fc69798f4e04f4c2efa2",
  "tree": "438d447229f9d3aee8efabb70b3861fe089498fd",
  "parents": [
    "b2e4d2abe78011284ddeec0d42ade308f24cf892"
  ],
  "author": {
    "name": "bjacob",
    "email": "benoitjacob@google.com",
    "time": "Tue Jan 31 12:36:23 2023 -0500"
  },
  "committer": {
    "name": "GitHub",
    "email": "noreply@github.com",
    "time": "Tue Jan 31 17:36:23 2023 +0000"
  },
  "message": "fix bad stride in pack_benchmark (#12009)\n\nFixes #12008\r\nRegression introduced in #11987\r\n\r\nI had tweaked the strides in the benchmark as I thought for a moment\r\nthat it was more realistic to benchmark round (power of two) strides\r\neven when padding makes sizes a little smaller. But now I\u0027m not so sure\r\nanymore what\u0027s the more important case in practice, so this just reverts\r\nto the old state.\r\n\r\nThe crash was because instead of the correct ` out_size1 * out_size3`\r\n(value for `in_size1` before adjustment for padding) I had incorrectly\r\ntyped `out_size0 * out_size2`.",
  "tree_diff": [
    {
      "type": "modify",
      "old_id": "5106a66ce8fafc071103d51d4122859c4ffe4482",
      "old_mode": 33188,
      "old_path": "runtime/src/iree/builtins/ukernel/tools/pack_benchmark.c",
      "new_id": "b62cf2947708430d9a95fe3ee1ff748cdaa05a05",
      "new_mode": 33188,
      "new_path": "runtime/src/iree/builtins/ukernel/tools/pack_benchmark.c"
    }
  ]
}