Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/21702
Note: Links to docs will display an error until the docs builds have been completed. ❗ 1 Active SEVsThere are 1 currently active SEVs. If your PR is affected, please view them below: ❌ 2 New Failures, 1 Unrelated FailureAs of commit 456b620 with merge base 9b91b43 ( NEW FAILURES - The following jobs have failed:
BROKEN TRUNK - The following job failed but were present on the merge base:👉 Rebase onto the `viable/strict` branch to avoid these failures
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
This PR needs a
|
…pytorch#21702) Summary: Annotate four core `ExportPass` subclasses across three files with `targeted_ops` so they participate in the cold-node fast-copy path introduced by parent D97528110. When fast-copy remains safe, D975 copies eligible non-targeted `call_function` nodes with existing `val` metadata instead of replaying them through FakeTensor dispatch. This diff does not add generic pass skipping: every pass still enters replay, and hot nodes continue through each existing `call_operator` implementation. Each set exactly mirrors the rewrite guard already present in its pass: - `MemoryFormatOpsPass` targets `DimOrderOpsMap` keys. - `DimOrderOpsRevertPass` targets `MemoryFormatOpsMap` keys. - `NormalizeTransposePass` targets `aten.t.default`. - `RemoveMixedTypeOperators` targets `add.Tensor`, `mul.Tensor`, `sub.Tensor`, both tensor `div` overloads, and `minimum.default`. The diff is now stacked directly on D97528110, which owns the consumer infrastructure. Its previous D109215317 parent left these attributes inert. Direct raw-graph regressions prove that transpose normalization and mixed-type rewriting still dispatch hot operators while eligible unrelated operators bypass `call_operator`; the mixed-type test also verifies inserted promotion casts and output dtypes. A/B against D97528110 on the same host, with each revision run twice: - Synthetic add/conv/fc/mul U55 suite: 79.000s / 79.516s here versus 81.238s / 82.371s in D975. Mean speedup 3.1%; warmed speedup 3.5%. - CombinedControl U55 LOWERING: 145.801s / 145.888s here versus 148.465s / 149.726s in D975. Mean speedup 2.2%; warmed speedup 2.6%. Differential Revision: D96247716
059fc38 to
08dd81c
Compare
…pytorch#21702) Summary: Annotate four core `ExportPass` subclasses across three files with `targeted_ops` so they participate in the cold-node fast-copy path introduced by parent D97528110. When fast-copy remains safe, D975 copies eligible non-targeted `call_function` nodes with existing `val` metadata instead of replaying them through FakeTensor dispatch. This diff does not add generic pass skipping: every pass still enters replay, and hot nodes continue through each existing `call_operator` implementation. Each set exactly mirrors the rewrite guard already present in its pass: - `MemoryFormatOpsPass` targets `DimOrderOpsMap` keys. - `DimOrderOpsRevertPass` targets `MemoryFormatOpsMap` keys. - `NormalizeTransposePass` targets `aten.t.default`. - `RemoveMixedTypeOperators` targets `add.Tensor`, `mul.Tensor`, `sub.Tensor`, both tensor `div` overloads, and `minimum.default`. The diff is now stacked directly on D97528110, which owns the consumer infrastructure. Its previous D109215317 parent left these attributes inert. Direct raw-graph regressions prove that transpose normalization and mixed-type rewriting still dispatch hot operators while eligible unrelated operators bypass `call_operator`; the mixed-type test also verifies inserted promotion casts and output dtypes. A/B against D97528110 on the same host, with each revision run twice: - Synthetic add/conv/fc/mul U55 suite: 79.000s / 79.516s here versus 81.238s / 82.371s in D975. Mean speedup 3.1%; warmed speedup 3.5%. - CombinedControl U55 LOWERING: 145.801s / 145.888s here versus 148.465s / 149.726s in D975. Mean speedup 2.2%; warmed speedup 2.6%. Differential Revision: D96247716
08dd81c to
6caf061
Compare
6caf061 to
fed7327
Compare
…pytorch#21702) Summary: Pull Request resolved: pytorch#21702 Annotate four core `ExportPass` subclasses with `targeted_ops` matching their existing rewrite guards: - `MemoryFormatOpsPass` uses the `DimOrderOpsMap` keys. - `DimOrderOpsRevertPass` uses the `MemoryFormatOpsMap` keys. - `NormalizeTransposePass` targets `aten.t.default`. - `RemoveMixedTypeOperators` targets the operators handled by its promotion path. These declarations enable eligible non-targeted nodes to use the `ExportPass` fast-copy path, improving CombinedControl U55 lowering by ~3%. Differential Revision: D96247716
…pytorch#21702) Summary: Pull Request resolved: pytorch#21702 Annotate four core `ExportPass` subclasses with `targeted_ops` matching their existing rewrite guards: - `MemoryFormatOpsPass` uses the `DimOrderOpsMap` keys. - `DimOrderOpsRevertPass` uses the `MemoryFormatOpsMap` keys. - `NormalizeTransposePass` targets `aten.t.default`. - `RemoveMixedTypeOperators` targets the operators handled by its promotion path. These declarations enable eligible non-targeted nodes to use the `ExportPass` fast-copy path, improving CombinedControl U55 lowering by ~3%. Differential Revision: D96247716
fed7327 to
0ab6d1d
Compare
…pytorch#21702) Summary: Annotate four core `ExportPass` subclasses with `targeted_ops` matching their existing rewrite guards: - `MemoryFormatOpsPass` uses the `DimOrderOpsMap` keys. - `DimOrderOpsRevertPass` uses the `MemoryFormatOpsMap` keys. - `NormalizeTransposePass` targets `aten.t.default`. - `RemoveMixedTypeOperators` targets the operators handled by its promotion path. These declarations enable eligible non-targeted nodes to use the `ExportPass` fast-copy path, improving CombinedControl U55 lowering by ~3%. Differential Revision: D96247716
0ab6d1d to
8f27d21
Compare
…pytorch#21702) Summary: Annotate four core `ExportPass` subclasses with `targeted_ops` matching their existing rewrite guards: - `MemoryFormatOpsPass` uses the `DimOrderOpsMap` keys. - `DimOrderOpsRevertPass` uses the `MemoryFormatOpsMap` keys. - `NormalizeTransposePass` targets `aten.t.default`. - `RemoveMixedTypeOperators` targets the operators handled by its promotion path. These declarations enable eligible non-targeted nodes to use the `ExportPass` fast-copy path, improving CombinedControl U55 lowering by ~3%. Differential Revision: D96247716
8f27d21 to
48c0fdc
Compare
…pytorch#21702) Summary: Annotate four core `ExportPass` subclasses with `targeted_ops` matching their existing rewrite guards: - `MemoryFormatOpsPass` uses the `DimOrderOpsMap` keys. - `DimOrderOpsRevertPass` uses the `MemoryFormatOpsMap` keys. - `NormalizeTransposePass` targets `aten.t.default`. - `RemoveMixedTypeOperators` targets the operators handled by its promotion path. These declarations enable eligible non-targeted nodes to use the `ExportPass` fast-copy path, improving CombinedControl U55 lowering by ~3%. Differential Revision: D96247716
48c0fdc to
19286d6
Compare
19286d6 to
bf4b1c9
Compare
…pytorch#21702) Summary: Annotate four core `ExportPass` subclasses with `targeted_ops` matching their existing rewrite guards: - `MemoryFormatOpsPass` uses the `DimOrderOpsMap` keys. - `DimOrderOpsRevertPass` uses the `MemoryFormatOpsMap` keys. - `NormalizeTransposePass` targets `aten.t.default`. - `RemoveMixedTypeOperators` targets the operators handled by its promotion path. These declarations enable eligible non-targeted nodes to use the `ExportPass` fast-copy path, improving CombinedControl U55 lowering by ~3%. Differential Revision: D96247716
…pytorch#21702) Summary: Annotate four core `ExportPass` subclasses with `targeted_ops` matching their existing rewrite guards: - `MemoryFormatOpsPass` uses the `DimOrderOpsMap` keys. - `DimOrderOpsRevertPass` uses the `MemoryFormatOpsMap` keys. - `NormalizeTransposePass` targets `aten.t.default`. - `RemoveMixedTypeOperators` targets the operators handled by its promotion path. These declarations enable eligible non-targeted nodes to use the `ExportPass` fast-copy path, improving CombinedControl U55 lowering by ~3%. Differential Revision: D96247716
bf4b1c9 to
d0b4a09
Compare
…pytorch#21702) Summary: Annotate four core `ExportPass` subclasses with `targeted_ops` matching their existing rewrite guards: - `MemoryFormatOpsPass` uses the `DimOrderOpsMap` keys. - `DimOrderOpsRevertPass` uses the `MemoryFormatOpsMap` keys. - `NormalizeTransposePass` targets `aten.t.default`. - `RemoveMixedTypeOperators` targets the operators handled by its promotion path. These declarations enable eligible non-targeted nodes to use the `ExportPass` fast-copy path, improving CombinedControl U55 lowering by ~3%. Differential Revision: D96247716
d0b4a09 to
b0caa01
Compare
…pytorch#21702) Summary: Annotate four core `ExportPass` subclasses with `targeted_ops` matching their existing rewrite guards: - `MemoryFormatOpsPass` uses the `DimOrderOpsMap` keys. - `DimOrderOpsRevertPass` uses the `MemoryFormatOpsMap` keys. - `NormalizeTransposePass` targets `aten.t.default`. - `RemoveMixedTypeOperators` targets the operators handled by its promotion path. These declarations enable eligible non-targeted nodes to use the `ExportPass` fast-copy path, improving CombinedControl U55 lowering by ~3%. Differential Revision: D96247716
b0caa01 to
42b032b
Compare
…pytorch#21702) Summary: Annotate four core `ExportPass` subclasses with `targeted_ops` matching their existing rewrite guards: - `MemoryFormatOpsPass` uses the `DimOrderOpsMap` keys. - `DimOrderOpsRevertPass` uses the `MemoryFormatOpsMap` keys. - `NormalizeTransposePass` targets `aten.t.default`. - `RemoveMixedTypeOperators` targets the operators handled by its promotion path. These declarations enable eligible non-targeted nodes to use the `ExportPass` fast-copy path, improving CombinedControl U55 lowering by ~3%. Differential Revision: D96247716
42b032b to
4358b11
Compare
…pytorch#21702) Summary: Annotate four core `ExportPass` subclasses with `targeted_ops` matching their existing rewrite guards: - `MemoryFormatOpsPass` uses the `DimOrderOpsMap` keys. - `DimOrderOpsRevertPass` uses the `MemoryFormatOpsMap` keys. - `NormalizeTransposePass` targets `aten.t.default`. - `RemoveMixedTypeOperators` targets the operators handled by its promotion path. These declarations enable eligible non-targeted nodes to use the `ExportPass` fast-copy path, improving CombinedControl U55 lowering by ~3%. Differential Revision: D96247716
4358b11 to
6061c40
Compare
…pytorch#21702) Summary: Annotate four core `ExportPass` subclasses with `targeted_ops` matching their existing rewrite guards: - `MemoryFormatOpsPass` uses the `DimOrderOpsMap` keys. - `DimOrderOpsRevertPass` uses the `MemoryFormatOpsMap` keys. - `NormalizeTransposePass` targets `aten.t.default`. - `RemoveMixedTypeOperators` targets the operators handled by its promotion path. These declarations enable eligible non-targeted nodes to use the `ExportPass` fast-copy path, improving CombinedControl U55 lowering by ~3%. Differential Revision: D96247716
6061c40 to
49379af
Compare
…pytorch#21702) Summary: Annotate four core `ExportPass` subclasses with `targeted_ops` matching their existing rewrite guards: - `MemoryFormatOpsPass` uses the `DimOrderOpsMap` keys. - `DimOrderOpsRevertPass` uses the `MemoryFormatOpsMap` keys. - `NormalizeTransposePass` targets `aten.t.default`. - `RemoveMixedTypeOperators` targets the operators handled by its promotion path. These declarations enable eligible non-targeted nodes to use the `ExportPass` fast-copy path, improving CombinedControl U55 lowering by ~3%. Differential Revision: D96247716
49379af to
c248bf2
Compare
…pytorch#21702) Summary: Annotate four core `ExportPass` subclasses with `targeted_ops` matching their existing rewrite guards: - `MemoryFormatOpsPass` uses the `DimOrderOpsMap` keys. - `DimOrderOpsRevertPass` uses the `MemoryFormatOpsMap` keys. - `NormalizeTransposePass` targets `aten.t.default`. - `RemoveMixedTypeOperators` targets the operators handled by its promotion path. These declarations enable eligible non-targeted nodes to use the `ExportPass` fast-copy path, improving CombinedControl U55 lowering by ~3%. Differential Revision: D96247716
c248bf2 to
7382466
Compare
…pytorch#21702) Summary: Annotate four core `ExportPass` subclasses with `targeted_ops` matching their existing rewrite guards: - `MemoryFormatOpsPass` uses the `DimOrderOpsMap` keys. - `DimOrderOpsRevertPass` uses the `MemoryFormatOpsMap` keys. - `NormalizeTransposePass` targets `aten.t.default`. - `RemoveMixedTypeOperators` targets the operators handled by its promotion path. These declarations enable eligible non-targeted nodes to use the `ExportPass` fast-copy path, improving CombinedControl U55 lowering by ~3%. Differential Revision: D96247716
7382466 to
e903419
Compare
e903419 to
35eb3d3
Compare
…pytorch#21702) Summary: Annotate four core `ExportPass` subclasses with `targeted_ops` matching their existing rewrite guards: - `MemoryFormatOpsPass` uses the `DimOrderOpsMap` keys. - `DimOrderOpsRevertPass` uses the `MemoryFormatOpsMap` keys. - `NormalizeTransposePass` targets `aten.t.default`. - `RemoveMixedTypeOperators` targets the operators handled by its promotion path. These declarations enable eligible non-targeted nodes to use the `ExportPass` fast-copy path, improving CombinedControl U55 lowering by ~3%. Differential Revision: D96247716
…pytorch#21702) Summary: Pull Request resolved: pytorch#21702 Annotate four core `ExportPass` subclasses with `targeted_ops` matching their existing rewrite guards: - `MemoryFormatOpsPass` uses the `DimOrderOpsMap` keys. - `DimOrderOpsRevertPass` uses the `MemoryFormatOpsMap` keys. - `NormalizeTransposePass` targets `aten.t.default`. - `RemoveMixedTypeOperators` targets the operators handled by its promotion path. These declarations enable eligible non-targeted nodes to use the `ExportPass` fast-copy path, improving CombinedControl U55 lowering by ~3%. Differential Revision: D96247716
35eb3d3 to
47aab31
Compare
…pytorch#21702) Summary: Annotate four core `ExportPass` subclasses with `targeted_ops` matching their existing rewrite guards: - `MemoryFormatOpsPass` uses the `DimOrderOpsMap` keys. - `DimOrderOpsRevertPass` uses the `MemoryFormatOpsMap` keys. - `NormalizeTransposePass` targets `aten.t.default`. - `RemoveMixedTypeOperators` targets the operators handled by its promotion path. These declarations enable eligible non-targeted nodes to use the `ExportPass` fast-copy path, improving CombinedControl U55 lowering by ~3%. Differential Revision: D96247716
47aab31 to
6cabc33
Compare
…pytorch#21702) Summary: Pull Request resolved: pytorch#21702 Annotate four core `ExportPass` subclasses with `targeted_ops` matching their existing rewrite guards: - `MemoryFormatOpsPass` uses the `DimOrderOpsMap` keys. - `DimOrderOpsRevertPass` uses the `MemoryFormatOpsMap` keys. - `NormalizeTransposePass` targets `aten.t.default`. - `RemoveMixedTypeOperators` targets the operators handled by its promotion path. These declarations enable eligible non-targeted nodes to use the `ExportPass` fast-copy path, improving CombinedControl U55 lowering by ~3%. Differential Revision: D96247716
6cabc33 to
456b620
Compare
Summary:
Annotate four core
ExportPasssubclasses withtargeted_opsmatching their existing rewrite guards:MemoryFormatOpsPassuses theDimOrderOpsMapkeys.DimOrderOpsRevertPassuses theMemoryFormatOpsMapkeys.NormalizeTransposePasstargetsaten.t.default.RemoveMixedTypeOperatorstargets the operators handled by its promotion path.These declarations enable eligible non-targeted nodes to use the
ExportPassfast-copy path, improving CombinedControl U55 lowering by ~3%.Differential Revision: D96247716