Repository navigation
Add ETDump tracing to CpuBackend (#23926) - #23926
JakeStevens wants to merge 1 commit into
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/23926
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New FailureAs of commit 39fcadc with merge base acb20a1 ( NEW FAILURE - The following job has failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
|
@JakeStevens has exported this pull request. If you are a Meta employee, you can view the originating Diff in D125525223. |
This PR needs a
|
CpuBackendCpuBackend (#23926)
Summary: `CPUPlan` records one ETDump delegate event per step, named `provider/implementation:first_node[+N]`, so every provider is traced without provider changes. The XNNPACK provider enables XNNPACK runtime profiling when a tracer is attached and logs `XNNPACK:<operator> #<n>` events inside its step, with each operator's input and output shapes as JSON delegate metadata. Shapes come from XNNPACK's internal runtime (`src/xnnpack/subgraph.h`). That header dependency and the code that reads it are only compiled when `ET_EVENT_TRACER_ENABLED` is defined. `runner` writes an ETDump when `ET_CPU_ETDUMP` is set. Authored with Claude Code. Differential Revision: D125525223
4e8defc to
13597eb
Compare
Summary: `CPUPlan` records one ETDump delegate event per step, named `provider/implementation:first_node[+N]`, so every provider is traced without provider changes. The XNNPACK provider enables XNNPACK runtime profiling when a tracer is attached and logs `XNNPACK:<operator> #<n>` events inside its step, with each operator's input and output shapes as JSON delegate metadata. Shapes come from XNNPACK's internal runtime (`src/xnnpack/subgraph.h`). That header dependency and the code that reads it are only compiled when `ET_EVENT_TRACER_ENABLED` is defined. `runner` writes an ETDump when `ET_CPU_ETDUMP` is set. Authored with Claude Code. Differential Revision: D125525223
13597eb to
7f9ebe9
Compare
Summary: `CPUPlan` records one ETDump delegate event per step, named `provider/implementation:first_node[+N]`, so every provider is traced without provider changes. The XNNPACK provider enables XNNPACK runtime profiling when a tracer is attached and logs `XNNPACK:<operator> #<n>` events inside its step, with each operator's input and output shapes as JSON delegate metadata. Shapes come from XNNPACK's internal runtime (`src/xnnpack/subgraph.h`). That header dependency and the code that reads it are only compiled when `ET_EVENT_TRACER_ENABLED` is defined. `runner` writes an ETDump when `ET_CPU_ETDUMP` is set. Authored with Claude Code. Differential Revision: D125525223
7f9ebe9 to
99ef808
Compare
Summary: `CPUPlan` records one ETDump delegate event per step, named `provider/implementation:first_node[+N]`, so every provider is traced without provider changes. The XNNPACK provider enables XNNPACK runtime profiling when a tracer is attached and logs `XNNPACK:<operator> #<n>` events inside its step, with each operator's input and output shapes as JSON delegate metadata. Shapes come from XNNPACK's internal runtime (`src/xnnpack/subgraph.h`). That header dependency and the code that reads it are only compiled when `ET_EVENT_TRACER_ENABLED` is defined. `runner` writes an ETDump when `ET_CPU_ETDUMP` is set. Authored with Claude Code. Differential Revision: D125525223
99ef808 to
39fcadc
Compare
Summary:
CPUPlanrecords one ETDump delegate event per step, namedprovider/implementation:first_node[+N], so every provider is traced without provider changes. The XNNPACK provider enables XNNPACK runtime profiling when a tracer is attached and logsXNNPACK:<operator> #<n>events inside its step, with each operator's input and output shapes as JSON delegate metadata.Shapes come from XNNPACK's internal runtime (
src/xnnpack/subgraph.h). That header dependency and the code that reads it are only compiled whenET_EVENT_TRACER_ENABLEDis defined.runnerwrites an ETDump whenET_CPU_ETDUMPis set.Authored with Claude Code.
Differential Revision: D125525223