[all-commits] [llvm/llvm-project] 73eb9b: [InstrProf] Evaluate function order using test tra...

[Ellis Hoag via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 73eb9b33147ba5157cbf5d8276ee718629dfbbda
      https://github.com/llvm/llvm-project/commit/73eb9b33147ba5157cbf5d8276ee718629dfbbda
  Author: Ellis Hoag <ellis.sparky.hoag at gmail.com>
  Date:   2024-05-23 (Thu, 23 May 2024)

  Changed paths:
    M llvm/include/llvm/ProfileData/InstrProf.h
    M llvm/lib/ProfileData/InstrProf.cpp
    A llvm/test/tools/llvm-profdata/show-order-error.proftext
    M llvm/test/tools/llvm-profdata/show-order.proftext
    M llvm/tools/llvm-profdata/llvm-profdata.cpp
    M llvm/unittests/ProfileData/BPFunctionNodeTest.cpp

  Log Message:
  -----------
  [InstrProf] Evaluate function order using test traces (#92451)

The `llvm-profdata order` command is used to compute a function order
using traces from the input profile. Add the `--num-test-traces` flag to
keep aside N traces to evalute this order. These test traces are assumed
to be the actual function execution order in some experiment. The output
is a number that represents how many page faults we got. Lower is
better.

I tested on a large profile I already had.
```
llvm-profdata order default.profdata --num-test-traces=30
# Ordered 149103 functions
# Total area under the page fault curve: 2.271827e+09
...
```

I also improved `TemporalProfTraceTy::createBPFunctionNodes()` in a few
ways:
* Simplified how `UN`s are computed
* Change how the initial `Node` order is computed
* Filter out rare and common `UN`s
* Output vector is an aliased argument instead of a return

These changes slightly improved the evaluation in my test.
```
llvm-profdata order default.profdata --num-test-traces=30
# Ordered 149103 functions
# Total area under the page fault curve: 2.268586e+09
...
```



To unsubscribe from these emails, change your notification settings at https://github.com/llvm/llvm-project/settings/notifications