[all-commits] [llvm/llvm-project] 932ad9: [Support] FoldingSetNodeID::AddString(): reserve m...
Roman Lebedev via All-commits
all-commits at lists.llvm.org
Mon Jun 8 13:27:42 PDT 2020
Branch: refs/heads/master
Home: https://github.com/llvm/llvm-project
Commit: 932ad9941deffeb540563973564514e4f8b3cb63
https://github.com/llvm/llvm-project/commit/932ad9941deffeb540563973564514e4f8b3cb63
Author: Roman Lebedev <lebedev.ri at gmail.com>
Date: 2020-06-08 (Mon, 08 Jun 2020)
Changed paths:
M llvm/lib/Support/FoldingSet.cpp
Log Message:
-----------
[Support] FoldingSetNodeID::AddString(): reserve memory
Summary:
It is traditionally potentially very inefficient to not preallocate the memory,
but rely on reallocation every time you push something into vector.
For example, looking at unity build of RawSpeed
(`-O3 -g0 -emit-llvm -Xclang -disable-llvm-optzns`),
the memory story is as follows:
```
total runtime: 11.34s.
calls to allocation functions: 2694053 (237612/s)
temporary memory allocations: 645188 (56904/s)
peak heap memory consumption: 231.36MB
peak RSS (including heaptrack overhead): 397.39MB
```
Looking at details, `FoldingSetNodeID::AddString()` is noteworthy, frequently called and is allocation-heavy.
But it is quite obvious how many times we will push into `Bits` - we will push `String.size()` itself,
and then we will push once per every 4 bytes of `String` (padding last block).
And if we preallocate, we get:
```
total runtime: 11.20s.
calls to allocation functions: 2594704 (231669/s)
temporary memory allocations: 560004 (50000/s)
peak heap memory consumption: 231.36MB
peak RSS (including heaptrack overhead): 398.06MB
```
Which is a measurable win:
```
total runtime: -0.14s. # -1.23 %
calls to allocation functions: -99349 (719920/s) # -3.69 %
temporary memory allocations: -85184 (617275/s) # -13.2 % (!)
peak heap memory consumption: 0B
peak RSS (including heaptrack overhead): 0B
total memory leaked: 0B
```
Reviewers: efriedma, nikic, bkramer
Reviewed By: bkramer
Subscribers: hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D81342
More information about the All-commits
mailing list