commit | 8b8f926fc3f0e8f002d0a8e97aab9500e4db83a7 | [log] [tgz] |
---|---|---|
author | Keith Randall <khr@golang.org> | Mon Jul 06 20:46:31 2020 -0700 |
committer | Keith Randall <khr@golang.org> | Mon Aug 17 22:00:17 2020 +0000 |
tree | d6b48dfe11fcc7a5ff93cf99fc625c79d5aec234 | |
parent | 4e5ed83e8d2fbbbc8f6524f40ab3b6733dc57a38 [diff] |
runtime: bit parallel implementation of findBitRange64 Use a bit-parallel implementation of findBitRange64. It uses a repeated shift-'N-and technique to erase all the free marks that are too small for the allocation. Also some small improvements to find1. name old time/op new time/op delta FindBitRange64/Pattern00Size2-16 4.19ns ± 0% 2.26ns ± 0% -46.04% (p=0.000 n=10+8) FindBitRange64/Pattern00Size8-16 4.19ns ± 0% 2.12ns ± 0% -49.35% (p=0.000 n=9+10) FindBitRange64/Pattern00Size32-16 4.20ns ± 0% 2.12ns ± 0% -49.49% (p=0.000 n=10+8) FindBitRange64/PatternFFFFFFFFFFFFFFFFSize2-16 2.13ns ± 0% 2.27ns ± 0% +6.28% (p=0.000 n=10+10) FindBitRange64/PatternFFFFFFFFFFFFFFFFSize8-16 2.13ns ± 0% 4.46ns ± 0% +109.39% (p=0.000 n=10+9) FindBitRange64/PatternFFFFFFFFFFFFFFFFSize32-16 2.13ns ± 1% 5.58ns ± 0% +162.37% (p=0.000 n=10+9) FindBitRange64/PatternAASize2-16 22.2ns ± 0% 2.3ns ± 0% -89.82% (p=0.000 n=9+8) FindBitRange64/PatternAASize8-16 22.2ns ± 0% 2.1ns ± 1% -90.41% (p=0.000 n=9+10) FindBitRange64/PatternAASize32-16 22.2ns ± 0% 2.1ns ± 1% -90.43% (p=0.000 n=10+10) FindBitRange64/PatternAAAAAAAAAAAAAAAASize2-16 156ns ± 1% 2ns ± 0% -98.54% (p=0.000 n=10+10) FindBitRange64/PatternAAAAAAAAAAAAAAAASize8-16 155ns ± 1% 2ns ± 0% -98.63% (p=0.000 n=10+8) FindBitRange64/PatternAAAAAAAAAAAAAAAASize32-16 155ns ± 0% 2ns ± 1% -98.63% (p=0.000 n=8+10) FindBitRange64/Pattern80000000AAAAAAAASize2-16 81.2ns ± 0% 2.3ns ± 1% -97.21% (p=0.000 n=10+10) FindBitRange64/Pattern80000000AAAAAAAASize8-16 81.1ns ± 0% 2.1ns ± 0% -97.39% (p=0.000 n=10+9) FindBitRange64/Pattern80000000AAAAAAAASize32-16 81.1ns ± 0% 2.1ns ± 0% -97.38% (p=0.000 n=10+10) FindBitRange64/PatternAAAAAAAA00000001Size2-16 76.8ns ± 1% 2.3ns ± 0% -97.05% (p=0.000 n=10+10) FindBitRange64/PatternAAAAAAAA00000001Size8-16 76.6ns ± 0% 2.1ns ± 0% -97.23% (p=0.000 n=8+10) FindBitRange64/PatternAAAAAAAA00000001Size32-16 76.7ns ± 0% 2.1ns ± 0% -97.23% (p=0.000 n=9+9) FindBitRange64/PatternBBBBBBBBBBBBBBBBSize2-16 2.13ns ± 0% 2.27ns ± 0% +6.57% (p=0.000 n=8+8) FindBitRange64/PatternBBBBBBBBBBBBBBBBSize8-16 76.7ns ± 0% 2.9ns ± 0% -96.20% (p=0.000 n=9+10) FindBitRange64/PatternBBBBBBBBBBBBBBBBSize32-16 76.7ns ± 0% 2.9ns ± 0% -96.20% (p=0.000 n=10+10) FindBitRange64/Pattern80000000BBBBBBBBSize2-16 2.12ns ± 0% 2.27ns ± 1% +6.74% (p=0.000 n=10+10) FindBitRange64/Pattern80000000BBBBBBBBSize8-16 44.8ns ± 0% 2.9ns ± 0% -93.49% (p=0.000 n=9+10) FindBitRange64/Pattern80000000BBBBBBBBSize32-16 44.9ns ± 0% 2.9ns ± 0% -93.49% (p=0.000 n=10+8) FindBitRange64/PatternBBBBBBBB00000001Size2-16 4.20ns ± 1% 2.27ns ± 1% -46.02% (p=0.000 n=10+10) FindBitRange64/PatternBBBBBBBB00000001Size8-16 44.9ns ± 0% 2.9ns ± 1% -93.51% (p=0.000 n=10+9) FindBitRange64/PatternBBBBBBBB00000001Size32-16 44.9ns ± 0% 2.9ns ± 0% -93.51% (p=0.000 n=10+9) FindBitRange64/PatternCCCCCCCCCCCCCCCCSize2-16 4.19ns ± 0% 2.26ns ± 0% -46.10% (p=0.000 n=10+10) FindBitRange64/PatternCCCCCCCCCCCCCCCCSize8-16 76.5ns ± 0% 2.9ns ± 0% -96.19% (p=0.000 n=8+7) FindBitRange64/PatternCCCCCCCCCCCCCCCCSize32-16 76.5ns ± 0% 2.9ns ± 0% -96.19% (p=0.000 n=10+8) FindBitRange64/Pattern4444444444444444Size2-16 76.4ns ± 0% 2.3ns ± 0% -97.04% (p=0.000 n=8+10) FindBitRange64/Pattern4444444444444444Size8-16 76.5ns ± 0% 2.1ns ± 0% -97.23% (p=0.000 n=9+10) FindBitRange64/Pattern4444444444444444Size32-16 76.5ns ± 0% 2.1ns ± 0% -97.23% (p=0.000 n=8+10) FindBitRange64/Pattern4040404040404040Size2-16 40.3ns ± 0% 2.3ns ± 0% -94.38% (p=0.000 n=7+10) FindBitRange64/Pattern4040404040404040Size8-16 40.2ns ± 0% 2.1ns ± 0% -94.75% (p=0.000 n=10+10) FindBitRange64/Pattern4040404040404040Size32-16 40.2ns ± 0% 2.1ns ± 0% -94.76% (p=0.000 n=10+6) FindBitRange64/Pattern4000400040004000Size2-16 22.2ns ± 0% 2.2ns ± 0% -89.86% (p=0.001 n=8+9) FindBitRange64/Pattern4000400040004000Size8-16 22.2ns ± 0% 2.1ns ± 0% -90.52% (p=0.000 n=8+10) FindBitRange64/Pattern4000400040004000Size32-16 22.2ns ± 1% 2.1ns ± 0% -90.50% (p=0.000 n=10+10) The cases that slow down aren't really that slow, and those inputs never actually occur (there's a short circuit before the call to findBitRange64 for that case). Change-Id: I50fae62915098032d8ce7fa57ef29eee9deb01ba Reviewed-on: https://go-review.googlesource.com/c/go/+/241279 Reviewed-by: Michael Knyszek <mknyszek@google.com>
Go is an open source programming language that makes it easy to build simple, reliable, and efficient software.
Gopher image by Renee French, licensed under Creative Commons 3.0 Attributions license.
Our canonical Git repository is located at https://go.googlesource.com/go. There is a mirror of the repository at https://github.com/golang/go.
Unless otherwise noted, the Go source files are distributed under the BSD-style license found in the LICENSE file.
Official binary distributions are available at https://golang.org/dl/.
After downloading a binary release, visit https://golang.org/doc/install or load doc/install.html in your web browser for installation instructions.
If a binary distribution is not available for your combination of operating system and architecture, visit https://golang.org/doc/install/source or load doc/install-source.html in your web browser for source installation instructions.
Go is the work of thousands of contributors. We appreciate your help!
To contribute, please read the contribution guidelines: https://golang.org/doc/contribute.html
Note that the Go project uses the issue tracker for bug reports and proposals only. See https://golang.org/wiki/Questions for a list of places to ask questions about the Go language.