weaselab/conflict-set
1
Fork 1
Code Issues 5 Pull Requests Actions 1 Packages Releases 13 Activity

Update README.md
CI / pre-commit (push) Successful in 1m59s
Details
CI / release (arm64, ubuntu-latest-arm64) (push) Successful in 1m51s
Details
CI / test (-DCMAKE_BUILD_TYPE=Debug, debug) (push) Successful in 2m11s
Details
CI / test (-DCMAKE_CXX_FLAGS=-DUSE_64_BIT=1, 64-bit-versions) (push) Successful in 2m11s
Details
CI / test (-DCMAKE_C_COMPILER=gcc -DCMAKE_CXX_COMPILER=g++, gcc) (push) Successful in 2m1s
Details
CI / test (-DUSE_SIMD_FALLBACK=ON, simd-fallback) (push) Successful in 2m10s
Details
CI / release (amd64, ubuntu-latest-amd64) (push) Successful in 4m13s
Details
CI / coverage (push) Successful in 2m48s
Details

Browse Source
This commit is contained in:
andrew
2026-07-14 14:32:08 -04:00
parent 7c6c116713
commit 9b7199567b
1 changed files with 34 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+34 -23
View File
@@ -2,7 +2,16 @@ A data structure for optimistic concurrency control on ranges of bitwise-lexicog
Intended as an alternative to FoundationDB's skip list.
Hardware for all benchmarks is an AMD Ryzen 9 7900 with (2x32GB) 5600MT/s CL28-34-34-89 1.35V RAM
Hardware for all benchmarks is an AMD Ryzen 9 7900 with (2x32GB) 5600MT/s CL28-34-34-89 1.35V RAM.
```
$ clang++ --version
Ubuntu clang version 21.1.8 (6ubuntu1)
Target: x86_64-pc-linux-gnu
Thread model: posix
InstalledDir: /usr/lib/llvm-21/bin
```
# Microbenchmark
@@ -10,44 +19,45 @@ Hardware for all benchmarks is an AMD Ryzen 9 7900 with (2x32GB) 5600MT/s CL28-3
| ns/op | op/s | err% | ins/op | cyc/op | IPC | bra/op | miss% | total | benchmark
|--------------------:|--------------------:|--------:|----------------:|----------------:|-------:|---------------:|--------:|----------:|:----------
| 172.03 | 5,812,791.77 | 0.4% | 3,130.62 | 879.00 | 3.562 | 509.23 | 0.0% | 0.01 | `point reads`
| 167.44 | 5,972,130.71 | 0.2% | 3,065.14 | 862.27 | 3.555 | 494.30 | 0.0% | 0.01 | `prefix reads`
| 238.77 | 4,188,130.84 | 0.9% | 3,589.93 | 1,259.30 | 2.851 | 637.12 | 0.0% | 0.01 | `range reads`
| 424.01 | 2,358,426.70 | 0.2% | 5,620.05 | 2,242.35 | 2.506 | 854.80 | 1.7% | 0.01 | `point writes`
| 418.45 | 2,389,780.56 | 0.4% | 5,525.07 | 2,211.05 | 2.499 | 831.71 | 1.7% | 0.01 | `prefix writes`
| 254.87 | 3,923,568.88 | 2.6% | 3,187.01 | 1,366.50 | 2.332 | 529.11 | 2.7% | 0.02 | `range writes`
| 675.96 | 1,479,374.50 | 3.3% | 7,735.41 | 3,468.60 | 2.230 | 1,386.02 | 1.8% | 0.01 | `monotonic increasing point writes`
| 137,986.20 | 7,247.10 | 0.6% | 789,752.33 | 699,462.00 | 1.129 | 144,824.14 | 0.0% | 0.01 | `worst case for radix tree`
| 21.63 | 46,231,564.03 | 1.0% | 448.00 | 107.14 | 4.181 | 84.00 | 0.0% | 0.01 | `create and destroy`
| 171.37 | 5,835,467.28 | 0.5% | 2,915.46 | 629.31 | 4.633 | 502.91 | 0.0% | 0.01 | `point reads`
| 168.16 | 5,946,774.62 | 0.5% | 2,859.73 | 619.03 | 4.620 | 488.59 | 0.0% | 0.01 | `prefix reads`
| 245.86 | 4,067,294.63 | 0.3% | 3,508.97 | 904.82 | 3.878 | 627.73 | 0.0% | 0.01 | `range reads`
| 381.14 | 2,623,691.76 | 0.2% | 5,127.16 | 1,402.60 | 3.655 | 830.59 | 1.7% | 0.01 | `point writes`
| 376.24 | 2,657,887.07 | 0.3% | 5,062.85 | 1,381.07 | 3.666 | 811.68 | 1.6% | 0.01 | `prefix writes`
| 257.09 | 3,889,688.44 | 3.8% | 3,010.09 | 949.42 | 3.170 | 521.34 | 2.9% | 0.01 | `range writes`
| 629.71 | 1,588,026.28 | 4.0% | 6,809.60 | 2,320.32 | 2.935 | 1,247.08 | 1.3% | 0.01 | `monotonic increasing point writes`
| 126,164.50 | 7,926.16 | 1.7% | 772,460.25 | 463,264.67 | 1.667 | 141,512.00 | 0.2% | 0.01 | `worst case for radix tree`
| 15.33 | 65,217,669.23 | 0.4% | 299.00 | 56.45 | 5.297 | 64.00 | 0.0% | 0.01 | `create and destroy`
## Radix tree (this implementation)
| ns/op | op/s | err% | ins/op | cyc/op | IPC | bra/op | miss% | total | benchmark
|--------------------:|--------------------:|--------:|----------------:|----------------:|-------:|---------------:|--------:|----------:|:----------
| 11.18 | 89,455,125.34 | 0.6% | 185.37 | 57.08 | 3.248 | 41.51 | 0.4% | 0.01 | `point reads`
| 14.53 | 68,800,688.89 | 0.4% | 282.41 | 74.80 | 3.776 | 55.06 | 0.3% | 0.01 | `prefix reads`
| 36.54 | 27,367,576.87 | 0.2% | 798.06 | 188.90 | 4.225 | 141.69 | 0.2% | 0.01 | `range reads`
| 16.69 | 59,912,106.02 | 0.6% | 314.57 | 86.29 | 3.645 | 39.84 | 0.4% | 0.01 | `point writes`
| 30.09 | 33,235,744.07 | 0.5% | 591.33 | 155.92 | 3.793 | 82.69 | 0.2% | 0.01 | `prefix writes`
| 35.77 | 27,956,388.03 | 1.4% | 682.25 | 187.63 | 3.636 | 96.12 | 0.1% | 0.01 | `range writes`
| 74.04 | 13,505,408.41 | 2.7% | 1,448.95 | 392.10 | 3.695 | 260.53 | 0.1% | 0.01 | `monotonic increasing point writes`
| 330,984.50 | 3,021.29 | 1.9% | 3,994,153.50 | 1,667,309.00 | 2.396 | 806,019.50 | 0.0% | 0.01 | `worst case for radix tree`
| 92.46 | 10,814,961.65 | 0.5% | 1,800.00 | 463.41 | 3.884 | 297.00 | 0.0% | 0.01 | `create and destroy`
| 12.81 | 78,088,759.03 | 0.7% | 187.38 | 47.15 | 3.974 | 33.70 | 0.5% | 0.01 | `point reads`
| 16.77 | 59,626,501.14 | 0.4% | 277.61 | 61.74 | 4.497 | 44.76 | 0.4% | 0.01 | `prefix reads`
| 42.45 | 23,556,818.87 | 0.4% | 856.96 | 156.09 | 5.490 | 126.22 | 0.2% | 0.01 | `range reads`
| 15.76 | 63,453,196.94 | 0.3% | 249.89 | 58.04 | 4.306 | 33.21 | 0.5% | 0.01 | `point writes`
| 29.71 | 33,662,499.39 | 0.1% | 509.14 | 109.33 | 4.657 | 70.26 | 0.5% | 0.01 | `prefix writes`
| 35.77 | 27,956,388.03 | 0.8% | 614.18 | 131.72 | 4.663 | 85.57 | 0.1% | 0.01 | `range writes`
| 80.13 | 12,480,456.47 | 1.5% | 1,279.04 | 294.90 | 4.337 | 234.68 | 0.1% | 0.01 | `monotonic increasing point writes`
| 360,748.00 | 2,772.02 | 2.6% | 4,401,835.00 | 1,318,754.00 | 3.338 | 728,537.00 | 0.0% | 0.01 | `worst case for radix tree`
| 90.69 | 11,027,103.45 | 1.0% | 1,686.00 | 333.80 | 5.051 | 284.00 | 0.0% | 0.01 | `create and destroy`
# "Real data" test
Point queries only, best of three runs. Gc ratio is the ratio of time spent doing garbage collection to time spent adding writes or doing garbage collection. Lower is better.
Point queries only. Gc ratio is the ratio of time spent doing garbage collection to time spent adding writes or doing garbage collection. Lower is better.
## skip list
```
Check: 4.47891 seconds, 364.05 MB/s, Add: 4.55599 seconds, 123.058 MB/s, Gc ratio: 37.1145%
Check: 4.42779 seconds, 368.253 MB/s, Add: 4.64942 seconds, 120.586 MB/s, Gc ratio: 28.8784%, Peak idle memory: 5.51735e+06
```
## radix tree
```
Check: 0.953012 seconds, 1710.94 MB/s, Add: 1.30025 seconds, 431.188 MB/s, Gc ratio: 43.9816%, Peak idle memory: 2.28375e+06
Check: 0.891163 seconds, 1829.69 MB/s, Add: 1.23064 seconds, 455.579 MB/s, Gc ratio: 42.9417%, Peak idle memory: 2.28333e+06
```
## hash table
@@ -55,5 +65,6 @@ Check: 0.953012 seconds, 1710.94 MB/s, Add: 1.30025 seconds, 431.188 MB/s, Gc ra
(The hash table implementation doesn't work on range queries, and its purpose is to provide an idea of how fast point queries can be)
```
Check: 0.804094 seconds, 2027.81 MB/s, Add: 0.652952 seconds, 858.645 MB/s, Gc ratio: 35.3885%
Check: 0.858484 seconds, 1899.33 MB/s, Add: 0.632886 seconds, 885.868 MB/s, Gc ratio: 41.252%, Peak idle memory: 0
```