55faf4c5bc
Recommend simdjson::ondemand over simdjson::builtin::ondemand ( #1380 )
...
Co-authored-by: Daniel Lemire <lemire@gmail.com>
2021-01-14 17:33:49 -05:00
5add8ac255
Rearrange benchmarks to be easier to create
2021-01-04 12:33:41 -08:00
dfc510f009
Add bench_ondemand_largerandom to check theory about executable format
2020-12-20 11:39:56 -08:00
e7e09e444c
Use find_field in benchmark
2020-12-20 11:39:56 -08:00
07a6e098c8
This would allow users to find out what builtin is. ( #1227 )
...
* This would allow users to find out what builtin is.
* Trying another approach.
* Added instructions.
* Cleaning up the printout.
* Let us be less invasive.
* Adding a comment.
2020-10-15 21:58:42 -04:00
5b926b8196
Support array iteration over document
2020-10-06 11:29:45 -07:00
30fe86ed32
Use simdjson::builtin instead of haswell/begin+end
2020-10-04 12:47:30 -07:00
baf6607e74
Make ondemand build without #include "simdjson.cpp"
2020-10-04 12:47:30 -07:00
b234d74f43
Remove unnamed namespace from ondemand
2020-10-04 12:47:30 -07:00
021dded9dd
Add Kostya benchmarks
2020-10-04 12:47:30 -07:00
fe7a4d42d3
Fix top level values
2020-10-04 12:47:30 -07:00
e89d6353af
Add a "sum" benchmark with no appending to vector
2020-10-04 12:47:30 -07:00
c5bb74d184
Pave the way for non-record-based benchmarks
2020-10-04 12:47:30 -07:00
157604b3a5
I think that this is better (fairer) code.
2020-10-04 12:47:30 -07:00
045377a594
Fix errors with g++
2020-10-04 12:47:30 -07:00
b5c8030f19
Fix LargeRandom<OnDemand>
2020-10-04 12:47:30 -07:00
9e433c2f19
Move benchmarks into their own directories
2020-10-04 12:47:30 -07:00
John Keiser
Daniel Lemire