Constantin Fürst
|
624e8b55ea
|
add script to record perf and make the flame graph
|
11 months ago |
Constantin Fürst
|
942d7be7e9
|
redo benchmarks for qdp
|
11 months ago |
Constantin Fürst
|
a83f208cd2
|
fix time evaluation for qdp bench
|
11 months ago |
Constantin Fürst
|
cc35131df8
|
Merge branch 'master' of https://git.constantin-fuerst.com/constantin/bachelor-thesis
|
11 months ago |
Constantin Fürst
|
cc8d203771
|
redo benchmarks for qdp, move previous results to old (folder)
|
11 months ago |
Constantin Fürst
|
94669924c8
|
implement cache in aggrj for qdp
|
11 months ago |
Constantin Fürst
|
b7559a18a6
|
remove cerr warning
|
11 months ago |
Constantin Fürst
|
c7877ecdf6
|
remove skeleton of now defunct function in qdp
|
11 months ago |
Constantin Fürst
|
20c6e54df7
|
remove broken implementation for non-divisible chunk-group-thread-counts
|
11 months ago |
Constantin Fürst
|
a3a8dff1aa
|
reset some changes to the aggregation and filter functions not quite needed
|
11 months ago |
Constantin Fürst
|
69aec6fa48
|
add plotter for the results of qdp which turns them into a donut-graph
|
11 months ago |
Constantin Fürst
|
122eab35b7
|
modify benchmarking code to measure time spent loading vectors too
|
11 months ago |
Constantin Fürst
|
3fc9bc6145
|
finish the section on using cache with qdp, also add a section on possible usage of dwcas for aba problem solution
|
11 months ago |
Constantin Fürst
|
98835799d4
|
also copy the invalid handlers pointer (see last commit) on CacheData copy constructor
|
11 months ago |
Constantin Fürst
|
75d72ce556
|
dont use uint64::max as invalid pointer but allocate a valid but empty vector, using its address as invalid
|
11 months ago |
Constantin Fürst
|
43254d0f3c
|
note that the cost observed for swq submission is lower than what reese kuper saw
|
11 months ago |
Constantin Fürst
|
8dcc248620
|
first pass of modifications to abstract and intro
|
11 months ago |
Constantin Fürst
|
b55196a7a7
|
redo reference types, using misc with howpublished for content that is not scientific work
|
11 months ago |
Constantin Fürst
|
94ee998c2e
|
finalize draft of abstract and intro
|
11 months ago |
Constantin Fürst
|
9bb68a7244
|
remove unnecessary cite by andres advice
|
11 months ago |
Constantin Fürst
|
8b635f7e87
|
update bachelor.pdf with recent changes
|
11 months ago |
Constantin Fürst
|
58f36279ec
|
reformulate implementation chapter - our chocie has changed and we now use push-pull and not smart-copy anymore for load balancer
|
11 months ago |
Constantin Fürst
|
eabba98972
|
include the new benchmarks for peak throughput and work division and modify their analysis
|
11 months ago |
Constantin Fürst
|
8bdc3e1d76
|
start formulation of thesis introduction
|
11 months ago |
Constantin Fürst
|
9d5fbe085b
|
formulate abstract
|
11 months ago |
Constantin Fürst
|
579494bc41
|
redo the plots for benchmarks of peak throughput and work division
|
11 months ago |
Constantin Fürst
|
db8751afc7
|
run the modified peak throughput benchmarks
|
11 months ago |
Constantin Fürst
|
1b6c60c49b
|
benchmark copy throughput for using 1,2,4,8 dsas and remove brute cpu bench (we steal it from andre)
|
11 months ago |
Constantin Fürst
|
b6f85ca202
|
redo benchmarks for pushpull
|
11 months ago |
Constantin Fürst
|
21bbf53e55
|
use local and one remote node for pushpull on intranode
|
11 months ago |
Constantin Fürst
|
c43bce3e13
|
add results for pushpull benchmark
|
11 months ago |
Constantin Fürst
|
850aebc6b9
|
update bachelor.pdf with the bullet points for abstract and intro
|
11 months ago |
Constantin Fürst
|
6b500c3396
|
cite figure source at end of caption and not mid-sentence for chapter2
|
11 months ago |
Constantin Fürst
|
25f55adcb2
|
formulate bullet points for abstract and introduction to the thesis
|
11 months ago |
Constantin Fürst
|
18ec95e201
|
adapt chapter on performance to the corrected measurements
|
11 months ago |
Constantin Fürst
|
23daabbd73
|
fix bad section references
|
11 months ago |
Constantin Fürst
|
321a4fb0bd
|
manually add data from communication with andre to the cpu benchmark plotters
|
11 months ago |
Constantin Fürst
|
1021197009
|
do not use the float-force parameter H but move to a more dynmic one (h!tb), also dont use Subsection anywhere instead use Section, add a small paragraph to the implementation chapter stating how we used the cache in qdp
|
11 months ago |
Constantin Fürst
|
27c57aa4ce
|
add node for content of evaluation chapter
|
11 months ago |
Constantin Fürst
|
9e329d39e4
|
add pushpul benchmark for peak throughput
|
11 months ago |
Constantin Fürst
|
33730c4a99
|
add all images which for now were committed only with -f
|
11 months ago |
Constantin Fürst
|
a580939d29
|
rewrite chapter 3 with the corrected benchmark results, add these corrected results, re-add structograms with different names
|
11 months ago |
Constantin Fürst
|
89d2a6c71f
|
redo the structograms for the benchmark code
|
11 months ago |
Constantin Fürst
|
94818536cd
|
improve the section on qdp in state chapter and use (redone) graphic for simple query
|
11 months ago |
Constantin Fürst
|
4f27e9c9c0
|
remove pdf files from gitignore
|
11 months ago |
Constantin Fürst
|
7572350b28
|
apply recommendations of andre to chapter 5
|
11 months ago |
Constantin Fürst
|
c6495b8b02
|
write introductory paragraph to design section
|
11 months ago |
Constantin Fürst
|
d1cc3e3b0c
|
modification to qdp benchmark, returns to per-chunk barrier wait, uses userspace semaphore for one-way barrier from scan_b to aggr_j as scan_b should submit asap but aggr_j should wait on submission from scan_b, contains TODO for modifying code to support chunkcount not divisible by 2
|
11 months ago |
Constantin Fürst
|
bf79435ff0
|
add new benchmark plots from the rewritten microbench
|
11 months ago |
Constantin Fürst
|
8ab5eb4902
|
finish adapting plotters to new result style, add division by thread count to the throughput plotters, adjust figure sizes to be small (larger font when scaled up in latex)
|
11 months ago |