This contains my bachelors thesis and associated tex files, code snippets and maybe more.
Topic: Data Movement in Heterogeneous Memories with Intel Data Streaming Accelerator
You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
Constantin Fürst
7abd83ca45
fix offloading cache bug, introduced by not using maxptr for secondary invalid value, more care needed to be taken on when the secondary invalid would be set and how, now we set in in cachedata:init for both the local task in access and the one in cache state
11 months ago
..
evaluation-results
improve debug output for relwithdebinfo in qdp, fix filename for record perf script, add perf.svg with better debug info
11 months ago
src
remove overlap-execution barriers and run for the entire block
11 months ago
.gitignore
add query driven prefetching code repository copy
11 months ago
CMakeLists.txt
improve debug output for relwithdebinfo in qdp, fix filename for record perf script, add perf.svg with better debug info
11 months ago
README.md
prettify credit in the readme
11 months ago
bench_max.sh
add prelimianry results, modify the launch script and provide macro-based selection of parameters for the three modes {dram,hbm,prefetch}
11 months ago
plotter.py
remove vector-load timing as its too expensive
11 months ago
record-perf.sh
improve debug output for relwithdebinfo in qdp, fix filename for record perf script, add perf.svg with better debug info
11 months ago
Constantin Fürst
7abd83ca45