gpu-microbench.git/constant_cycles_kernel.cu, branch master Lightweight, hyper-accurate microbenchmarks and measurement tools for GPU scheduling examination. Fix unlimited iterations in constant_cycles_kernel 2025-02-04T22:23:05+00:00 Joshua Bakita jbakita@cs.unc.edu 2025-02-04T22:23:05+00:00 c28c53c3b3c58b808553ba8475147d9e1dd6e3a5 






Ensure all benchmarks support --help and cleanup
2024-02-27T01:36:27+00:00

Joshua Bakita
jbakita@cs.unc.edu

2024-02-27T01:36:27+00:00

f1eb1f41ab81571d23654bb15af655c17152bcd6












Split SAFE() macro into API-specific typed variants
2024-02-20T01:39:39+00:00

Joshua Bakita
bakitajoshua@gmail.com

2024-02-20T01:39:39+00:00

cd9ee070e2fcaa49fe35944ea0fd60ed5d197ba2

Avoids incorrectly interpreting CUDA Driver Library error codes as
though they were CUDA Runtime Library error codes (the numbering is
similar, but not identical).

Also cleans up how we initialize and terminate a context for
capability checking in `mon_cross_ctx_copies`.





Avoids incorrectly interpreting CUDA Driver Library error codes as
though they were CUDA Runtime Library error codes (the numbering is
similar, but not identical).

Also cleans up how we initialize and terminate a context for
capability checking in `mon_cross_ctx_copies`.







Add constant_cycles_kernel benchmark + header split and Makefile
2023-06-09T23:38:01+00:00

Joshua Bakita
bakitajoshua@gmail.com

2023-06-09T23:38:01+00:00

5ba80e14efb595688a3dc3d49c212bc393840513

Benchmark supports:
=> Looping on the GPU for a specified number of iterations
=> Looping infinitely on the GPU
=> Logging the sum time (ns and ms) for all iterations to complete

Also splits `testbench.h` out of `copy_testbench.h` for use in other
benchmarks.





Benchmark supports:
=> Looping on the GPU for a specified number of iterations
=> Looping infinitely on the GPU
=> Logging the sum time (ns and ms) for all iterations to complete

Also splits `testbench.h` out of `copy_testbench.h` for use in other
benchmarks.