diff --git a/doc/sphinx/03_vibe/vibe.rst b/doc/sphinx/03_vibe/vibe.rst index a8f31816..6bfcd96b 100644 --- a/doc/sphinx/03_vibe/vibe.rst +++ b/doc/sphinx/03_vibe/vibe.rst @@ -31,7 +31,6 @@ as well as computing an auxiliary quantity :math:`d` that resemebles a kinetic e d = \frac{1}{2} q^0 \mathbf{u}\cdot\mathbf{u}. Parthenon-VIBE makes use of a Godunov-type finite volume scheme with options for slope-limited linear or WENO5 reconstruction, HLL fluxes, and second order Runge-Kutta time integration. -Characteristics Figure of Merit @@ -78,7 +77,7 @@ On Crossroads the relevant modules for the results shown here are: .. code-block:: bash - intel/2023.2.0 cray-mpich/8.1.25 + intel-classic/2023.2.0 cray-mpich/8.1.25 .. @@ -102,6 +101,8 @@ The benchmark includes an input file ``_burgers.pin_`` that specifies the base ( The executable `burgers-benchmark` will be built in `parthenon/build/benchmarks/burgers/` and can be run as, e.g. +Note that the + .. code-block:: bash NX=128 @@ -199,6 +200,12 @@ Throughput performance of Parthenon-VIBE on a 40GB A100 is provided within the f VIBE Throughput Performance on A100 + +Validation +========== + + + References ========== diff --git a/doc/sphinx/09_Microbenchmarks/M3_OSUMB/OSU_ats3_results.csv b/doc/sphinx/09_Microbenchmarks/M3_OSUMB/OSU_ats3_results.csv index 14cb042d..53183682 100644 --- a/doc/sphinx/09_Microbenchmarks/M3_OSUMB/OSU_ats3_results.csv +++ b/doc/sphinx/09_Microbenchmarks/M3_OSUMB/OSU_ats3_results.csv @@ -1,12 +1,12 @@ "Test","Rank settings","Message Size","Nodes","Result" -"osu_latency","1 per node","8 B","2", -"osu_bibw","1 per node","1 MB","2", -"osu_mbw_mr","1 per NIC","16 KB","2", -"osu_mbw_mr","1 per core","16 KB","2", -"osu_get_acc_latency","1 per node","8 B","2", -"osu_get","1 per node","8 B","2", -"osu_put","1 per node","8 B","2", -"osu_barrier","1 per physical core","N/A","full-system", -"osu_ibarrier","1 per physical core","N/A","full-system", -"osu_allreduce","1 per physical core","8B, 25 MB","full-system", -"osu_alltoall","1 per physical core","1 MB","full-system", \ No newline at end of file +"osu_latency","1 per node","8 B","2","1.61 us" +"osu_bibw","1 per node","1 MB","2","45307.17 MB/s" +"osu_mbw_mr","1 per NIC","16 KB","2","49656.45 MB/s" +"osu_mbw_mr","1 per core","16 KB","2","45198.46 MB/s" +"osu_get_acc_latency","1 per node","8 B","2","10.85 us" +"osu_get","1 per node","8 B","2","3.59 us" +"osu_put","1 per node","8 B","2","4.87 us" +"osu_barrier","1 per physical core","N/A","full-system","550.66 us" +"osu_ibarrier","1 per physical core","N/A","full-system","4802.82 us" +"osu_allreduce","1 per physical core","8B, 16 MB","full-system","345.55, 2477365.95 us" +"osu_alltoall","1 per node","8B","full-system","1954.35 us" \ No newline at end of file diff --git a/doc/sphinx/09_Microbenchmarks/M6_IOR/IOR.rst b/doc/sphinx/09_Microbenchmarks/M6_IOR/IOR.rst index 6a33b1ce..4127b1e1 100644 --- a/doc/sphinx/09_Microbenchmarks/M6_IOR/IOR.rst +++ b/doc/sphinx/09_Microbenchmarks/M6_IOR/IOR.rst @@ -20,9 +20,6 @@ The github repo also contains mdtest. Problem ------- -Figure of Merit ---------------- - Run Rules --------- @@ -71,6 +68,7 @@ Crossroads Full system tests were run with 5000 nodes and 10 tasks per node. Single node tests were run with 112 tasks per node. +This test was compiled with cce/16.0.0 and cray-mpich/8.1.26. .. csv-table:: IOR benchmark :file: ats3_ior.csv diff --git a/doc/sphinx/09_Microbenchmarks/M6_IOR/ats3_ior.csv b/doc/sphinx/09_Microbenchmarks/M6_IOR/ats3_ior.csv index 970bc06a..a5476c9f 100644 --- a/doc/sphinx/09_Microbenchmarks/M6_IOR/ats3_ior.csv +++ b/doc/sphinx/09_Microbenchmarks/M6_IOR/ats3_ior.csv @@ -1,5 +1,5 @@ Node_Config,MPIIO_task,POSIX_task,MPIIO_shared,POSIX_shared "Single Write",38615.88,38508.96,35964.32,37724.38 "Single Read",41830.12,42963.57,41933.79,42000.99 -"Full System Write",1213100.17,1292122.2,, -"Full System Read",863661.43,858742.17,, \ No newline at end of file +"Full System Write",1213100.17,1292122.2,TBD,TBD +"Full System Read",863661.43,858742.17,TBD,TBD \ No newline at end of file