The confrontation of complex Earth system model (ESM) codes with novel supercomputing architectures poses challenges to efficient modeling and job submission strategies. The modular setup of these ...models naturally fits a modular supercomputing architecture (MSA), which tightly integrates heterogeneous hardware resources into a larger and more flexible high-performance computing (HPC) system. While parts of the ESM codes can easily take advantage of the increased parallelism and communication capabilities of modern GPUs, others lag behind due to the long development cycles or are better suited to run on classical CPUs due to their communication and memory usage patterns. To better cope with these imbalances between the development of the model components, we performed benchmark campaigns on the Jülich Wizard for European Leadership Science (JUWELS) modular HPC system. We enabled the weather and climate model Icosahedral Nonhydrostatic (ICON) to run in a coupled atmosphere–ocean setup, where the ocean and the model I/O is running on the CPU Cluster, while the atmosphere is simulated simultaneously on the GPUs of JUWELS Booster (ICON-MSA). Both atmosphere and ocean are running globally with a resolution of 5 km. In our test case, an optimal configuration in terms of model performance (core hours per simulation day) was found for the combination of 84 GPU nodes on the JUWELS Booster module to simulate the atmosphere and 80 CPU nodes on the JUWELS Cluster module, of which 63 nodes were used for the ocean simulation and the remaining 17 nodes were reserved for I/O. With this configuration the waiting times of the coupler were minimized. Compared to a simulation performed on CPUs only, the MSA approach reduces energy consumption by 45 % with comparable runtimes. ICON-MSA is able to scale up to a significant portion of the JUWELS system, making best use of the available computing resources. A maximum throughput of 170 simulation days per day (SDPD) was achieved when running ICON on 335 JUWELS Booster nodes and 268 Cluster nodes.
We determine the masses of the light and the strange quarks in the
MS
-scheme using our high-statistics lattice simulation of QCD with dynamical Wilson fermions. For the light quark mass we find
m
...light
MS
(2
GeV) = 2.7 (2)
MeV
, which is lower than in quenched simulations. For the strange quark, in a sea of two dynamical light quarks, we obtain
m
strange
MS
(2
GeV) = 140(20)
MeV
.
SESAM and T χL results for Wilson action—A status report Lippert, Th; Bali, G.; Eicker, N. ...
Nuclear physics. B, Proceedings supplement/Nuclear physics. B, Proceedings supplements,
1998, 1998-1-00, Letnik:
60, Številka:
1
Journal Article
Recenzirano
Odprti dostop
Results from two studies of full QCD with two flavours of dynamical Wilson fermions are presented. At
β = 5.6, the region
0.83
>
m
x
m
p
>
0.56
at
m
x
a
>
(
0.23
L
)
−
1
is explored. The SESAM ...collaboration has generated ensembles of about 200 statistically independent configurations on a 16
3 × 32-lattice at three different
k-values and is entering the final phase of data analysis. The T
χL simulation on a 24
3 × 40-lattice at two
k-values has reached half statistics and data analysis has started recently, hence most results presented here are preliminary. The focus of this report is threefold: (
i) we demonstrate that algorithmic improvements like fast Krylov solvers and parallel preconditioning recently introduced can be put into practise in full QCD simulations, (
ii) we present encouraging observations as to the critical dynamics of the Hybrid Monte Carlo algorithm in the approach to the chiral limit, (
iii) we mention signal improvements of noisy estimator techniques for disconnected diagrams to the
π-
N σ term, and (iv) we report on SESAM's results for light hadron spectrum, light quark masses, and heavy quarkonia.
PDF
