Modern real-time systems require accurate characterization of task timing behavior to ensure predictable performance, particularly on complex hardware architectures. Existing methods, such as worst-case execution time analysis, often fail to capture the fine-grained timing behaviors of a task under varying resource contexts (e.g., an allocation of cache, memory bandwidth, and CPU frequency), which is necessary to achieve efficient resource utilization. In this paper, we introduce a novel generative profiling approach that synthesizes context-dependent, fine-grained timing profiles for real-time tasks, including those for unmeasured resource allocations. Our approach leverages a nonparametric, conditional multi-marginal Schrödinger Bridge (MSB) formulation to generate accurate execution profiles for unseen resource contexts, with maximum likelihood guarantees. We demonstrate the efficiency and effectiveness of our approach through real-world benchmarks, and showcase its practical utility in a representative case study of adaptive multicore resource allocation for real-time systems.
Figures & tables
Fig. 1 : Effect of CPU frequency, cache, and memory bandwidth on the instruction retirement rate of fft [ 74 ] . The benchmark shows distinct phases, with varying relationships (no effect, linear, nonlinear) between instruction rate and CPU frequency, depending on resource allocation (middle phase).
Fig. 2 : Distributions of microarchitectural execution states (rates of instructions, cache requests and cache misses) of fft at three time points under two different resource contexts.
Fig. 3 : Our proposed generative profiling algorithm scheme with maximum-likelihood guarantee. From empirical profiles of a task’s microarchitectural execution states, conditioned on a sparse set of resource allocations B′ , we generate ‘synthetic’ profiles for the unknown resource allocations.
Fig. 4 : The relationship between a transport plan M , its projections, and the transport cost C for ns=3 empirical distributions {μσ}σ∈[[ns]] . Unimarginal projections equal the distributions, and for the three arbitrary colored points, [Mi1,i2,i3] encodes the total probability mass transported, and [Ci1,i2,i3] the per-unit cost thereof, along the grey-colored path therebetween. Similarly, the bimarginal projections of M and the pairwise cost c pertain to the pairwise sections of the path.
Fig. 5 : Maximum-likelihood synthetic profile ( blue ), mean synthetic profile ( red ), and all empirical profiles ( grey ) for the benchmarks fft and canneal when β=(7,12,2.1)⊤ on our default experimental platform.
Fig. 6 : Maximum-likelihood synthetic profile ( blue ), mean synthetic profile ( red ), and all empirical profiles ( grey ) for the benchmarks fft and canneal when β=(13,11,2.1)⊤ on PlatformLarge .
Fig. 7 : Accuracy and relative profiling time vs. % of resource contexts used for training (workload canneal ).
Baseline
Generative
Improvement
blackscholes
0.0429
0.0343
20.0%
bodytrack
0.0437
0.0375
14.2%
canneal
0.0227
0.0027
88.1%
dedup
0.0321
0.0191
40.5%
fft
0.0508
0.0478
5.9%
fluidanimate
0.0357
0.0275
23.0%
TABLE I : Per-benchmark accuracy (normalized DTW) of baseline vs. generated profiles, both trained on ≈6% of resource contexts, averaged over all β∈B. Smaller DTW indicates better accuracy. Improvement % is computed via 100×(baseline DTW−generative DTW)/ baseline DTW .
Count
Mean
90th
95th
99th
Max
28347
1.068
1.536
2.008
6.204
10.727
TABLE II : Runtime Overhead of DNA in μ s
Fig. 8 : Taskset Schedulability
Total Time (hrs)
# Empirical Profiles
Empirical
231
456,000
Baseline
0.64
1,250
Generative
1.14
1,250
TABLE III : Avg. End-to-end Measurement & Generation Time
Fig. 9 : DNA Performance Comparison using Generative vs. Baseline vs. Empirical Profiles.