Simulating all threads in a scaled GPU workload results in prohibitive simulation cost. Cycle-level
simulation is orders of magnitude slower than native silicon, the only solution is to …

Deep learning kernels exhibit a high level of predictable memory accesses and compute
patterns, making GPU's architecture well-suited for their execution. Moreover, software and …

Ray tracing is traditionally only used in offline rendering to produce images of high fidelity
because it is computationally expensive. Recent Graphics Processing Units (GPUs) have …

… We would like to thank Cesar Avalos for his help in the project. We would also like to
thank Shichen Qiao and Matthew D. Sinclair for their work on per-stream stat in GPGPU-Sim. …

Simulating all threads in a scaled GPU workload results in prohibitive simulation cost. Cycle-level
simulation is orders of magnitude slower than native silicon, the only solution is to …

With the end of Moore’s law, computer architects have turned to alternative approaches to
enhance computational capabilities. One prominent strategy involves a shift towards …

Deep learning kernels exhibit predictable memory accesses and compute patterns, making
GPUs' parallel architecture well-suited for their execution. Software and runtime systems for …

GPUs, due to their massively-parallel computing architectures, provide high performance for
data-parallel applications. However, existing GPU simulators are too slow to enable …

Today, DNNs’ high computational complexity and sub-optimal device utilization present a
major roadblock to democratizing DNNs. To reduce the execution time and improve device …

Heterogenous systems consisting of processors of varying nature which complement each
other’s deficiencies are rapidly eclipsing the homogeneous systems of past. The consumer …