Write a Blog >>
LCTES 2019
Sat 22 - Fri 28 June 2019 Phoenix, Arizona, United States
co-located with PLDI 2019
Sun 23 Jun 2019 16:30 - 16:35 at 105A - Session 4: Benchmarking and In-progress Works Chair(s): Hyunok Oh

Modern GPUs are the most successful accelerators as they provide outstanding performance gain by using CUDA or OpenCL programming models. For maximum performance, programmers typically try to maximize the number of thread blocks of target programs, and GPUs also generally attempt to allocate the maximum number of thread blocks to their GPU cores. However, many recent studies have pointed out that simply allocating the maximum number of thread blocks to GPU cores does not always guarantee the best performance. Thus, identifying proper number of thread blocks per GPU core is a major challenge. Despite these studies, most existing architectural techniques cannot be directly applied to current GPU hardware. Furthermore, the optimal number of thread blocks can vary significantly depending on the target hardware and application characteristics. To solve these problems, this study proposes a just-in-time thread block number adjustment system using CUDA binary modification upon an LLVM compiler framework, referred to as the CTA Limiter, in order to dynamically maximize GPU performance on real GPUs without reprograming. The framework gradually reduces the number of concurrent thread blocks of target CUDA workloads using extra shared memory allocation, and compares the execution time with the previous version to automatically identify the optimal number of thread blocks. The results showed meaningful performance improvements, averaging at 30%, 40%, and 44%, in GTX 960, GTX 1050, and GTX 1080 Ti, respectively.

Sun 23 Jun

Displayed time zone: Tijuana, Baja California change

16:00 - 16:45
Session 4: Benchmarking and In-progress WorksLCTES 2019 at 105A
Chair(s): Hyunok Oh Hanyang Univ
16:00
15m
Full-paper
BitBench: A Benchmark for Bitstream Computing
LCTES 2019
Kyle Daruwalla University of Wisconsin – Madison, Heng Zhuo University of Wisconsin - Madison, Carly Schulz University of Wisconsin - Madison, Mikko H. Lipasti
16:15
5m
Short-paper
PANDORA: A Parallelizing Approximation-Discovery Framework (Work in progress)
LCTES 2019
Greg Stitt University of Florida, David Campbell University of Florida
16:20
5m
Short-paper
On Intermittence Bugs in the Battery-less Internet of Things (Work in progress)
LCTES 2019
Andrea Maioli Politecnico di Milano, Italy, Luca Mottola Politecnico di Milano, Italy and RI.Se SICS, Sweden, Muhammad Hamad Alizai LUMS, Pakistan, Junaid Haroon Siddiqui
16:25
5m
Short-paper
Raising Binaries to LLVM IR with MCTOLL (Work in progress)
LCTES 2019
16:30
5m
Short-paper
A Compiler-based Approach for GPGPU Performance Calibration using TLP Modulation (Work in progress)
LCTES 2019
Yongseung Yu Hanyang University, Seokwon Kang Hanyang University, Yongjun Park Hanyang University
16:35
5m
Short-paper
An Empirical Comparison between Monkey Testing and Human Testing (Work in progress)
LCTES 2019
Mostafa Mohammed Virginia Tech, Haipeng Cai Washington State University, USA, Na Meng Virginia Tech