Lost in Abstraction: Pitfalls of Analyzing GPUs at the Intermediate Language Level
| Autor: | Bradford M. Beckmann, Alexandru Dutu, Akshay Jain, Anthony Gutierrez, John Kalamatianos, Sooraj Puthoor, Xianwei Zhang, Matthew D. Sinclair, Mark Wyse, Joseph Gross, Jieming Yin, Brandon Potter, Timothy G. Rogers, Matthew Poremba, Onur Kayiran, Michael LeBeane |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
010302 applied physics
Intermediate language Source code Computer science Programming language media_common.quotation_subject 02 engineering and technology computer.software_genre 01 natural sciences 020202 computer hardware & architecture Microarchitecture Instruction set Kernel (image processing) 0103 physical sciences 0202 electrical engineering electronic engineering information engineering Hardware_CONTROLSTRUCTURESANDMICROPROGRAMMING computer Resource utilization media_common |
| Zdroj: | HPCA |
| Popis: | Modern GPU frameworks use a two-phase compilation approach. Kernels written in a high-level language are initially compiled to an implementation agnostic intermediate language (IL), then finalized to the machine ISA only when the target GPU hardware is known. Most GPU microarchitecture simulators available to academics execute IL instructions because there is substantially less functional state associated with the instructions, and in some situations, the machine ISA’s intellectual property may not be publicly disclosed. In this paper, we demonstrate the pitfalls of evaluating GPUs using this higher-level abstraction, and make the case that several important microarchitecture interactions are only visible when executing lower-level instructions. Our analysis shows that given identical application source code and GPU microarchitecture models, execution behavior will differ significantly depending on the instruction set abstraction. For example, our analysis shows the dynamic instruction count of the machine ISA is nearly 2× that of the IL on average, but contention for vector registers is reduced by 3× due to the optimized resource utilization. In addition, our analysis highlights the deficiencies of using IL to model instruction fetching, control divergence, and value similarity. Finally, we show that simulating IL instructions adds 33% error as compared to the machine ISA when comparing absolute runtimes to real hardware. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|