اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدNVIDIA Tensor Core Programmability, Performance & Precision
105
0
0.0
(
0
)
نشر من قبل
Stefano Markidis Prof.
تاريخ النشر
2018
مجال البحث
الهندسة المعلوماتية
والبحث باللغة
English
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
The NVIDIA Volta GPU microarchitecture introduces a specialized unit, called Tensor Core that performs one matrix-multiply-and-accumulate on 4x4 matrices per clock cycle. The NVIDIA Tesla V100 accelerator, featuring the Volta microarchitecture, provides 640 Tensor Cores with a theoretical peak performance of 125 Tflops/s in mixed precision. In this paper, we investigate current approaches to program NVIDIA Tensor Cores, their performances and the precision loss due to computation in mixed precision. Currently, NVIDIA provides three different ways of programming matrix-multiply-and-accumulate on Tensor Cores: the CUDA Warp Matrix Multiply Accumulate (WMMA) API, CUTLASS, a templated library based on WMMA, and cuBLAS GEMM. After experimenting with different approaches, we found that NVIDIA Tensor Cores can deliver up to 83 Tflops/s in mixed precision on a Tesla V100 GPU, seven and three times the performance in single and half precision respectively. A WMMA implementation of batched GEMM reaches a performance of 4 Tflops/s. While precision loss due to matrix multiplication with half precision input might be critical in many HPC applications, it can be considerably reduced at the cost of increased computation. Our results indicate that HPC applications using matrix multiplications can strongly benefit from using of NVIDIA Tensor Cores.
قيم البحث
اقرأ أيضاً
Performance tools for forthcoming heterogeneous exascale platforms must address two principal challenges when analyzing execution measurements. First, measurement of extreme-scale executions generates large volumes of performance data. Second, perfor
mance metrics for heterogeneous applications are significantly sparse across code regions. To address these challenges, we developed a novel streaming aggregation approach to post-mortem analysis that employs both shared and distributed memory parallelism to aggregate sparse performance measurements from every rank, thread and GPU stream of a large-scale application execution. Analysis results are stored in a pair of sparse formats designed for efficient access to related data elements, supporting responsive interactive presentation and scalable data analytics. Empirical analysis shows that our implementation of this approach in HPCToolkit effectively processes measurement data from thousands of threads using a fraction of the compute resources employed by the application itself. Our approach is able to perform analysis up to 9.4 times faster and store analysis results 23 times smaller than HPCToolkit, providing a key building block for scalable exascale performance tools.
FaaS allows an application to be decomposed into functions that are executed on a FaaS platform. The FaaS platform is responsible for the resource provisioning of the functions. Recently, there is a growing trend towards the execution of compute-inte
nsive FaaS functions that run for several seconds. However, due to the billing policies followed by commercial FaaS offerings, the execution of these functions can incur significantly higher costs. Moreover, due to the abstraction of underlying processor architectures on which the functions are executed, the performance optimization of these functions is challenging. As a result, most FaaS functions use pre-compiled libraries generic to x86-64 leading to performance degradation. In this paper, we examine the underlying processor architectures for Google Cloud Functions (GCF) and determine their prevalence across the 19 available GCF regions. We modify, adapt, and optimize three compute-intensive FaaS workloads written in Python using Numba, a JIT compiler based on LLVM, and present results wrt performance, memory consumption, and costs on GCF. Results from our experiments show that the optimization of FaaS functions can improve performance by 12.8x (geometric mean) and save costs by 73.4% on average for the three functions. Our results show that optimization of the FaaS functions for the specific architecture is very important. We achieved a maximum speedup of 1.79x by tuning the function especially for the instruction set of the underlying processor architecture.
Big data applications and analytics are employed in many sectors for a variety of goals: improving customers satisfaction, predicting market behavior or improving processes in public health. These applications consist of complex software stacks that
are often run on cloud systems. Predicting execution times is important for estimating the cost of cloud services and for effectively managing the underlying resources at runtime. Machine Learning (ML), providing black box solutions to model the relationship between application performance and system configuration without requiring in-detail knowledge of the system, has become a popular way of predicting the performance of big data applications. We investigate the cost-benefits of using supervised ML models for predicting the performance of applications on Spark, one of todays most widely used frameworks for big data analysis. We compare our approach with textit{Ernest} (an ML-based technique proposed in the literature by the Spark inventors) on a range of scenarios, application workloads, and cloud system configurations. Our experiments show that Ernest can accurately estimate the performance of very regular applications, but it fails when applications exhibit more irregular patterns and/or when extrapolating on bigger data set sizes. Results show that our models match or exceed Ernests performance, sometimes enabling us to reduce the prediction error from 126-187% to only 5-19%.
Much of the current focus in high-performance computing is on multi-threading, multi-computing, and graphics processing unit (GPU) computing. However, vectorization and non-parallel optimization techniques, which can often be employed additionally, a
re less frequently discussed. In this paper, we present an analysis of several optimizations done on both central processing unit (CPU) and GPU implementations of a particular computationally intensive Metropolis Monte Carlo algorithm. Explicit vectorization on the CPU and the equivalent, explicit memory coalescing, on the GPU are found to be critical to achieving good performance of this algorithm in both environments. The fully-optimized CPU version achieves a 9x to 12x speedup over the original CPU version, in addition to speedup from multi-threading. This is 2x faster than the fully-optimized GPU version.
Can cloud computing infrastructures provide HPC-competitive performance for scientific applications broadly? Despite prolific related literature, this question remains open. Answers are crucial for designing future systems and democratizing high-perf
ormance computing. We present a multi-level approach to investigate the performance gap between HPC and cloud computing, isolating different variables that contribute to this gap. Our experiments are divided into (i) hardware and system microbenchmarks and (ii) user application proxies. The results show that todays high-end cloud computing can deliver HPC-competitive performance not only for computationally intensive applications but also for memory- and communication-intensive applications - at least at modest scales - thanks to the high-speed memory systems and interconnects and dedicated batch scheduling now available on some cloud platforms.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
