Search or ask a question

What is a transistor in a GPU?

General-purpose computing on graphics processing units

Graphics pipeline

Traffic simulation

Answers from top 7 papers

PDF

Open Access

More filters

Papers (7)	Insight
Proceedings Article•DOI Fast Batched Matrix Multiplication for Small Sizes Using Half-Precision Arithmetic on GPUs Ahmad Abdelfattah, Stanimire Tomov, Jack Dongarra - Show less +2 more 20 May 2019 34 Citations	The outcome is a highly flexible GPU kernel that provides a lot of controls to the developer, despite the aforementioned restrictions.
Journal Article•DOI A GPU-Based Parallel Genetic Algorithm for Generating Daily Activity Plans Kai Wang, Zhen Shen - Show less +1 more 01 Sep 2012-IEEE Transactions on Intelligent Transportation Systems 52 Citations	We think that we can employ a Graphics Processing Unit (GPU), which has been applied in many areas.
Proceedings Article•DOI Balancing Scalar and Vector Execution on GPU Architectures Zhongliang Chen, David Kaeli - Show less +1 more 23 May 2016 9 Citations	To better serve both scalar and vector operations, we propose a novel scalar-vector GPU architecture.
Proceedings Article•DOI Characterization of bit transistors in a functional SRAM Xiaowei Deng, Wah Kit Loh, Beena Pious, Theodore W. Houston, Larry Liu, Bashar Khan, Dan Corum - Show less +6 more 18 Jun 2008 26 Citations	It allows, for the first time, characterization of each bit transistor in a functional SRAM.
Proceedings Article•DOI Nyami: a synthesizable GPU architectural model for general-purpose and graphics-specific workloads Jeff Bush, Philip Dexter, Timothy Miller, Aaron Carpenter - Show less +3 more 29 Mar 2015 15 Citations	This approach allows us to more easily explore the GPU design space in a synthesizable, cycle-precise, modular environment.
Open access•Book Chapter•DOI Benchmarking the memory hierarchy of modern GPUs Xinxin Mei, Kaiyong Zhao, Chengjian Liu, Xiaowen Chu - Show less +3 more 18 Sep 2014 55 Citations	Our benchmarking results offer a better understanding on the mysterious GPU memory hierarchy, which can help in the software optimization and the modelling of GPU architectures.
Proceedings Article•DOI Overview and comparison of OpenCL and CUDA technology for GPGPU Ching-Lung Su, Po-Yu Chen, Chun-Chieh Lan, Long-Sheng Huang, Kuo-Hsuan Wu - Show less +4 more 01 Dec 2012 36 Citations	The benefit of involving the two programming models in GPU is that researchers and developers don't have to understand OpenGL, DirectX or other program design, but can use GPU through simple programming language.

My columns

Related Questions

Are transistors expensive?9 answers

Are transistors worth anything?18 answers

How big are transistors in a CPU?8 answers

How to use transistor socket?7 answers

What does a transistor on a CPU look like?8 answers

What transistors are used in CPU?5 answers

See what other people are reading

How LSM do merge of disk components and also preventing flush stalls?

What are the latest advancements in radiation hardening techniques for space-bound semiconductor chips?

What are the latest advancements in radiation hardening techniques for space-bound semiconductor chips?

What are the steps of a blockchain transaction?

What is a multi-core processor?

What is a multi-core processor?

What is the optimal mesh repartition per core for a parallel cfd simulation?

What innovations has NVIDIA made, and what innovations and types of innovations are central today?

What innovations has NVIDIA made, and what innovations and types of innovations are central today?

What can i use to learn about rocky programe wich deal with dem?

To learn about the ROCKY program, which deals with improving the robustness of STT-MRAM cache memory hierarchy against write failures, you can refer to research by Talebi et al.. The ROCKY architecture proposes efficient replacement policies to enhance the reliability of STT-MRAM memories by reducing susceptible transitions during write operations. The study demonstrates that ROCKY can decrease the Write Error Rate (WER) of STT-MRAM cache memories by up to 35.4% with minimal performance overhead. This research provides valuable insights into addressing the critical reliability challenges faced by STT-MRAM technology, particularly focusing on mitigating write failures in cache memory hierarchies. By studying the ROCKY program, you can gain a deeper understanding of strategies to enhance the robustness of STT-MRAM-based systems in the face of reliability issues.What is pMTOR?

pMTOR stands for "previously merging for masking repeats," a method proposed for masking repeats in DNA fragment assembly. The Pebble Bed Modular Reactor (PBMR) technology, used for electricity production and process heat applications, is a significant development in the nuclear energy sector. Additionally, a resource-oriented computing model called COR has been introduced to integrate user-level multithreading and communication in symmetrical multiprocessor clusters, enhancing distributed application design. Moreover, a new free-form profilometer, the MPR-700, has been designed for precise 3D metrological measurements of optics, offering high accuracy and speed in data acquisition. South Africa's PBMR programme has seen advancements, including changes in turbine orientation and core design, with a power uprate to 400 MWt, making it a prominent next-generation reactor development effort.