Stack Overflow
Stack Overflow

Questions tagged [cuda-uva]

CUDA's Unified Virtual Addressing feature distinguishes the address spaces of the different GPUs on a system from the host memory space, so that pointers are unique across all computational devices.

UVA stands for Unified Virtual Addressing, a feature of the CUDA GPU programming environment distinguishing the address spaces of the different GPUs on a system from the host memory space, so that pointers are unique across all computational devices.

See this GTC 2011 presentation about using UVA for peer-to-peer copies between GPUs.

6 questions
2
votes
1 answer

GPU memory oversubscription with mapped memory, Unified Virtual Addressing and Unified Memory

I'm considering possibilities to process data on a GPU, that is too big for the GPU memory, and I have a few questions. If I understand that correctly, with mapped memory the data resides in the main memory and is transferred to the GPU only when…
lawful_neutral
  • 633
  • 8
  • 29
0
votes
0 answers

Problem 101 The Blocks Problem UVA gives runtime-error on submission. works fine on Visual Studio Code

I have been trying to solve the UVA 101 The Blocks Problem. I wrote the solution in C++ and ran the sample input. It gives the correct output on visual studio code but on submitting on UVA it gives runtime error. Any advice to solve this would be…
Zain
  • 1
0
votes
2 answers

Why is cuMemAddressReserve() failing with CUDA_INVALID_VALUE?

Consider the following program (written in C syntax): #include #include #include int main() { CUresult result; unsigned int init_flags = 0; result = cuInit(init_flags); if (result != CUDA_SUCCESS) {…
einpoklum
  • 118,144
  • 57
  • 340
  • 684
0
votes
1 answer

CUDA P2P memory access and __constant__ memory

I cannot find the answer anywhere and I may have overlooked it but it seems that one cannot use __constant__ memory (along with cudaMemcpyToSymbol) and peer-to-peer access with UVA. I've tried the simpleP2P nvidia sample code which works fine on the…
salvaS
  • 13
  • 3
0
votes
1 answer

Odd behavior of cudaMemcpyAsync: 1. cudaMemcpyKind makes no difference. 2. Copy fails, but silently

I'm familiarizing myself with a new cluster equipped with Pascal P100 GPUs+Nvlink. I wrote a ping-pong program to test gpu<->gpu and gpu<->cpu bandwidths and peer-to-peer access. (I'm aware the cuda samples contain such a program, but I wanted to…
Michael Carilli
  • 371
  • 2
  • 12
0
votes
1 answer

In CUDA, does UVA depend on any hardware features?

I know CUDA only got UVA (Unified Virtual Addressing) with version 4.0. But - is that only a software feature? Or does it require some kind of hardware support (on the GPU side I mean)? Notes: In this GTC 2011 presentation it says a Fermi-class GPU…
einpoklum
  • 118,144
  • 57
  • 340
  • 684