StackOverflow Questions for Tag: gpgpu

IPribec

Reputation: 236

OpenMP equivalent for OpenACC default(present) clause

fortranopenmpgpgpuopenacc

Score: 0

Answers: 0

Louis Child

Reputation: 97

Invalid global write despite index being within bounds

c++cudagpgpu

Score: 0

Answers: 1

Merlin1896

Reputation: 1821

Parallel Convex Hull Algorithm for 2D Convex Hull of a Simple Polygon

cudapolygoncomputational-geometrygpgpuconvex-hull

Score: 2

Answers: 2

timdim

Reputation: 1291

How can I flush GPU memory using CUDA (physical reset is unavailable)

cudagpgpuremote-access

Score: 126

Answers: 14

Taylor

Reputation: 6430

accelerate sparse point deformation in Metal

iosgpgpumetal

Score: 1

Answers: 0

比尔盖子

Reputation: 3637

Do GPU architectures have Persistent Last-Level Cache Across Kernel Launches?

cachinggpugpgpu

Score: 7

Answers: 2

trent.tong

Reputation: 21

GPU L1 Cache Coherence

cachingcudagpuopenclgpgpu

Score: 2

Answers: 2

Gerrard

Reputation: 49

Why computed prefilter radiance map looks different in opengl api comparing to dx11?

c++openglgraphicsdirectxgpgpu

Score: 1

Answers: 1

kenba

Reputation: 4549

OpenCL Device Vendor Ids

openclgpgpu

Score: 0

Answers: 3

LC Nielsen

Reputation: 63

What is the correct way to use OpenMP Target Enter/Exit/Update for unstructured, asynchronous device-side computations?

c++oopasynchronousopenmpgpgpu

Score: 0

Answers: 1

Kensmosis

Reputation: 115

Can't seem to achieve anywhere near my GPU global memory bandwidth in OpenCL

openclgpgpuamd-gpuopencl-cmemory-bandwidth

Score: 0

Answers: 1

SailingOnThoughts

Reputation: 137

Whats actually happens when you call cudaMalloc inside device?

c++cudagpgpu

Score: 4

Answers: 2

Danimator

Reputation: 31

OpenCL flush absurdly slow, seemingly triggered by clEnqueueReleaseGLObjects in OpenCL/OpenGL interop

concurrencyparallel-processingopenclgpgpu

Score: 1

Answers: 0

RNK

Reputation: 5792

gnupg get_key failed in php

phpgpgpugnupg

Score: 3

Answers: 3

Lokananda Hari

Reputation: 1

Understanding MUBUF instruction in AMD GCN Architecture

gpgpuamd-gpuamd-rocmhipamd-gcn

Score: 0

Answers: 0

Danimator

Reputation: 31

OpenCL 1.2: Global memory consistency surrounding atomic operations?

concurrencyparallel-processingopenclgpgpuconsistency

Score: 1

Answers: 1

cache

Reputation: 1319

Running more than one CUDA applications on one GPU

cudagpugpgpunvidia

Score: 59

Answers: 3

berk2609

Reputation: 9

GPU Thread Management

parallel-processingcudagpuopenclgpgpu

Score: -2

Answers: 1

einpoklum

Reputation: 131986

Making some, but not all, CUDA memory accesses uncached

cachingcudagpgpu

Score: 6

Answers: 2

dv1729

Reputation: 1057

Coalesced memory access performance

openglcudagpugpgpu

Score: 1

Answers: 1

PreviousPage 2Next

StackOverflow Questions for Tag: gpgpu

OpenMP equivalent for OpenACC default(present) clause

Invalid __global__ write despite index being within bounds

Parallel Convex Hull Algorithm for 2D Convex Hull of a Simple Polygon

How can I flush GPU memory using CUDA (physical reset is unavailable)

accelerate sparse point deformation in Metal

Do GPU architectures have Persistent Last-Level Cache Across Kernel Launches?

GPU L1 Cache Coherence

Why computed prefilter radiance map looks different in opengl api comparing to dx11?

OpenCL Device Vendor Ids

What is the correct way to use OpenMP Target Enter/Exit/Update for unstructured, asynchronous device-side computations?

Can&#39;t seem to achieve anywhere near my GPU global memory bandwidth in OpenCL

Whats actually happens when you call cudaMalloc inside device?

OpenCL flush absurdly slow, seemingly triggered by clEnqueueReleaseGLObjects in OpenCL/OpenGL interop

gnupg get_key failed in php

Understanding MUBUF instruction in AMD GCN Architecture

OpenCL 1.2: Global memory consistency surrounding atomic operations?

Running more than one CUDA applications on one GPU

GPU Thread Management

Making some, but not all, CUDA memory accesses uncached

Coalesced memory access performance

Invalid global write despite index being within bounds

Can't seem to achieve anywhere near my GPU global memory bandwidth in OpenCL