Questions tagged [gpu]
Graphical Processing Unit - a specialized, relatively inexpensive hardware unit built for fast graphical computations and highly data-parallel scientific computations.
104
questions
6
votes
2
answers
103
views
Computing $\frac{x - y}{x - z}$ when $x,y,z$ are close to each other
What is the most stable way to compute
$$\frac{x - y}{x - z}$$
when $x$, $y$, and $z$ are all close to each other? I would like to compute expressions of this form in low precision on a GPU, but when ...
- 3,205
0
votes
1
answer
141
views
recommended simple linear solver on gpu
I'm looking for recommendations for a simple GPU linear equation system solver that is a dropin replacement for scipy.linalg.solve. Right now, I'd rather not go the Petsc/TriLinos/Slate route. ...
- 832
0
votes
0
answers
72
views
How is kernel fusion done?
I have a computational graph (DAG) consisting of element-wise operations (potentially with broadcasting) and reshape/reduce operations (reshaping/sum/max). I'm trying to understand how vertical kernel ...
- 121
2
votes
1
answer
430
views
How to leverage the GPU for parallel 3-body problem computations
I have a 3-body simulation which must run millions of times.
As far as I know, the GPU shines when it gets to preform simple operations on huge matrices/arrays. Currently I'm debugging and running my ...
- 41
5
votes
0
answers
142
views
Single precision vs double precision conjugate gradients
I tested my conjugate gradients implementation with float and double precision and contrary to my guess the double code was twice faster than the single precision code. The reason is that I need many ...
- 2,352
0
votes
1
answer
291
views
Questions on the theory of distributed numerical algebraic computation
I'm trying to build a pure python distributed numerical algebra computation kernel based on GPU. but after I've learnt most of the software engineering, I realise that I'm seriously lacking in ...
2
votes
0
answers
86
views
OpenMP Fortran array operations in target regions
I am asking this here for the possibility that someone here is familiar with OpenMP offloading. Is there some other way to parallelise Fortran array operations outside of unrolling the loops of the ...
- 131
0
votes
1
answer
376
views
How can I convert a C program into a CUDA program?
Suppose I already have a C program that solves a specific computational problem. I want to convert that into a CUDA program.
What steps should I follow to do that?
For instance, can I think as follows?...
- 75
2
votes
0
answers
180
views
Why GPU scaling (speedup) is usually worse than CPU scaling?
Let's define scaling, as how linear the speedup of using more than one GPU or CPU is. For example, having 2 GPUs gives you 2x faster execution time.
I have noticed that in many software (e.g. ...
- 123
0
votes
0
answers
58
views
Calculate the time taken to run an algorithm on GPU
I want to calculate the total time taken for a fixed code run using an NVIDIA GPU (for instance, Tesla K40). The code has to run 1 million single-bit comparisons. All the comparisons are independent ...
3
votes
0
answers
192
views
How can I improve this matrix product calculation in OpenCL?
I am trying to compute a matrix-matrix product of N stacked complex double N x N matrices. For simplicity, I assume N = 512. I have written code in C++ parallelized with OMP and using OpenBLAS for the ...
- 31
3
votes
2
answers
6k
views
GPU vs CPU FLOP counts
I apologise if this is somewhat of a rookie question. So, from my understanding, on a GPU board, far more of the space is allocated to ALUs compared to CPUs which have far more cache available. This ...
- 141
3
votes
1
answer
467
views
Solving DAE in Julia using GPUs
I'm trying to solve a Differential Algebraic Equation (DAE) in Julia which is very computationally expensive using GPUs. I'm brand new to Julia and don't have much experience coding with GPUs. The ...
- 53
4
votes
0
answers
181
views
How amenable is this 2D Frenkel–Kontorova-like energy minimization problem in Python to the use of a modest PC + GPU? (Heavy reliance on indexing)
@Richard's answer to Going to try to move some of my scipy/numpy calculation to a new GPU, how to avoid disappointing results? is quite helpful, and as promised I've added a simple running example ...
- 1,078
4
votes
1
answer
613
views
Going to try to move some of my scipy/numpy calculation to a new GPU, how to avoid disappointing results?
update: I've refactored the question based on helpful advice in the linked meta.
I'm a heavy user of Python's NumPy and SciPy (and not much else) and for years I could run anything I need on my laptop....
- 1,078
6
votes
1
answer
521
views
PETSc-like library for Julia
I want to build an application for Material Point Method (and probably other meshfree methods too) in Julia and I am looking for library for direct and iterative solvers that can help me with it. One ...
- 163
1
vote
3
answers
620
views
Optimization on MCMC codes
I am looking for MCMC codes with a GPU suport (like NVIDIA or OpenCL libraries) to make faster run chains.
If someone could have a state of the art ...
user14831
5
votes
0
answers
222
views
Solving multiple linear regression in parallel
I am working on a problem where I need to solve approximately 500 Million Linear Regressions (OLS).
What would be the most efficient way to do this (e.g. using GPU or a some framework that can do this ...
- 51
5
votes
0
answers
236
views
hardware agnostic (GPU/CPU) sparse linear algebra C++ solvers framework/technology
I am looking for recommendations on matured C++ solver for Linear Sparse Algebra problems.
The goal is to select between more or less GPU hardware agnostic libraries/frameworks that can be compiled on ...
- 51
1
vote
1
answer
622
views
MATLAB : find an algorithm to inverse quickly a large matrix of symbolic variables
I have to solve the equality between 2 matrixes 12x12 containing a lot of symbolic variables and with which I perform inversion of matrix. There is only one unknown called "...
user14831
0
votes
0
answers
51
views
Methodology to develop parallel GPU simulations
I'm quite new to GPU or in general parallel programming. I am working on a Lattice-Boltzmann simulation that should be parallelized on GPU's. I wanted to asked more experienced people how to attack ...
- 11
-1
votes
1
answer
177
views
Source Code for Particle Simulation, Cuda, PyCuda
I am looking for references, pointers to CUDA code that runs particle simulation in parallel, calculating particle trajectories, handling collisions, etc. I've seen some in NVidia source base, but was ...
- 239
13
votes
3
answers
40k
views
How to properly calculate CPU and GPU FLOPS performance?
Problem
I'm trying to calculate CPU / GPU FLOPS performance but I'm not sure if I'm doing it correctly.
Let's say we have:
A Kaby Lake CPU (clock: 2.8 GHz, cores: 4, threads: 8)
A Pascal GPU (clock: ...
- 231
1
vote
0
answers
60
views
Hardware supporting floats with fraction beyond 64 bit
Is there any computation accelerator (like a GPGPU) available, that natively (this means in hardware, not emulated by a library) supports arithmetics using floating point numbers with a fractional ...
- 163
2
votes
1
answer
73
views
Understading memory sharing in a GPGPU using a lattice example
I am new in the GPUs world, I used them in Matlab ambient so I didn't need to appreciate the subtleties of these devices.
I know that a GPU can be divided into multiprocessors (also called Streaming ...
- 23
1
vote
1
answer
528
views
Implementation of sparse matrix SVD for GPU
I have a sparse matrix $W$ which is almost-squared ($N+1 \times N$) and I would like to know the eigenvalues of $A = W^T W$. $A$ is Hermitian so the eigenvalues are real-positive valued.
The usual ...
- 11
25
votes
10
answers
9k
views
Are there any embarrassingly parallel tasks that require a CPU rather than GPU?
I am looking for tasks that
are unsuitable for GPUs
gain significant speedup as more CPU nodes are added
don't require large data transfer or inter-thread communication between nodes.
Do any ...
- 259
2
votes
0
answers
66
views
Solving a complex ODE with large number of variables (>1e6 variables) - best practise?
I have to solve a non-linear ODE of the shape
$$\partial_zA=f(A)$$
with $f$ a non-linear function and $A$ a matrix/vector with >1e6 variables (i.e. $A$ is a matrix with >1000x1000 entries). For each ...
- 563
2
votes
2
answers
360
views
Writing code on the CPU while developing, running it on the GPU when live - which approach?
In my simulations I am using dense matrix-vector multiplications and 2D-fft transformations quite often, for matrix sizes of 8kx8k and up. Hence, I assume that using a GPU is beneficial for speeding ...
- 563
1
vote
2
answers
90
views
Augmented Dickey Fuller (ADF) test statistics GPU formulation
I have followed different sources of information and achieved the following formulation for the ADF $t$ test statistics. I implemented it to run several hundred thousands of ...
- 366
6
votes
1
answer
756
views
Consumer hardware for scientific computing?
I'm interested in problems around probability, statistics, and statistical mechanics, and often I find it useful to perform simulations to get some sense of the underlying phenomena. Example ...
- 105
4
votes
3
answers
234
views
GPGPU computing, software selection
I am using an existing GCC C++ x86 Qt application that filters, displays and stores results computed by some C code. Since the computation by now got too complex for CPUs I intend to port the small C ...
- 163
2
votes
1
answer
178
views
Fusing callbacks with FFTs: an open-source GPU FFT implementation?
I'm using cuFFT to do some 2D FFTs on matrices of size 2048x2048 or larger. The FFTs are preceded and followed by various scaling operations.
These scaling operations are memory-bound, so they take ...
- 4,021
1
vote
0
answers
590
views
OpenFOAM and CFDEM on GPU
I have a simulation project written for OpenFOAM and CFDEM and would like to find an alternative to run it on GPU since raising the number of cores already provided a promising speed up and ...
- 111
5
votes
2
answers
832
views
GPGPU language for AMD?
Nvidia seems to be dominating the HPC / GPGPU computing landscape with CUDA. If I want to write a scientific application using and AMD GPU, what is the preferred language these days? I believe it used ...
- 2,149
3
votes
2
answers
1k
views
Lost on Matrix Inversion
I try to implement some big matrix inversion. My system configuration is Hardware:- Memory: 62.8GiB, Processor: Intel Xeon(R)CPU E5-2670 v3 @2.30GHZ*48 To implement matrix inversion I am using ...
- 35
0
votes
1
answer
193
views
Use of GPU with respect to CPU
I have research work where I need to compute a matrix inversion. The matrix has a size $31300\times31300$. I am using a universal java matrix package to invert this matrix. But as the dimension of the ...
- 35
1
vote
2
answers
3k
views
Demo example for OpenFOAM with CUDA
I am looking for a simple usage example/demo of OpenFOAM + CUDA and would like to understand how exactly OpenFOAM benefits from CUDA. The thing is I do not have any background in fluid dynamics and so ...
- 181
2
votes
0
answers
111
views
Accelerate computation speed by using a different syntax [closed]
I was reading a book about Matlab ("Accelerating Matlab with GPU computing - A Primer with Examples" by Jung Suh and Youngming Kim, 2013. Chapter 1.7 Examples).
I read an example where it said that: ...
- 153
0
votes
1
answer
210
views
Compare 64gb dd3 ram with 2gb Quadro M1000M gpu on Lenovo P50
I frequently work with Keras and tensorflow-gpu on my Lenovo P50 workstation which has 64GB ram and a 2GB Nvidia QUadro M1000M GPU.
Today while training my model on GPU, it ran into memory error and ...
- 103
0
votes
1
answer
646
views
Can I convert CUDA core to CPU core and use it as cpu core while running any program?
I was using Metatrader5 and have designed a strategy for trading using MQL5 programming language.
While I was running a Strategy Optimization process, I saw the it will need 10,00= iterations or ...
- 101
1
vote
1
answer
387
views
Why is FLOP(Floating Point Operations Per Second) mentioned as a specification on every GPU?
Counting FLOP may not be representative of the actual algorithm real world performance but still all the GPU manufacturers mention FLOPS as a metric of Performance on GPU. Is there any way that this ...
- 113
7
votes
3
answers
8k
views
Performance of kd-tree vs brute-force nearest neighbor search on GPU?
I wonder if there is any study that compares the performance of kd-tree vs brute-force nearest neighbor search on GPU. Post #4 on this page suggests that kd-tree may not be the optimal algorithm for ...
- 173
1
vote
0
answers
139
views
Porting from MPI to GPU
Assuming that the underlying algorithm can be ported to multi GPU, what aspects should one consider while porting from MPI (on multiple nodes) to multi GPU (again on multiple nodes)?
Making use of ...
- 111
1
vote
1
answer
104
views
1
vote
2
answers
421
views
Computational Science Hardware Benchmark Database
I am looking for a website/database of computer hardware (CPUs/GPUs) benchmarked with common scientific tools, e.g. *GEMM (see comment below for more info on this tool).
Currently, I am quite ...
- 111
0
votes
1
answer
188
views
Hyperscale Vs Strong-scale HPC
NVIDIA's Tesla GPUs for Servers includes market segments called "Hyperscale HPC" and "Strong-Scale HPC". How different is ...
- 287
3
votes
2
answers
218
views
HPC reading material
I am an undergraduate, and enthusiastic about HPC. I am currently familiar with the tools OpenMP, MPI, CUDA, OpenCL, thrust libraries etc. But I want to know the core functioning of these tools, I ...
1
vote
2
answers
2k
views
New to CFD, Lattice Boltzmann or Navier-Stokes?
I apologize if some of my questions are naive; I am very new to computer simulations and fluid-dynamics.
I am going to start a PhD in early 2017, and I would like to bone-up on some Computational ...
- 11
3
votes
1
answer
2k
views
Why am I not seeing faster neural network training after upgrading to a vastly better GPU?
I was previously running my neural networks using the Lasagne library to build and train neural networks in Theano on an NVIDIA GTX 750 Ti. I'm using a genetic algorithm to tune the hyperparameters of ...
- 141