Stack Overflow
Stack Overflow

Questions tagged [hip]

Key features include:

  • HIP is very thin and has little or no performance impact over coding directly in CUDA or hcc "HC" mode.

  • HIP allows coding in a single-source C++ programming language including features such as templates, C++11 lambdas, classes, namespaces, and more.

  • HIP allows developers to use the "best" development environment and tools on each target platform.

  • The "hipify" tool automatically converts source from CUDA to HIP.

  • Developers can specialize for the platform (CUDA or hcc) to tune for performance or handle tricky cases

https://github.com/ROCm-Developer-Tools/HIP

Interesting Use Case

We ported CAFFE to HIP http://gpuopen.com/ported-caffe-hip-heres-happened/

19 questions
24
votes
2 answers

Understanding oneAPI and SYCL in AMD GPU

I am a GPGPU developer and I have done all my work using CUDA. Lately I have acquired an AMD GPU for my home setup and I have been reading about SYCL and oneAPI but I'm not sure I understand what each of those are, how they complement. If I have…
jjcasmar
  • 1,387
  • 1
  • 18
  • 30
3
votes
1 answer

GPU Programming, CUDA or OpenCL or?

What is the best way to do programming for GPU? I know: CUDA is very good, much developer support and very nice zo debug, but only on NVidia Hardware OpenCL is very flexible, run on NVidia, AMD and Intel Hardware, run on Accellerators, GPU and CPU…
Matthias F.
  • 119
  • 1
  • 5
3
votes
1 answer

How to generate an image using Haskell Image Processing

I just started learning Haskell, so I am likely missing something very trivial. I am attempting to generate images using Haskell Image Processing. I am adapting the code from sample snippets from the docs. My code is as follows. {-# LANGUAGE…
Mad Wombat
  • 14,490
  • 14
  • 73
  • 109
2
votes
2 answers

How to detect whether GPU is AMD or NVIDIA from inside HIP code

I'm currently writing a HIP equivalent to NVIDIA's deviceQuery sample code. I want my code to work on both AMD and NVIDIA hardware. Now, hipDeviceProp_t isn't exactly the same as cudaDeviceProp_t, because the former has both new and missing fields…
wyphan
  • 216
  • 3
  • 12
2
votes
1 answer

HIP-Clang Inline Assembly

What is the Hip-Clang equivalent of this CUDA function? __device__ __forceinline__ uint32_t add_cc(uint32_t a, uint32_t b) { uint32_t r; asm volatile ("add.cc.u32 %0, %1, %2;" : "=r"(r) : "r"(a), "r"(b)); return r; } I'm porting a CUDA…
Andrew H
  • 321
  • 4
  • 9
2
votes
1 answer

How to convert precision in Image type from Double to Word8 using HIP?

I have an image in the type Image VS Y Double (after using function readImageY from HIP library) and I want to convert it to Image VS Y Word8. How should I go about doing this? I need to have it in this precision for the next function I am applying…
FifthCode
  • 65
  • 6
2
votes
1 answer

Haskell HIP : Apply Filter to an Image

I'm trying to add a filter to an image using the Haskell Image Processing package HIP, I was able to read the image using the ByteString Package and convert the image to type Image VS YCbCr Word8 using HIP. Now, how do I convert from Image VS YCbCr…
Silva
  • 625
  • 1
  • 6
  • 25
2
votes
0 answers

HCC Runtime Error when trying to run hipTensorFlow (Ubuntu 16.04, R9 290)

I installed hipTensorFlow following the instructions here. I am running Ubuntu 16.04 as they say in the guide and I have an AMD R9 290 card. But when attempting to import Tensorflow I get the following output: >>> import…
Alex McMurray
  • 173
  • 1
  • 5
1
vote
0 answers

CUDA's device properties in HIP

My task is to port caches' latency measurement program written in CUDA to HIP, and for that i need to get characteristics of GPU. I'm using HIP 4.5.0, and the problem is that for some data from CUDA's deviceInfo, there're no (direct) analogues from…
Max Azatian
  • 53
  • 7
1
vote
1 answer

how to get default device id for calling host thread in opencl

i am working with opencl "c" in a multi gpu scenario, where for various calls i have to get the default device id for the current calling host thread in opencl. unfortunately i am not able to figure it out and internet hasnt been kind in this…
Yogeesh Agarwal
  • 51
  • 5
1
vote
1 answer

Haskell Image Processing (HIP) operate on Pixel RGB

I'm new to this library and I want a way to operate a (for example) Pixel RGB Double like: p <- I know substracts or sums affects the whole RGB pixel p = p +…
050
  • 57
  • 6
1
vote
0 answers

Haskell HIP improve Performance when slicing Images

For X-Ray Slicing I would like to create a program that reconstructs slices and performs the inverse radon transform. The first step is to create sinograms of the images. But it takes very long to create one sinogram. I have 1500 Images, each…
Iakov Kholodkov
  • 43
  • 6
1
vote
1 answer

What are the requirements for using `shfl` operations on AMD GPU using HIP C++?

There is AMD HIP C++ which is very similar to CUDA C++. Also AMD created Hipify to convert CUDA C++ to HIP C++ (Portable C++ Code) which can be executed on both nVidia GPU and AMD GPU: https://github.com/GPUOpen-ProfessionalCompute-Tools/HIP There…
Alex
  • 12,578
  • 15
  • 99
  • 195
0
votes
0 answers

hipMemcpy fails to copy

I am trying to use library, but I keep getting gibberish when exchanging data. here is my code: #include #include int main() { int* hipC; int a = 123; int* ap = &a; int* ap2 = new…
Nika Tark
  • 1
0
votes
0 answers

AMD HIP executable with undefined symbols during runtime

I want to use the AMD HIP framework for my self-written GPU kernels. I do that by using a third-party library, which takes responsibility of taking the code and compiling it with HIP (and additional backends if desired). The technical setup looks as…
hydrochloric acid
  • 1
  • 2
1
2