Hi,
I would like to confirm whether CL_MEM_USE_HOST_PTR has extra overhead, such as memory copy, on Mali G72.
According to ARM OpenCL Optimization Guide, using CL_MEM_USE_HOST_PTR is discouraged.
Hi,
I would like to confirm whether CL_MEM_USE_HOST_PTR has extra overhead, such as memory copy, on Mali G72.
According to ARM OpenCL Optimization Guide, using CL_MEM_USE_HOST_PTR is discouraged.
Hello everyone
I am trying to perform matrix vector multiply(both dense and sparse matrix) using Mali, I have looked at ARM ComputeLibrary and I don't really see a specialized sgemv, just wondering if I should just use sgemm for this purpose?
Is there…
Hi Guys,
I am actively optimizing my OpenCL program running on Mali Bifrost GPU.
I wonder whether cache prefetch would have some performance improvements for my program.
I didn't find any materials about mali GPU prefetching, however, I found there is…
Hi, everyone
Background:
I am working on a project utilizing MACE(https://github.com/XiaoMi/mace a CNN inference framework designed for mobile devices like Mali GPU). This framework uses OpenCL to perform computation on Mali GPU. And I have an Android…
Currently I run Ubuntu on Huawei Hikey 970 board, and try to run gnuradio with gr-fosphor on it, but failed.
At first, it failed with these lines:
[!] CL Error (-1001, /build/gr-fosphor-9QC8j4/gr-fosphor-3.7.0.2.7b6b996/lib/fosphor/cl.c:272): Unable to…
Hi,
I am trying to implement an OpenCL kernel on G76 with DDK r16.
I find that if I define and use an array like "half A[16];", the performance will be poor.
But if I use "half16 A;", the performance is very good.
I wonder if array…
I wanted to find out if the ARM NN supports the ARM Mali 400 MP2 .
Regards
Fatima
Hello, we are developing a product based on maili T764 (RK3288) with OpenCL. In our kernel, we use about 1kB local memory every workgroup. I was wondering where is these local memory allocated, and if it is possible for us to taking advantage of the L2…
Hi
I have a newbie question
What are the main differencies between OpenCl and OpenGl Es ?
In which case do you use the first or the second ?
May you explain me shortly ?
Thanks & regards,
Hi
I am working on Odroid board which has Mali GPU - T628. To understand the architecture better , for my research, I am looking for answers to following questions (Any help will be highly appreciated)
Q. What is size of L1 cache (Does this hold true: …
I wan to debayer, white balance and .. using available hard ware on this ARM processor. I am not sure if it relates to this forum or not ( ), but hopefully someone redirect me to some detail information where I can find information.
My images are arriving…
Hi,
I have a couple of ODroid XU3s and they are working great. They are running the Mali T628 GPUs and currently support OpenCL 1.1.
However, I want to switch over to OpenCL 1.2 or 2.0 for future development work.
Does anyone know when…
I have a fairly complex OpenCL implementation with 2D NDRange as follows:
Num of Work Groups - {10,7}
Work Group Size {64,1},
With this I get a performance of 0.625 Secs, But when i decrease the number of work groups to {10,4} the performance degrades…
Hello, I'm using Odroid-XU3.
And I installed Opencv 3.0.0-rc1 on odroid-xu3 ubuntu 14.04.
I want to use function clCreateProgramWithBinary() instead of clCreateProgramWithSource().
Because of build time for clCreateProgramWithSource() and clBuildProgram…
Hello Guys peterharris I am using a Mali T628 GPU on the Odroid XU3 board with Exynos 5422 chip. I have a couple of questions regarding OpenCL on the Mali GPU:
1. Can we get information of active threads or work groups per shader core for Mali-T6xx similar…
Hey!
I'm trying to debug an opencl application on my Odroid Xu3 (With the Mali-T628 MP6), and when i try to use MGD, it completely crashes after the first opencl call giving me this error that the passthroughglesapi could not locate the handler function…
I used opencl1.1 on Mali628(Exynos5422)。
1.
first I create a buffer
buffer = clCreateBuffer(context, CL_MEM_READ_WRITE | CL_MEM_ALLOC_HOST_PTR, 1280*720*4, NULL, &errorNumber);
next call the kernel to handle the buffer and waiting the command queue finish…
Hello Nice to meet you
Please understand my bad english
To learn to program using GPU, I have been searching informations.
My device for test is Galaxy S6 and GPU is ARM Mali T-760.
I'm going to try to use GPU for computer vision.
To set up environment…
Hello,
I am developping a short application to downsampling images on my samsung alpha.
I use OpenCL to develop on my GPU.
I have a problem when I use a sampler_t. Just when I decrare a sampler_t variable in my kernel, the program crash and gave me that…
Hello,
I found out that on qcom platform, there's a extension,
https://www.khronos.org/registry/cl/extensions/qcom/cl_qcom_ion_host_ptr.txt
Can I do the same on mali T760, android platform?
Songmao
Dear experts,
I am looking for a board with a Mali T-8xx and a reasonable CPU (A9/A15/A53/A57/etc.) for developing software IPs over OpenCL
I have been opencl on the Odroid-XU3 board, this has an ARM big.LITTLE core and a Mali-T628.
I am trying to run the Rodinina Benchmarking Suite (Found here) on each core and the GPU separately. I have gotten the code working on each CPU using POCL. Now…
ARM Graphic expert:
I have a cl_mem buffer, which will be reused every camera frame, so it need reset to zero before we can use it.
for opencl 1.2 we can use clEnqueueFillBuffer, for mali driver, what would be the most…
Hi,
I have an OpenCL program that runs on a Mali T628 platform. Originally I was using kernel driver r5p1-00rel1 and user driver r5p0-06rel0. But I was constantly hitting what seemed like a deadlock in the close-source user driver. And my program would…
Hi, I am accelerating a image processing algorithm with OpenCL on the cellphone, however I met a case which had a very poor performance.
The case is to calculate the prefix sum of each row on the image (a 2D buffer). For example, a 3x3 image:
50 32