• Cache data invalidation between kernel calls in OpenCL

    Yury
    Yury

    Hello.

    Does L2 cache data invalidated after finishing each kernel invocation? If not the case, does invalidation depends on memory type (SVM, old buffers, mapped old buffers, etc)?

    Question related to Bifrost and Valhall architectures.

    • Answered
    • 1 month ago
    • Graphics and Gaming
    • Graphics and Gaming forum
  • The difference between clEnqueueSVMMap and clEnqueueMapBuffer

    willhua
    willhua

    Hi, Is there some difference between clEnqueueSVMMap for coarse SVM and clEnqueueMapBuffer in theory? If there is, will this cause difference about performance?

    • 4 months ago
    • Graphics and Gaming
    • Graphics and Gaming forum
  • Register spilling for different threads count

    Yury
    Yury

    Hi. According to Arm Mali GPU Datasheet 2020.pdf document there are several modes for maximum thread count, for Mali G76 it is 2 such modes, 768 threads for 0-32 work registers, and 384 for 33-64 work registers.

    Is it possible that register spilling can…

    • Answered
    • 4 months ago
    • Graphics and Gaming
    • Graphics and Gaming forum
  • The efficient way to load and store memory in Mali G-72

    Tarun Annapareddy
    Tarun Annapareddy

    Hi,

    I am doing an image crop and writing to the destination. I am using a vector load and store of 8 uchar's. can someone help in optimizing this kernel . any mali G-72 gpu specific changes required?

    uchar* src_y : source pointer to Y data of the…

    • 6 months ago
    • Graphics and Gaming
    • Graphics and Gaming forum
  • Buffer create taking 10 ms on mali G-72

    Tarun Annapareddy
    Tarun Annapareddy

    Hi,

    I am working on a video solution code. where I have to provide source image to GPU and do computation and write in the destination. I read that using buffer creates in the loop every time will add GPU overhead.so, I implemented the following. but…

    • Answered
    • 6 months ago
    • Graphics and Gaming
    • Graphics and Gaming forum
  • How to pass "-cl-std=CL2" option to malioc?

    ivn
    ivn

    I wan to build OpenCL 2.0 kernel (it uses OpenCL C 2.0 language in kernel code) using malioc (Mali Offline Compiler) .

    Here is my command line:

    malioc --name TestKernel --core Mali-G76 kernels.cl

    In my kernel code I check value of __OPENCL_VERSION__ and it…

    • Answered
    • 8 months ago
    • Graphics and Gaming
    • Graphics and Gaming forum
  • Map/Unmap operations with Zero copy buffer.

    abhi.verma
    abhi.verma

    When we create physical zero copy buffers using cl_arm_import_memory, do we really need to perform map/unmap operations everytime we make changes to the buffer from the CPU side. Since, both GPU and CPU access the same memory, will not the changes propagate…

    • Answered
    • over 1 year ago
    • Graphics and Gaming
    • Graphics and Gaming forum
  • Optimised OpenCL SGEMM implementation for ARM Mali Midgard GPUs.

    abhi.verma
    abhi.verma

    I wish to implement an optimised sgemm for Mali MidGard Gpu whichas of now only support OpenCL 1.2.  As far as I know, OpenCL 1.2 doesn't support subgroup extensions and Mali GPUs don't have any benefits for local memory tiling. So What should be the best…

    • over 1 year ago
    • Graphics and Gaming
    • Graphics and Gaming forum
  • Irregular behaviour of vectors in OpenCL(1.2) kernels

    abhi.verma
    abhi.verma

    So, I am trying to perform some operation inside an OpenCL kernel. I have this buffer named filter which is a 3x3 matrix initialized with value 1.

    I pass this as an argument to the OpenCL kernel from the host side. The issue is when I try to fetch this…

    • Answered
    • over 1 year ago
    • Graphics and Gaming
    • Graphics and Gaming forum
  • Zero Copy Buffer Allocation on Arm Mali MidGard GPUs Opencl1.2

    abhi.verma
    abhi.verma

    I am trying to allocate a zero copy buffer on  Mali Midgard GPUs . The OpenCL 1.2 guide mentions that the only sure shot way to do this is to use the flag

    CL_MEM_ALLOC_HOST_PTR

    SO, First we need to allocate the Gpu memory using the flag and then perform…

    • Answered
    • over 1 year ago
    • Graphics and Gaming
    • Graphics and Gaming forum
  • cl_khr_subgroups questions

    Yury
    Yury

    Hello,
    Since lack of local memory in Mali, I am trying to use subgroups as Intel does in clDNN library, although they have local memory but registers exchange even faster than local memory. I have three questions about subgroups in Bifrost and Valhall implementation…

    • Answered
    • over 1 year ago
    • Graphics and Gaming
    • Graphics and Gaming forum
  • What is the specific structure of Mali-T880 on Helio X20?

    david
    david

    Hi,all

    I am now based on MediaTek's Helio X20 development Opencl algorithm, but it is not clear that the specific structure of the X20 mali-T880, including the number of shadercore, the size of the L1 cach, L2 cach size, etc.. Can you provide specific…

    • over 3 years ago
    • Graphics and Gaming
    • Graphics and Gaming forum
  • Where is the OpenCL SDK for Mali T604

    Tim Legrand
    Tim Legrand
    Note: This was originally posted on 30th January 2013 at http://forums.arm.com

    Hi,

    Where is the OpenCL SDK for Mali GPUs if available, and when will it be if not?

    Many thanks,
    Tim
    • over 7 years ago
    • Graphics and Gaming
    • Graphics and Gaming forum
  • OpenCL on Samsung Chromebook Mali-T604 (Chrubuntu OR ChromeOS)

    Todd Thompson
    Todd Thompson
    Note: This was originally posted on 19th February 2013 at http://forums.arm.com

    Question: How to get OpenCL drivers installed on either Chrubuntu or ChromeOS?

    Background: I am able to successfully compile and execute OpenCL code  (using Chrubuntu on sdcard…
    • over 7 years ago
    • Graphics and Gaming
    • Graphics and Gaming forum
  • OpenCL for Arndale board and Nexus 10

    rahul garg
    rahul garg
    Note: This was originally posted on 7th November 2012 at http://forums.arm.com

    Wondering if OpenCL drivers will be made available for Arndale Board for Linux and Android, preferably without NDAs? And will we see OpenCL drivers shipping on Nexus 10?

    edit…
    • over 7 years ago
    • Graphics and Gaming
    • Graphics and Gaming forum
  • Signal Processing with MALI 400 MP

    Laurent Ovaert
    Laurent Ovaert
    Note: This was originally posted on 16th April 2012 at http://forums.arm.com

    Hi, I would like to offload the main CPU from some heavy brute-force signal processing and use the GPU for that.

    For example, multiplying an array of floats by a scalar, or doing…
    • over 7 years ago
    • Graphics and Gaming
    • Graphics and Gaming forum
  • fp64 on Mali T604

    rahul garg
    rahul garg
    Note: This was originally posted on 21st August 2012 at http://forums.arm.com

    First of all, congrats to ARM for submitting Mali T604 for OpenCL full profile conformance. I hope the tests are finished soon.
    I was wondering about fp64 support on the T604…
    • over 7 years ago
    • Graphics and Gaming
    • Graphics and Gaming forum
  • Initial Look at OpenCL Accelerated SQLite Performance numbers on Mali

    Tom Gall
    Tom Gall

    Here's a link to a blog post from today about my work on accelerating SQLite with OpenCL on the ARM based Samsung Chromebook with a Mali T604.

    Details & Early Benchmarks of OpenCL accelerated SQLite on ARM Mali | Tom Gall

    Comments, questions and…

    • over 6 years ago
    • Graphics and Gaming
    • Graphics and Gaming forum
  • I am new to mali graphics,i want to deveop for t760,can I code in assembler?what is the best way to learn coding?

    Adnan Kilic
    Adnan Kilic

    What is the best way to learn coding for mali t760?

    • Answered
    • over 6 years ago
    • Graphics and Gaming
    • Graphics and Gaming forum
  • OpenGL ES and OpenCL support on the Samsung Chromebook 2

    Chris
    Chris

    I saw another post mentioning the Samsung Chromebook 2 on this forum but I thought I'd ask the question outright. Are there any or will there be any plans for ARM to release OpenGL ES and Open CL drivers for HW accel support on the new Samsung Chromebook…

    • Answered
    • over 6 years ago
    • Graphics and Gaming
    • Graphics and Gaming forum
  • What is the GLops of Mali T628MP6? Can't get 17 flops per pipe using OpenGL.

    chen20062308
    chen20062308

    For Mali T604 and T628, peak performance is 17 FP32 FLOPS per ALU per cycle.http://malideveloper.arm.com/downloads/OpenCL_FAQ.pdf shows this is compsed of:

    • 7: dot product (4 Muls, 3 adds)
    • 1: scalar add
    • 4: vec4 add
    • 4: vec4 multiply
    • 1: scalar multiply

    And also…

    • Answered
    • over 6 years ago
    • Graphics and Gaming
    • Graphics and Gaming forum
  • Mali Graphics Debugger - debugging native Android application

    Krzysztof Bzowski
    Krzysztof Bzowski

    Is it possible to debug native Android application using Mali graphics Debugger?

    I have confirmed that debugging is working properly with Android Java applications, but with native C++ application (built using NDK toolchain) - debugger does not capture…

    • Answered
    • over 5 years ago
    • Graphics and Gaming
    • Graphics and Gaming forum
  • I have few questions about guide which is Graphic and Compute development on Samsung chromebook.

    Woojung Myung
    Woojung Myung

    Dear All,

    Hi, I have few questions about linux on samsung chromebook

    I followed all the instructions then successfully generated SD image and then installed x11 using script.

    But when I start x11 windowing system, it only shows me one terminal frame…

    • Answered
    • over 5 years ago
    • Graphics and Gaming
    • Graphics and Gaming forum
  • Can I measure the power performance of GPU based on Samsung Chromebook2?

    Woojung Myung
    Woojung Myung

    Dear All,

    I want to say really thanks for everyone. Because when I have a question, always this forum give me a precious answer

    Cut to the chase, I am wondering whether I can measure the power performance of Mali GPU based on Samsung Chromebook 2.

    Or any…

    • Answered
    • over 5 years ago
    • Graphics and Gaming
    • Graphics and Gaming forum
  • CPU to GPU Copying Speed tuning.

    Narendra Kumar
    Narendra Kumar

    Hi,

    Is there any way to speed the data copying from CPU buffers which are allocated using "malloc" to GPU accessible memory. currently I am using simple memcpy for copying data.

    Thanks & Regards,

    Narendra Kumar Chepuri.

    • Answered
    • over 5 years ago
    • Graphics and Gaming
    • Graphics and Gaming forum
  • View related content from anywhere
  • More
  • Cancel
>