Offload transfer question

Hi, i have a question about transfer data from host do coprocessor. Look at samplce code below. Are data transferred asynchronously to coprocessor? I would like to overlap transfer and computation performed on Intel Xeon Phi with computation carried out by CPU. When i use combination of offload transfer signal() and offload wait() performance of computation is a lower than in code presented below.

Запись и воспроизведение последовательностей потоков в Intel® RealSense™ SDK

В Intel® RealSense™ SDK предусмотрена новая возможность для записи последовательности потоков с камеры на диск для дальнейшего воспроизведения. Это очень удобно для отладки и устранения проблем с камерой в приложениях. Запись необработанных потоков цветного изображения и глубины налагает достаточно высокие требования на пропускную способность ввода-вывода дисков системы. Например, при конфигурации цветного изображения 1920 x 1080, 32 бита RGB, 30 кадров в секунду, и конфигурации канала глубины 640 х 480, 30 кадров в секунду, для записи на диск пропускная способность подсистемы ввода-вывода должна составлять около 272 МБ/с. Это значение превышает максимальную возможную скорость большинства обычных дисков и даже некоторых твердотельных накопителей.

kernel with pipe parameter: compilation error


I tried compiling the following kernel with the last version of OpenCL SDK:

__kernel void pipe_producer (__write_only pipe float rng_pipe)



And got the following errors:

1:3:30: error: expected parameter declarator
1:3:43: error: expected ')'
1:3:29: note: to match this '('
Compilation failed

Can you tell why ?





I stumbled on some interesting behaviour w.r.t. allocating memory that I was hoping someone could shed some light on. I've written a simple program that shows the behaviour (I'm happy to provide it, but I imagine the behaviour might differ across systems based on the available memory).

my specs are:

GPU: Intel HD 5500
OS: Windows 10
Driver Version:
Host memory: 8 GB

Intel® SDK for OpenCL™ Applications Download Link Broken


I'm trying to download the Intel® SDK for OpenCL™ Applications tool and can't get past the registration form to download it. I fill in the relevant details, click submit and the page goes blank. I've tried on both Chrome and IE, but no luck. Can anyone get me a working download link or something?


Linux does not detect Xeon Phi card

Here is our setup:

Motherboard: Asus P9X79 WS BIOS version 4802 (Above 4G decoding is enabled)
CPU: Intel Core i7 4820K
OS: CentOS 7.1 with Linux 3.10.0-229

I have a Xeon Phi 31S1P. I have not been able to display the card
with lspci. I have tried to put in a different PCI slot. I have
upgraded the BIOS of the motherboard to the latest version. I have
tried passing noapic and pci=realloc to the Linux kernel. Nothing
seems to work.

I do not have a Xeon processor. Could that be the problem?

Below is the complete dmesg output.

Intel Iris GPU Boost in OpenCL

     I have the mac mini, cpu is intel i7-4578U with Intel Iris 51000 whose max clock is 1275MHz. I find that GPU has been locked the clock,  GPU clock is 750MHz. So I install the window OS in the mac mini.  I found that the GPU clock just boost 800MHz when I run the OpenCL code, But for the oridinarily using, GPU can boost to the max clock. My question is that why the GPU can't boost to the max clock when I run  the OpenCL code ?

Suscribirse a Profesores