SYCL contexts and memory access

[Pascuzzi__Vincent]

My understanding of the cl::sycl::context is that they are used among the different devices on a system. For example, I can only access memory allocated on a given cl::sycl::device using a cl::sycl::queue that was instantiated with the cl::sycl::context associated to said device, i.e. using cl::sycl::device::get_context().

Is this correct?

A summary of my problem: I generate random numbers in one class and store put them into the memory of an Neo device using a cl::sycl::queue member variable in this class. In another class, I allocate a bunch of memory on the ‘same’(?) Neo device using a cl::sycl::queue member variable in this other class. I get the associated device in both classes with the same common static function, i.e. the same Neo device is used. There are 3-4 classes that are implemented similarly. Now, it seems in some cases that I can use a single cl::sycl::queue from an arbitrary class to access data allocated in other classes, but in other cases I can’t; I need to use the queue/context that was used to allocate the memory. Of course I can’t operate this way since I need to access data stored among multiple classes using a single queue.

Is there a preferred/common/proper way to achieve what I want to do? Should I have a global “queue manager” class of sorts that uses a single queue/device/context to take care of all device-side tasks? Should I be explicitly using the same context is shared among all classes? (I wouldn’t think this mattered if my understanding of contexts is correct, and there is only a single iGPU on each machine. Unless there is different memory that is not shareable among different cl::sycl::queue objects?)

Thanks in advance.

Vince

[GouthamK_Intel · Accepted solution]

Hi,

Thanks for reaching out to us!

My understanding of the cl::sycl::context is that they are used among the different devices on a system. For example, I can only access memory allocated on a given cl::sycl::device using a cl::sycl::queue that was instantiated with the cl::sycl::context associated to said device, i.e. using cl::sycl::device::get_context().

When you create multiple queues even with the same device, multiple contexts get created. As they are two different SYCL contexts and any buffer you create will be a part of that context.

Could you please send us a sample code/ pseudo code if possible which depicts the problem statement that you are trying to solve.

Thanks & Regards

Goutham

[GouthamK_Intel]

Hi,

Could you please confirm if your issue is resolved?

If not, provide us a sample code/ pseudo code that depicts the problem statement that you are trying to solve?

Regards

Goutham

[Pascuzzi__Vincent]

Yes -- thanks. (I thought that was implied after selecting your post as the solution.)

[GouthamK_Intel]

Hi,

Thanks for the confirmation!

As this issue has been resolved, we will no longer respond to this thread. 

If you require any additional assistance from Intel, please start a new thread. 

Any further interaction in this thread will be considered community only.

Thanks & Regards

Goutham

[Gregg_S_Intel]

A SYCL context contains a collection of devices that the host can use and manages memory objects that can be shared between the devices.

Multiple devices on same platform can share a context, and multiple queues can share same context.

SYCL USM data is accessible on other devices in same context.

auto P = sycl::platform p(sycl::gpu_seclector_v);
auto devices = P.get_devices();
auto C = sycl::context(devices);
sycl::queue q0 = new sycl::queue(C, devices[0]);
sycl::queue q1 = new sycl::queue(C, devices[1]);
a = sycl::malloc_device<float>(N, q0);
b = sycl::malloc_device<float>(N, q1);
q0.memcpy(a, host_a, sizeof(float) * N).wait();
q1.memcpy(b, host_b, sizeof(float) * N).wait();
q0.parallel_for(sycl::range{N}, [=](sycl::item<1> i) {
  a[i] += b[i];  // buffer b on device 1 is added to buffer a on device 0
});