Shared Virtual Memory (SVM) Functions

Description

Shared Virtual Memory (SVM) (Glossary): An address space exposed to both the host and the devices within a context. SVM causes addresses to be meaningful between the host and all of the devices within a context and therefore supports the use of pointer based data structures in OpenCL kernels. It logically extends a portion of the global memory into the host address space therefore giving work-items access to the host address space. There are three types of SVM in OpenCL Coarse-Grained buffer SVM: Sharing occurs at the granularity of regions of OpenCL buffer memory objects. Fine-Grained buffer SVM: Sharing occurs at the granularity of individual loads/stores into bytes within OpenCL buffer memory objects. Fine-Grained system SVM: Sharing occurs at the granularity of individual loads/stores into bytes occurring anywhere within the host memory.

共享虚拟内存（SVM）（词汇表）：在上下文中向主机和设备公开的地址空间。SVM 使主机和上下文中的所有设备之间的地址有意义，因此支持在 OpenCL 内核中使用基于指针的数据结构。 它在逻辑上将全局内存的一部分扩展到主机地址空间，因此使工作项能够访问主机地址空间。OpenCL 粗粒度缓冲区 SVM 中有三种类型的 SVM：共享发生在 OpenCL 缓冲区缓冲区缓冲区对象的区域粒度处。精细粒度缓冲区 SVM：共享以 OpenCL 缓冲区内存对象中单个负载/存储到字节的粒度进行。精细系统 SVM：共享以单个负载/存储的粒度发生，以在主机内存中任意位置发生的字节。

OpenCL™ 2.0 Shared Virtual Memory Overview

One of the remarkable features of OpenCL™ 2.0 is shared virtual memory (SVM). This feature enables OpenCL developers to write code with extensive use of pointer-linked data structures like linked lists or trees that are shared between the host and a device side of an OpenCL application. In OpenCL 1.2, the specification doesn't provide any guarantees that a pointer assigned on the host side can be used to access data in the kernel on the device side or vice versa. Thus, data with pointers in OpenCL 1.2 cannot be shared between the sides, and the application should be designed accordingly, for example, with indices used instead of pointers. This is an artifact of a separation of address spaces of the host and the device that is addressed by OpenCL 2.0 SVM.

OpenCL 2.0 的显著功能之一™共享虚拟内存 （SVM）。此功能使 OpenCL 开发人员能够编写代码，广泛使用指针链接的数据结构，如在 OpenCL 应用程序的主机和设备端之间共享的链接列表或树。在 OpenCL 1.2 中，规范不提供任何保证，保证在主机端分配的指针可用于访问设备端内核中的数据，反之亦然。因此，在 OpenCL 1.2 中具有指针的数据不能在两者之间共享，并且应用程序应相应地进行设计，例如，使用索引而不是指针。这是由OpenCL 2.0 SVM寻址的主机和设备地址空间分离的产物。

The Compute Architecture of Intel® Processor Graphics Gen9

Intel® Processor Graphics

Architecture Overview for Intel® Processor Graphics Gen11

Optimizing Matrix Multiply for Intel® Processor Graphics Architecture Gen9

Shared Virtual Memory

Pass a Pointer: Exploring Shared Virtual Memory Abstractions in OpenCL Tools for FPGAs