@@ -10,7 +10,7 @@ Purpose of this Document
10
10
========================
11
11
12
12
This high-level design (HLD) document describes the usage requirements
13
- and high level design for Intel® Graphics Virtualization Technology for
13
+ and high level design for Intel | reg | Graphics Virtualization Technology for
14
14
shared virtual :term: `GPU ` technology (:term: `GVT-g `) on Apollo Lake-I
15
15
SoCs.
16
16
@@ -26,10 +26,10 @@ Audience
26
26
========
27
27
28
28
This document is for developers, validation teams, architects and
29
- maintainers of Intel® GVT-g for the Apollo Lake SoCs.
29
+ maintainers of Intel | reg | GVT-g for the Apollo Lake SoCs.
30
30
31
31
The reader should have some familiarity with the basic concepts of
32
- system virtualization and Intel® processor graphics.
32
+ system virtualization and Intel processor graphics.
33
33
34
34
Reference Documents
35
35
===================
@@ -45,19 +45,19 @@ The following documents were used as references for this specification:
45
45
Background
46
46
**********
47
47
48
- Intel® GVT-g is an enabling technology in emerging graphics
48
+ Intel GVT-g is an enabling technology in emerging graphics
49
49
virtualization scenarios. It adopts a full GPU virtualization approach
50
50
based on mediated pass-through technology, to achieve good performance,
51
51
scalability and secure isolation among Virtual Machines (VMs). A virtual
52
52
GPU (vGPU), with full GPU features, is presented to each VM so that a
53
53
native graphics driver can run directly inside a VM.
54
54
55
- Intel® GVT-g technology for Apollo Lake (APL) has been implemented in
55
+ Intel GVT-g technology for Apollo Lake (APL) has been implemented in
56
56
open source hypervisors or Virtual Machine Monitors (VMMs):
57
57
58
- - Intel® GVT-g for ACRN, also known as, "AcrnGT"
59
- - Intel® GVT-g for KVM, also known as, "KVMGT"
60
- - Intel® GVT-g for Xen, also known as, "XenGT"
58
+ - Intel GVT-g for ACRN, also known as, "AcrnGT"
59
+ - Intel GVT-g for KVM, also known as, "KVMGT"
60
+ - Intel GVT-g for Xen, also known as, "XenGT"
61
61
62
62
The core vGPU device model is released under BSD/MIT dual license, so it
63
63
can be reused in other proprietary hypervisors.
@@ -119,7 +119,7 @@ virtualization technology. It has been used in commercial virtualization
119
119
productions, for example, VMware*, PCoIP*, and Microsoft* RemoteFx*.
120
120
It is a natural path when researchers study a new type of
121
121
I/O virtualization usage, for example, when GPGPU computing in VM was
122
- initially proposed. Intel® GVT-s is based on this approach.
122
+ initially proposed. Intel GVT-s is based on this approach.
123
123
124
124
The architecture of API forwarding is shown in :numref: `api-forwarding `:
125
125
@@ -170,7 +170,7 @@ capability among VMs. Only one VM at a time can use the hardware
170
170
acceleration capability of the GPU, which is a major limitation of this
171
171
technique. However, it is still a good approach to enable graphics
172
172
virtualization usages on Intel server platforms, as an intermediate
173
- solution. Intel® GVT-d uses this mechanism.
173
+ solution. Intel GVT-d uses this mechanism.
174
174
175
175
.. figure :: images/APL_GVT-g-pass-through.png
176
176
:width: 400px
@@ -189,7 +189,7 @@ with each VF directly assignable to a VM.
189
189
Mediated Pass-Through
190
190
*********************
191
191
192
- Intel® GVT-g achieves full GPU virtualization using a "mediated
192
+ Intel GVT-g achieves full GPU virtualization using a "mediated
193
193
pass-through" technique.
194
194
195
195
Concept
0 commit comments